Defining a caffeine demethylation system for improved decaffeination

Abstract

The present disclosure provides enzyme-based compositions, kits, and methods of their use for reducing or removing caffeine from food and beverages.

Description

DEFINING A CAFFEINE DEMETHYLATION SYSTEM FOR IMPROVEDDECAFFEINATIONCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Provisional Application No. 63 / 562,448, filedMarch 7. 2024, the entire content of which is incorporated herein by reference.REFERENCE TO SEQUENCE LISTING

[0002] The instant application contains a Sequence Listing which has been submitted electronically in XML format and is hereby incbtporated by reference in its entirety. Said XML copy, created on March. 3, 2025, is named 3000188-000001 Sequence Listing $T26.xml, and is 232,590 bytes in size.FIELD

[0003] The present disclosure relates to enzyme-based compositions, kits, and methods of their use for reducing or removing caffeine from food and beverages.BACKGROUND OF THE DISCLOSURE

[0004] While some consumers value the energizing effects of caffeine, many others wish to avoid caffeine for reasons such as insomnia, anxiety, or caffeine addiction ( / ). Certain decaffeination technologies, which use solvents to remove caffeine, alter the flavor of the food and require the consumer to purchase separate caffeinated and decaffeinated products (2, 3),

[0005] Enzymes that metabolize caffeine could create better quality and more convenient decaffeinated foods by allowing the consumer to convert caffeine specifically and directly into non-psychoactive compounds.

[0006] While enzymes called caffeine dernethylases have been discovered that convert caffeine to theobromine, a less psychoactive metabolite, there have not yet been reports showing that these enzymes are active in brewed coffee. These enzymes also require NA DH, which adds significant expense and must be used at extremely low levels if it were to be a viable consumer technology.

[0007] Enzyme-based methods for removing caffeine from foods have the potential to improve the quality and convenience of decaffeinated foods. Thus, there is a great need for enzyme-based compositions, kits, and me t hods that more easily and conveniently reduce or removecaffeine froin foods.SUMMARY OF THE DISCLOSURE

[0008] The present disclosure provides caffeine demethylases that are soluble and active on caffeinated substances such as, for example, purified caffeine and black unsweetened cold brew coffee.

[0009] The present disclosure provides enzymes, compositions, and / or kits that produce a reduced caffeine containing substance or a caffeine-free containing substance after the caffeinated substance encounters or contacts the enzymes, compositions, and / or kits provided herein, The present disclosure provides enzymes, compositions, and / or kits that may be used to remove caffeine froma caffeinated substance, such as a caffeinated foodindudingbut not lim ited to coffee and tea. In some embodiments, the encountering or contact occurs when the enzymes, compositions, and / or kits of the present disclosure are added to the substance. In some embodiments, the enzymes, compositions, and / or kits are added to the substance in an amount effective to reduce or eliminate the caffeine that the substance contained prior to the enzymes, compositions, and / or kits of the present disclosure being added to the caffeinated substance. According to the present disclosure, the enzymes, compositions, and / or kits provided herein may be used to decaffeinate a substance, such as a food or a food precursor.

[0010] In some embodiments, the enzymes, compositions, and / or kits of the present disclosure may be used as an alternative to carbon filters used to filter caffeine from Green Coffee Extract (GCE), for example as used during Swiss Water™ decaffein ation processes.

[0011] The present disclosure, also provides an N A DM regeneration system using a sugar, NAD* and an enzyme that can catalyze the sugar selected from enzyme class (EC) 1.1.1: oxidoreductases that use NAD(P)+as an electron acceptor. In some embodiments, the regeneration systems of the present disclosure can replace the need for expensive NADH with comparable activity on, for example, purified caffeine and caffeine from cold brew coffee.

[0012] In some embodiments, the present disclosure provides compositions and / or kits comprising: at least one amino acid sequence coding for at least one caffeine demethy lase cdmA domain; at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain : at least one sugar; at least one coenzyme; and optionally at least one amino acid sequence coding for a glucose dehydrogenase.

[0013] In some embodiments, the at least one amino add sequence coding for at least one caffeine demethylase cdmA domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ I D NO: 21 , 23, 25, 27, 29, 31 , 33, 35, 37, 39, 40,42, 44, 46, 48, 50,52, 54, 56, 58, 99, or 100, optionally lacking a poly-His (HHHHHH) sequence.

[0014] In some embodiments, the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEO ID NO: 22, 24, 26, 28, 30, 32, 34, 36, 38, 41 , 43, 45, 47, 49, 51, 53, 55, 57, 59, 101 , 102, 103, 104, 105, 106, 107, 108, or 109, optional- lacking a poly-His (HHHHHH) sequence.

[0015] In some embodiments, the at least one amino acid sequence coding for a glucose dehydrogenase comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 1 , 2, 3 , 4, 5, 6, 7, 8, 9, 10, 1 10, 1 11, 112, or 113 , In some embodiments, the glucose dehydrogenase is an enzyme that can catalyze the sugtr selec ted from ettzy meclass (EC) 1 .1 ..1 ; oxidoreduclases that u se NAD(P)+as an electron acceptor. In some embodiments, addingthe composition and / or kilto a caffeine containing substance results in some or all the caffeine being converted to theobromine.

[0016] In some embodiments, the cdmA and cdmD domains are derived from one or more source organ i&ms comprising: puiida, Meihylorubrtim populi, Paraburkholderia coffeinilytica, Pseudomonas flurorescens, Leifsoniaxyli, Burkholderia ambifaria, Cupriavidus sp. 0384, Pseudomontis sp. 836, Delftia lacustris, Caldhnonas fhermodepolymerans, ITterntomonas sp., Afipia felis, Pseudooceanicola nitratireducens, Patococcus zhejiangensis, Acetabacter senegalensis, Paracoccus versulus, Paraburkholderia fingorum, Caballeronia hypogeia, and / or Pandoraea captiosa.

[0017] In some embodiments, the compositions and / or kits comprise a natural or synthetic caffeine demethylase protein , the natural or sy nthetic caffeine demethylase protein comprises the at least, one amino acid sequence coding for at least one caffeine demethylase cdmA domain and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain. In some embodiments, the natural or synthetic caffeine demethylase protein comprises the at least one ainino acid sequence coding for at least one caffeine demethylase cdmA domain, the at least one aini.no acid sequence coding for at least one caffeine demethylase cdmD domain, and the at leastone amino acid sequence coding for a glucose dehydrogenase. hi some embodiments, adding die compositions to a caffeine containing substance results in some or all the caffeine being converted io theobromine.

[0018] In some embodiments, the at least one ammo acid sequence coding for at least one caffeine demethylase cdmA domain and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain are linked wife a linker, the linker is a peptide chain comprising 1 , 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 , 12, 1.3, 14, 15, 16, 17, 18, 19, 20, 21 ,22, 23, 24, 25,26, 27, 28, 29, 30, 31 , 32, 33, 34, 35, 36, 37, 38, 39, 40, 41 , 42,43 , 44, 45, 46,47, 48, 49, or 50 amino acids.

[0019] In some embodiments, the at least one amino add sequence coding for at least one caffeine demethylase cdmD domain comprises a ferredoxin domain. In some embodiments, the at least one amino acidsequence coding for at least one caffeine demethylase cdmD domaindoes not comprise a ferredoxin domain.[O02OJ In some embodiments, the enzymes, compositions, and / or kits of the present disclosure rue such that each of the cdmA and cdmD domains are selected from fee cdmA and cdmD domains, respectively, as provided herein. See, e.g., Table 4.

[0002] j In some embodiments, the enzymes, compositions, and / or kits of fee present 'disclosure are such that each of fee cdmA and cdmD domains are derived from one or more source organisms as provided herein. See, e.g., Table 3.

[0022] In some embodiments, the enzymes, compositions, and / or kits of the present disclosure include a natural or synthetic caffeine demethylase protein having amino acid sequences coding for the cdmA and cdmD domains.,

[0023] cdmD domain is located at the N-termimrs region, and the cdmA domain is located at the C-terminus region. In some embodiments, the cdmD domain is located at the C-tenninus region, and the cdmA domain is located at the N-terminus region.

[0024] In some embodiments, one or more of the at least one am ino acid sequence coding for at least one caffeine demethylase cdmA domain, the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain, and / or the at least one amino acid sequence coding for a glucose dehydrogenase comprises one or more intra -molecular disulfide bonds.

[0025] In some embodiments, the at least one sugar comprises one or more of glucose, galactose, fructose, aliose, altrose, mannose, gtilose, idose, talose, psicose, sorbose, tagatose, xylose, arabinose, sucrose, lactose, and / ormaltose. In some embodiments, the at least one sugar is glucose.

[0020] In some embodiments, the at least one coenzyme comprises NAD;7NADH and / or NAD(P);7NAI)(P)H.

[0027] hi some embodiments, at least 90%, or at least 91%, or at least 92%, or at least 93%, or at least 94%, or at least.95%, or at least 96%, or at least 97%, or at least 98%, or at least 99% of the caffeine is converted into theobromine after the composition and / or the kit is added to a caffeine containing substance. In some embodiments, essentially all the caffeine is converted into tiieobromine after the composition and / or the kit is added to the caffeine containing substance.

[0028] In some embodiments, only a portion of the caffeine contained in a caffeine containing substance is converted into theobromine after the composition and / or the kit is added to thecaffeine containing substance. In some embodiments, about 50-80%, about 50-75%, about 50- 70%, about 50-65%, about 50-60%, about 55-80%, about 55-75%, about 55-70%, about 55-65%, about 60-80%, about 60-75%., or about 60-70% of the caffeine is converted Into theobromine after the composition and / or the kit is added to a caffeine containing substance.

[0029] In some embodiments, die substance, or die caffeine containing substance, is a food or a food precursor. In some embodiments, the caffeine containing substance is brewed ground roasted coffee comprising water. In some embodiments, the caffeine containing substance is about 8 ounces, or about 10 ounces, or about 12 ounces of the brewed ground roasted coffee comprising water, to some embodiments, the caffeine containing substance is a beverage or liquid containing coffee, tea, guarana extract, or a mixture thereof.

[0030] to some embodiments, the caffeine containing substance is brewed ground roasted coffee containing about 200 mg caffeine, about 175 mg caffeine, about 150 mg caffeine, about 125 mg caffeine, about 100 mg caffeine, about 75 mg caffeine, about 50 mg caffeine, or about 25 mg caffeine.

[0031] In some embodiments, the caffeine containing substance is instant or bottled coffee containing about 200 mg caffeine, about 175 mg caffeine, about 150 mg caffeine, about 125 mg caffeine, about 100 mg caffeine, about 75 mg caffeine, about 50 mg caffeine, or about 25 mg caffeine.

[0032] In some embodiments, the caffeine containing substance is an unoxidized / lightly oxidized tea (e.g., green tea, yellow tea, and white tea), a partially oxidized tea (e.g., oolong tea), a fuBy oxidized tea (e.g., black tea), or a post-fermented tea (e.g., Pu'er tea) containing about 150 mg caffeine, about 125 mg caffeine, about 100 mg caffeine, about 75 mg caffeine, about 50 mg caffeine, about 25 mg caffeine, or about 12,5 mg caffeine.

[0033] hi some embodiments, the caffeine containing substance is an energy drink containing caffeine-rich extracts (e.g., coffee extract or guarana extract). Such energy drink may contain about 300 mg caffeine, about 275 mg caffeine, about 250 mg caffeine, about 225 mg caffeine, about 200 rng caffeine, about 175 mg caffeine, about 150 tag caffeine, about 125 mg caffeine, about 100 mg caffeine, about 75 mg caffeine, about 50 mg caffeine, or about 25 mg caffeine.

[0034] In some embodiments, the caffeine containing substance may contain one or more additives. For example, the caffeine containing substance may contain sugars (e.g., glucose and sucrose), buffering salts (e.g., citric acid, potassium phosphate, boric acid, sodium bicarbonate, magnesium carbonate, and / or diethyl barbituric acid), and / or nutrients (e.g., B vitamins, amino acids, and taurine).

[0035] In some embodiments, the caffeine containing substance may also contain other xanthine derivatives, such as Theobromine and Theophylline, in some embodiments, the amount of the otherxanthine derivatives contaij^din the caffeine containingsubstancemay be about 5 mg, about 10 mg, about 15 mg, about 20 mg, about 25 mg, about 30 mg, about 35 mg, about 40 mg, about 45 mg, about 50 mg, about 55 mg, about 60 mg, about 65 mg, about 70 mg, about 75 mg, about 80 mg, about 85 mg, about 90 mg, about95 mg, about 100 mg, about 105 mg, about 1 10 mg, about 115 mg, about 120 mg, about 125 mg, about 130 mg, about 135 mg, about 140mg, about 145 mg about 150 mg, about 155 mg, about 160 mg, about 165 rng, about 1 70 mg, about 175 mg, about 180 mg, about 185 mg, about 190 mg, about 195 mg, or about 200 mg.

[0036] In some embodiments, the composition and / or the kit comprises: the at least one amino acid sequence coding for at least one caffeine demethylase cdm A domain comprising an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 21 , 23, 25, 27, 29, 31 , 33, 35, 37; 39, 40, 42, 44, 46,48, 50, 52, 54, 56,58, 99, or 100; the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain comprising an amino acid sequence having at least 80%, 85% , 90%, 95% „ 98%, 99%, or 100% sequence identity to one of SEQ ID NO; 22, 24, 26, 28, 30, 32, 34, 36, 38, 41 , 43, 45, 47,49, 51 , 53, 55, 57, 59, 101 , 102, 103, 104. 105, 106, 107, 108, or 109, optionally lacking a poly- His (HHHHHH) sequence; glucose; NAD+ / NADH; and the at least one amino acid sequence coding fora glucose dehydrogenasecomprising an amino acid, sequence having at .Ieasi'80%, 85%, 90%, 95%, 98%, 99%, or 1.00% sequence identity to one of SEQ ID NO: .1 , 2, 3, 4, 5, 6, 7 / 8, 9, 10, 110, 11 L 112, or 113, optionally lacking a poly-His (HHHHHH) sequence.[00371 In some embodiments, the composition and / or the kit comprises: the at least one amino acid sequence coding for at least one caffeine demethyiase cdmA domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 23, 25, 27, or 31 ; and / or the at least one amino acid sequence coding for at Ieastone caffeine demethyiase cdmD domain comprises an ammo acid sequence having at least 80*%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 24, 26, 28, 32, or 36, optionally lacking a poly-His (HHHHHH) sequence,[00381 In some embodiments, the composition and / or the kit comprises: the at least one amino acid sequence codingfor at Ieastone caffeine demethyiase cdmA domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 99 or 100; and / or the at least one amino acid sequence codingfor at Ieastone caffeine demethyiase cdmD domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 101 , 102, 103, 104, 105, 106, 107, 108, or 109, optionally lacking a poly-His (HHHHHH) sequence.[00391 In some embodiments, the composition and / or the kit comprises: a natural or synthetic caffeine demethyiase protein comprising an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 114, 115, 1.16, 1 17, 118, 119, 120, or 121 , optionally lacking a poly-His (HHHHHH) sequence.

[0040] In some embodiments, the composition and / or the kit comprises: the at least one amino acid sequence coding for at least one caffeine demethyiase cdmA domain comprises, based on SEQ ID NO: 99, one or more active site residues of: a Q1 52, a Y 155, a R164, a N 167, a F168, a T 169, a D 170, a F1 71 , a H 173, a F1 74, a H 178, a L182, a E217, a A218, a P219, a 1220, a F223, a Y225, a L235, a V237, a L248, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a F287, and / or a D290 residue. In some embodiments, the at least one caffeine demethyiase cdm A domain has at leastabout 70%, about 75%, about 80%, about85%, about 90%, about 95, or 100% identity to the active site residues of cdmA domain.

[0041] In some embodiments, the composition and / or the kit comprises: at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain ("cdmA"); at least one amino acid sequence coding for at least one- caffeine demethylase cdmD domain ("cdmD" j; at least one sugar: at least one coenzyme: and at least one amino acid sequence coding for a glucose dehydrogenase (“gdh”), wherein concentration ratios of cdmA:cdmD:gdb range from about 23:1.0:1 .0 to about 14.0:1.0:1.0.

[0042] hi some embodiments, the concentration ratios of cdmA:cdmD:gdh are about 3.5: 1;1 , respectively. In some embodiments, the concentration ratios of cdmA :cdmD:gdh are about 35 μM: 10 μM: 10 μM, respectively.

[0043] In some embodiments, the cdm A comprises an amino acid sequence having SEQ ID NO: 99. In some embodiments, the cdmD comprises an amino acid sequence having SEQ ID NO: 24. In some embodiments, the gdh comprises an amino acid sequence having SEQ ID NO: 1 .

[0044] hi some embodiments, the composition and / or the kit is in solid form or in liquid form, In some embodiments, the composition and / or the kit is packaged in a suitable storage or container. In some embodiments, the composition and / or the kit is packaged in a sachet, capsule, pod (e.g, coffee roast K-cuppod), jar, bottle, vial, syringe, bowl, can, box, bag, pouch (e.g., stand up pouch), or packet (e.g., square packet, rectangle packet, stick packet). In some embodiments, the composition and / or the kit is packaged in a suitable storage or container made of paper, cardboard (e.g., craft cardboard), foil, plastic, or the like. [

[0045] In some embodiments, the composition and / or the kit further comprises at least one formaldehyde dehydrogenase.

[0046] In some embodiments, the composition and / or the kit is provided in a single use package. In some embodiments, the composition and / or the kit is provided in separate packages: a first- package comprising the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain ; and a second package comprising the at least one sugar, the at least one coenzyme, and the at least one amino acid sequence coding for a glucose dehydrogenase. In some embodiments, the composition and / or the kit is provided in separate packages: a first package comprising the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain, the at least one amino acid sequence coding for at least onecaffeinedemeth yiase cdmD domain, and the at least one amino acid sequence eodingfor a glucose dehydrogenase; and a second package comprising the at least one sugar and the at least one coenzyme.

[0047] In some embodiments, the present disclosure provides methods of preparing a decaffeinated beverage, comprising; brewing ground roasted coffee with water such that a liquid coffee extract is formed; separating spent coffee grounds from the liquid coffee extract; adding one or more additives to the liquid coffee extract; and pasteurizing and bottling the liquid coffee extract. In some embodiments, the composition and-'or the kit is added to the liquid coffee extract when brewing the ground roasted coffee with water, after separating spent coffee grounds from the liquid coffee extract, and / or when adding the one or more additives to fee liquid coffee extract In some embodiments, the one or more additives comprises sugar, -flavors, dairy, and / or pH adjusting ingredients.

[0048] In some embodiments, the present disclosure provides methods of converting some or al! caffeine to theobromine in coffee comprising caffeine, the method comprising adding to the caffeinated coffee a composition comprising: at least one amino acid sequence coding for at least one caffeine demethylase cdmA. domain (‘fedmA’’); at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain (“cdmD”); at least one sugar; at least one coenzyme; and at least one amino acid sequence coding for a glucose dehydrogenase C‘gdh”). thereby converting some or all the caffeine in the coffee to theobromine.

[0049] In some embodiments, the pH adjusting ingredients (pH adjustments) may include one or more buffering salts. For example, a non-limiting list, of pH adjusting ingredients may include one or more of citric acid, potassium phosphate, boric acid, and / or diethyl barbituric acid.[0050 J In some embodiments, the present disclosure provides polypeptides, comprising: an ammo acid sequence coding for at least one caffeine demethylase cdmA domain comprisingat. least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 21 , 23, 25, 27, 29, 31 , 33, 35, 37, 39, 40, 42, 44, 46, 48, 50,52, 54, 56, 58, 99, or 100, optionally lacking a poly-His (HHHHHH) sequence.

[0005] ] In some embodiments, the present disclosure provides polypeptides, comprising: an amino acid sequence eodingfor at least one caffeine demethylase cdmD domain comprisingat least .80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 22, 24, 26, 28, 30,32, 34, 36, 38, 41 , 43, 45, 47, 49, 51 , 53, 55, 57. 59, 101 , 102, 103, 104, 105, 106, 107, 108, or 109, optionally lacking a poly-His (HHHHHH) sequence.

[0052] In some embodiments, the present disclosure provides polypeptides, comprising: at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, .98%, 99%, or I (X)% sequence identity to one of SEQ ID NO: 21 , 23 , 25, 27, 29, 31 , 33, 35, 37, 39, 40, 42, 44, 46, 48.50, 52, 54, 56, 58, 99, or 100, optionally lacking a poly-His (HHHHHH) sequence; and / or at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%s, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 22,24, 26, 28, 30, 32, 34, 36. 38, 41 , 43, 45, 47, 49, 51, 53, 55, 57, 59, 101, 102, 103, 104, 105, 106, 107, 108, or 109, optionally lacking a poly-His (HHHHHH ) sequence.

[0053] In some embodiments, the present disclosure provides polypeptides, comprising: an amino acid sequence coding for at least one caffeine demethylase cdmA domain comprising one of SEQ ID NO: 21, 23, 25, 27, 29, 31, 33, 35, 37, 39, 40, 42, 44, 46, 48, 50. 52, 54, 56, 58, 99, or 100, wherein the amino acid sequence optionally has 1, 2, 3, 4, or 5 amino acid substitutions and / or optionally lacking a poly-His (HHHHHH) sequence.

[0054] In some embodiments, the present disclosure provides polypeptides, comprising: an amino acid sequence coding for at least one caffeine demethylase cdmD domain comprising one of SEQ ID NO: 22, 24 , 26, 28, 30, 32, 34, 36, 38, 41, 43, 45, 47,49, 51 , 53, 55, 57, 59, 101 J 02, 103, 104, 105, 106, 107, 108, or 109, wherein the amino acid sequence optionally has 1 , 2, 3, 4, or 5 amino acid substitutions and / or optionally lacking a poly-His (HHHHHH) sequence.

[0055] In some embodiments, the presen t disclosure provides polypeptides, comprising: at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain comprises an amino acid sequence having one of SEQ ID NO: 21 , 23 , 25, 27, 29, 31 , 33, 35,37, 39, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 99, or 100, wherein the amino acid sequence optionally has 1 ,2, 3, 4, or 5 amino acid substitutions and / or optionally lacking a poly-His (HHHHHH) sequence: and / or at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain comprises an amino acid sequence having one of SEQ ID NO: 22 , 24, 26, .28 , 30, 32 , 34, 36, 38, 41 , 43, 45, 47, 49, 51 , 53, 55, 57, 59, 101, 102, 103, 104, 105, 106, 107, 108, or 109, wherein die amino acid Sequence optionally has I , 2, 3, 4, or 5 amino acid substitutions and / or optionally lacking a poly-His (HHHHHH) sequence.

[0056] In some embodiments, the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain does not include a poly-His sequence, and / or the at least one amino acid sequence coding for at least one- caffeine demethylase cdraD domain does no t include a poly- His sequence.

[0057] In some embodiments, the present disclosure provides polynucleotides and vectors encoding the polypeptides. In some embodiments, the present disclosure provides cells comprising heterologous polynucleotides encoding the polypeptides.

[0058] In some embodiments, the present disclosure provides methods of expressing the polypeptides in the cells and purifying the polypeptides from the cells.

[0059] In some embodiments, the present disclosure provides uses of the compositions and / or tire kits for decaffeinating a caffeine containing substance.BRIEF DESCRIPTION OF THE DRAWINGS

[0060] FIGs. 1A-1F provide the caffeine demethylase discovery, expression, and activity on caffeine. FIG, 1A: Schematic of the oxidation -reduction reaction of caffeine, NADH, and O2to theobromine, NAD+, and HCHO. FIGs, SDS-PAGE of (he elution fractions of expressed cdmA (B) and cdrnD (C) enzymes. FIGs. 1 D-1 F: Soluble enzymes were tested for activity on caffeine. Fig. ID, area under the curve (AU'C) for the mass spectrometry signal corresponding to theobromine (181 m / z) over time; Fig. 1 E, AUG for caffeine ( 195 m / z); Fig. 1 F, % theobromine of total methylxanthines (theobromine F caffeine).

[0061] FIGs. 2A-2B provide the caffeine demethylase activity with ready-to-drink cold brew. FKA 2 A: Activity in ready-to-drinkmultiserve Starbucks black unsweetened coId brew, measured as % theobromine of total methylxanthines in (theobromine + caffeine). FIG. 2B: Activity in Trader Joe’s ready-to-drink rnultiserve black unsweetened cold brew.

[0062] FIGs. 3A-3E provide fueling caffeine demethylation with a cost-effective glucose dehydrogenase / NADH regeneration system. 3A: Schematic of the regeneration system: the oxidation-reductionreaction of caffeine, NADH, and O2to theobromine, NAD+, and HCHO is now fueled by the NADH produced by glucose dehydrogenase, which converts NAD+and glucose into NADH and gluconolactone. FIG. 3B. SDS-PAGE of the elution fractions of expressed glucose dehydrogenase (gdh) enzymes. FIG. 3C: Conversion of NAD+into NADH by glucose dehydrogenase, as measured by the increased absorbance at 340 rim. FIGs. 3D-3E: theregeneration system was tested with gdhl and cdm2 (left lines, darker grey) or cdm4 (right lines, lighter grey), with different levels of NAD;and glucose using caffeine (FIG. 3D) or ready-to- drink Starbucks cold brew coffee (FIG. 3E).[00631 FIGs. 4A-4D provide the sequence and structural analysis ofcdmDL FIG. 4A: Sequence alignment of published cdmD 1 from P. putida (“Published”) vs a highly similar homolog, also from P. pidida, reveals a P446 A mutation . FIG. 4B: The predicted structure of D1 t AiphaFold2 modeled showing the proline to alanine mutation (arrow); the N-tertninal Rieske domain in D1 is not shown here. FIG. 4C: The version of D1 with the truncated Rieske domain and with alanine(D1 t. A) is much more soluble when expressed in A coli compared to full length (D1) orRieske- tnrncated D1t, as visualized by SDS-PAGE and Coomassle. FIG. 41): Pure caffeine is converted by cdmA1 with cditnD.lt. A (collectively, cdm I), but less rapidly than other demethylation systems such as cdm2, 3, or 6; cdmA and cdmD enzymes were at 5 μM concentrations.

[0064] FIG. 5 provides the conversion rate of some cdmA and cdmD enzymes. Some cdmA and cdmD enzymes from Pseudomonas species appear cross-reactive in a 10% cold brew solution. Enzymes were at 5 / 5 / 1 μM for cdmA / cdmD / gdhl , respectively, and the reaction proceeded for 1 h. Numbers represent percent theobromines, of total meihylxanthines (theobromine + caffeine) after 1 h.

[0065] FIGs. 6A-6D provide the structural analysis of some modified enzymes. FIG. 6A: A2t (light grey) is a truncated version of cdmA2 (dark grey), with 5 N-terminal residues and 8 C- teiminal residues removed. FIG. 613; A2..10 is a VI 82L mutation (white) of cdmA2 (grey) near the active site iron (sphere) and caffeine. FIG. 6C. A2t and A2.10 more rapidly convert the caffeine in cold brew coffee compared to the natural demethylases A2 or A3. FIG. 6D: Enzymes retain 20-30% ofthei.rdecaffeina.tionactiv.ity in coffee heated to 75 °C. edrnA concentrations were 100 pM in C and D, with 20 μM of the corresponding cdmDs and 10 μM gdh l.

[0066] FIGs. 7A-7D provide the conversion analysis of some enzymes. FIGs. 7A-7B: A2t (FIG. 7 A) and A2.10 (FIG. 7B) activity at decreasing concentrations ofeach demethylasein l x cold brew coffee. Concentrations of D2 and gdhl were 20 μM and 10 μM, respectively. FIG. 7C: Caffeine in lx cold brew remaining when lowering D2 and gdh l levels, with 70 μM A2t The numbers below each bar refer to the concentration of D2 or gdh l , respectively, in μM. FIG. 7D: Additional time points for the demethylation system using A2t, D2, and gdhl (at 70, 10, 5 μM respectively) show near total decaffeination at 4 hours in 1 x coffee.

[0067] FIGs. 8A-8E provide the structural and conversion analysis of some selected enzymes FIG. 8A: A sequence similarity network from a HMMER search of cdmA2, visualized in Cytoscape, with a close-up inset of. the cluster connected to cdmA2 (black circular node). Datk grey diamond nodes are previously tested cdmAs; medium grey triangle nodes are new cdmAs referred to cdmA 12-A19 hereafter; light grey circular notes in this cluster were not tested and appeared to be either theobromine demethylases or protein fragments. FIG. 8B: pairwise comparisons of all tested natural cdm As (left) reveal a network of enzymes with similarities mostly between 65-99% sequence identity, cdm A9 -A11 had lower identity to the other cdmAs in the network, andas they were inactive, probably have other non-caffeine activities. The same .pairwise matrix for cdrnD (right) shows less overall sequence similarity. FIG .8C: the active site o f modeled caffeine demethylases (with the N residue near the caffeine) compared to the active site of theobromine demethylases (with the larger Q residue) show a characteristic difference between otherwise similarenzymes. FIG.8D: Al] ordered cdm .12-19 A and D genes were soluble per SDS- PAGE. FIG. 8E: While all cdm 12- 19 enzymes had some activity on caffeine in lx cold brew, none appeared to be as active as the A2tfD2 control; cdmA, cdrnD, and gdhl enzymes were at 70 ,μM, 10 μM and 5 μM (respectively).[00681 FIGs. 9A-9D provide the structural and conversion analysis of some selected enzymes. FIG. 9A: Structure of AD3 Jinkl (light grey), a fusion of the Oterm of D3 (dark grey, left-hand side) to the N-term of A3 (dark grey, right-hand side) through a 17-residue linker designed via RFDiffo sion and ProteinMPNN. FIG. 9B SDS-PAGE showing soluble expression of multiple linked designs. Designs labeled “nofd” also had the ferredoxin domain of their respective cdmDs removed. FIG. 9C: Caffeine conversion in 0.5 mM caffeine or a 10% cold brew solution of linked protein designs. FIG. 9D: In a lx cold brew solution, AD3 Jinkl demonstrated some conversion of caffeine. For unlinked controls, 100 μM cdmA and 20 μM cdrnD were used, while 95 μM AD3 _link l was used; 10 μM gdhl was added to all conditions.

[0069] FIGs. 1.0A-10D provide the protein dialysis results of some selected enzymes. FIG. 10A, SDS-PAGE was used to estimate the protein concentration of dialyzed protein dilutions by comparing against column purified (IM AC) controls. FIGs. 10B-10D: comparing different levels of dialyzed proteins shows that A2t (FIG. 10B), D2 (FIG, 10C), and gdhl (FIG. 10D)can all be lowered from their baseline levels (dashed line with down-facing triangle for all) with retained activity; increasing gdhl also led to quicker caffeine conversion. IMAC conditions useimmobilized metal affinity chromatography-purified proteins, all at 70 / 10 / 10 μM (A2t / D2 / gdhl respectively). Unless specified in the legend, concentrations of A2t / D2 / gdhl are also 70 / 10 / 10 μM.

[0070] FIGs. 11 A-l ID provide the expression and conversion analysis of some selected enzymes. FIG. 11 A: SDS-PAGE shows soluble expression of D2’s FAD / NAD domain, 5 new genome mines linked to D2’s ferredoxin domain (D2.N1-5), and 4 ProteinMPNN redesigns of D2 (D2.mpnn 1 -4). D2’s ferredoxin domain (~10 kDa) was minorly soluble, FIG. 1 IB: Most ordered genome mines or designs led to a lower 340 nm signal (corresponding to NADH oxidation) compared to either a blank or the D2 ferredoxin domain alone. FIGs, 11O11D: While most genome mines and MPNN designs still led to caffeine demethylation of pure caffeine solutions at room temperature (FIG. I I C), none were clearly faster than the .02 control; in 65C,C coffee (FIG. 1 ID), the D2 control had the highest demethylation activity. cdmA, cdmD, and gdhl enzymes were at 100 μM, 20 μM and 10 μM (respectively ).

[0071] FIGs. 12A-12D provide the expression and conversion analysis of some selected enzymes. FIG. 12 A: SDS-PAGE shows soluble expression of 10 natural gdhs (gdh l -10), and 4 ProteinMPNN redesigns of gdh 1 (gdh 1.mpnnl -4). FIGs, 12B-120 Most ordered genome mines or designs led to an increased 340 nm signal (corresponding to N AD+ reduction) at room temperature (FIG. 12B) or 75°C (FIG. 12C). FIG. 12D: The use of gdhl to regenerate NADH still led to the most caffeine demethy lation in 1 x coffee solutions heated to 75 °C. cdm A, cdmD, and gdhl enzymes were at 100 μM, 20 μM and 10 μM (respectively).

[0072] FIG. 13 provides a simplified process overview of bottled coffee production including where a decaffeinatingenzyniecouldbe used. From leftto right; ground roasted coffee is extractod with water; spent coffee grounds are separated from the brewed liquid coffee; this coffee extinct is then used as an ingredient in a ready-to-driak coffee formula that may include other ingredients or specifications (e.g. sugar, flavors, dairy, pH adjustments); the product is pasteurized then 'bottled, or bottled then pasteurized, depending on the thermal process selec ted. A caffeine-reactive enzyme could be added during the brew stage, after the grounds are separated from the coffee extract, or during the ingredient mixing-adjustment (batching) stage. Pasteurization would likely inactivate the enzyme, depending on pasteurization conditions and enzyme denaturation temperature.

[0073] FIGs. 14A-14F provides the test results of activity of cdmA2t, cdmD2, and gdh l in Starbucks Signature Black Cold Brew Coffee Concentrate with 0.05 mM Fe(Cl)2 , 12.5 mM glucose, and 0.5 mM NADU Unless otherwise specified, cdmA2t was 70 μM, cdmD2 was 10 μM, and gdh l was 10 μM. Assays were performed at room temperature and caffeine concentration quantified by LCMS. FIGs. 14A-14C: Effect of varying concentrations of cdmA2t (FIG. 14A), cdm.D2 (FIG. 14B), and gdhl (FIG. 14C) on caffeine reduction over a 240 minute time period. FIGs. 14D-14F; Effect of varying concentrations of cdmD2 on caffeine reduction while CdmA2t. concentration is held at 40 μM ( FIG. 14D), 35 μM (FIG. 14E), or 30 μM ( FIG. 14F), from 60 to 240 minutes.

[0074] FIG. 15 provides the testing results of the effect of freeze drying on enzyme activity. Each enzyme (cdmA2txedmD2, or gdhl.) was purified by the dialyzed lysateprocedure. Concentration of enzyme was estimated by SDS-PAGE. cdmA2t was 40 mg / mL, cdmD2 was 2 mg / mL, and gdhl was 10 mg / mL. For each enzyme, 1.5 mL of enzyme was combined with 1.5 mL of 1 M sucrose. Each solution was then flash-frozen in liquid nitrogen and freeze dried. Freeze drying was completed usinga Blue Alpine Medium Freeze Dry er (#BA40 MED), using the standard “Liquids'” Recipe with default settings. In brief, the Quick Start Freeze Cycle was initiated for 1 hour, followed by a 16-hour'Dty Cycle., The Final Shelf Temperature (maximum allowed temperature) was set to 44°F. After freeze-drying, the resulting white powder was stored at 22°C and reconstituted in 1 .5mL water immediately before use. Each freeze-dried enzyme was individually added to a reaction in which the other components of the reaction were freshly-prepared enzyme (e.g., freeze-dried cdmA2t. was complemented with freshly prepared cdmD2 and gdhl ) in the standard 70 μM: 10 μM: 10 μM reaction (cdm A2t:cdmD2:gdh I) and compared to a control reaction with only freshly prepared enzyme.DETAILED DESCRIPHON OF THE DISCLOSU REI. Definitions

[0075] Unless stated otherwise, ail technical and scientific terms used herein have the same meaning as commonly underSood by those of ordinary skill in the art to which the disclosure belongs. While the following terms are believed to be well understood by one of ordinary skills in the art, the following definitions are set forth to facilitate explanation of the presently disclosed subjectmatter. Although any methods and . materials similar or equivalent to those described hereinmay be used in the pra ctice or testing of the present disclosure, preferred methods and materials are described. The following terms are defined below. These definitions are for illustrative purposes and are not intended to limit the common meaning in the art of the defined terms,

[0076] The term “a” or “an” refers to one or more of that entity, i.e., can refer to a plural referent. As such, the terms “a” or “an,” “one or more” and “at least one” are used interchangeably herein. In addition, reference to “an element” by the indefinite article “a” or “an” does not exclude the possibility that more than one of the elements is present, unless the context clearly requires that there be one and only one of the elements.

[0077] As used in this specification, the term “and / or” is used in this disclosure to mean either “and” or “or” unless Indicated otherwise.

[0078] Throughout this specification, unless the context requires otherwise, the words “comprise,” or variations such as “comprises” or “comprising,” will be understood to imply the inclusion of a stated element or integer or group of elenrenitsorintegers bin northe exclusion of any other element or integer or group of elements or integers.

[0079] As used in this application, the terms “about” and “approximately”' are used, as equivalents. Any numerals used in this application with or without about / approximately are meant to cover any normal fluctuations appreciated by one of ordinary skill in the relevant art. In certain embodiments, the term “approximately” or “about” refers to a range of values that fall within 25%, 20%, 19%, 18%, 17%, 16%, 15%, 1.4%, 13%, 12%, 1 1 %, 10%, 9%, 8%, 7%, 6%, 5%, 4%, 3%, 2%, 1%, or less in either direction (greater than or less than ) of the stated reference value unless otherwise stated or otherwise evident from the context (except where such number would exceed 100% of a possible value),

[0080] As used herein, “food” refers to any substance that is eaten, drunk, inhaled, or otherwise taken into the body of an animal or a human . As used herein, “food precursor” refers to any raw material that is used in making edible items.

[0008] ] As used herein, an “effective amount,” “in an amount to be effective,” or “in an amount to effectively” are synonymous and all refer to the amount (e.g., in volume, size, or weight) of the enzymes, compositions, and / or kits of the presen t disclosure that .is sufficient to achieve the desired level or percentage of decaffeinaticm (i.e,, reduction or elimination of caffeine) when those enzymes, compositions, and / or kits are applied to, added to, combined with, or are otherwise comein contact with a substance (e.g., a food) containing caffeine (e.g. , coffee, tea, or energy drink containing guarana extract),

[0082] As used herein, the term “at least a portion” or '‘fragment” of a nucleic acid or polypeptide means a portion having the minimal size characteristics of such sequences, or any larger fragment of the full-length molecule, up to and including the full-length molecule. A fragment of a polynucleotide of the disclosure may encode a biologically active portion of a genetic regulatory element. A biologically active portion of a genetic regulatory element, can be prepared by isolating a portion of one of the polynucleotides of the disclosure that comprises the genetic regulator element and assessing activity as described herein. Similarly, a portion of a polypeptide may be 4 amino acids, 5 amino acids, 6 amino acids, 7 amino acids, and so on, going up to the full-length polypeptide. The length of the portion to be used will depend on the application. A portion of a nucleic acid useful as a hybridization probe may be as short as 12 nucleotides; in some embodiments, it is 20 nucleotides. A portion of a polypeptide useful as an epitope maybe as short as 4 amino acids. A portion of a polypeptide that performs the function of the full-length polypeptide would generally be longer than 4 amino acids. In some embodiments, a fragment of a polypeptide or polynucleotide comprises at least 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 95%, 96%, 97%, 98%, or 99% of the entire length of the reference polypeptide or polynucleotide. In some embodiments, a polypeptide or polynucleotide fragment may contain 5, 10, 15 , 20, 25, 30, 35 , 40, 45 , 50, 60, 70, 80, 90, I 00, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 2000 or more nucleotides or amino acids. The term “domain” as used herein refers to a portion of a polypeptide having a specified activity. For example, a cdmA domain has cdmA activity, e.g., as described herein.

[0083] As used herein, the term “codon optimization" implies that the codon usage of a DNA or RNA is adapted to that of a cell or organism of interest to improve the transcription rate of said recombinant nucleic acid in the cell or organism of interest. Th e skilled person knows a target nucleic acid can be modified at one position due to the codon degeneracy, whereas this modification willstill lead to the same amino acid sequence atdiat position after translation, which is achieved by codon optimization to take into consideration the species-specific codon usage of a target cell or organism.

[0084] As used herein, the term “endogenous” or “endogenous gene,” refers to the naturally occurring gene, in the location in which it is naturally found within the host cell genome.“Endogenous gene” is synonymous with “native gene'’ as used herein. An endogenous gene as described herein can include alleles of naturally occurring genes that have been mutated according to any of the methods of die present disclosure.

[0085] As used herein, the term “exogenous" refers to a substance coming from some source other than its native source. For example, the terms “exogenous protein, ” or “exogenous gene” refer to a protein or gene from a non-native source, and that has been artificially supplied to a biological system. As used herein, the term “exogenous" is used interchangeably with the term “heterologous,”' and refers to a substance coming from some source other than its native source.

[0086] The terms “genetically engineered host cell,” “recombinant host cell,” and “recombinant strain” are used interchangeably herein and refer to host cells thathave been genetically engineered by the methods of the present disclosure. Thus, the terms include a host cell (e.g., bacteria, yeast, cell, fungal cell, etc. ) that has been genetically altered, modified, or engineered, such that itexhibits an altered, modified, or different genotype and / or phenotype (e.g. , when, the genetic mod ification affects coding nucleic acid sequences), as compared to the naturally-occurring host cell from which it was derived. It is understood that the terms refer not only to the recombinant host cell in question, but also to the progeny or potential progeny of such a host cell.

[0087] As used herein, the term “heterologous” refers to a substance coming from some source or location other than its native source or location. In some embodiments, the term “heterologous nucleic acid” refers to a nucleic acid sequence that is not naturally found, in the organism. For example, the term “heterologous promoter” may refer to a promoter that has been taken from one source organism and utilized in another organism, in wh icb the promoter is not naturally found. However, the term “heterologous promoter" may also refer to a promoter that is from within the same source organism, but has merely been moved to a novel location, in which said promoter .is not normally located.

[0088] Heterologous gene sequences can be introduced into a target cell by using an “expression vector,” which can be a eukaryotic expression vector. Methods used to construct vectors are well known to a person sk illed in the art and described in various publications. In particular, techniques for constructing suitable vectors, including a description of the functional components such -as promoters, enhancers, termination and polyadenylation signals, selection markers, origins of replication, and splicing signals, are reviewed in the prior art. Vectors may include but are not limited to plasmid vectors, phagemids, cosmids, artiiicial / mini-chroniosomes (e.g. ACE), or viralvectors such as baculovirus, retro virus, adenovirus, adeno-associated virus, herpes simplex virus, retroviruses, bacteriophages. The eukaryotic expression vectors will typically contain also prokaryotic sequences that facilitate the propagation of the vector in bacteria such as an origin of replication and antibiotic resistance and / or tolerance genes for selection in bacteria. A variety of eukaryotic expression vectors, containing a cloning site into which a polynucleotide can be operatively linked, are well known in the art and. some are commercially available from companies such as Siratagene, La Jolla, Calif.; Invitrogen, Carlsbad, Calif.; Promega, Madison, Wis., or BD Biosciences Clontecb, Palo Alto, Calif. In one embodiment the expression vector comprises at least one nucleic acid sequence which is a regulatory sequence necessary for transcription and translation of nucleotide sequences that encode for a peptide / polypeptlde / pfotein of interest.

[0089] As used herein, the term “naturally occurring’’ as applied to a nucleic acid, a polypeptide, a cell, or an organism, refers to a nucleic acid, polypeptide, cell, or organism that is found in nature. The term “naturally occurring'' may refer to a gene or sequence derived from a naturally occurring source. Thus, for the purposes of this disclosure, a “non-naturally occurring” sequence is a sequence that has been synthesized, mutated, engineered, edited, or otherwise modified to have a different sequence from known natural sequences. In some embodiments, the modification may be at the protein le ve I (e..g. , amino acid substitutions). In other embodiments, the modification may be at the DMA level (e.gx, nucleotide substitutions).

[0090] As used herein, the term '’nucleotide change" or “nucleotide modification” refers to, e.g„ nucleotide substitution, deletion, and / or insertion, as is well understood in the art. For example, such nucleotide changes / modifications include niirtationscontainingakerations tliatproduce silent substitutions, additions, or deletions, but do not alter the properties or activities of the encoded protein or how the proteins are made. As another example, suchnucleotidechanges / modificatkrns include mutations containing alterations that produce replacement substitutions, additions, or deletions, that alter the propertiesor activities of the encoded protein or how the proteins are made.

[0091] As used herein, the term “protein modification” refers to, e,g., amino acid substitution, amino acid modification, deletion, and / or insertion, as is well understood in the art.

[0092] As used herein, the term “operably linked” refers to the association of nucleic acid sequences on a single nucleic acid fragment so that the function of one is regulated by the other. For example, a promoter is operably linked with a coding sequence when it can regulate the expression of that coding sequence (i.e., that the coding sequence is under the transcriptionalcontrol of the promoter). Coding sequences can be operably linked to regulatory sequences in a sense or antisense orientation. In another example, the complementary RNA regions of the disclosure can be operably linked, either directly or indirectly, 5' to the target mRNA, or 3' to the target mRNA , or within the target mRNA, or a first complementary region is 5' and its complement is 3' to the target mRNA.

[0093] The terms “polynucleotide ” “nucleic acid,” and “nucleotide sequence / ’ used interchangeably herein, refers to a polymeric form of nucleotides of any length, either ribonucleotides or deoxyribonncleotides, or analogs thereof, This term refers to the primaiy structure of the molecule, and thus includes double- and single-stranded DNA, as well as double- and single-stranded RNA. This term includes, but is not limited to, single-, double-, or rnulti- stranded DNA or RNA, genomic DNA, cDNA, DNA-RNA hybrids, or a polymer comprising purine and pyrimidine bases or other natural, chemically, or biochemically modified, non-natural, or derivatized n ucleotide bases. It also includes modified nucleic acids such as methylated and'br capped nucleic acids, nucleic acids containing modified bases, backbone modifications, and the like. “Oligonucleotide” refers to polynucleotides of between about 5 and about 100 nucleotides of single- or double-stranded DNA. However, for the purposes of this disclosure, there is no upper limit to the length of an oligonucleotide. Oligonucleotides are also known as ‘’oligomers” or “oligos” and may be isolated from genes, or chemically synthesized by methods known in the art. The terms “polynucleotide” “nucleic acid,” and “nucleotide sequence” should be understood to include, as applicable to the embodiments being described, single -stranded (such as sense or antisense) and double-stranded polynucleotides.

[0094] The terms “peptide,” “polypeptide,” and. “protein” are used interchangeably herein, and refer to a polymeric form, of amino acids of any length, which can inchide coded andnon-coded amino acids, chemically or biochemically modified or derivatized amino acids, and polypeptides having modified peptide backbones. As used herein, an amino acid sequence “coding for” a protein means the protein comprises that amino acid sequence.

[0095] As used herein, the phrases “recombinant construct,” “expression construct, chimeric construct,” “construct,” and “recombinant DN A construct” are used interchangeably herein. A recombinant construct comprises an artificial combination of nucleic acid fragments, e.g., regulatory and coding sequences that are not found together in nature. For example, a chimeric construct may comprise regulatory sequences and coding sequences that are derived from varioussources, or regulatory sequences and coding sequences derived from the same source but arranged in a manner different than that found in nature. Such construct may be used by itself or may be used in conjunction with a vector. If a vector is used then the choice of vector is dependent upon the method that will be used io transform host cells as is well k no wn to those skilled in the art. For example, a plasmid vector can be used. The skilled artisan is aware of the genetic elements that must be present on the vector to successfully transform, select and propagate host cells comprising any of the isolated nucleic acid fragments of the disclosure. The skilled artisan will also recognize that different independent transformation events will result in various levels and patterns of expression (Jones tri of , (1985) EMBO J. 4:2411 -2418; De Almeida tri al , (1989) Mol, Gen. Genetics 218:78-86), and thus that multiple events must be screened to obtain lines displaying the desired expression level and pattern. Such screening may be accomplished by Southern analysis of DNA, Northern analysis of mRNA expression, immunoblotting analysis of protein expression, or phenotypic analysis, among others. Vectors can be plasmids, viruses, bacteriophages, proviruses, phagemids, transposons, artificial chromosomes, and the like, which replicate autonomously or can integrate into a chromosome of a hosted L A vector can also be a naked RNA polynucleotide, a naked DNA polynucleotide, a polynucleotide composed of both DNA and RNA within the same strand, a poly-lysine-canjugated DNA or RNA, a peptide-conjugated DNA or RNA, a liposome-conjugated DNA, or the like, which is not autonomously replicating. As used herein, the term “expression” refers to the production of a functional end-product mg., an mRNA or a protein (precursor or mature).[00961 The term “sequence identity" refers to the percentage of bases or amino acids between two polynucleotide or polypeptide sequences that are the same, and in the same relative position. As such one polynucleotide or polypeptide sequence has a certain percentage of sequence identity compared to another polynucleotide or polypeptide sequence. For sequence comparison, typically one sequence acts as a reference sequence, to which test sequences are compared. The term “reference sequence''’ refers to a molecule to which a test sequence is compmed. When percentag? of sequence identity is used in reference to proteins it is recognized that residue positions which are not identical often differ by conservative amino acid substitutions, where amino acid residues are substituted for other amino acid residues with similar chemical properties (e g., charge or hydrophobicity) and therefore do not change die functional properties of the molecule. Where sequences differ in conservative substitutions, the percent sequence identity may be adjustedupwards to correct for the conservative .nature of the substitution. Sequences which differ by such conservative substitutions are said to have "sequence similarity" or "similarity . " Means for making this adjustment are well-known to those of skill in the art. Typically this involves scoring a conservative substitution as a partial rather than a full mismatch, drerebyincreasingthe percental sequence identity. Thus., for example, where an identical amino acid is given a score of 1 and a non-conservative substitution is given a score of zero, a conservative substitution is given a score between zero and 1 , The scoring of conservative substitutions is calculated, e.g., according to the algorithm of .Meyers and Miller, Computer App lie. Biol. Sci., 4:11-17 (1988).

[0097] “Complementary” refers to the capacity for pairing, through base stacking and specific hydrogen bonding, between two sequences comprising naturally ornon-naturally occurring bases or analogs thereof. For example, if a base at one position of a nucleic acid is capable of hydmgen bonding with a base at the corresponding position of a. target, then the bases are considered to be complementary to each other arthat position. Nucleic acids can comprise universal bases, or inert abasic spacers that provide no positive or negative contribution to hydrogen bonding. Base pairings may include both canonical Watson-Crick base pairing and non-Watson-Crick base pairing (e.g,, Wobble base pairing and Hoogsteen base pairing). It is understood that for complementary base pairings, adenosine-type bases (A ) are complementary to thymidine-type bases (T) or uracil-type bases (U), that cytosine-type bases (C) are: complementary to guanosine-type bases (G), and that universal bases such as such as 3-nitropyrroleor 5-nitroindole can hybridize to and are considered complementary to any A, C, U, or T. Nichols ez at , Nature, 1994 ;369:492-493 and Loakes et aL Nucleic Acids Res., 1994;22:4039-4043. Inosine (I) has also been considered in the art. to be a universal base and is considered complementary to any A, C, U, or T. See Watkins and Santa Lucia, Nucl. Acids Research, 2005; 33 (19): 6258-6267.

[0098] As referred to herein, a “complementary nucleic acid sequence" is a nucleic acid sequence comprising a sequence of nucleotides that enables it to non-covalently bind to another nucleic acid in a sequence-specific, antiparallel, manner (z,e., a nucleic acid specifically binds to a complementary nucleic acid) under the appropriate in vtiro and / or in. vivo conditions of temperature and solution ionic strength.

[0099] Methods of sequence alignment for comparison and determination of percent sequence identity and percent complementarity are well known in the art. Optimal alignment of sequences for comparison, can be conducted, by the homology alignment algorith m of Needleman. andWunsch, (1970) J. Mol. Biol. 48:443, by the sea rch for similarity method of Pearson and Lipmao, ( 1988) Proc. Nat' L Acad, Sei. USA 85 :2444, by computerized implementations ofthese algorithms (GAP, BESTFIT, FASTA, and TFASTA in the Wisconsin Genetics Software Package, Genetics Computer Group, 575 Science Dr.. Madison, WT), by manual alignmentand visual inspection (see, e.g, , Brent et al., (2003) Current Protocols in Molecular Biology), by use of algorithms know in the art including the BLAST and BLAST 2.0 algorithms, which are described in Altschul et al., (1977) Nuc. Acids Res. 25:3389-3402; and Altschul et al., (1.990) J. Mol. Biol. 215:403-410, respectively. Software for performing BLAST analyses is publicly available through the National Center for Biotechnology Information. Some alignment programs are Mac Vector (Oxford Molecular Ltd, Oxford, U.K..), ALIGN Plus (Scientific and Educational Software, Pennsylvania) and AlignX ( Vector NTL hmtrogen, Carlsbad, CA). Another alignment program is Sequencher (Gene Codes, Ann Arbor, Michigan), using defan It parameters, and MUSCLE (Multiple Sequence Comparison by Log-Expection; a computer software licensed as public domain).

[0100] Herein, the term “hybridize" refers to pairing between complementary nucleotide bases (e.g. , aden ine (A) forms a base pair with thymine (T) in a DNA molecule and with uracil (U) in an RNA molecule, and guanine (G) forms a base pair with cytosine (C) in both DNA and RNA molecules) to form a double-stranded nucleic acid molecule. (Nee, e,g. , Wahl and Berger (1987) Methods Enzymol. 152:399; Kimmel, (1987) Methods Enzymol 152:507). In addition, it is also known in the art that for hybridization between two RNA molecules (e.g., dsRNA), guanine (G) base pairs with uracil (U). For example, G / U base-pairing is partially responsible for the degeneracy ( i.e. , redundancy) of the genetic code in the context of tRN A anti-codon base-pairing with codons in niRN A . In the context of this disclosure, a guanine (G) of a protein-binding segment (dsRNA dup lex) of a guide RNA molecule is considered complementary to an uracil (U), and vice versa. As such, when a G / U base-pair can be made at a given nucleotide position a protein-binding segment (dsRNA duplex) of a guide RNA molecule, the position is not considered to be non- complementaiyybutis instead considered to be complementary. It is understood in the art that the sequence of polynucleotide need not be 100% complementary to that of its target nucleic acid to be : specifically hybridizable. Moreo ver, a polynucleotide may hybridize over one or more segments such that intervening or adjacent segments are not involved in the hybridization event (e.g., a loop structure or hairpin structure). A polynucleotide can comprise at least 70%, at least 80%, at least90%, at least 95%, at least 99%, or 100% sequence complementarity to a target region within the target nucleic acid sequence to which they are targeted.

[0101] The term “modified” refers to a substance or compound (e.g., a cell, a polynucleotide sequence, and / or a polypeptide sequence) that has been altered or changed as compared to the corresponding unmodified substance or compound.

[0102] “Isolated” refers to a material that is free to varying degrees from components which normally accompany it as found in its native state.

[0103] By “biologically active portion” means a portion of a full-length parent peptide or polypeptide which portion retains an activity of the parent molecule. As used herein, the tenn “biologically active portion” includes deletion mutants and peptides, for example of at least about 8, 9, 10, 11. 12, 13, 14, 1 5, 16, 17, 18, 19, 20, 21 , 22, 23, 24, 25, 30,40, 50, 60, 70, 80, 90, 100, 120, 150, 300, 400, 500, 600, 700, 800, 900 or 1000 contiguous amino acids, which comprise an activity of a parent molecule. Portions of this type may be obtained through the application of standard recombinant nucleic acid techniques or synthesized using conventional liquid or solid phase synthesis techniques. For example, reference may be made to solution synthesis or solid phase synthesis as described, for example, in Chapter 9 entitled “Peptide Synthesis” by Atherton and Shephard which is included in a publication entitled “Synthetic Vaccines” edited by Nicholson and published by Blackwell Scientific Publications. Alternatively, peptides can be produced by digestion of a peptide or polypeptide of the disclosure with proteinases such as endoLys-C, endoArg-C, endoGlu-C, and staphylococcus V8 -protease. The digested fragments can be purified by, for example, high performance liquid chromatographic (IIPLC) techniques. Recombinant nucleic acid techniques can also be used to produce such portions.

[0104] By “corresponds to” or “corresponding to” is meant a polynucleotide (a) having a nucleotide sequence that is substantially identical or complementary to all or a portion of a reference polynucleotide sequence or (b) encoding an amino acid sequence identical to an amino acid sequence in a peptide or protein,. This phrase also includes within its scope a peptide or polypeptide having an amino acid sequence that is substantially identical to a sequence of amino acids in a reference peptide or protein.

[0105] As used herein, the term “derived from” refers to the origin or source, and may include naturally occurring, recombinant, unpurified, or purified molecules. A nucleic acid or an aminoacid derived from an origin or source may have all kinds of nucleotide changes or protein modification as defined elsewhere herein.

[0106] By “obtained from” means that a sample such as, for example, a nucleic acid extractor polypeptide extract is isolated from, or derived from, a particular source.

[0107] By “variant” polypeptide is intended a polypeptide derived from the native protein by deletion (so-called truncation) or addition of one or more amino acids to the N-terminal and / or C- terminal end of the native protein; deletion or addition of one or more amino acids at one or more sites in the native protein; or substitution of one or more amino acids at one or more sites in the native protein. Variant proteins encompassed by the present disclosure are biologically active, dial is they continue to possess the desired biological activity of the native protein, that is, modulating or regulatory activity as described herein. Such variants may result from, for example, genetic polymorphism or from human manipulation. Biologically active variants of a native protein of die disclosure will have at least 40%, 50%, 60%, 70%, generally at least 75%, 80%, 85%, preferably about 90% to 95% or more, and more preferably about 98%o.nnore sequence identity to the amino acid sequence for the native protein as determined by sequence alignment programs described elsewhere herein using default parameters. A biologically active variant of a protein of the disclosure may differ from that protein by as few as 1 -15 amino acid residues, as few as I -10, such as 6-10, as few as 5, as few as 4, 3, 2, or even I ammo acid residue.

[0108] The proteins of the disclosure may be altered, in various ways including amino acid substitutions, deletions, truncations, and insertions. Methods for such manipulations are known in the art. For example, amino acid sequence variants of the proteins can be prepared by mutations in the DNA. Methods for mutagenesis and nucleotide sequence alterations are well known in the art. See, for ex ample, Kunkel (1985) Proc. Natl. Acad, Sci. USA 82:488-492; Kunkel etal, (1987) Methods in Enzymol. 154:367-382; U.S. Pat. No. 4,873,192; Walker and Gaastra, eds. ( 1983) Techniques in Molecular Biology (MacMillan Publishing Company, New York) and the references cited therein. Guidance as to appropriate ammo acid substitutions that do not affect biological activity of the protein of interest may be found in the model of Dayhoff etal. (1978) Allas of Protein Sequence and Structure (Nall. Biomed. Res. Found., Washingion, D.C.), herein: incorporated by reference. Conservative substitutions, such as exchanging one amino acid with another having similar properties, may be preferable.

[0109] Individual substitutions deletions or additions that alter, add, or delete a single amino acid or a small percentage of amino acids (typically less than 5%, more typically less than 1%) in an encoded sequence are “conservatively modified variations,'’ where the alterations result in the substitution of an amino acid with a chemically similar amino acid. Conservative substitution tables providing functionally similar ammo acids are well known in the art, I'he following five groups each contain amino acids that are conservative substitutions for one another. Aliphatic: Glycine (G), Alanine (A), Valine (V), Leucine (L), Isoleucine (I); Aromatie: Phenylalanine (F), Tyrosine (Y), Tryptophan (W); Sulfur-containing: Methionine (M), Cysteine (C); Basic: Arginine I, Lysine (K), Histidine (H); Acidic: Aspartic acid (D), Glutamic acid (E), Asparagine (N), Glutamine (Q). See also Creighton, 1984. In addition, individual substitutions, deletions, or additions which alter, add or delete a single amino acid or a small percentage of amino acids in an encoded sequence are also “conservatively modified variations.''

[0110] As used herein, the term “gene” refers to any segment of DMA associated with a biological function. Thus, genes include, but are not limited to, coding sequences and / or the regulatory sequences required for their expression. Genes can also include nonexpressed DMA segments that, for example, form recognition sequences for other proteins. Genes can be obtained from a variety of sources, including cloning from a source of interest, or synthesizing from known or predicted sequence information, and may include sequences designed to have desired parameters.

[0111] As used herein, the term “genotype” refers to the genetic makeup of an individual cell, cell culture, tissue, organism (e.g., a bacteria), or group of organisms.

[0112] As used herein, the term “allele(s)” means any of one or more alternative forms of a gene, all of which alleles re la te to at least one trait or characteristic, In a diploid cell, the two alleles of a given gene occupy corresponding loci on a pair of homologous chromosomes. Since the present disclosure relates to QTLs, i.e., genomic regions that may comprise one or more genes or regulatory sequences, ir is in some instances more accurate to refer to “hap lotype” (i.e., an allele of a chromosomal segment) instead of “allele,” however, hi those instances, the term “allele” should be understood to comprise the term “haplotype ” Alls les are considered identical when they express a similar ph eno type. Differences in sequence are possible but not important if they do not influ en ce ph eno type ,

[0113] As used herein, the term “locus’' (plural: “loci”) refers to any site that has been defined genetically. A locus may be a gene, or part of a gene, or a DNA sequence that has some regulatory role, and may be occupied by different Sequences.

[0114] As used herein, the term ’'homologous" or "homolog" is known in the art and refers to related sequences that share a common ancestor or family member and are determined based on the degree of sequence identity. The terms “homology,” ‘'homologous,” “substantially similar” and “corresponding substantially” are used interchangeably herein. Homologs usually control, mediate, or Influence the same or similar biochemical pathways, yet homologs may give rise to differing phenotypes. It is therefore understood, as those skilled in the art will appreciate, that the disclosure encompasses more than the specific exemplary sequences. These terms describe the relationship between a gene found in one species, subspecies, variety, cultivar, or strain and the corresponding or equivalent gene in another species, subspecies, variety-, cultivar or strain. For purposes of this disclosure homologous sequences are compared.

[0115] 'lire term “homolog” is sometimes used to apply to the relationship between genes separated by the eventof speciation (see “ortholog”) or to the relationship between genes separated by the event of genetic duplication (see “paralog”).

[0116] The term “homeolog” refers to a homeologous gene or chromosome, resulting from polyploidy or chromosomal duplication events. This contrasts with the more common 'homolog,' which is defined immediately above.

[0117] The term “otfholog” refers to genes in different species that evolved from a common ancestral gene by speciation. Normally, orthologs retain the same function during evolution. Identification of orthologs is critical for reliable prediction of gene function in newly sequenced genomes.

[0118] The term “paralog” refers to genes related by duplication within a genome, While orthologs generally retain the same function in the course of evolution, paralogs can evolve new functions, even if these are related to the original one.

[0119] “Homologous sequences” or “homologs” or “orthologs” are thought, believed, or known to be functionally related. A functional relationship may be indicated in any one of several ways, including, but not limited to: (a) degree of sequence identity and / or (b) the same or similar biological function. Preferably, both (a) and (b) are indicated. The degree of sequence identity may vary, but in one embodiment, is at least 50% (when using standard sequence alignmentprograms known in the art), at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, at least. 85%, at least 90%, at least about 91 %, at least about 92%, at least about 93%, at least about 94%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least 98.5%, or at least about 99%, or at least 99.5%, or at least 99.8%, or at least 99.9%. Homologcan be determined using software programs readily available in the art, such as those discussed in Current Protocols in Molecular Biology (F.M. Ausubel e / u / ., eds. , 1987) Supplement 30, section 7.718, Table 7.71. Some alignment programs are iMac Vector (Oxford Molecular Ltd, Oxford, U .K .) and ALIGN Plus (Scientific and Educational Software, Pennsylvania ). Other non-limiting alignment programs include Sequencher (Gene Codes, Ann Arbor, Michigan), AlignX, and Vector NTI (Invitrogen, Carlsbad, CA).

[0120] As used herein, the term “derived from" refers to the origin or source, and may include naturally occurring, recombinant, unpurified, or purified molecules. A nucleic acid or an amino acid derived from an origin or source may have all kinds of nucleotide changes or protein, modification as defined elsewhere herein.IL Caffeinated Food[001.211 The chemical name for the bitter white powder known as caffeine is 1 ,3,7 trimethylxanthi.ne. Caffeine is a naturally occurring substance present in coffee beans, tea leaves, guarana, and cocoa beans. Guarana is a seed from a South American plant that is processed as an extract in foods, energy drinks, and energy supplements. Caffeine has become the world’s most popular stimulant due to its ability to boostalertness and energy levels. Caffelneis absorbed wiflm about 45 minutes after consuming, and peaks in the blood anywhere from 15 minutes to 2 hours.

[0122] A cup or 8 ounces of brewed coffee contains about 95- 100 mg caffeine, while that same amount of instant coffee contains about 60 mg caffeine. Decaffeinated coffee contains about 4 mg of caffeine. An espresso shot or 1.5 ounces contains about 63-65 mg caffeine. A cup of black tea contains about 47-48 mg caffeine per 8 ounces, while a cup of green tea contains about 28 mg. Decaffeinated tea contains about 2 mg caffeine. A 12 -ounce can of regular or diet dark cola contains about 40 mg caffeine. The same amount of Mountain Dew contains 55 mg caffeine. One ounce of dark chocolate contains about 24 mg caffeine., whereas milk chocolate contains one- quarter of that amount. Guarana seeds contain about four times the amount of caffeine as that found in coffee beans. Some drinks containing extracts of guarana seeds can contain up to 125 mg caffeine per serving. One cup or 8 ounces of an energy drink contains about 85 mg caffeine.However the standard energy drink serving is 16 ounces, which doubles the caffeine to 170 mg Energy shots are much more concentrated than the drinks; a small 2 ounce shot contains about 200 mg caffeine. Caffeine supplements contain about 200 mg per tablet, or the amount in 2 cups of brewed coffee.

[0123] The average American adult consumes between 120 milligrams and 215 milligrams of caffeineper day . The recommended limit of caffeine is 400 milligrams. Compared to people living in the countries of Europe, Asia, and Latin America, U.S. residents consume significantly more of their caffeine in the form of soda, sports drinks, and energy drinks.

[0124] The Food and Drug Administration (FDA) only requires added caffeine to be listed on food and drink ingredient labels. Products that contain naturally occurring caffeine do not have to list caffeine as an ingredient, which means not all consumers realize which foods and drinks have caffeinein. them. For example, a signifi.cantportionof daily caffeine intake comes not from coffee, tea, and energy drinks, but from flavored sodas, chocolate, and other hidden sources.

[0125] Despite the name, decaffeinated coffee available as of the filing date of the present disclosure still contains trace amounts of caffeine that .may result in side effects if the consumer is sensitive to caffeine. While the exact amount may vary depending on the brand and the strength of the brew, there is still about 5 milligrams of caffeine in a standard or typical 8-ounce cup of decaf coffee.

[0126] For the information provided in this section see, e.g., Harvard TH. Chan, School of Public Health, The Nutrition Source, Caffeine and Michael Breus, What Foods Contain Caffeine, Sleep Doctor, January 24, 2024; both accessed online February 1, 2024.

[0127] The caffeinated food can be at various temperatures when applying the enzymes, enzyme compositions, and kits of the present disclosure. For example, the caffeinated food may be a hot coffee (about 50-90°C), a warm coffee (about 30-50°C), a room temperature coffee (about 15- 30°C), or a cold coffee (about 5-15°C).

[0128] In some embodiments, the caffeinated food to be decaffeinated may be at about 90°C, at about 85°C, at about 80°C, at about 75°C, at about 70°C, at about 65°C, at about 60°C, at about 55 °C, at about 50°C, at about 40°C, at about 30°C, at about 25°C, at about 20°C, at about 15°C, at about 10°C, or at about 5°C, when applying the enzymes, enzyme compositions, and kits of the pre sent disc Io sure.

[0129] In some embodiments, the caffeinated food to be deca ffeinated may be at about 5- 1. (FC, at about 5-15°C, at about 2~10°C, at about 2-5°C, at about 15-20°C, at about 15-25°C, at about 20- 22°C, at about.20-25°C, at about 15-30°C, at about 25-30°C, at about 30-50°C2 at about 50-85°C7 at about 50-80°C, at about 50~75°C, at about 50-70°C, at about 50-65°C, at about 55-75°C, at about 55-70°C; or at about 55-65°C, when applying the enzymes, enzyme compositions, and kits of the present disclosure.III. Enzymes That React With Caffeine

[0130] Several enzymes are know to react with caffeine but have disadvantages for use in food technologies. Caffeine dehydrogenases convert caffeine to trimethylurate, but there is only one published caffeine oxidase sequence, and there is not much safely data on trimethylurate consumption (4). Tn humans, caffeine is metabolized by the cytochrome P450CYPIA2, which mostly converts caffeine into paraxanthine, theophylline, and theobromine with formaldehyde as a by-product (5); however, paraxanthine maintains some of caffeine’s physiological effects such as increased blood pressure (6), and CYP1A2 also has broad substrate specificity.

[9131] We hypothesized that a class of enzymes called caffeine demethylases (cdm) could offer promise for enzymatic decaffeination. Cdms catalyze the oxidation-reduction conversion of caffeine, NADU, and O2into theobromine, NAIL, and formaldehyde (FIG. 1A) (7). The formaldehyde produced in a hypothetical reaction of 100 mg of caffeine (about 1 cup of coffee) would be about 15 mg, equivalent to the amount found naturally in about 1-2 pears (5). Caffeine demethylases are heteromeric complexes that con tain an NAD1-1 dehydrogenase protein that passes the electrons from NADH to a deme thy lase protein.

[0132] Demethylases from Pseudomonas piitida and Parabnrfcholderia caffeinifytica have been purified using Esotierzc / ua coH bacterial expression systems and. were confirmed to have activfty on caffeine (9, 10).

[0133] Other bacteria, such as Meihykinihtvin populi, ha ve been show n to metabolize caffeine in whole cell assays or to grow on caffeine-con taining media (11).

[0134] Still additional bacteria have suggested caffeine metabolism activity due to the presence of homologous demethylase genes, though these haven’ t directly been shown to be active on caffeine yet (12). These enzymes are promising for decaffeination technologies as theobromine is much less psychoactive than caffeine (13); however, the NADH requirement is expensive, andnecessitates future work in order to make this enzy matic system commercially viable. In addition, these purified enzymes have yet to have confirmed activity in foods such as roasted and brewed coffee, instead focusing on solutions of purified caffeine.

[0135] As provided in the present disclosure, we have confirmed, the activity of published caffeine demethylases, as well as disco vered new caffeine demethylases from bacteria known to act on caffeine. Of 9 ordered caffeine demeth ylase pairs, 6 pairs of enzymes were both present in the soluble fraction, and 5 enzyme pairs converted caffeine to theobromine.

[0136] As provided in the present disclosure, NADH can be replaced in the system by NAD+; glucose, and glucose dehydrogenase, which is a crucial step forward towards making this technology economically viable.

[0137] As provided, in the present disclosure, the formaldehyde produced in a hypothetical reaction of 100 mg of caffeine (about 1 cup of coffee) would be about 15 mg, equivalent to the amount found naturally in about 1 -2 pears (8). The formaldehyde produced in the reaction is minimal arid can be removed by known methods. For example, the formaldehyde produced may be removed by adding at least erne formaldehyde dehydrogenase to the enzyme cocktail.

[0138] The disclosure encompasses isolated or substantially purified enzymes, including their isolated nucleic acid or protein compositions.

[0139] Enzymes are typically isolated from microbial, animal, or plant sources. Microbial sources are particularly useful because they can be quickly grown into large colonies and are easy to store in vats prior to isolation. The separation and purification of enzymes requires multiple separation steps involving filtration, centrifugation, chromatography, and more frequently biomagiietie separation.

[0140] An '“isolated” or “purified” nucleic acid molecule orprotein, or biologically active portion thereof, is- substantially or essentially tree from components that normally accompany or interact with the nucleic acid molecule or protein as found in its naturally occurring environment. Thus, an isolated or purified polynucleotide or polypeptide is substantially free of other cellular material, or culture medium when produced by recombinant techniques, or substantially free of chemical precursors or other chemicals whenchernically synthesized. Suitably, an “isolated” polynucleotide is free of sequences (especially protein encoding sequences) that naturally flank the polynucleotide (i.e., sequences located, at the 5' and 3' ends of the polynucleotide) in the genomic DNA of the organ ism from which the polynucleotide was derived. For example, in various embod iments, (lieisolated polynucleotide can contain less than about 5 kb, 4 kb, 3 kb, 2 kb, 1 kb, 0.5 kb, or 0.1 kb of nucleotide sequences that naturally flank the polynucleotide in genomic DNA of the cell from which tiie polynucleotide was derived. A polypeptide that is substantially free of cellular material includes preparations of protein having less than about .30%, 20%, 10%, 5%, (by dry weight) of contaminating protein. When die protein of the disclosure or biologically active portion thereof is recombinantly produced, culture medium suitably represents less than about 30%, 20%, 10%, or 5% (by dry weight) of chemical precursors or non-protein-of-interest chemicals.

[0141] ] A portion of a caffeine demethylase cdmA domain or cdmD domain nucleotide sequence that encodes a biologically active portion of a cdmA or cdmD polypeptide, respectively, of the disclosure can comprise or encode at least about 5, 6, 7, 8, 9; 10, 1 1, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21 , 22, 23, 24, 25,30, 40, 50, 60, 70, 80, 90, 1.00, 120, 150, 300, 400, 500, 600, 700, 800, 900 or 1000 contiguous amino acid residues, or almost up to the total number of amino acids present in a full-length cdm polypeptide of the disclosure, Portions of a cdm nucleotide sequence that are useful as hybridization probes or PCR primers generally need not encode a biologically active portion of a cdm polypeptide, respectively.

[0142] Thus, a portion of a caffeine demethylase cdmA domain or cdinD domain nucleotide sequence may encode a biologically active portion of a cdmA or cdmD polypeptide, respectively, or it may be a fragment that can be used as a hybridization probe or PCR primer using standard methods known in the art. A biologically active portion of a cdm polypeptide can be prepared by isolating a portion of one of the cdm nucleotide sequences of the disclosure, expressing the encoded portion of the cdm polypeptide (e.g., by recombinant expression in vitro), and assessing the activity of the encoded .portionofthe cdm polypeptide. Nucleic acidmolecules thatare portions of a cdm nucleotide sequence comprise at least about 15, 16, 17, .18, 19, 20, 25, 30, 50, 75, 100, 150, 200, 250, 300, 350,400, 450, 500, 550, 600, or 650 nucleotides, or almost up to the number of nucleotides present in a full-length cdm nucleotide sequence disclosed, herein.

[0143] The disclosure also contemplates variants of the disclosed nucleotide sequences. Nucleic acid variants can be naturally occurring, such as allelic variants (same locus), homologues (dif ferent locus), and orthok>gues(dif ferentorgrinism) or can be uon-naturally occurring. Naturally occurring variants such as these can be identified with the use of well-known molecular biology techniques, as, for example, with polymerase chain reaction (PCR ) and hybridization techniques as known in the art. non -naturally occurring variants can be made by mu tagenesis techn iques,including. those applied to polynucleotides, cells, or organisms: The variants can contain nucleotide substitutions, deletions, inversions, and insertions. Variation can occur in either or both the coding and non-coding regions. The variations can produce both conservative and non -conservative amino acid substitutions (as compared in the encoded product). For nucleotide sequences, conservative variants include those sequences that, because of the degeneracy of the genetic code, encode the amino acid sequence of one of the cdm polypeptides of the disclosure. Variant nucleotide sequences also include synthetically derived nucleotide sequences, such as those generated, for example, by using site-directed mutagenesis but which still encode a cdm polypeptide of the disclosure . V ariants of a particular nucleotide sequence of the disclosure will have at least about 30%, 40% 50%, 55%, 60%, 65%, 70%, generally at least about 75%, 80%, 85%, desirably about 90% to 95% or more, and more suitably about 98% or more sequence identity to that nucleotide sequence as determined by sequence alignment programs described elsewhere herein using default parameters.

[0144] Variant nucleotide sequences also encompass sequences derived from a mutagenic or recombinant procedures such as ‘DNA shuffling’ which can be used for swapping domains in a polypeptide of interest with domains of other polypeptides. With DNA shuffling, one or more different cdm coding sequences can be manipulated to create a new cdm sequence possessing desired properties. In this procedure, libraries of recombinant polynucleotides are generated from a population of related polynucleotides comprising sequence regions that have substantial sequence identity and can be homologously recombined in vitro or in vivo. For example, using this approach, sequence motifs encoding a domain of interest may be shuffled between the cdm gene of the disclosure and other known cdm genes to obtain a new gene coding for a protein with an improved property of interest . Strategies for DNA shuffling are known in the art. See, for example: Stemmer (1994, Proc. Natl. Acad. Set. USA 9I: 10747-10751; 1994, Nature 370:389- 391 ); Crameri etal. ( 1997, Nature Biotech. 15:436-438 ); Moore etal. { 1997, J. Mol. Biol . 272:336- 347); Zlang et al. (1997 Proc. Natl. Acad. Set. USA 94:450-44509); Crameri etal. (1998, Nature 391 :288-291 ); and U.S. Pat. Nos. 5,605,793 and 5,837,458, the contents of each which are incorporated by reference in their entirety .As discussed herein, targeted mutagenesis within the active site of the enzymes of the present disclosure may be used to improve binding or catalysis properties to the substrate caffeine molecule.

[0145] Redesigning the interaction region between the cdmA and cdmD enzymes to facilitate better / tighter interactions, may be accomplished, e.g., by using either rational mutagenesis or machine learn ing-basedniethods forredesigtt such as diffusion or ProteiftMPNN (Protein Message Passing Neural Network), a deep learning model that predicts amino acid sequences for proteins. Machine learning based methods such as Protein.MPNN may be used to improve the stability of the enzyme system to allow for higher activity, especially at higher temperatures. Dauparas et al. Robust deep learning-based protein sequence design using ProteinMPNN. Science. 2022 Oct 7;378(6615):49-56, which is herein incorporated in its entirety.

[0146] Targeted mutagenesis in and around the active site may be used to adjust pKa values of certain residues to improve activity at selected pH.

[0147] Directed evolution campaigns with high-throughput outcome measurements may allow good coverage of screening many mutants for improved activity.

[0148] Genetically linking cdrnA and cdmD, linking cdmD and gdh, or linking all three (i.e., linking cdmA, cdmD, and gdh) might be used for improved activity and / or simplified manufacturing processes. Circularly permuting cdmA and cdmD might be used .for improved activity and / or simplified manufacturing process.

[0149] Incorporation of intra-moleculai disulfide bonds might be used to improve stability, Identification and use of cdmA, cdmD, or gdh homologues from thermophilic and / or acidophilic organisms might be used to enable enhanced.acti.vity in warmer and / or more acidic temperatures.

[0150] Incorporation of a formaldehyde dehydrogenase into the enzyme system might be used to convert generated formaldehyde to formate (if needed).

[0015] ] The present disclosure provides nucleotide sequences encoding at least a portion of or all of the disclosed cdms, homologs of cdms, orthologs of cdms, paralogs of cdms, and fragments and variations thereof.

[0152] In some embodiments, the present disclosure provides a nucleotide sequence encoding a caffeine demethylase cdmA domain or cdmD domain, and / or functional fragments and variations thereof comprising a nucleotide sequence that shares at least about 70%, about 75%, about 80%, about 81 %, about 82%, about 83%, about 84%, about 85%, about 86%, about 87%, about 88%, about 89%, about 90%, about 91%, about 92%, about 93%, about 94%, about 95%, about 96%, about 97%, about 98%, about 99%, about 99.1%, about 99.2%, about 99.3%, about 99.4%, about99.5%, about 99.6%, about 99.7%, about 99.8%, or about 99,9% sequence identity to the sequences disclosed herein.

[0153] In some embodiments, the present disclosure provides nucleotide sequences for a caffeine demethylase cdmA domain or cdmD domain, homologs of the edms, orthologs of the edms, paralogs of the edms, and fragments and variations thereof comprising nucleotide sequences that share at least about 70%, about 75%, about 80%, about 81 %, about 82%, about 83 %, about 84%, about 85%, about 86%, about 87%, about 88%, about 89%, about 90%, about 91 %, about 92%, about 93%, about 94%, about 95%, about 96%, about 97%, about 98%, about 99%, about 99.1%, about 99.2? / o, about 99.3%, about 99.4%, about 99.5%, about 99.6%, about 99.7%, about 99.8%, or about 99,9% sequence identity tn the sequences disclosed herein,

[0154] The present disclosure provides polypeptides and amino acid sequences comprising at least a portion of the proteins encoded by nucleotide sequences for a caffeine demethylase cdmA domain. or cdmD domain, homologs of the edms* orthologs of edms, paralogs of edms, and fragments and variations thereof.

[0155] The present disclosure also provides an amino add sequence encodedby the nucleic acid sequences of a caffeine demethylase cdmA domain or cdmD domain, homologs of the edms, orthologs of the edms, paralogs of edms, and / or fragments and variations thereof. In some embodiments, the present disclosure provides an isolated, polypeptide comprising an amino acid sequence that shares at least about 70%, about 75%, about 80%, about 85%, at least about 90%, about 91 %, about 92%, about 93%, about 94%, about 95%, about 96%, about 97%, about 98%, about 99%, about 99.1%, about 99.2%, about 99.3%, about 99.4%, about 99.5%, about 99.6%, about 99.7%, about 99.8%, or about 99.9% identity to an amino acid sequence encoded by the nucleic acid sequences of a caffeine demethylase cdmA domain or cdmD domain, homolog of the edms, orthologs of edms, paralogs of edms, and / or fragments and variations thereof.

[0156] In. some embodiments, the present disclosure provides an. isolated, polypeptide comprising an amino acid sequence which encodes an amino acid sequence that shares at least about 85%, about 86%, about 87%, about 88%, about 89%, about 90%, about 91%, about 92%, about 93%, about94%, about95%,about96%, about97%, about98%,about99%, about99.1%, about99.2%, about 99.3%, about 99.4%, about 99.5%, about 99.6%, about 99.7%, about 99.8%, or about 99.9% identity to an amino acid sequence encoded by the nucleic acid sequences of a caffeinedemethylase cdmA domain or cdmD domain, homologs of the cdms, orthologs of cdms, para lags of cdms, and / or fragments and- variations thereof.

[0157] The cdmA domain or cdmD domain, may have one or more active site residues. For example, in some embodiments, the cdmA domain may have, based on SEQ ID NO: 99, one or more active site residues of: a Q152, a Y 155, a R164, aN167, a F168, a T169, a D170, a F171, a H173, a F174, a H178, a L182, a E217, a A218, aP219, a I220,a F223, a Y225, a L235, a V237, a 1248, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a. F287, anddr a D290 residue. In some embodiments, the present disclosure provides a polypeptide comprising an amino acid sequence that shares at least about 70%, about 75%, about 80%, about 85%, about 90%, about 95%, or 100% identity to the active site residues of cdmA domainand / or cdmD domain wherein the cdmA domain and / or cdmD domain comprise, based on SEQ ID NO: 99, on e or more of active site residues a Q152, a Y155, a R164, a N 167, a F168, a T169, a D170, a F171 , a H173, a F174, a H178, a L182, a E217, a A218, a P219, a I220, a F223, a Y225, a 1235, a V237, a 1248, aN250, a L264, a F266, a H279,a F282, a N283, a D284, a L285, a V286, a F287, and / or a D290 residue. In other embodiments, thepresent disclosure provides a polypeptide comprisingan amino acid sequence having one, up to two, up to three, up to four, up to five, up to six , up to seven, up to eight, up to nine, or up to ten ammo acid substitutions in the active site residues of cdmA domain and / or cdmD domain, wherein the cdmA domain and / or cdmD domain comprise, based on SEQ ID NO: 99, one or more of active site residues a Q152, a Y155, a R164 , a N167, a F168, a T169, a D 170, a FI 71 , a H F73, a F1 74, a H 178, a L182, a E217, a A218, a P219, a 1220, a F223 , a Y225, a L235, a V237, a 1248, a N250, a 1264, a F266, a H279, a F282, a N283, a D284, a 1285, a V286, a F287, and / or a D290 residue.

[0158] The cdmA. domain or cdmD domain may have one or more active site residues. For example, in some embodiments, the cdmA domain may have, based on. SEQ ID NO: 100, one or more active site residues of: a Q157, a Y160, a R169, a N172, a F173, a T174, a D175, a F176, a H178, a F179, a H 183, a L187, a E222, a A223, a P224, a 1225, a F228, a Y230, a L240, a V242, a L253, a N255, a 1269, a F271, a H284, a F287, a N288, a D289, a L290, a V29L a L292, and / or a D295 residue. In some embodiments, the present disclosure provides a polypeptide comprising an amino acid sequence that shares at least about 70%, about 75%, about 80%, about 85%, about 90%, about 95%, or 100% identity to the active site residuesof cdmA domainand / or cdmD domain wherein the cdmA domain and / or cdmD domain comprise, based on SEQ I D NO: 100, one ormore of active site residues a Q 157, a Y160, a R1 69, a N172, a F173, a T1 74, a D175, a F176, a H 178, a F179, a H183, a L1 87, a E222, a A223, a P224, a 1225, a F228, a Y230, a 1240, a V242, a L253, a N255, a L269, a F271, a H284, a F287, a N288, a. D289, a L290, a V29 1, a F292, and / or a D295 residue. In other em.bodimen.ts, the present disclosure provides a polypeptide comprising an amino acid sequence having one, up to two, up to three, up to four, up to .five, up to six, up to seven, up to eight, up to nine, or up to ten amino acid substitutions in the active site residues of cdmA domain and / or cdmD domain, wherein the cdrn A domain and / or cdmD domain comprise, based on SEQ ID NO: .100, one or more of active site residues a Q 157, a Y 160, a R 169, a N172, a F173, a T174, a D175, a F176, a H178, a F179, a H183, a L187, a E222, a A223, a P224, a 1225, a F228, a Y230, a L240, a V242 , a L253 , a N255 , a L269 , a F271 , a H284., a F287 , a N288 , a D289, a L290, a V29 1, a F292, and / or a D295 residue.

[0159] In further aspects, the present disdosurep.rov.ides a polypeptide comprising an amino acid sequence that shares at least about 70%, about 75%, about 80%, about 85%, about 90%, about 95%, or 1 00% identity to SEQ ID NO: 99, wherein SEQ ID NO: 99 comprises one or more of active site residues a Q 152, a Y 155, a R164, a N 1 67, a F168, a T169, a D170, a F171 , a H173, a F174, a H178, a L182, a E21 7, a A21 8, a P21 9, a 1220, a F223, a Y225, a L235, a V237, a L248, a N250, a L264, a F266, a H279,a F282, a. N283, a D284, a L285, a V286, a F287, and / or a D290 residue. In further aspects, the present disclosure prov ides for SEQ ID NO: 99, wherein SEQ ID NO: 99 comprises one, up to two, up to three, up to four, up to five, up to six, up to seven, up to eight, up to nine, or up to ten amino acid substitutions and further comprises one or more active site residues a Q152, a Y 155, a R 164, a N 167, a F168, a T169, a D170, a F171 , a H 173, a F 174, a H178, a L182, a E217, a A218, a P219, a I220, a F223, a Y225, a L235 , a V237, a L248, a N250, a L264, a F266, a H279, a F282, a N283, a. D284, a L285, a. V286, a F287, and / or a. D290 residue.

[0160] In further aspects, the present disclosure providesapolypeptideconiprisingan amino add sequence that shares at least about 70%, about 75%, about 80%, about 8536, about 90%, about. 9534, or 10034 identity to SEQ ID NO: 100, wherein SEQ ID NO: 100 comprises one or mote of active site residues a Q157, a Y 160, a R 169, a N1 72, a F173, a. 1174, a Di 75, a F176, a H178, a F1 79, a H 183, a L187, a E222, a. A223, a P224, a 1225, a F228, a Y230, a L240, a V242, a. 1253, a N255 , a L269, a F271 , a H284, a F287, a N288, a D289, a L290, a V291, a F292. and / or a D295 residue. In further aspects, the present disclosure provides for SEQ ID NO: 100, wherein SEQ ID NO: 100 comprises one, up to two, up to three, up to four, up to five, up to six, up to seven, up toeight, tip to nine, or up to ten amino acid substitutions and further comprises one or more active site residues a Q157, a Y 160, aR169, a N172, a F1 73, a TI74, a D175, a F1 76, a H178, a F179, a H183, a L187, a E222, a A223, a P224, a 1225, a. F228, a Y230, a L240,a V242, a L-253, aN255, a L269, a F271 , a H284, a F287, a N288, a D289, a L290, a V291 , a F292, and / or a D295 residue.[0 0161 ]] In aspects, Die cdmA domain or cdmD domain comprises, based on SEQ ID NO; 99, each of the active site residues of: a Q152, a Y 155, a R164, a N 167, a F168, a T169, a D170, a F1 71 , a H173, a F1 74, a H178, a L182, a E217, a A218, a P219, a 1220, a F223, a Y225, a L235, a V237, a L248. a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a F287, and D290 residue. In other embodiments, the present disclosure provides a polypeptide comprising an amino acid sequence that shares at least about 70% , about 75%, about 80%, about 85%, about 90%, about 95%, or 100% identity to the active site residues of cdmA domain and / or cdmD domain, wherein the cdmA domain and / or cdmD domain comprises, based on SEQ ID NO: 99, each of the active site residues of a Q1 52, a Y 155, a RI64, a N167, a F168, a.T169, a D170, a F171 , a H173 , a F174, a H178, a L182, a E217, a A218, a P219, a 1220, a F223, a Y225, a L235, a V237, a L248, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a F287, and a D290 residue. In some embodiments, the present disclosure provides a polypeptide comprising the active site residues of cdm A domain and / or cdmD domain, wherein the cdmA domain and / or cdmD domain comprises one, up to two, up to three, up to four, up to five, up to six, up to seven , up to eight, up to nine, or up to ten am ino acid substitutions and further comprises, based on SEQ ID NO: 99, each of a Q152, a Y.155, a R164, a N167, a F168, a. 1169, a D170, a F1 71 , a H l 73, a F1 74, a H178, a L1 82, a E217, a A218. a P219, a 1220, a F223, a Y225, a L235, a V237, a L248, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a F287, and a D290 residue.

[0162] In aspects, The cdmA domain or cdmD domain comprises, based on SEQ ID NO: 100, each of the active site residues of: a Q157, a Y 160, a R.169, a N 172, a F173, a T174, a D175, a F176, a H178, a F1.79, a H183, a L187, a E222, a A223,a P224. a 1225, a F228, a Y230, a L240, a V242, a L253, a N255, a L269, a F271, a H284, a F287, a N2S8, a D289, a L290, a V29 L a F292, and a D295 residue. In other embodiments, the present disclosure provides a polypeptide comprising an amino acid sequence that shares at least about 70%, about 75%, about 80%, about 85%, about 90%, about 95%, or 100% identity to the active site residues of cdmA domain and.br cdmD domain, wherein the cdmA domain and / or cdmD domain comprises, based on SEQ ID NO:100; each of the active site residues o f a Q157, a Y160, a R.169, a N172, a F1 73, a T1.74, a D175, a F1 76, a H 178, a F1 79, a H 1 S3 , a L 187, a E222,. a A223, a P224, a.1225, a F228, a Y230, a L240, a V242, a L253, a N255, a L269, a F27 1, a H284, a F287, a N288, a D289, a L290, a V291, a F292, and a D295 residue. In some embodiments, the present disclosure provides a polypeptide comprising the active site residues of cdmA domain and / or cdmD domain, wherein the cdmA domain and / or cdmD domain comprises one, up to two. up to three, up to four, up to five, up to six, up to seven , up to eight, up to nine, or up to ten amino acid substitu tions and further comprises, based on SEQ ID NO: 100, each of a Q 157, a Y160, a R169, a N 172, a F173, a T174, a D 175, a F176, a H178, a F1 79, a H183, a L187, a E222, a A223, a P224, a 1225, a F228, a Y230, a L240, a V242, a L253, a N.255, a L269, a F271, a H284, a F287, a N288, a D289, a L290, a V29.1 , a F292, and a D295 residue.

[0163] In further aspects, the present disdosureprovides a polypeptide comprising an amino acid sequence that shares at least about 70%, about 75%, about 80%, about 85%, about 90%, about 95%, or 100% identity to SEQ ID NO: 99, wherein SEQ ID NO: 99 comprises each of a Q152, a Y 155, a RI64, a N I67.a F168. a TI 69, a D170, a F171, aH173, a Fi 74,a H I78, a L182, a E217, a A218, a P219, a 1220, a F223, a Y225, a L235, a V237, a L248, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a F287, and a D290 residue. In further aspects, the present disclosure provides for SEQ ID NO: 99, wherein SEQ ID NO: 99 comprises one, up to two, up to three, up to four, up to five, up to six, up to seven, up to eight, up to nine, or up to ten amino add substitutions and further comprises each ofactive site residues a Q152, a Y 155, a R 164, a N 167, a F1 68, a T169, a D1 70, a F1 71 , a H173 , a F1 74, a H178, a L1.82, a E217, a A218, a P219, a 1220, a F223, a Y225, a L235, a V237, a L248, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a V286, a F287, and a D290 residue.

[0164] In further aspects, the present disclosure providesa polypeptide comprising an amino add sequence that shares at least about 70%, about 75%, about 80%, about 85%, about 90%, about 9534, or 100% identity to SEQ ID NO: 100, wherein SEQ ID NO: 100 comprises each of a Q157, a Y160, aR169,aN172,a.F173,a T174,aD175,a.F176,aH178,aF179,a H183, aL187,a E222, a A223 , a P224, a 1225, a F.228, a Y230, a L240, a V242, a. L253, a N'255, a. 1.269, a F271 , a H284, a F287, a N288, a D289, a L290, a V291 , a F292, and a D295 residue. In further aspects, die present disclosure provides for SEQ ID NO: 100, wherein SEQ ID NO: 100 comprises one, up to two, up to three, up to four, up to five, up to six, up to seven, up to eight, up to nine, or up to tenamino acid substitutions and further -comprises each of active site residues a Q157, a Y 160, a R 169, a N 172, a Fl 73 , a T 174, a D 175, a F 176, a H178 , a F 179, a H183, a L 187, a E222, a A 223, a P224, a 1225, a F228, a Y230, a L240, a V242, a L253, a N255, a L269, a F271 , a H284, a F287, a N288, a D289, a L290, a V291 , a F292, and a D295 residue.

[0165] In yet another aspect, the present disclosure provides for the amino acid sequence of SEQ ID NO: 99 comprisingamino acid 152 - 290 of SEQ ID NO: 99, and wherein the remainingamino acid sequences outside of amino acids 152 - 290 have one, up to two, up to three, up to four, up to five, up to six, up to seven, up to eight, up to nine, or up to ten amino acid substitutions in SEQ ID NO: 99. In aspects, the amino acid substitutions are conservative substitutions.

[0166] The disclosure also encompasses variants and fragments of proteins of an amino acid sequence en coded by the nu c leic a c i d sequenc e s of a caffein e demethyl ase cdm A domain or cdmD domain, homologs of cdms, orthologs of cdms and / or paralogs of the cdms. The variants may contain alterations in the amino acid sequences of the constituent proteins. The term “variant” with respect to a polypeptiderefers to an amino add sequence that is altered by one or more amino acids with respect to a reference sequence. The variant can have “conservative” changes, or “tionconservaii ve” changes, e. g. , analogous minor variations can also include amino acid deletions or insertions, or both.

[0167] Functional fragments and variants of a polypeptide include those fragments and variants that maintain one or more functions of the parent polypeptide. It is recognized that the gene or cDNA encoding a polypeptide can be mutated, without materially altering one or more of the polypeptide ’s functions. First, the genetic code is well-known to be degenerate, and thus different codons encode the same ammo acids. Second, even where an amino acid substitution is introduced, the mutation can be conservative and have no material impact on the essential function(s) of a protein. See, e.g., Stryer Biochemistry 3rd Ed., 1988 . Third, part of a polypeptide chain can be deleted without impairing or eliminating all its functions. Fourth, insertions or additions can be made in the polypeptidechain for example, adding epitope tags, without impairing or eliminating its functions (Ausubel et ah J. Immunol 159(5): 2502-12, 1997 ). Other modifications that can be made without materially impairing one or more functions of a polypeptide can include, for example, in vivo or in vitro chemical and biochemical modifications or the incorporation of unusual amino acids. Such modifications include, but are not limited io, for example, acetylation, carboxylation, phosphorylation, glycosylation, ubiquination, labelling, e.g.with rad io nucleotides, and various enzymatic modification s, as will be readily appreciated by those well skilled in the art. A variety of methods for labelling polypeptides, and labels useful for such purposes, are well known in the art, and include radioactive isotopes such as 32P, ligands which bind to or are bound by labelled specific binding partners (e.g., antibodies), fl u orop hores, chemiluminescent agents, enzymes, and anti-ligands. Functional fragments and variants can be of varying length. For example, some fragments have at least 10, 25, 50, 75, 100, 200, or even more amino add residues. These mutations can be natural or purposely changed. In some embodiments, mutations containing alterations that produce silent substitutions, additions, or deletions, but do not alter the properties or activities of the proteins or how the proteins are made are an embodiment of the disclosure.|00168 | Conservative amino acid substitutions are these, substitutions that, when made, least interfere with the properties of the original protein , that is, the structure and especially the function of the protein is conserved and not significantly changed by such substitutions. Conservative substitutions maintain (a) the structure of the polypeptide backbone around the substitution, for example, as a sheet or helical conformation, (b) the charge or hydrophobicity of the molecule at the target site, or (c) the bulk of the side chain. Further information about conservative substitutions can be found, for instance, in Ben Bassat et al. (J. Bacterio!., 169:751 757, 1987), O’Regan et al. (Gene, 77:237251, 1989), Sahin Toth etal. (Protein Sci., 3:240247, 1994), Hochuli ei al. (Bio / Technology , 6:1321 1.325 , 1988) and in widely used textbooksof genetics and molecular biology. The Blosum matrices are commonly used for determining the relatedness of polypeptide sequences. The 'Blosum matrices were created using a large database of trusted alignments (the BLOCKS database), in which pairwise sequence alignments related by less than some threshold percentage identity were counted (l ienikoffetal.. Proc. Natl. Acad. Sci. USA. 89:10915-10919, 1992 ). A threshold of 90% identity was used for the highly conserved target frequencies of iie BLOSUM90 matrix. A threshold of 65%, identity was used for the BLOSUM65 matrix. Scores of zero and above in the Bio surn matrices are considered ‘'conservative substitutions” at. the percentage identity selected. The following Table 1 shows exemplary conservative amino acid substitutions.Table I . Exemplary conservative amino acid substitutions listed

[0169] hi some examples, variants can have no more than 3 , 5 , I 0, 15, 20, 25, 30, 40, 50, or .100 conservative amino acid changes (such a s very highly conserved or highly conserved amino acid substitutions). In other examples, one or several hydrophobic residues (such as Leu, I le, Val, Met, Phe, or Trp) in a variant sequence can be replaced with a different hydrophobic residue (such as Leu, lle, Val, Met, Phe, or Trp) to create a variant functionally similar to the disclosed an amino acid sequences encoded by the nucleic acid sequences of a caffeine demethylase cdmA domain or cdmD domain, homologs of the cdms, orthologs of cdrns and / or paralogs of cdms, and / or fragments and variations thereof.

[0170] ] In some embodiments, variants may differ from the disclosed sequences by alteration of the coding region to fit the codon usage bias of the organism into which the molecule is to be introduced. In other embodiments, the coding region may be altered by taking advantage of the degeneracy of the genetic code to alter the coding sequence such that., while the nucleotide sequence is substantially altered, It nevertheless encodes a protein having an amino add sequence substantially similar to the disclosed an amino acid sequences encoded by the nucleic acidsequences of a caffeine demethykise cdmA domain or cdmD domain, homologs of the cdms, orthologs of cdms and / or paralogs of the cdms, and / or fragments and variations thereof.

[0017] 1 In some embodiments, functional fragments derived from the cdm orthologs of the present disclosure are provided. The functional fragments can still reduce or remove caffeine from a food.

[0172] ] In some embodiments, the functional fragments contain at least the conserved region or NAC domain of a wild type cdm orthologs, or functional variants thereof.

[0173] In. some embodiments, the functional fragments contain one or more conserved region shared by two or more cdm orthologs or shared by two or more cdm orthologs in the same genus. The conserved. regions or NAC domains can be determined by any suitable computer program, such as NCBI protein BLAST program and NCBI Alignment program, or equivalent programs. In some embodiments, tike functional fragments are 1 , 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 , 12, 13, 14, 15, 16, 17, 18, 19, 20, 21 , 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43 , 44 , 45 , 46, 47, 48, 49, 50 or more amino adds shorter compared to the cdm orthologs of the presen t disclosure. In some embodiments, the functional fragments are made by de leting one or more ammo acid, of the cdm orthologs of die present disclosure. In some embodiments, the functional fragments share at least 80%, 85%, 90%, 95%, 96%, 97%, 98%, 99%, or more identify to the cdm orthologs of the present disclosure, In some embodiments, functional chimeric or synthetic polypeptides derived from the cdm orthologs of the present disclosureare provided. The functional chimeric or synthetic polypeptides can still reduce or remove caffeine from food,

[0174] la some embodiments, the enzymes or polypeptides may comprise both the cdmA domain and the cdmD domain. The position, of the cdmA domain and the cdmD domain may vary. For example, in some embodiments, the cdmD domain may be located at the N-temiinus region, and the cdmA domain may be located at the ( / -terminus region.. In some embodiments, the cdmD domain may be located at the C-termrnus region, and the cdmA domain may be located at the N- terminus region.

[0175] In some embodiments, the enzymes or polypeptides may further comprise a glucose dehydrogenase or a glucose dehydrogenase active site.

[0176] In some embodiments, the enzymes or polypeptides may include one or more intramolecular disulfide bond.IV. Theubroniiue

[0177] Theobromine (3,7-dimethylxanthi.ne) is a melhyLxatithine alkaloid, closely related to caffeine and theophylline, sharing a purine ring structure. Methy lxanthines are known for their diverse pharmacological effects, primarily attributed to adenosine receptor antagonism and phosphodiesterase inhibition.[00 178] Theobromine, while structurally like caffeine but differing from caffeine by the absence of a methyl group at the -nitrogen- 1 position, has a distinct pharmacological effect from caffeine including exhibiting a milder stimulant effect. Theobromine is naturally found in Theobromti cacao beans, the primary ingredient in chocolate . Cocoa beans and chocolate products are the most significant dietary sources of theobromine, with dark chocolate containing higher concentrations than milk chocolate.

[0179] Emerging evidence suggests potential benefits of theobromine for vascular and cardi.ometa.bolichealth, includingthe following: (1 )asa diuretic- making it particularly useful after a person has experienced cardiac failure; (2) for its ability to dilate blood vessels, improve blood flow, and lower blood pressure; (3) as a weak stimulant; (4) raising levels of serotonin making it an inexpensive anti-depressant; (5) as an appetite suppressant and a useful adjunct for weight reduction; (6) relaxing bronchi in the lungs, making it useful for treating asthmatic and pulmonary' diseases; (7) enhancing alertness, attention, mental energy, memory, cognition, and a sense of wellbeing; (8) lowering the central blood pressure and / or lowering central systolic- blood pressure, and (9 ) as an inhibitor of the crystallization of uric acid to avoid the formation of uric acid crystals in urine and as a consequence of renal lithiasis or specifically uric acid renal lithiasisU.S. Patent Nos. 7,291 ,352, 10, 149,851, and 1 1 ,376,294; and U.S. Published Patent Application Nos. US 2013 / 0052280 A1 and US 2016 / 0000110 A1 .

[0180] Excessive use of caffeine or theobromine causes nervousness, agitation, arrhythmias, bradycardia , tachycardia, increased blood pressure and vasoconstriction, leading to mild anxiety, jitteriness, insomnia, increased sleep latency and reduced coordination. See, e.g., U.S. Patent No. 1 1 ,376,294. Theobromine, however, is generally considered less toxic than caffeine. The LD50 (lethal dose, 50% ) of theobromine in rats is significantly higher than that of caffeine . In humans, typical dietary' intake of theobromine from chocolate consumption is considered safe. However, high doses of theobromine can cause adverse effects, including gastrointestinal discomfort, increased heart rate, anxiety, and insomnia. Theobromine is toxic to dogs and ca ts because they metabolize it much slower than humans.V. Common Production Methods fo r Beverages

[0018] ] The compositions, servings, and kits of the present disclosure are applicable to any of the common production methods that are used primarily in the beverage Ready-To- Drink (“RTD’3 or concentrated drink formats. Examples of such common production methods include but are not limited to the fo Ho wing, wherein one or more of these production methods can be used for a single RTD or concentrated drink format:

[0182] 1 . Heat-Based Processing. These methods involve the application of heat to ensure microbial safety, extend shelf life, and stabilize the beverage.(a) Pasteurization. High-Temperature, Short-Time (HTST). Heating to 72-85°C (160-185°F) for 15 -30 seconds. Used for refrigerated beverages like co Id brew concentrates with limited shelf life.(b) Ultra-Pasteurization. Heating to 135 -450°C (275 - -302°F) for a few seconds.

[0183] 2, Aseptic Processing. Combines ultra-pasteurization with sterile packaging. Used for shelf-stable beverages like ready-to-drink coffee or juice concentrates.

[0184] 3. Hot Fill, Filling the beverage into containers at high temperatures (85—95 °C), then sealing to ensure sterility.

[0185] 4. Evaporation. Used in concentrating production to remove water by heating under reduced pressure.

[0186] 5, Cold Processing.(a) High-Pressure Processing (HPP). Uses extreme pressure (up to 87,000 psi) to inactivate pathogens without heat. Maintains flavor and freshness, commonly used for premium juices and cold brew.(b) Cold Filtration. Uses microfiltration or ultrafiltration to physically remove microorganisms without heat. Often combined with refrigeration for cold brew or other sensitive beverages,

[0187] 6. Fermentation -Based Processing. Involves controlled fermentation for flavor development and natural preservation. Common in beverages like kombucha, kefir, and some specialty cold brews.

[0188] 7 Carbonation. Adds carbon dioxide underpressure to enhance taste and extend shelf life.

[0189] 8.. Sweetener or Flavor Addition. Includes the addition of sugars, syrups, or natural flavors during or after processing. Often paired with pasteurization to ensure stability,

[0190] 9. Freeze Concentration. Freezing the beverage to remove water while concentrating flavors. Often used for premium cold brew concentrates or fruit juice concentrates.VI. Enzyme Decaffeination of Food

[0191] Food-grade enzymes are commonly usedin food processing(i.uc;udingpreservatiouX as well as in production of specific ingredients aimed at formulation, Since enzymes traditionally isolated, from cultivable microorganisms, or from plants and mammalian tissues, do not possess sufficient parity and are often not adapted to the strict conditions used in. modern food process, the use of recombinant DNA technology has made it possible to manufacture existing enzymes to much higheryieids, asweHasnovelenzymeswith tailor-made features, Enzymesare thus obtained, by first screening microorganisms and other cells sampled from diverse environments for the desired activities, and then expressing the underlying enzymes in specific hosts - or via modification of existing enzymes using tools of protein engineering (e.g., site-directed, mutagenesis). As a result, not only much larger amounts of several important food-grade enzymes have become available at affordable prices, but also novel enzymes tailored to processes and products have been created in recent decades. Another important achievement encompasses improvement of the strains normally used as microbial hosts, for example, via engineering aimed at increasing enzyme yield by deleting native genes,, or .modification io reduce (or even eliminate) parallel synthesis of potentially toxic byproducts as secondary metabolites. See, Oscar Leandro Ramos, Abstract, Chapter 3.48 Food-Grade Enzymes, January 2010, hr. Comprehensive Biotechnology (pp. 555-569), Second Edition, Elsevier B.V., Murray Moo-Young, Editor (DOI: 10.1016 / B978-0-08-()88504-9.00213-0).

[0192] The decaffeinating enzymes, enzyme compositions, and kits of the present disclosure cast be added to food, by mixing it with the food, sprinkling it on the food, stirring it into the food, or by any practical method, in which an enzyme can be added to food,

[0193] ] The decaffeinating enzymes, enzyme compositions. and kits of the present disc lo sure .may be added to food prior to or during the actual or anticipated consumption of the food. For example, the enzymes, enzyme compositions, and kits may be used in industrial processes, such as baking, brewing, detergents, and fermented products. In some embodiments. the enzymes, enzyme compositions, and kits of the present disclosure may be used in nutraceuticals, supplements.functional foods, superfoods, food fortifiers, botanical drugs, and pharmaceuticals. In some embodiments, a person makes or procures a cup of hot or cold, brewed coffee and adds the enzymes, enzyme compositions, and / or kits to the cup of coffee prior to consuming it to reduce or eliminate the caffeine in the cup of coffee.

[0194] In some embodiments the decaff einating enzyme,, enzyme composition, or kit is added without any additional ingredients, while in other embodiments the decaffeinating enzyme or enzyme composition is mixed with other ingredients either before or during its addition to the food. For example, enzyme preparations consisting of biologically active proteins are sometimes combined with metals, carbohydrates and / or lipids.

[0195] In some embodiments the enzymes, enzyme compositions, and kits of the present disclosure reduce or remove caffeine when they ate added to the food containing, consisting of, or comprising caffeine. When the enzymes, enzyme compositions, and kits of the present disclosure are added to a caffeinated food they reduce the amount of caffeine by at least 80%, or at least 81 %., or at least 82%, or at least 83%, or al least 84%, or at least 85%, or at least 86%, oral least 87%, or at least 88%, or at least 89%, or at least 90%, or at least 91%, or at least 92%, or at least 93%, or at least 94%, or at least 95%, or at least 95.5%, or at least 96%, or at least 96.5%, or at least 97%, or at least 97.5%, oral least 98%, or at least 98.5%, or at least 99%, or at least 99.1%, o r at least 99.2%, or at least 99.3%, or at least 99.4%, or at least 99.5%, oral least 99.6%, oral least99,7%, or al least 99.8%, or at least 99.9%, or at least 99.95%, or by 1.00%.

[0196] When the enzymes, enzyme compositions, and kits o f th e present disclosure are added to a caffeinated food they reduce the amount of caffeine by about 80%, or about 81%, or about 82%, or about 83%, or about 84%, or about 85%, or about 86%, or about 87%, or about 88%, or about 89%, or about 90%, or about 91%, or about 92%, or about 93%, or about 94%, or about 95%, or about 95.5%, or about 96%, or about 96.5%, or about 97%, or about 97.5%, or about 98%, or about 98.5%, or about 99%, or about 99.1%, or about 99.2%, or about 99.3%, or about 99.4%, or about 99.5%, or about99.6%, or about 99.7%, or about99.8%, or about 99.9%, or about99.95%, or about 100%), or 100%;.

[0197] When the enzymes, enzyme compositions, and kits of th e present disclosure are added to a caffeinated food they reduce the amount of caffeine by at least 504% or at least 51%, or at least 52%, or at least 53%, or at least 54%, or at least 55%o, or at least 56%, or at least 57%>, or at least 58%, or at least 59%), or at least 60%, or at least 61%, or at least 62%, or at least 63%, or at least64%, or at least 65%, or at least 66%, or at least 67%, or at least 68%, or at least 69 %, or at least 70%, or at least 71%, or at least 72%, or al least 73%, or at least 74%, or at least 75%, or at least 76%, or at least 77%, or at least 78%, or at least 79%, or at least 80%.

[0198] When the enzymes, enzyme compositions, and kits of the present disclosure are added to a caffeina ted food they reduce th e amount of ca ffe in e by about 50%, o r about 51%, or about 52%, or about 53%, or about 54%, or about 55%, or about 56%, or about 57%, or about 58%, or about 59%, or about 60%, or about 61%, or about 62%, or about 63%, or about 64%, or about 65%, or about 66%, or about 67%, or about 68%, or about 69%, or about 70%, or about 71 %, or about 72%, or about 73%, or about 74%, or about 75%, or about 76%, or about 77%, or about 78%, or about 79%, or about 80%, or about 50-80%, or about 50-75%, or about.50-70%, or about 50-65%, or about. 50-60%, or about 55-80%, or about 55-75%, or about 55-70%, or about 55-65%, or about 60-80%, or about 60-75%, or about 60-70%.

[0199] In some embodiments when the enzymes, enzyme compositions, ami kits of the present, disclosure are added, to a caffeinated food they reduce or remove all, nearly all, or essentially all the caffeine.

[0260] When the enzymes, enzyme compositions, and kits of the present disclosure are added to an average cup of coffee (e.g., about 5 ounces to about 8 ounces) comprising about 100 milligrams (mg) of caffeine, the enzymes or enzyme compositions reduce the amount of caffeine by at least 80 mg or at least 81 mg or at least 82 mg or at least 83 mg, or at least 84 mg or at least 85 mg, or at least 86 mg, or at least 87 mg, or at least 88 mg, or at least 89 mg, or at least 90 mg, or at least 91 mg, or at least 92 mg, or at least 93 mg, or at least 94 mg, or at least 95 mg, or at least 95.5 mg, or at least 96 mg, or at least 96.5 mg, or at least 97 mg, or at least 97.5 mg, or at least 98 mg, or at least. 98.5 mg, or at least 99 mg, or at least 99.1 mg, oral least 99.2 mg, or at least 99.3 mg, oral least 99.4 mg. or at least 99.5 mg, or at least 99.6 mg, or at least 99.7 mg, or at least 99,8 mg, oral least 99.9 mg, or at least 99.95 mg, or by 100 mg.

[0201] When the enzymes, enzyme compositions, and kits of the present disclosure are added to an average cup of coffee (e.g.., about "5 ounces to about 8 ounces) comprising about 100 milligrams (mg) of caffeine, the enzymes, enzyme compositions, and kits reduce the amount of caffeine by about 80 mg, or about 8.1 mg, or about 82 mg, or about 83 mg, or about 84 mg, or about 85. mg, or about 86 mg, or about 87 mg, or about 88 mg, or about 89 mg, or about 90 mg, or about 91 mg or about 92 mg, or about 93 mg, or about 94 mg, or about 95 mg, or about 95.5 mg, or about 96 mg,or about 96.5 mg, or about 97 mg, or about 97.5 mg, or about 98 mg, or about 98.5 mg, or about 99 mg, or about 99.1 mg, or about 99.2 mg, or about 99.3 mg, or about 99.4 mg, or about 99.5 mg, or about 99.6 mg, or about 99.7 mg, or about 99.8 mg, or about 99.9 mg, or about 99.95 mg, or about 100 mg. In some embodiments when the enzymes, enzyme compositions, and kits of the present disclosure are added to about a 5 -ounce to an 8-ounce cup of coffee comprising about 100milligrams (mg) of caffeine, they reduce or remove ail or nearly all the caffeine.

[0202] When the enzymes, enzyme compositions, and kits of the present disclosure are added to an average cup of coffee (e.g., about 5 ounces to about 8 ounces) comprising about 100 milligrams (mg) of caffeine, the enzymes or enzyme compositions reduce the amount of caffeine by at least 50 mg or at least 51 mg or at least 52 rag or at least 53 mg. or at least 54 mg or at least 55 mg, or at least 56 mg, or at least 57 mg, or at least 58 mg, or at least 59 mg, oral least 60 mg, or at least 61 mg, oral least 62 mg, or at least 63 mg, or at least 64 mg, or at least 65 mg, or at least 66 mg, or at least 67 rag, or at least 68 mg, or at least 69 mg, or at least 70 mg, or at least 71 mg, or at least 72 mg, or at least 73 mg, or at least 74 mg, or at least 75 mg, or at least 76 mg, or at least 77 mg, or at least 78 mg, or at least 79 mg, or at least 80 mg.

[0203] When the enzymes, enzy me compositions, andkits of the present disclosure are added to an average cup of coffee (e.g., about 5 ounces to about 8 ounces) comprising about 100 milligrams (mg) of caffeine, the enzymes, enzyme compositions, and kits reduce the amount of caffeine by about 50 mg, or abou t 51 mg, or about 52 mg, or about 53 mg, or about 54 mg, or about 55 mg or about 56 mg, or about 57 mg, or about 58 mg, or about 59 mg, or about 60 mg, or about 61 mg. or about 62 mg, or about 63 mg, or about 64 mg, or about 65 mg, or about 66 mg, or about 67 mg or about 68 mg, or about 69 mg, or about 70 mg, or about 71 mg, or about 72 mg, or about 73 mg, or about 74 mg, or about 75 mg, or about 76 mg, or about 77 mg, or about 78 mg, or about 79 mg or about 80 mg, or about 50-80 mg, or about 50-75 mg, or -about 50-70 mg, or about 50-65 mg, or about 50-60 mg, or about 55-80 mg, or about 55-75 mg, or about 55-70 mg, or about 55-65 mg, or about 60-80 mg, or about 60-75 mg, or about 60-70 mg.

[0204] The caffeinated food or beverage to be decaffeinated may be at various temperatures when applying the enzymes, enzyme compositions, and kits of the present disclosure. For example, the caffeinated foodor beverage to be decaffeinated may be a hotdrink (about ,50-90°C), a warm drink (about 30-50°C), a room temperature drink (about 15-30°C),ora.cold drink (about 5-15 °C [when applying the enzymes, enzyme compositions, and kits of fee present disclosure.

[0205] In some embodiments, the caffeinated food or beverage to be decaffeinated may be at about 90°C, at about 85°C, at about 80°C, at about 75°C, at about 70°C, at about 65°C, at about 60°C, at about 55°C, at about 50°C, at about 40°C, at about 30°C, at about 25°C, at about 20°C, at about 15°C, at about 10°C, or at about 5°C, when applying the enzymes, enzyme compositions, and kits of the present disclosure.

[0206] In some embodiments, the caffeinated food or beverage to be decaffeinated may be at about 5-10°C, at about 5-15°C, at about 2-10°C, at about2-5°C, at about 15-20°C, at about 15- 25°C, at about 20-22°C, at about 20-25°C, at about 15-30°C, at about 25-30°C, at about 30-50°C, at about 50-85°C, at about 50-80°C, at about 50-75°C, at about 50-70°C, at about 50-65°C, at about 55-75°C, at about 55-70°C, or at about 55-65 °C, when applying the enzymes, enzyme compositions, and kits of the present disclosure.

[0207] The measurements used to calculate any or all these caffeine reductions in. the food can be calculated based on a volutne / volume basis., a fresh weight / weight basis, a dry weight-weight basis, or any combination thereof.[00208 j hi some embodiments when the enzymes, enzyme compositions, and kits of the present disclosure are added to a caffeinated food they reduce or remove the amount of caffeine by an amount so that the remaining caffeine does not disrupt a consumer ’s natural sleep-wake cycle.

[0209] hi some embodiments the enzymes, enzyme compositions, and kits of the present disclosure are added to a caffeinated food in an effective amount so that they reduce or remove die amount of caffeine by an amount so that the remaining caffeine does not disrupt a consumer’s natural sleep-wake cycle.

[0210] In some embodiments, the enzymes, enzyme compositions, and. kits of the present disclosure operate in an in vitro system. In some embodiments, the enzymes, enzyme compositions, and kits of the present disclosure operate independently without the interference of live microorganisms such as bacteria (e.g., E. coli, Bacillus subtilis), yeast (e,g., Saccharomyces cetevisiae), and cyanobacteria. In some embodiments, the enzymes, enzyme compositions, and kits of the present disclosure are added to a caffeinated food in an effective amount, without the presence or addition of live microorganisms. In another aspect, the enzymes, enzyme compositions, and kits of the present disclosure do not operate in an in vivo system. In yet otheraspects, E-coli or other bacterial are not added directly to the enzymes, enzyme compositions, and kits of the present disclosure.

[0211] In another aspect, one or more enzymes of the present disclosure .may be added to a food or food, precursor by adding a microorganism that produces it, wherein such food or food precursors include but are not limited to mature, intact coffee fruit, hulled coffee beans, roasted coffee beans, or roasted and ground coffee beans. In another aspect, microorganisms producing one or more enzymes of the presentdisclosure are administered as a probiotic prior to consumption of a food containing caffeine . In some aspects, only one microorganism is used to prod uce one or more of the enzy mes, while in other aspects more than one microorganism is used to produce two or more of the enzymes. For example, one microorganism may express cdmA while another expresses cdmD. Examples of suitable microorganisms include but are not limited to yeast (e.g., Saccharomyces cerevisiae), Lactobacillus, algae, blue green algae (e.g., Spirulina), and bacteria (e.g., Escherichia coll, Sirepiomyces lividans, Pseudomonas putida, Rhicobhrm legiminosimtm, Bacillus sublilis, Bacillus lichen iformis, and Bacillus ai«yloliqne / aciens)'.In some embodiments when the enzymes, enzyme compositions, and kits of the present disclosure are added to a caffeinated food they reduce or remove the amount of caffeine by an amount so that one or more of the following symptoms, conditions, or physiological effects are reduced or eliminated: insomnia, fest heartbeat, headaches, nervousness, dehydration, dizziness, frequent urination, high blood pressure, tremors, diarrhea, increased alertness, irritability, anxiety, caffeine toxicity, adverse cardiovascular effects, fatigue, pain, acid reflux. Gastroesophageal refluxdisease (GERD), and / or rapid breathing. In some embodiments when the enzymes., enzyme compositions, and kiis of tire present disclosure are added to a caffeinated food they reduce or remove the amount of caffeine by an amount clinically necessary and / or personally desired during pregnancy.VII Euzyme-Cantammg Compositions and Kits

[0212] The enzymes of the present disclosure may be used hi any suitable form whether when alone or when present in a composition or a kit[002131 Suitable examples of forms of the enzymes, enzyme compositions, and / or kits of the present disclosure may include but are not limited to one or more of pow ders (e.g., coarse, medium, fine, and superfine powders), granules, crystals, cubes, tablets, pills, capsules, ovules, solutions, and / or suspensions, which may also optionally contain fla voring or coloring agents. The forms may also include gelatin capsules, fiber capsules, fiber tablets, fiber beverages, and the like. Dieforms may be for immediate, delayed, modified, sustained, pulsed, or controlled-release applications depending on the specific situation of their use,

[0214] By way of example, the enzyme compositions or kits may include but are not limited to one or more of the following: (I) excipients, for example, such as microcrystalline cellulose, lactose, sodium citrate, calcium carbonate, dibasic calcium phosphate, and glycine; (2) disintegrants, for example, such as starch (e.g., corn, potato or tapioca starch), sodium starch giycollate, croscarmellose sodium, and certain complex silicates; (3) granulation binders, for example, such as polyvinylpyrrolidone, hydroxypropylmethylcellulose (HPMC). hydroxypropylcellulose (HPC), sucrose, gelatin, and acacia; and / or (4) lubricating agents, for example, such as magnesium stearate, stearic acid, glyceryl behenate and talc may be included.

[0215] Examples of nutritionally acceptable carriers for use in preparing the forms of enzymes, enzyme compositions, or kits may include but are not limited, to one or more of water, salt solutions, alcohol, silicone, waxes, petroleum jelly, vegetableoils, polyethyleneglycols, propylene glycol, liposomes, sugars, gelatin, lactose, amylose, magnesium stearate, talc, surfactants, silicic acid, viscous paraffin, perfume oil, fatty acid monoglycerides, d [glycerides, petrcethral fatty acid esters, hydroxynietiiyl-cellulose, polyvinylpyrrolidone, and the like.

[0216] Alternatively, the enzymes, enzyme compositions, and / or kits of the present disclosure may be in liquid form For example, the enzymes, enzyme compositions, and / or kits of the present disclosure may be dissolved in. a suitable solvent (e.g., pure water or saline solution ) before being added to a food or food precursor.

[0217] For aqueous suspensions and / or elixirs, the enzymes, enzyme compositions, and kits of tire present d isclosure and functional derivatives thereof may be combined with but are not limited to one or more of various sweetening or flavoring agents, coloring matter or dyes, with emulsifying and / or suspending agents, and with diluents such as water, ethanol, propylene glycol and glycerin, and any / 'all. combinations thereof.

[0218] In some embodiments the enzymes of the present disclosure are in compositions and'br kits containing an amino acid sequence coding for a caffeine demethylase cdmAdomain, an amino acid sequence codingfor a caffeine demethylase cdmD domain, a sugar, NAD+, and an amino acid sequence coding for an enzyme suitable for catalyzing the sugar, wherein the enzyme is selected from, enzyme class (EC) 1.1.1 :oxidoreductases that use NAD(P)4-as an electron acceptor, whereinadding the composition to a caffeine containing substance results in some or all the caffeine being convened to theobromine.

[0219] Coenzymes are important electron carriers in an enzyme catalyzed oxidation- reaction. Common coenzymes include Nicotinamide adenine dinucleotide (NAD), Nicotinamide adenine dinucleotide phosphate (NAD(P)), Nicotinamide mononucleotide (NMN), reduced Diphosphopyridine (DPNH), Flavin adenine dinucleotide (FAD), and Flavin mononucleotide (FMN)..

[0220] Nicotinamide adenine dinucleotide (N AD) is a coenzyme central to metabolism which is found in all living cells- NAD is called a dinucleotide because it consists of two nucleotides joined through their phosphate groups. One nucleotide contains an adenine nucleobase and the other, nicotinamide. NAD exists in two forms: an oxidized and reduced form, abbreviated as NAD+and NADH (H for hydrogen), respectively.

[0022] ] The present disclosure provides N A D(P)H or NADH regeneration systems using a. sugar, N A D+ or NAD(P)+, and an enzyme that can catabolize or catalyze (i.e., catalytically breakdown) tire sugar wherein the enzyme is selected from enzyme class (EC) 1.1.1 : oxidoreductases that use N AD(P)+ an d / or N AD+ as an electron acceptor. In some embodiments the systems of the present disclosure are in compositions and / or kits containing an amino acid sequence coding for a caffeine demethylase cdmA domain, an amino acid sequence coding for a caffeine demethylase cdmD domain, a sugar, NAD(P)+ or NAD+, and an amino acid sequence coding for an enzyme suitable for catalyzing the sugar, wherein the enzyme is selected from enzyme class (EC) 1.1.1: oxidoreductases that use NAD(P)+ or NAD+as an electron acceptor, wherein adding the composition to a caffeine containing substance results in some or all the caffeine being con verted to theobromine.

[0222] Any enzymes in enzyme class (EC) 1.1.1: oxidoreductases that use NAD(P)+ as an electron acceptor may be used in the compositions and kits of the presently disclosed systems along with the corresponding sugars that the specific oxidoreductases catalyze. ENZYME provides a list of all UniProKB / Swiss-Prot entries corresponding to Class 1.1.1 : oxidoreducastes available as of January 24, 2024. ENZYME is a repository of information relative to the nomenclature of enzymes, wherein that information is primarily based on the recommendations of the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology(IUBMB) and which describes each type of characterized enzyme for which an EC (Enzyme Commission) number has been provided.

[0223] The compositions and methods of the present disclosure could also accommodate oilier nicotinamide-containing molecules like Nicotinamide mononucleotide (NMN), which is a compound that helps produce NAD+.

[0224] Examples of EC Class 1.1.1 : oxidoreductases which, may be used in the compositions and kits of the presently disclosed systems include but are not limited to glucose dehydrogenase, lactate dehydrogenase, malate dehydrogenase, sorbose dehydrogenase, fructose dehydrogenase, galactose dehydrogenase, formate dehydrogenase, and. formaldehyde dehydrogenase, wherein the corresponding sugars catalyzed by these enzymes are glucose, lactate, malate, sorbose, fructose, galactose, formate, and formaldehyde, respectively.

[0225] Glucose is a sugar with the molecular formula C6H12O6, Glucose is overall the most abundant monosaccharide, a subcategory of carbohydrates. Glucose is mainly made by plants and most algae during photosynthesis from water and carbon dioxide, using energy from sunlight, where it is used to make cellulose in cell walls, the most abundant carbohydrate in the world.[0 0226]] Glucose 1 -dehydrogenase is an enzyme that catalyzes the chemical reaction beta-D- glucose + NAD(P)+D-glucono- 1 ,5-lactone + N AD(P)H + H . This enzyme belongs to the family of oxidoreductases, specifically those acting on the CH-OH group of donor with NAD:or NADP" as acceptor. The systematic name of this enzyme class is D-ghicoserNAD+1- oxidoreductase. Other names in common use include D-glucose: NAD+oxidareductase, D- aidohexose dehydrogenase, and glucose 1 -dehydrogenase (NAD+).

[0227] The compositions and kits of the presently disclosed, systems include but are not limited to systems containing less than about one gram of sugarper serving for about a 5-ounce to about an 8-ounce cup of coffee (i.e.. about a quarter teaspoon of sugar per serving). In some embodiments when, the presently disclosed systems comprising a small amount of sugar are added, to about a 5-ounce to about an 8-ounce cup of coffee comprising about 100 milligrams (mg) of caffeine, they reduce or remove all or nearly all the caffeine, hi some embodiments when the presently disclosed systems comprising a. small amount, of glucose are added to about a 5-ounce to about an 8-ounce cup of coffee comprising about 100 milligrams (mg) of caffeine, they reduce or remove all or nearly all the caffeine.

[0228] Single serving sizes of the presently disclosed systems for use in an average cup of coffee (e.g., about 5 ounces to about 8 ounces) comprise no sugar, or comprise sugar of about 0.1 g, or about 0.2 g, or about 0.3 g, or about 0.4 g, or about 0.5 g, or aboutO.6 g, or about 0.7 g, or about 0.8 g, or about 0.9 g, or about 1 .0 g, or about 1 . 1 g, or about 1 .2 g, or about 1 .3 g, or about 1 .4 g or about 1.5 g.

[0229] Single serving sizes of the presently disclosed systems for use in an average cup of coffee (e.g., about 5 ounces to about 8 ounces) comprise no sugar, or comprise sugar of less than 0. 1 g, or less than 0.2 g, or less than 0 3 g, or less than 0.4 g, or less than 0,5 g, or less than 0.6 g, or less than 0.7 g, or less than 0.8 g, or less than 0.9 g, or less than 1 .0 g, or less than 1 .1 g, or less than 1 .2 g, or less than 1.3 g, or less than 1.4 g, or less than 1 .5 g.

[0230] This small amount of sugar con tributes minimal taste impactand may be under the amount of sugar required to be listed on a food label. If required to be listed on a. food label such small amounts of sugar may be identified as “reduced sugar,” '‘zero sugar,” “without added sugar, ” or “adds a trivial amount of sugar.”VIII. Enzyme Ratios

[0023] ] In some embodiments the enzymesof the presentdisclosnreare in compositions, servings, and / or kits containing an amino acid sequence coding for a caffeine demethy lase cdmA domain, an amino acid sequence coding for a caffeine demethylase cdmD domain, glucose, NAD+, and an amino acid sequence coding for a glucose dehydrogenase (“gdh”), wherein adding the compositions, servings, and / or kits to a caffeine containing substance results in some or all the caffeine being converted to theobromine.

[0232] In some embodiments the concentrations of cdmA, cdmD, and gdh per composition, serving, and / or kit are in micromolar amounts (μM).

[0233] “1x coffee” refers to coffee that is at the strength at which it is intended to drink, “2x coffee” refers to coffee that has to be diluted 1 : 1 (equal parts coffee with equal parts water) before consume. This convention is used to scale the amount of coffee used, to get a desired flavor.

[0234] In some embodiments the ratios of cdmAx*dmD:gdh used in the compositions, servings, and / or k its of the present disclosure are influenced by the methods used to prepare arid purify the enzymes, enzyme cost, and / or sensory impact of the enzymes, wherein the enzyme ratios can beadjusted for each individual enzyme used in the compositions, servings, and kits of the present disclosure so as to achieve the desired flavor and impact,

[0235] In some embodiments of the present disclosure, the ratios of cdmA:cdmD:gdh (e.g., A2t:D2:gdh1 ) per composition, serving, and / or kitcanbe about 35 μM: 10 μM: 10 μM (i.e., about 3,5;1 ;1), which correlates to about 350. mg.90 mg, and 70 mgof each enzyme, respectively, per 8 fl oz cup of 1 x coffee.

[0236] In other embodiments the ratios of cdmA:odmD:gdh(e.g,,A2t:D2:gdh I) per composition, serving, and / or kit can range from about 35 μM: 2.5 μM: 2.5 μM (i.e,, about 14:1 : 1 ) to about 80 μM: 35 μM: 35 μM (i.e., about 2,3:1 ;1 ),

[0237] In other embodiments the ratios of cdmA:cdmD-:gdh (e.g,, A2t;D2:gdhl ) per composition, serving, and / or kit can. range from about 80 μM: 2.5 μM: 2.5 μM (te., about 32: 1:1) to about 30 μM: 30 μM: 30 μM (i.e., about 1:1:1).

[0238] In some embodiments according to the present disclosure the ratios of cdmA:cdrnD:gih (e.g., A2t:D2:gdhl ) per composition, serving, and / or kit can be about 1.0:1:1, 1.1:1:1, 1.2:1:1, 1.3:1.1, 1 ,4:1 :1 ,L5;1:1, 1.6:111, 1.7:1. -.1,1 ,8:1:1, 1.9:1 :1, 2.0:1:1, 2.1.1:1, 2.2:1:1, 2.3:1:1, 2.4:1:1, 2.5:1: 1, 2.6:1 :1, 2.7:1:1, 2.8: 1:1, 2.9:1:1, 3.0:1:1, 3.1:1:1, 3.2:1:1, 3.3:1.1,3.4:1:1, 3.5:1:1, 3.6:1:1, 3.7:1:1, 3.8:1:1, 3.9:1:1, 4.0:l:l, 5.0:l:l, 6.0:1 :1, 7.0:1:1, 8.0:1:1, 90:1:1, 10.0:1:1, 11.0:1:1, 12.0:1:1, 13.0:1:1, 14.0:1:1, 15.0:1:1. 16.0:1:1, 17.0:1:1, 18.0.1:1, 19.0:1:1, 20.0:1:1.21.0:1:1, 22.0:1:1, 23.0:1:1,24.0:1:1,25.0:1:1, 26.0:1:1, 27.0:1:1, 28.0:1:1, 29.0:1:1, 30.0:1 :1, 31.0:1:1,32.0:1:1, 33.0:1:1, 34.0:1:1, 35.0:1:1, 36.0:1:1, 37.0:1:1, 38.0:1:1, 39.0:1:1, or 40.0:1:1.IX. Industrial Supply Chain, and Consumer Applications[002391 Caffeine has historically been removed from substances such as caffeinated foods using chemical-based methods well known to those of skill in the art, wherein such methods include but are not limited to the Direct-Solvent Process, Indirect-Solvent Process, attd / or Carbon Dioxide Process. Each of these processes uses chemicals or sol vents like but not lim ited to methylene chloride, benzene, and ethyl acetate, and / or steps involvingpressurized liquid carbon dioxide. The enzymes, compositions, and / or kits and the methods of ustngthem to decaffeinate substances (e.g, foods such as beverages) as provided herein provide alternative technologies to the harsh, dated, costly, solvent-based, decaffeination methods using such chemicals or solvents. Unlike thechemical and / or solvent-based processes presently used, the enzymes, compositions, and / or k its of the present disclosure produce decaffeinated food with m in imal or no adverse effects on taste.

[0240] The Swiss Water™ decaf process is an alternative chemical-free and solvent-fiee decaffeination process presently available that uses only coffee, time, temperature, and water to remove the caffeine from green cof fee beans. In one example, the Swiss Water™ decaf process removes caffeine by gently soaking green beans in a water solution for just over 8 hours. Generally, the Swiss Water™ decaf process involves cleaning the green coffee beans, hydrating them with pure water to prepare the beans for caffeine removal, and. then immersing the beans in Green Coffee Extract (GCE). GCE is an extract of unroasted, green coffee beans. In some examples, the water used for the soaking step may be tap water, pure fresh water, glacial water, purified water, deionized water, and / or distilled water. The beans are immersed in the GCE solution and the caffeine begins to seep out of the beans and into the GCE. This step is continued until the ratio of compounds in the GCE and beans reach a point of equilibrium. The solution absorbs caffeine from the beans and is then repeatedly carbon filtered until 99% of the caffeine is removed. The beans are then dried and roasted.

[0241] In some embodiments, the enzymes, compositions, and / or kits of the present disclosure are used as an easier, more economical alternative to carbon filters used to filter caffeine from green coffee extract during Swiss Water™ Process decaffeination.

[0242] ] The enzymes, enzyme compositions, and / or kits of the present disclosure may be provided in any suitable storage or container form including but not limited to sachets, capsules, pods (e.g;, coffee roast K-cup puds), jars, bottles, vials, syringes, bowls, cans, boxes, bags, pouches (e.g., stand up pouches), and packets (e.g., square packets, rectangle packets, stick packets). The packaging may be in any suitable form including but not limited, to paper, cardboard (e.g., craft cardboard), foil, plastic, and the like. The packaging may or may not be heat sealed, waterproof, and / or moisture-proof. Individual, single-serving size packaging is convenient to carry, easy to sprinkle into a caffeinated beverage, and will result in a decaffeinatedbeverage with, full flavor and taste. In some embodiments, methods of using the enzymes, compositions, and / or kits of the present disclosure may be accomplished similarly to adding a packet of sugar to a beverage or pumping a serving of flavoring or sweetener into a beverage. In some embodiments, the enzymes, compositions, and / or kits of the present disclosure may be added to instant coffee blends or single cups of coffee to decaffeinate the ground coffee upon it being hydrated.

[0243] As will be evident to one skilled in the art, the size of the packaging will depend on its intended use. For example, a single use package or packaging of the enzymes, compositions, and / or kits of the present disclosure may consist of a paper stick packet with enough of the enzymes , compositions, and / or kits for decaffeinatinga single 8-ounce cup of hot or cold coffee or tea containingcaffeine. The paper stick package may optionally co n ta in a printed line or scoring on one end to indicate where it can be tom to pour the contents into the coffee.

[0244] In some embodiments, the enzymes, compositions, and / or kits of the present disclosure may be used directly by a person to decaffeinate a food containin g caffeine, For example, the person (i.e,, a consumer) may add it directly to their coffee brewed at home or obta ined at a coffee shop so they can more easily enjoy their decaffeinated coffee without compromising on taste and / or convenience.

[0245] The enzymatic technologies of the present disclosure can convert caffeine into a nonpotent product at a pH higher or lower than normal coffee. Normal black coffee, for example, has a pH of approximately 5.0. The enzymatic technologies of fee present disclosure can be applied to various caffeine containing food such as green tea (pH about 5 ,5-7.5 ), black tea (pH about 6-7), oolong tea (pH about 5, 5-7.5), white tea (pH about 6.5-7.5 ), and energy drinks (pH about 2.4-4.5).

[0246] In some embodiments, the enzymes, compositions, and / or kits of the present disclosure may be used by mid-chain businesses such as but not limited to coffee shops, coffee extract manufacturers, or instant coffee manufacturers* thereby providing the means for them to easily offer decaf products and cut their processing costs. In some embodiments, the manufacturers may use the enzymes, compositions, and / or kits of the present disclosure during the standard bre wing process and / or apply them during the brewing process just prior to spray drying instant decaf coffee. In some embodiments, the enzymes, compositions, and / or kits and the methods of their use as provided in the present d isclosure allow for the elimination of maintaining a decaf bean inventory, reduce equipment requirements and costs, reduce labor requirements and costs, and / or provide an overall more sustainable process. Such benefits may be realized throughout the entire value chain of producing and providing decaf beverages, such as coffee or tea.EXAMPLES

[0247] The present disclosure is further illustrated by the following examples that should not be construed as limiting. The contents of all references, patents, and publishedpatent applicationscited throughout this application, as well as the Figures, are incorporated herein by reference in their entirety for all purposes.Representative ProtocolI Gene Selection.

[0248] Potential caffeine demethylase sequences were selected directly from previous reports or from using protein sequence alignment tools BLAST (Basic Local Alignment Search Tool) or HMMER to estimate cdmA genes in target organisms that have been associated with caffeine metabolism (10-12, 16-19). Sequence similarity networks were made using EFI-EST and visualized in Cytoscape to aid in selecting genes, as in FIG.8A (20), Corresponding cdmD genes were then determined by looking in host organism genomes for nearby homologs of known cdmDs. Protein structures for cdmA and cdmD were predicted using AlphaFold2 (14) or CoIabFold (21), using 2-3 copies of each cdmA and one cdmD, as a previous structure from a P. patidti showed cdmD binding at the interface between cdmA subunits (9). Ordered caffeine demethylase domains were labeled cdmA1 -19; accessory NADH dehydrogenases were labeled cdmD M 9; in. both cases, names are interchangeably shortened to A1 -19 and D1 -19. For cdmA10, two options were ordered as it was not clear which was more likely to be a caffeine demethylase subunit, labeled A10a and A 10b,

[0249] For genome mines of cdmD (DN, 1 -5; FIG. 11 ), a HMMER search was completed using D2 as the input N ADFI dehydrogenases were found and genetically fused to the D2 ferredoxin domain m sllico, in order to preserve the binding interface between A2t and D2.

[60250] In some cases, unstructured regions were removed from cdm A amino acid sequences, which, were then codon-optimized into nucleotides for E. coll expression and cloned into a pet29b+-based vector between Ndel and Xhol with a 6x-His C -terminal tag. In cases where N- tenninal Rieske domains were present on cdmDs, sequences were truncated, to remove these domains as they were not hypothesized to participate in caffeine demethylation reactions for all ordered cdmDs except cdmD 1 , wh ich was left intact to better follow previous literature; cdmD1t was later made, which represents the version of cdmD1 without the Rieske domain. Nucleotide sequences for cdmDs were appended with an N-terminal 6x-FHg tag and thrombin, cleavage site, and also encoded into the same pet29b+- vector between Ndel and Xhol cut sites; the N-terminal His-tags and thrombin cleavage sites were added to match previous reports.II. Glucose Dehydrogenase Selection and Expression,

[0251] Initial glucose dehydrogenase sequences (gdh 1-4) were selected from genomic databases, favoring single chain bacterial enzymes that were previously shown to be active in the literature (22). Additional gdh sequences (gdh5 - 10) were searched for by performing a HMMER search with gdh 1 as the input. Sequences were codon-optimized for E. colt expression, appended with an N- terminal 6× -His tag. Genes were transformed, expressed, and purified as described above except that no FeCb was added during induction,III. CdmAD Fusion Design.

[0252] In put models for lin ked cdmAD designs were generated using AlphaFold2 to predict the structure of two copies of each cdmA with one copy of cdmD; two copies of cdmA were used because cdmD binds near the homomeric interface between cdmAs. Top scoring outputs were then used as inputs in RFDiffusion to design linkers between the C-terminus of cdmD with the N- tenninus of one of the cdmA copies (23). The other cdmA copy was not altered, but was kepi intact during the RFDiffusion loop generation so that the loop would, not clash with other cdmA chains. Loop lengths were between 5-30 residues, and 3 structures were generated for each loop length. ProteinMPNN was used to assign a sequence to the RFDiffusion loop outputs, but no oiherportion of the fused protein was designed besides the new loop (24). For “nofd” designs, i.e. the designs where the cdmD domains did. not have the ferredoxin domain present, the same input structures were used as before, but RI D If fusion started budding the loop after the FAD-binding domain and before the ferredoxin , thereby truncating out the ferredoxin domain. Another round of AlphaFoW2 was performed to predict the newly fused protein structures, and final designs were filtered based on pLDDT.IV. CdmD and gdh Designs.

[0253] New redesigns for cdmD2 and gdh I were perforated using ProteinMPNN and follo wing the strategy of a previous study that found successin designingTEV proteases (25). Residues were selected to be frozen from the input structures based, on two criteria; proximity to important, domains such as the active site, and also evolutionary conservation For proximity -based residue selecting, residues within 6 Å of the active site, cofactors, or protein-protein interfaces were selected using Py MOL, To incorporate evolutionary data, a HMMER. search was performed to determine homologous sequences, and the resulting sequences were used to determine the positions with highest amino acid conservation (i.e,, how often is the most conserved residue present at each site). These positions were ranked based on amino acid, conservation, and the top50% or 70% conserved positions were prevented from being designed. After running Protein.MPNN with these residue site restrictions, outputs had their structures predicted w ith AlphaFoldZ, and were selected based on pLDDT.V. Protein Expression and Piirification.

[0254] Vectors were resuspended in nuclease-free water to 20 ng / uL and / transformed into BLR(DF3 ) chemically competent E. coli cells using standard heal shock protocols, cells w ere thawed on ice. mixed with resuspended DNA, heat shocked foi 1 5-30 seconds, recoveied in I .uria Broth ( LB) for 1 h, plated onto Terrific Broth (TB) agar w ith 50 pg ml. kanamycin. and incubated overnight at 37 C. Glycerol stocks of cells w ere made from a 50:50 mix of 50% glycerol and ox ernight cultures of transformed cells grown in LB.

[0255] To express the proteins, 5 mL overgrown cultures from transformed cells or glycerol stocks were added to 500 mL flasks of LB with 50 pg / mL kanamycin. These flasks were incubated at 37 °C until reaching an OD600 of 0.6-1.0, when flasks were transferred to 18 °C. 10 μM FeCL and 0. 1 mM IP I'G were added, flasks were grown for 1 8-24 hours and cells were han ested by centrifugation at 4500xg. Cell pellets were resuspended in lysis buffer (25 mM potassium phosphate at pH 7.5. 300 mM NaCl. 10 mM imidazole) supplemented w ith Ivsozyme and DNAse. Resuspendedcclls w ere disrupted via sonication for 2 5 min with I sec on offcycles. andseparated from insoluble material by centrifugation at I3000xg

[0256] Proteins were further purified using immobilized metal affinity chromatography (IMAC). Lysate was poured over 0.5 mL of Ni-NTA beads that were pre-equilibrated with lysis buffer. Beads w eie w ashed tw ice w ith 5 ml wash buffer (25 m.M potassium phosphate al pH 7.5. 300 mM NaCl, 25-50 mM imidazole) and eluted; with. 2-3 mL elution buffer (25 mM potassium phosphate at pH 7.5, 300 mM NaCl, 250 mM •imidazole). For initial experiments (FIGs. 1-5), eluted proteins were exchanged into PBS - glycerol assay buffer (50 m.M potassium phosphate at pH 7.5, 50 mM NaCl, 5% glycerol) to remove imidazole using 30 kDa MWCO spin columns. For later experiments (FIGs. 6-12). assay buffer w as changed to only 50 mM potassium phosphate, and proteins were also spun concentrated into that buffer. Proteins w ere ana ly zed using sodium dodecy l-stillale polyacrylamide gel electrophoresis (SDS-PAGE). stained w ith Coomassie Blue, and destained with distilled w ater.

[0257] For proteins purified using the dialysis method (FIG. 10), 5 mL of overnight cultures w ere added to 500 ml of Terrific Broth. Again, cells w ere incubated at 37 C until reaching anOD600 of 0 6-1.0, whenftasks were transferred to 18 °C. Here, 1 mM IPTG was added to all cells, in addition to 10 μM FeCl3for cdmA- and cdm D-ex pressing cells. Cells w ere harv ested and lysed as described above. After centrifugation at 15000xg, the lysate supernatants were dialyzed twice into 50 mM potassium phosphate (pH 7.5 ) using 30 kDa MWCO dialy sis cassettes. Protein concentration of dialyzed proteins was estimated by comparing against known concentrations of IMAC-purified enzymes using SDS-PAGE as A280 might not accurately show protein concentration of dialyzed samples giv en then higher background.VI. Caffeine Demethylation Assays,

[0258] For reactions using NADH (FIGs. 1 -2. 41). 9( ) a typical reaction mixture contained 5 μM cdmA, 5 μM cdmD, 0.5 mM caffeine, 50 μM iron (II) ammonium sulfate, and 5 mM NADH, prepared in PBS - glycerol assay buffer. In Figure 9C. a 10% ( v v) cold brew solution was also included as a condition in the experiment. The reaction was incubated at 30 °C, and timepoints were prepared by remov ing aliquots of the reaction and mixing w ith 50-70% methanol or aceton in ile. stopping the reaction by denaturing the enzymes.

[0259] In FIGs. 3D-3E reactions w ere set up as described above w ith sev eral exceptions. 5 μM glucose dehydrogenase, glucose, and NAD (Acres Biosy stems) w ere added at concentrations specified in figure legends. Timepoints were taken at 0 and 90 minutes, and % theobromine of total methylxanthines was calculated as above cdm2 andedmd were selected for this experiment as they had high activity on caffeine in initial experiments. 0.5 mM caffeine (3D) or 10% cold brew (3E) was used.

[0260] In FIGs. 6-12, with the exception of FIG. 9€ as described above, reaction mixtures contained single-strength cold blew that vv as prepared by diluting 2 x black multi-sei v e concentrate by half v v te g . 50 nl . cold brew would be mixed w ith 50 pl. total other ingredients for 100 uL final). For experiments involving dilute coffee (FIGs. 3E,5, 9C), a 10% cold brew solution was used Final caffeine concentrations w eie calculated to be around 2.2 mM. roughly equivalent to 100 mg caffeine per 8 fl oz w hich is within the expected caffeine concentration range of singlestrength brewed coffee. Enzyme concentrations are all specified in figure legends, and cdm A / D pairs are used from the same organism unless otherwise noted (e.g. in FIG. 5). A typical reaction also included 0.5 mM NAD+,50 μM iron (II) ammoni um sulfete or iron (II) chloride, and either 50 mM glucose (FIGs. 6C-6D, 9D) or 12.5 mM glucose (FIGs. 7, 8E, 10B-10D, 1 ID, 12D). The remaining reaction volume was made up w ith 50 m\l potassium phosphate, the same buffer thatthe enzymes were exchanged into. Unless otherwise specified, reactions occurred at room temperature.

[0261] Theobromine and caffeine were separated using an SB-CT 8 column and a rev erse phase high pressure liquid chroinaioeraphy mass spectrometry method with water and methanol or acetonitrile as the mobile -phases. Theobromine ( 181 m / z) and caffeine (195 m / z) peaks were obtained w ith selected ion monitoring(SIM). and peaks were integrated using Agilent Openlnb CDS Data. Analysis software to calculate die area under the curve. % theobromine of total methylxanthines was calculated by div iding the AUC of theobromine by the summed AUCs of theobromine and caffeine. % caffeine remaining w as calculated by comparing the AUC of the caffeine peak to a no-enzyme condition with the same coffee concentiationVII.. CdmD NADH Dehydrogenatfen Assays. :

[0262] The activity of cdmDs on NADH, without the presence of cdmA or caffeine, was assayed based on the higher absorbance of NADH at 340 nni compared to NAD . 2 uM of cdmD was combined with 5 mM NADH in 50 mM potassium phosphate (pH 7.5) buffer. Controls included buffer instead of protein, or the D2 ferredoxin domain alone, wh ich does not har e EAD or NAD binding sites. Reactions w ere incubated at room temperature, and absorbances were read at 340 ntn to determine NADH dehydrogenation.VIII. Glucose Dehydrogenase NADU Reduction Assays.

[0263] A typical reaction consisted of 2.5 μM glucose dehy drogenase. 140 mM glucose, and 3 mM NAD in 25 mM Tris-HCl buffer (pH 8.0) Reactions were initiated by adding glucose. Glucose dehy drogenase act i v ity w as measured as the increase of absorbance at 340 mn over time on a plate reader. Reactions occurred at room temperature unless otherwise specified, such as in FIG. 12CExample 1: Glucose Dehydrogenase Expression and Assays.:

[0264] Glucose dehydrogenase sequences were selected from the scientific literature of known enzymes that reduced NADH in the presence of glucose, favoring single chain and bacterial enzy mes ( fable 2) SEQ ID NO. I is "gdh I SEQ ID NO 2 is "gdh2 ": SEQ ID NO. 3 is "gdh3 SEQ ID NO. 4 is "gdh4": SEQ ID NO: 5 is "gdh5"; SEQ ID NO. 6 is gdh6". SEQ ID NO. 7 is "gdh7": SEQ ID NO. 8 is "gdh8": SEQ ID NO 9 is "gdh9": and SEQ ID NO: 10 is "gdh 10"

[0265] Sequences were codonroptimized for E. coff expression, appended with an N-terminal6x- His tag Genes were transfouned. expressed, and purified as described abov e with minor changes: 0.5 mM I PIG w as used and no FeCh was added. A tv pica! reaction consisted of 2.5 μM glucose dehydrogenase. 140 mM glucose, and 3 mM NAD in 25 mM Tt is-HCl buffer (pH 8.0k Reactions were initiated by adding glucose,

[0266] Glucose dehydrogenase activity was measured as the increase of absorbance at 340 nm overtime on a plate reader.Example 2: Identification of Demethylase Genes & New Protein Designs

[0267] Nineteen potential caffeine dumethv lase genes designated cdm l - cdm!9 were determined from the scientific literature and from protein-protein BLAST searches using a known caffeine demethylase from Psendomonos putida (Tables 3-4).

[0268] New designs for cdinA. cdml). gdh. and linked cdm XD are prm ided in T able 5.Table 3. Natural protein source organisms that were expressed and tested for demethylation activity'

[0269] Each caffeinedemethy laseconsists ofa demethylase (cdmA) domain as well as an N ABH dehydrogenase domain I cdmD). We obtained structures of each potential cdmA and D domain using AlphaFold2 (14) to ensure that the structures generally matched a previously-reported cdm from P. pmkid The structures were also used to remot e unstructured N-tetminal regions from cdmA and N-terminal Rieske domains in cdml) that were not hypothesized to be inv olved in NADH dehydrogenation. DMA encoding cdmA and cdmD sequences were inserted in pet28b + v ectors, transfoimed into competent BLR ow cells, expressed, and purified using immobilized metal affinity chromatography (see Methods & Methods for additional details').

[0270] b ight cdm A and sex en cdmD sequences were present in the elution fraction according to SDSLPAGE (FIG. -1 B-1C), correspondingto six. pairs of enzymes that both expressed. 'Five of tibe six cdm pairs were able to catalyze the conversion of 0.5 m M caffeine to theobromine, converging near 100% conversion after 20-60 mm depending on the enzvme ( FIG. 1 D-1 F ) One of these enzymes (cdm3) has been previously -expressed and shown to be -active on caffeine; the other four (cdm2. -I. 6, and 8 ) are from organisms that have been prev iously associated w ith caffeine demethy lation and (or) metabolism

[0271] When the five functional edms were tested using ready-to-drink black unsweetened cold brew as the caffeinesottrce at approximately the same concentration, theobromine production was still observed for the five working cdms;however;only approximately 5-20% of the caffeine was converted into theobromine (FIG. 2).

[0272] Eight additional cdm subunits (cdml 2- 19 A and D) were further tested and evaluated. As show n in FIG . 81) ail ordered cdm 12-19 A and D polypeptides w ere soluble per SDS-PAGE. The activ ities of cdm 12 - 19 A and I) were also tested. As show n in FIG. 8E. while all cdm 12-19 enzv mes had some activ ity on caffeine in I x cold btew.none appeared to be as activ e as the A2t / D2 control. CdmA. cdmD. and gdh I enzy mes were at 70 μM, 10 μM and 5 μM. respectivelyExample 3 : Glucose Dehydrogenase-Based Regeneration System

[0273] We next determined if the X'ADIl requ iement for cdm activ ity could be replaced w ith a glucose dehy drogenase-based regeneration sy stem Glucose dehydrogenase catalyzes the reduction of NAD+by -glucose, and so we hypothesized that we could add catalytic amounts of N AD+to our system and maintain cdm activity (FIG. 3A). Because NADH is costly and requbes cold storage, it would be economically necessary to either significantly reduce the N ADH addedor to replace the NADU with something less expensive such as NAD+. Four glucose dehydrogenase genes were expressed, and all were found to reduce NAD+in the presence of glucose (FIG. 3B-3C).

[0274] When glucose dehydrogenase, glucose, and NAD+replaced NADH in the caffeine demethylation reaction, full demethylation was still observed on caffeine for cdm2 (left lines, darker grey) and cdm4 (right lines, lighter grey) enzymes (FIG. 3D). Concentrations of NAD+as low as 50 ,μM, and glucose as low as 1.4 mM, were still sufficient to convert nearly 100% of caffeine to theobromine for both enzymes that were tested. In coffee, the enzymes converted caffeine to theobromineat comparable levels to NADH controls ( FIG. 3E). Here, cdm2 converted 1.0-15% more of the caffeine from coffee in the reaction mixture as compared to cdm4.

[0275] Enzymatic conversion of caffeine to theobromine has great potential to improve the quality and convenience of decaffeinated foods. However. caffeine demethylaseshave not yet been- shown to be active in coffee and require expensive concentrations of NADH. We have confirmed the activity of five caffeine demethy lases on caffeine in buffer and have shown that these enzymes maintain 5-20% of their activity in cold brew coffee.

[0276] We developed a glucose dehydrogenase-based NADH regeneration system that uses catalytic amounts of NADyand is less expensive than adding equimolar (to caffeine) levels of NADH. The NADHregeneration system was fueled by glucose in this example due to the lo w cost of glucose but is in principle possible using any of the many other enzymes that reduce NAD"- , e.g,, alcohol dehydrogenases or sugar dehydrogenases.Example 4: Modified Enzymes

[0277] Activities and properties of modified enzymes were also tested,

[0278] CdmD1twas made, which represents the version of cdinD1 without the Rieske domain. FIG. 4C shows the SDS-PAGE results of D1 (cdinD1 ) as compared with D1t (D1 with the truncated Rieske domain) and D1t.A (D1 with the truncated Rieske domain and with alanine). Compared, with the two other versions, D1t. A exhibited very good solubility when expressed in E colt FIG. 41) shows the caffeine conversion rate ofcdml (cdmA1 with cdmD1tA), cdm2, cdm3, and cdm6. The results show that the demethylation system based on the modified protein cdml (cdmA1 with cdmD1tA) is also functionable. CdmA and cdmD enzymes were at 5 μM concentrations.

[0279] FIG. 5 compares the caffeine conversion rate of cross-combinations of cdmA (A1 / A2 / A3 / A4 / A6 / A8) and cdmD (D 1 / D2(D3 / D4 / D6 / D8) subunits in a 10% cold brew solution. Some cross-combinations exhibited very good conversion rate, indicating that enzyme crosscombinations may be a method of improving the activities of the engineered caffeine demethylases. Enzymes were at 5 / 5 / 1 μM forcdtnA / cdmD / gdh I , respectively, and the reaction proceeded, for 1 h. Numbers represent percent theobromines, of total methylxanthines (theobromine + caffeine) after 1 h.

[0280] FIG.6 A compares the structures of cdmA2 and A2t. A2t(lightgrey)isa truncated version of cdm.A2 (dark grey), with 5 N -terminal residues and 8 C-tenninal residues removed. FIG. 6B compares the structures of cdmA2 and A2. I 0. A2.10 is a V 182 L mutation (white ) of cdmA2 ( grey) near the active site iron (sphere) and caffeine. FIG. 6C shows that A2t and A2. 10 more rapidly convert the caffeine in cold brew coffee compared to the natural demethylases A2 or A3, FIG. 6D shows that enzymes retain 20-30%of their decaf&inationactivity in coffeeheatedto 75 °C CdmA concentrations were 100 μM in C and D, with 20 μM of the corresponding cdmDs and 10 μM gdhl .

[0281] FIGs. 7A-7B show the activities of A2t ( FIG. 7 A.) and A2.10 (FIG. 7B) at different concentrations in 1.x cold brew coffee. Concentrations of D2 and gdh l were 20 μM and 10 μM, respectively. FIG.7C shows the caffeine remaining in 1 x. cold brew when lowering D2 and gdhl levels, with 70 μM A.2t. FIG. 71) shows additional time points for th e demethylation system using A2t, D2. and gdhl (at 70, 10, 5 μM respectively). The results indicated feat the testing coffee underwent near total decaffeination at 4 hours.

[0282] FIGs.9B-9D show the properties and activities of linked pro teins. FIG.9 B shows soluble expression of multiple linked designs. Desi gns labeled “not'd’' also had. the ferredoxin domain of their respective cdmDs removed FIG. 9C shows the caffeine conversion in 0.5 mM caffeine or a 10% cold brew solution of linked protein designs. FIG. 9D shows the timepoints of caffeine conversion of linked protein designs in lx cold brew solution. For unlinked controls, 100 μM cdmA and 20 μM cdmD were used, while 95 μM AD3 _linkl was used; 10 μM gdhl was added to all conditions. The results indicate that some linked proteins exhibited acceptable solubility and activities comparable to unlinked control.

[0283] FIG. 10A shows the protein concentration of dialyzed proteins purified using immobilized metal affinity chromatography (IMAC). FIGs. .10B-10D compare the conversion rateof different levels of dialyzed proteins The results indicate that A2t (FIG. 10B), D2 (FIG. 10C), and gdh 1 (FIG. 1 OD) can all be lowered from their baseline levels (dashed line with down-fadng triangle for all) with retained activity; increasing gdhl also led to quicker caffeine conversion. IMAC conditions use immob ilized metal affinity chromatography-purified proteins, all at 70 / 10 / 10 μM (A2t / D2 / gdh I respectively). Unless specified in the legend, concentrations of A2t / D2 / gdhl are also 70 Z 10 / 10 μM.

[0284] FIG. 11 A shows soluble expression of D2’s FAD / NAD domain; 5 new genome mines linked to D2’s ferredoxin domain (D2.N 1-5), and 4 Protein MPNN redesigns of D2 (D2.mpnnl- 4). D2’s ferredoxin domain (-10 kDa) was minorly soluble. FIG. 11 B shows that most of die designed / genome mined proteins resulted led to a lower 340 nm signal (corresponding to NADH oxidation) compared to either a b lank or the D2 ferredox in domain alone . FIGs. 11C-11 D show the caffeine conversion rate of the designed / genome mined proteins. While most genome mines and MPNN designs still led to caffeine demethylation of pure caffeine solutions at room temperature (FIG. 11C), none were clearly faster than the D2 control; in 65°C coffee (FIG. 11D), the- D2 control had the highest demethylation activity. CdmA, cdmD, and gdh I enzymes were at 100 μM, 20 μM, and 10 μM, respectively.

[0285] FIG. 12 A shows soluble expression of .10 natural gdhs (gdhl -10), and 4 ProteinMPNN redesigns of gdh 1 (gdh I .mpnn 1 -4), FIGs. 12B-12C show thatmost of the designed / genome mined, proteins led to an increased 340 nm signal (corresponding to NAD+reduction) at room temperature (FIG. 12B) or 75°C (FIG. 12C). FIG. 12D shows that the use of gdh I to regenerate NADH still led to the most caffeine demethylation in lx coffee solutions heated to 75°C. CdmA, cdmD, and gdhl enzymes were at 100 μM, 20 μM and 10 μM, respectively.

[0286] Overall, the experimental results of the modified enzymes show that protein modification, such asintroducing truncations or iinkingdiff erent activity domains together, may be a practicable way to further improve the caffeine demethylation activity' of the modified enzymes. The results also show that the modified enzymes may retain functions when being placed in a warm or hot te mp e ra tu re en v iron m ent.Example 5: Dec a fie illation resting Results

[0287] FIGs. I4A-14F provides the test results of acti vity of cdmA2t cdmD2, and gdh I inStarbucks Signature Black Cold Brew Coffee Concentrate with 0.05 m.M FefCI'h , 12.5 mMglucose, and 0.5 mM NAD+ Unless otherwise specified, cdmA2twas 70 μM, cdmD2 was 10 μM, and gdhl was 10 μM. Assays were performed at room temperature and caffeine concentration quantified by LCMS. FIGs. 1.4A-14C: Effect of varying concentrations of cdmA2t (FIG. 14 A), cdmD2 (FIG. 14B), and gdhl (FIG. 14C) on caffeine reduction over a 240 minute time period. FIGs. 14D-14F: Effect of varying concentrations of cdmD2 on caffeine reduction while CdmA2t concentration is held at 40 μM (FIG. 140). 35 μM (FIG. 14E), or 30 μM (FIG. 14FX from 60 to 240 minutes.

[0288] FIG. 14 A shows that cdmA2t was more active at a concentration of about 70 μM.

[0289] FIG. 14B shows that cdmD2 exhibited comparable activity at a concentration of about 10 μM, at a concentration of about 5 μM, or at a concentration of about 2.5 μM.

[0290] FIG. 14C shows that gdhl was more active at a concentration of about 10 μM.

[0291] FIG. 14 D shows dial a cdmA2t:cdm D2 ratio of about 70 μM: 10 μM exhibited better activity.

[0292] FIG. 14E shows that a cdmA2tcdmD2 ratio of about 70 μM: 10 μM, of about 35 μM:7.5 μM, or of abou t 35 μM:5 μM exhibited comparable activity.

[0293] FIG. 14F shows that a cdmA2t:cdmD2 ratio of about 70 μM: 10 μM, of about 30 μM:7.5 μM, or of about 30 μM;5 μM exhibited comparable activity.

[0294] Overall, tire experimental results show that the enzyme combination of cdmA2t, cdmD2, and gdhl may be able to ef ficiently convert caffeine to theobromine in commercially available caffeine beverages.Example 6: Freeze-Dried Enzymes

[0295] FIG. 15 provides the testing results of the effect of freeze drying on enzyme activity. Each enzyme (cdmA2t, cdmD2, or gdhl) was purified by the dialyzed lysate procedure. Concentration of enzyme was estimated by SDS-PAGE. cdmA2t was 40 mg / mL, cdmD2 was 2 mg / rnL, and gdhl was lO ntg / mL. For each enzyme, 1.5 mL of enzyme was combined with 1.5 mL of I .M sucrose. Each solution was then flash-frozen in l iquid nitrogen and freezedried. Freeze drying was completed using a Blue Alpine Medium Freeze Dryer (#BA40MFD), using the standard “Liquids” Recipe with default settings. In brief, the Quick Start Freeze Cycle was initiated for 1 hour, followed by a 16-hour Dry Cycle, The Final Shelf Temperature (maximum allowed temperature ) was set to 44°F, After freeze-drying, the resulting white powder was storedat 22'C; and reconstituted in 1 5ml.. water immediately before use . Each freeze-dried enzyme' was individually added to a reaction in which the other components of the reaction were freshly- prepared enzyme (e.g., freeze-dried cdmA2t was complemented with, freshly prepared cdmD2 and gdh l) in the standard 70u.M:10uM:10uM reaction (cdmA2t:edmD2:gdh1 ) and compared to a control reaction with only freshly prepared enzyme.[00296 Overall, the testing results show that freeze-dried enzymes (cdmA2t, cdmD2, and gdhl) exhibited activity comparable to their freshly prepared counterparts..Example 7: Green Coffee Extract Assays

[0297] The ability of the enzymes of the present disclosure to convert caffeine in a green coffee extract (GCE) was investigated to determine if enzymes could assist or replace current caffeine removal steps of water-based decaffeination processes.

[0298] GCE was made by soakingS grams of green beans In 15 ml.. water, incubated at 70 °C for 6 hours, after which the spent, green coffee beans were removed to create the final GCE solution.

[0299] The enzyme activity assay used a 10% GCE solution in the final mixture, 25 μM cdnaA (A2t, A2.10, and A3 were used), 5 μM cdmD (D2 or D3 was used corresponding to the cdmA type), 5 μM gdh 1 , 50 m.M glucose, 0.5 inM. NAD:, and 100 μM Fe( Il)C1. All reactions occurred in a 50 mM KPi (pH 7.4) buffer.

[0300] Timepoints for HPLC-MS were taken at 0, 1, 2, 4, and 21 hours. Comparing the 21- hour time points, A2t / D2 was the most active enzyme system with 8% caffeine remaining, then A2.10 / D2 with 23% caffeine remaining, and finally A3 / D3 with 48% caffeine remaining.Further Numbered Embodiments of the Disclosure

[0301] Other subject matter contemplated by the present disclosure is set out in the following n umbered embodimen is :I . A composition comprising an amino acid sequence coding for a caffeine demethylase cdmA domain, an amino acid sequence coding for a caffeine demethylase cdmD domain, glucose, N ADf and an amino acid sequence coding for a glucose dehydrogenase, wherein adding the composition to a caffeine containing substance results in at least 90% of the caffeine being converted to theobromine.2. A kit comprising an amino acid sequence coding for a caffeine dernethylase cdmA domain, an amino acid sequence coding for a caffeine dernethylase cdmD domain, glucose, NAD+, and an amino acid sequence coding for a glucose dehydrogenase, wherein adding the kit to a caffeine containing substance results in at least 90% of the caffeine being converted to theobromine.3. The composition of embodiment 1. or the kit of embodiment 2, wherein each of the cdm A and cdmD domains are derived from one or more source organisms as set forth in Table 3.4. The composition of embodiment 1 or the kit of embodiment 2, wherein each of the c-dmA and cdmD domains are selected from the cdmA and cdmD domains, respectively, as provided in Table 4.5. The composition of embodiment 1 or the kit of embodiment 2, wherein a natural or synthetic caffeine dernethylase protein comprises the amino acid sequences coding for die cdmA and cdmD domains.6. The composition of embodiment 1 or the kit of embodiment 2, wherein the caffeine dernethylase protein is isolated from or derived from a source organism as set forth in Table 3.7 The composition of embodiment. 1 or the kit of embodiment 2, wherein the cdm A and cdmD domains of a na tural or synthetic caffeine dernethylase protein are selected from the cdmA and cdmD domains, respectively, as provided In fable 4.8. The composition of embodiment 1 or the kit of embodiment 2, wherein at least 91 %, or at least 92%, or at least 93%, or at least 94%, or at least 95%, or at least 96%, or at least 97%, or at least 98%, or at least 99% of the caffeine is con verted into theobromine after the composition is added to the substance.9. The composition of embodiment 1 or the kit of embodiment 2, wherein essentially all the caffeine is converted into theobromine after the composition is added to the substance.10. A. method, of decaffeiftating a substance comprising adding one or more of the compositions of embodiment 1 - embodiment 9 to the substance.1 1 . The method of embodiment 10, wherein the substance is brew ground roasted coffee comprising water.12. The method of embodiment 11 , wherein the substance is about 8 ounces, or about 10 ounces, or about 12 ounces of brew ground coffee comprising water.13. The method of any one of embodiment 10 - embodiment 12, wherein the composition is provided in a single use package.14. The method of any one of embodiment 10 ~ embodiment 12, wherein the kit is provided as a single use package comprising cdmA and cdmD, and a separate single use package of glucose, NAD+, and an amino acid sequence coding for a glucose dehydrogenase.15. A method comprising the process as set out In Figure 1.3.

[0302] Additional embodiments are listed below:1 . A composition comprising an amino acid sequence coding for a caffeine demethylase cdmA domain, an amino acid sequence coding for a caffeine demethylase cdmD domain, glucose, NADT, and an amino acid sequence coding for a glucose dehydrogenase, wherein addingthe composition to a. caffeine containing substance results in at least 90% of the caffeine being converted to theobromine.2. A kit comprising an amino acid sequence coding for a caffeine demethylase cdmA domain, an amino acid sequence coding for a caffeine demethylase cdmD domain, glucose, NAD4-, and an amino acid sequence coding for a glucose dehydrogenase, wherein adding the kit to a caffeine containing substance results in at least 90% of the caffeine being converted to theobromine.3. The composition of embodiment 1 or the kit of embodiment 2, wherein each of the cdmA and cdmD domains are derived from one or more source organisms as set forth in Table 3.4. The composition of embodiment i or the kit of embodiment 2, wherein each of the cdmA and cdmD domains are selected from the cdmA and cdmD domains, respectively, as provided in Table 4,5. The composition of embodiment 1 or the kit of embodiment 2, wherein a natural or synthetic caffeine demethylase protein comprises the amino acid sequences coding for the cdmA and cdmD domains.6. The composition of embodiment 1 or the kit of embodiment 2, wherein the caffeine demethylase protein is isolated from or derived from a source organism as set forth in Table 3.7. The composition of embodiment 1 or die kit of embodiment 2, wherein the cdmA and cdmD domains of a natural or synthetic caffeine demethylase protein are selected from the cdmA and cdmD domains, respectively, as provided in Table 4,8. The composition of embodiment I or the kit of embodiment 2, wherein at least 91%, or at least 92%, or at least 93%, or at least 94%, or at least 95%, or at least 96%, or at least 97%, or at least 98%, or at least 99% of the caffeine is converted into theobromine after the composition is added to the substance.9. The composition of embodiment I or die kit of embodiment 2, wherein essentially all the caffeine is converted into theobromine after the composition is added to the substance. i 0. A method of decaffeinating a substance comprising adding one or more of the compositions of embodiment 1 embodiment 9 to the substance. 11. The method of embodiment 10, wherein the substance is brew ground roasted coffee comprising water.12. The method of embodiment 11 , wherein the substance is about 8 ounces, or about 10 ounces, or about 12 ounces of brew ground coffee comprising water.13. The method of any one of embodiment 10 - embodiment .12, wherein the composition is provided in a single use package.14. The method of any one of embodiment 10 embodiment 12, wherein the kit is provided as a single use package comprising cdmA and cdmD, and a separate single usepackage comprising glucose, NAD+, and an amino acid sequence coding for a glucose dehydrogenase.15. A method comprising the process as set out in Figure 13.16. A polypeptide comprising an amino acid sequence having at least 80, 85, 90, 95,98, 99, or 100% sequence identity with a cdmA or cdmD amino acid sequence disclosed in Table 4 but optionally lacking a poly-His sequence,17. Tire polypeptide o f embodimen t 16, wherein the amino acid sequence is fused io a heterologous amino acid sequence.18. A polynucleotide encoding the polypeptide of embodiment 16 or 17.19. A vector comprising a promoter operably linked to the polynucleotide of embodiment 18.20. A cell comprising a heterologous polynucleotide, wherein the heterologous polynucleotide is the polynucleotide of embodiment 18 or the vector of embodiment 19.21. The cell of embodiment 20, where in the cell is a bacterial cell.22. A method of making the polypeptide of embodiment 20, the method comprises expressing the polypeptide in the cell and purifying the polypeptide from the cell.23. A composition comprising a a first polypeptide comprising a cdmA domain, a second polypeptide comprising a cdmD domain, glucose and a glucose dehydrogenase.24. A composition of embodiment 23, wherein the first polypeptide comprises an amino acid sequence having at least 80, 85, 90, 95, 98, 99, or 100% sequence identity with a cdmA amino acid sequence disclosed in "fable 4 but optionally lacking a poly-His sequence and / or the second polypeptide comprises an amino acid sequence having at least 80, 85, 90, 95, 98, 99, or 100% sequence identity with a cdmD amino acid sequence disclosed in Table 4 but optionally lacking a poly-His sequence.25. The composition of embodiment 23 or 24, wherein the first polypeptide comprises an amino acid sequence to the cdmA domain and / or the second polypeptide comprises an amino acid sequence to the cdmD domain.26. A method of decaffeinating a substance, the method comprising, mixing the composition of any one of embodiment 23-25 with the substance for sufficient time to convert caffeine in the substance to theobromine.27. The method of embodiment 26, wherein at least 91 %, or at least 92%, or at least 93%, or at least 94%, or at least 95%, or at least 96%, or at least 97%, or at least 98%, or at least 99% of the caffeine is converted into theobromine after the composition is added to the substance.28. The method of embodiment 26 or 27, wherein the substance is coffee or tea.INCORPORATION BY REFERENCE

[0303] All references, articles, publications., patents, patent publications, and patent applications cited herein within the above text and / or cited below are incorporated by reference in their entireties for all purposes. However, mention of any reference, article, publication, patent, patentpublication, and patent application. cited herein is not, and should not be taken as acknowledgment or any form of suggestion that they constitute valid prior art or form part of the common general knowledge in any country in the world.

[0304] 1 . S. Rodda, N . Booth, J. McKean, A. Chung, J . J . Park, P. Ware, Mechanisms for the reduction of caffeine consumption; What, how and why. Dn / g / Ucohoi Depend. 212, 108024 (2020).

[0305] 2. Y. Zou, M. Gaida, F. A. Fran china, P.-H. Stefanuta, J.-F. Focant, Distinguishing between Decaffeinated and Regu lar Coffee by F1S-SPME-GC×GC-TOFMS, Chemometrics, and Machine Learning, MVet’u&v. 27 (2022), dot: 10.3390 / molecules27061806.

[0306] 3, S. M. Lee, H.-S. Lee,K,-H. Kirn,K.-O. Kim, Sensory characteristics and consumer acceptability of decaffeinated green teas. J. Food Set 74, SI 35 -41 (2009).

[0307] 4. C. L, Yu, Y. Kale, S. Gopishetty, T. M, Louie, M. Subramanian, A navel caffeine dehydrogenase in Pseudomonas sp. strain CBB1 oxidizes caffeine to trimethyluric acid. J. Bacterial. 190, 772- 776 (2008).

[0308] 5 , D,-D. Tian, S . Natesan , J, R, White , Jr, M. F, Pain e, Effects of Common CY Pl A2Genotypes and Other Key Factors on Intraindividual Variation in the Caffeine Metabolic Ratio: An Exploratory Analysis. Clin. Transl. Sei 12, 39-46 (2019).

[0309] 6. N. L. Benowitz, P. Jacob 3rd, H. Mayan, C. Dena.ro, Sy mpathomimetic effects of paraxanthine and caffeine In humans. Clin. Pharmacol. Then. 58, 684-691 (1995).

[0310] 7, R. M. Summers, T, M. Louie, C.-L. Yu, L, Gakhar, K. C. Louie, M, Subramanian, Novel, highly specific 'N-demethylases enable bacteria to live on caffeine and related purine alkaloids. J. BacterioL 194, 2041-2049 (2012).

[0311] 8. P. Wahed, M. A. Razzaq, S. Dharmapuri, M. Corrales, Determination of formaldehyde in food and feed by an in-house validated HPLC method. Food Chem. 202, 476- 483 (2016).

[0312] 9. J. H. Kim, B. H. Kim, S. Brooks, S. Y. Kang, R. M. Summers, FL K. Song, Structural and Mechanistic Insights into Caffeine Degradation by the Bacterial N-Demethylase Complex. J. Mol. Biol. 431 , 3647-3661 (2019).

[0313] 10. D. Sun, X. Yang, C. Zeng, B. Li, Y. Wang, C. Zhang, W. Hu, X. Li, Z Gao, Novel caffeinedegradation gene cluster is mega-plasmid encoded in Paraburkholderia caffeimlytica CFI . Appl. Microbiol. BioteehnoL 104, 3025-3036 (2020).

[0314] 1 1. R. E. Parales, G. Sharma, X. Zhang, G. A. Subuyuj, J, T. Langner, M. E. Wright, J. L, Ditty, S. C. Dawson, Draft Genome Sequence of the (Yiffeine-DegradiugMethylotropli Pinkel Microbiol Resour Announc. 8 (2019), doi: 10.1128 / MRA.01300-19.

[0315] 12. F. E, Vega, S. Emche J. Shao, A. Simpkins, R. M. Summers, M. B. Mock, D. Ebert F. Infante, S. Aoki, L E. Maul, Cultivation and Genome Sequencing of Bacteria Isolated From die Coffee Beny Borer (), With Emphasis on the Role of Caffeine Degradation, Front. Microbiol 12, 644768 (2021 ).

[0316] 13. D, A. Judelson, A. G. Preston, D. I... Miller, C, X. Munoz, M. D. Kellogg, H. R. Lieberman, Effects of theobromine and caffeine onmood and vigilance. J. Clin. Psyehophrrrmocoi. 33, 499-506 (2013).

[0317] 14, J. jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvtmakool, R, Bates, A. Zidek, A. Potapenko, A. Bridgland, C. Meyer, S. A. A. Kohl, A, j. Ballard, A. Cowie, B. Romera-Paredes, S. Nikolov, R. Jain. J. Adler, I. Back, S. Petersen, D. Reiman, E. Clancy, M. Zielinski, M. Ste megger, M. PachoIska, T. Bergliammer, S. Boden stem, D, Silver, O. Vin.yals, A. W. Senior. K. Kavukcuoglu, P. Kohli, D. Hassabis, Highly accurate protein structure prediction with AlphaFold. Nufure. 596, 583-589 (2021).

[0318] 15. F. Madeira, M, Pearce, A. R. N. Trvey, P. Basutkar, J. Lee, O. Edbali, N. Madhusoodanan, A. Kolesnikov, R. Lopez, Search and sequence analysis tools services from EMBL-EBI in 2022. Mudeic Acids Res. 50, W276-W279 (2022).[00 319] 16. C. L. Ya, T, M. Louie, R, Summers, Y. Kale, S. Gopishetty,M. Subramanian, Two distinct pathways for metabolism of theophylline and caffeine are coexpressed in Pseudomonas putlda CBB5. J Bacterial 191, 4624-4632 (2009).

[0320] 17. S. Ibrahim, M. Y. Shukor, M. A. Syed, W. L. Wan Johari, S. A. Ahmad, Characterisation and growth kinetics studies of caffeine-degrading bacterium Leifsonia sp. strain: SIU. Annals of Microbiology 66, 289-298 (2015).

[0032] ] 18. Y. Y. Win, M Singh, M, B, Sadiq, A. K. Anal, Isolation and identification of caffeine-degrading bacteria from coffee plantation area. Food Biotechnol 33, 109-124 (2019).

[0322] 19. S. Watahiki, N. Kimura, Draft Genome Sequence of a Caffeine-lltilizsig Bacterium, Cupriavidus sp. Strain D384. Genome Xmtomcemejtts, doi: 10.1 128 / genomea.00370- 17 (2017).

[0323] 20, R. Zallot, N, Oberg, J . A. Gerlt, The EFI Web Resource for Genomic Enzymology Tools: Leveraging Protein , Genome , andMetagenome Databases to Discover Novel Enzymes and Metabolic Pathways. Biochemisfry, doi: 10.1021 / acs.biochem.9b00735 (2019).

[0324] 21. G. Kim, S. Lee, E. Levy Karin, H. Kim, Y. Moriwaki, S. Ovchinnikov, M. Stelnegger, M. Mirdita, Easy and accurate protein structure prediction using CoIabFoid. AGr Protoc, doi: 10.1038 / s41596-024-01060-5 (2024).

[0325] 22, W, Hilt, G. Pfleiderer, P. Fottnagel, Glucose dehydrogenase from Bacillus subtilis expressed in Escherichia coli. I: ^Purification, characterization and comparison with gluco® dehydrogenase from Bacillus megaterium. Biochim Brophys Acta 1076, 298-304 (1991 ),

[0326] 23. J. L. Watson, D. Juergens, N. R. Bennett, B L, frippe, J. Yim, H. E. Eisenach, W. Ahem, A. J. Borst, R. J. Ragotte, L. F. Milles, B. L M. Wicky,N. Hanikel, S. J. Pellock, A. Courbet, W, Sheffier, J. Wang, P, Venkatesh, I. Sappington, S. V. Torres, A, I,auko, V. De Bortoli, E. Mathieu, S. Ovchinnikov, R. Barzilay, T. S. Jaakkola, F. DiMaio, M. Baek, D. Baker, De novo design of protein structure and function with RFdiffusion. hfawe 620, 1089-1 100 (2023).

[0327] 24. J. Dauparas, I Anishchenko, N. Bennett, H. Bai, R. J. Ragotte, L, F. Milles, B. I M. Wicky. A, Courbet R, J. de Haas, N. Bethel, P, I. Y. Leung, T, F. Ruddy, S. Pellock, D, Tischer, F. Chan, 13. Koepnick, H. Nguyen, A, Kang, 13. Sankaran, A. K. Bera, N. P. King, D. Baker, Robust deep learning-basedprotein sequence design using lYotein.MPNN.5'£.?zewee378?49- 56 (2022).

[0328] 25. K. IL Sumida, R. Nunez-Franco, I. Kalvet, S, J. Fetlock. B, I, M. Wicky, L. F. Milles, J. Dauparas, J. Wang. Y. Kipnis, N. Jameson, A. Kang, J. De La Cruz, B. Saakaran, A. K. Bera, G. Jimenez-Oses, D. Baker, .Improving Protein Expression, Stability, and. Function with ProteinMPNN. , / 4 / n Chem Sac 146, 2054-2061 (2024).

Claims

CLAIMSWhat is claimed is:1 . A composition . comprising: at least one amino add sequencecoding for at leastone caffeine demethylase cdmA domain (“cdmA”); at Ieastone amino acid sequencecodingfor atleast one caffeine demethylase cdmD domain (“cdmD”); at least one sugar; at least one coenzyme; and at least one amino acid sequence coding for a glucose dehydrogenase (“gdh”), wherein concentration ratios of cdmA;cdmD:gdh range from about 2,3:1 ,0:1 ,0 to about 14,0:1 .0:1 .0.

2. The composition of claim. 1 , wherein the concentration ratios of cdmA:cdmD:gdh are about 3.5 : 1 : 1 , respectively.

3. The composition of claim 2, wherein the concentrations of edmA:cdmD:gdh are approximately 35 μM: 10 μM: 10 μM, respectively.

4. The composition of claim 1 , wherein cdmA comprises an amino acid sequence having SEQ ID NO: 99.

5. 'Hie composition of claim 1 , wherein cdmD coinprises an ammo acid sequence having SEQ ID NO:. 24.

6. The composition of claim I , wherein gdh comprises an amino acid sequence having SEQ ID NO: 1 .

7. The composition of claim 1 , wherein cdmA comprises an amino acid sequence having SEQ ID NO: 99, cdmD comprises an amino acid sequence having SEQ ID NO: 24, and gdh comprises an amino acid, sequence having SEQ ID NO: 1 ,8. The composition of claim I , wherein the sugar is glucose.

9. The composition of claim 1 , wherein the coenzyme is Nicotinamide adenine dinucleotide (NAD).

10. The composition of claim 9, wherein the NAD is 'NAD+,.

11. A composition comprising a cdmA having an amino acid sequence of SEQ ID NO: 99, a cdmD having an amino acid sequence of SEQ ID NO: 24, a gdh having an amino acid sequence of SEQ ID NO: 1, glucose, and NAD , wherein concentration ratios ofcdmA:cdmD:gdh range from about 2.3:1 .0:1 .0 to about 14.0:1 .0:1 .0.

12. A method of converting some or all caffeine to theobromine in coffee comprising caffeine, the method comprising adding to the caffeinated coffee a composition comprising: at least one amino add sequence coding for atleasi one caffeine demeth ylase cdmA domain (“cdmA”); at least one amino acid, sequence coding for at least one caffeine demethylase cdmD domain (“cdmD”); at least one sugar; at least one coenzyme; and at least one amino acid sequence coding for a glucose dehydrogenase (“gdh”), thereby convening some or all the caffeine in the coffee to theobromine.

13. The method of claim 12, wherein concentration ratios of cdmArcdmD.gdh range from about 2,3:1, 0:1 ,0 to about 14.0: 1 .0:1 .0.

14. The method of claim 13, wherein the concentration ratios of cdmA:cdmD.gdh ate about 3 ,5 : 1 : 1 , respectively.

15. The method of claim 14, wherein concentrations of cdmA:cdmD:gdh are approximately 35 qM: 10 μM: 10 μM, respectively.

16. The method of claim 12, wherein cdmA comprises an amino acid sequence having SEQ ID NO: 99.

17. The method of claim 12, wherein cdmD comprises an amino acid sequence having SEQ ID NO: 24.

18. The method of claim 12, wherein gdh comprises an amino acid sequence having SEQID NO: 1.

19. The method of claim 12, wherein cdmA comprises an amino add sequence having SEQ ID NO: 99, cdmD comprises an amino acid sequence having SEQ ID NO: 24, and gdh comprises an amino acid sequence having SEQ ID NO: 1 .

20. The method of claim 12, wherein the sugar is glucose.

21. The method of claim 12, wherein the coenzyme is Nicotinamide adenine dinuc leo tide (N AD ) .

22. The method of claim 21 , wherein the NAD is NAD+.

23. A composition, comprising: at least one amino acid sequence coding for at least one caffeine demeth yiase cdmA domain (“cdmA”); at least one amino add sequencecoding for at least one caffeine demethylase cdmD domain (“cdmD”); at least one sugar; at least one coenzyme; and at least one amino acid sequence coding for a glucose dehydrogenase (“gdh”).

24. The composition of claim 23, wherein the at least, one amino acid sequence coding for al least one caffeine demethylase cdmA domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 21 , 23, 25, 27, 29, 31 , 33, 35, 37, 39, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 99, or 100; and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain comprises an amino acid sequence having at least 80%. 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 22, 24, 26, 28, 30, 32, 34, 36, 38, 41 , 43, 45, 47, 49, 5.1 , 53, 55, 57, 59, 10L 102, 103, 104, 105, 106, 107, 108, or 109.

25. The composition of claim 23 or claim 24, wherein the at least one amino acid sequence coding for a glucose dehydrogenase comprises an. amino acid sequence having at least 80%, 85%, 90%, 95%, 98%. 99%., or 100% sequence identity to one of SEQ ID NO: 1 , 2, 3, 4, 5, 6, 7, 8, 9, 10, 1 10, 111, 112, or 113.

26. The composition of any one of claims 23-25, wherein the cdmA and cdmD domains are derived from one or more source organisms comprising: Methylornbnmi poptdi, Paraburlcholderia caffedidyilca, Pseudomonas jhwrescens, Lelfsoniaxylt, Burkholderid. amblfaritg Cupriavidus sp. D384, Pseudomonas sp. S36, Delftia lacusiris, Caldimtmas thermodepolymerans, Thermomonas sp. Afipia fells, .Pseudoocetmlcola miratireducims, Paracoceus zbefiangensis, Acetobacter senegalensls, Paracoccus versntos, Parahurkholderia furggorom, Caballeronia hypogeia, and / or Pandoraea captiosa.

27. The composition of any one of claims 23-26, comprising a natural or synthetic caffeine demethylase protein, the natural or synthetic caffeine demethylase protein comprises the at least, one amino acid sequence coding for at least one caffeine demethylase cdmA domain and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain.

28. The composition ofclaim 27, wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain and the at least one amino acid sequence coding for at least, one caffeine demethylase cdmD domain are linked with a linker, wherein the linker is a peptide chain comprising 1 , 2, 3, 4, 5, 6, 7. 8, 9, 10, 1 1 , 12, 13, 14, 15, 16, 17, 18, 19, 20, 21 , 22, 23, 24, 25, 26, 27, 28, 29, or 30 amino acids.

29. The composition of claim 27 or claim 28, wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain comprises a ferredoxin domain.

30. The composition of claim 27 or claim 28, wherein the at least one amino acid sequence coding for at least one caffe ine demethylase cdmDdomain do not comprise a ferredoxin domain.31 . The composition of any one of claims 27-30, wherein the cdmD domain is located at the N-terminus region, and the cdmA domain is located at the €~temii.nns region.

32. The composition of any one of claims 27-30, wherein tire cdmD domain is located at the C -terminus region, and die cdmA domain is located at the N-termmus region.

33. The composition of any one of claims 27-32, wherein the natural or synthetic caffeine demethy lase protei n co mprises the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain, the at least one amino acid sequence coding for at least one caffeine demethylase cdrnD domain, and the at least one amino acid sequence coding for a glucose dehydrogenase.

34. The composition of any one of claims 23-33, wherein one or more of the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain, the at least one amino acid sequence coding for at least one caffeinedemeth ylasecdmD domain, and / or the at least one amino acid sequence coding for a glucose dehydrogenase comprises one or more intramolecular disulfide bonds.

35. The composition of any one of claims 23-34, wherein the at least one sugar comprises one or more of glucose, galactose, fructose, allose, altrosc, mannose, gulose, idose, talosc, psicose, sorbose, tagatose, xy lose, arabinose, sucrose, lactose, and / or maltose.

36. The composition of any one of claims 23-35, wherein the at least one coenzyme comprises NA07NADH and / or NAD(P)VNAD(P)H.

37. The composition of any one of claims 23-36, wherein at least 90%, or at least 91 %, or at least 92%, or at least 93%, or at least 94%, or at least 95%, or at least 96%, or at least 97%, or al least 98%, or at least 99%, or about 50-80%. or about 50-75%, or about 50-70%, or about 50- 65%, or about 50-60%, or about 55-80%, or about 55-75%, or about 55-70%, or about 55-65%, or about 60-80%, or about 60-75%, or about 60-70% of the caffeine is converted into theobromine after the composition is added to a caffeine containing substance.

38. The composition of claim 37, wherein essentially all the caffeine is converted into theobromine after the composition is added to the caffeine containing substance;39. The composition of claim 37 or claim 38, wherein the caffeine containing substance is a food or a food precursor.

40. The composition of any one of claims 23-39, wherein the composition is in solid form or in liquid form.

41. The composition of any one of claims 23-40, wherein the composition further comprises at least one formaldehyde dehydrogenase.

42. The composition of any one of claims 23-41 , wherein the composition comprises: the at least one amino acid, sequence coding for at least one caffeine demethylase cdmA domain comprising an amino acid sequence having at least 80%, 85%, 90%, 95% , 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 21, 23, 25, 27, 29, 31 , 33, 35, 37, 39, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 99, or 100:the at least one am ino acid, sequence coding for at least one caffeine demethylase cdmD domain comprising an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO; 22, 24, 26, 28, 30, .32, 34, 36, 38, 41, 43, 45, 47, 49, 51 , 53, 55, 57, 59, 101 , 1.02, 103, .104, 105, 106, 107, 108, or 109; glucose;NAD / NADH; and the at least one amino add sequence coding for a glucose dehydrogenase comprising an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 1, 2, 3, 4. .5, 6, 7, 8, 9, 10, 110, 111, 112, or 113.

43. The composition of any one of claims 23-42, wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain comprises an amino acid sequence ha ving at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 23, 25, 27, or 31 ; and / or the at least one amino add sequence coding for at least one caffeine demethylase cdmD domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO; 24, 26, 28, 32, or 36.,44. The composition of any one of claims 23-42, wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain comprises an amino acid sequence having at least 80%. 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 99 or 100; and / or the at least one am ino acid sequence coding for at least one caffeine demethylase cdmD domain comprises an amino acid sequence ha ving at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 101 , 102, .103, 104, 105, 106, 107, 108, or 109.

45. The composition of any one of claims 27-33, wherein the natural or synthetic caffeine demethylase protein comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity' to one of SEQ ID NO: 114, 115 , 1 16, 117, 1 18, 1 19, 120, or 121.46, The composition of any one of claims 23-45, wherein the at least one caffeine demethylase cdmA. domain comprises, based on SEQ ID NO: 99, one or more active site residues of. a Q152, a Y 155, a R164, a N 167, a F168, a T169, a D170, a F171, a H173, a F174, a H 178, a L182, a E217, a A218, a P219, a 1220, a F223, a Y225, a L235, a V237, a L24S, a N250, a L264, a F266, a H279, a F282, a N283, a D284, a L285, a . V286, a F287, and / or a D290 residue.

47. The composition of claim 46, wherein the at least one caffeine demethylase cdmA domain has at least about 70%, about 75%, about 80%, about 85%. about 90%. about 95, or 100% identity to the active site residues of cdmA domain.48, The composition of any one of claims 23-47, wherein the composition is provided in a single use package.49, A kit, comprising the composition of any one of claims 1 -11 or 23-4850, The kit of claim 49, comprising: a first package comprising the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain; and a second package comprising the at least one sugar, the at least one coenzyme, and the at least one amino acid sequence coding for a glucose dehydrogenase.51 . A method of decaffeinating a caffeine containing substance, comprising; adding the composition of any one of claims 1 -11 or 23-48, or the kit of any one of claims 49-50 to the caffeine containing substance.

52. The method of claim 51 , wherein the caffeine containing substance is brewed ground roasted coffee comprising water.

53. 1'he method of claim 52, wherein the caffeine containing substance is about 8 ounces, or about 10 ounces, or about 12 ounces of the brewed ground roasted coffee comprising water.

54. A method of preparing a decaffeinated beverage, comprising: brewing ground roasted coffee with water such that a liquid coffee extract is formed; separating spent coffee grounds from the liquid coffee extract; adding one or more additives to the liquid coffee extract; and pasteurizing and bottling the liquid coffee extract, wherein the one or more additives comprises sugar, flavors., dairy, and / or pH adjusting ingredients, wherein tire composition of any one of claims 1 -11 or 23-48, or the kit of any one of claims 49-50 is added to the liquid coffee extract when brewing the ground roasted coffee with water, after separating spent coffee grounds from the liquid coffee extract, or when adding the one or more additives to the liquid coffee extract.

55. A polypeptide comprising an amino add sequence coding for at least one caffeine demethylase cdmA domain comprising at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO; 21 , 23, 25, 27, 29, 31 , 33, 35, 37, 39,40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 99, or 100.56, A polypeptide comprising an amino acid sequence coding for at least one caffeine demethylase cdmD domain comprising at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to one of SEQ ID NO: 22, 24, 26, 28, 30, 32, 34, 36, 38, 41 , 43, 45, 47, 49, 51, 53, 55, 57, 59, 101 , 102, 103, 104, 105, 106, 107, 108, or 109.

57. At least one polypeptide comprising: at leastone amino add sequence coding foratleastone caffeine demethylase cdmA domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to SEQ ID NO: 21, 23, 25, 27, 29, 31, 33,35, 37, 39, 40, 42, 44, 46, 48, 50. 52, 54, 56, 58, 99, or 1.00; and / or at least one amino add sequence coding foratleastone caffeine demethylase cdmD domain comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%. or 100%sequence identity to SEQ ID NO: 22 , 24, 26, 28, 30, 32, 34,36, 38, 41, 43. 45, 47, 49, 51 , 53, 55, 57, 59, 101 , 102, 103, 104, 105, 106, 107, 108, or 109.

58. The polypeptide of any one of claims 55-57, wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain does not include a poly -His sequence, and / or the at least one amino ac id sequence coding for at least one caffeine demethylase cdmD domain does not include a poly-His sequence.

59. The polypeptide of any one of claims 55-58, wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmA. domain and the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain are linked with a linker, wherein the linker is a peptide chain comprising 1 , 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13. 14, 15, 16, 17, 18, 19, 20, 21 , 22, 23, 24, 25, 26, 27, 28, 29, or 30 amino acids.

60. The polypeptide of any one of claims 57-59, further comprises the at least one amino acid sequence coding for a glucose dehydrogenase, wherein the at least one amino acid sequence coding for a glucose dehydrogenase comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to SEQ ID NO:

1. 2, 3, 4, 5, 6, 7, 8, 9, 10, 110, 1 11, 112, or 113.61 . The polypeptide of any one of claims 55-60. wherein the at least one amino acid sequence coding for at least one caffeine demethylase cdmA domain,, the at least one amino acid sequence coding for at least one caffeine demethylase cdmD domain, and / or the at least one amino acid sequence coding for a glucose dehydrogenase are fused to a heterologous amino acid sequence.

62. A polynucleotide encoding the polypeptide of any one of claims 55-6163. A vector comprising a promoter operably linked to the polynucleotide of claim 62.

64. A cell comprising a heterologous polynucleotide, wherein the heterologous polynucleotide is the polynucleotide of claim 60 or the vector of claim 63.

65. The cell of claim 64, where in the cell is a bacterial cell.

66. A method of making the polypeptide of any one of claims 55-61, the method comprises expressing the polypeptide in the cell and purifying the polypeptide from the cell67. A composition, comprising: a first polypeptide comprising a cdmA domain; a second polypeptide comprising a cdmD domain; at least one sugar; and a glucose dehydrogenase.68, The composition of claim 67, wherein the first polypeptide comprises an amino acid sequence ha ving at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to SEQ ID NO: 21 , 23, 25, 27, 29, 31, 33, 35, 37, 39, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 99, or 100; and / or the second polypeptide comprises an amino acid sequence having at least 80%, 85%, 90%, 95%, 98%, 99%, or 100% sequence identity to SEQ ID NO: 22, 24, 26, 28, 30, 32, 34, 36, 38, 41, 43, 45, 47, 49, 51, 53, 55, 57, 59, 101, 102, 103, .104, 105, 106, 107, 108, or 109.

69. The composition of claim 68, wherein the first polypeptide does not have a poly-1 dis sequence; and / or the second polypeptide does not have a poly-His sequence.

70. A method of decaffeinating a caffeine containing substance, comprising: mixing the composition of any one of claims 67-69 with the caffeine containing substance for sufficient time to convert caffeine in the caffeine containing substance to tireobromine.71 . The method of claim 70, wherein at least 90%, or at least 91 %, or at least 92%, or at least 93%, or at least 94%, or at least 95%, or at least 96%, or at least 97%, or at least 98%, or at least 99% of the caffeine is converted into theobromine after the composition is mixed with the caffeine containing substance.

72. The method of claim 70 or claim 71 , wherein the caffeine containing substance is a beverage containing coffee, tea, guarana extract, or a mixture thereof.

73. Use of the composition of any one of claims 1-1 1, 23-48, or 67-69, or the kit of any one of claims 49-50, for decaffeinating a caffeine containing substance.

Images