Computational Generation of Chemical Synthetic Routes and Methods

Abstract

To provide a method and system for determining chemical synthesis routes for determining one or more optimal synthetic routes to generate a target compound.SOLUTION: Methods disclosed herein relies on a plurality of reactions 110 for retrosynthesis. The reactions 110 can be comprised of both known reactions 120 and predicted reactions 130, which may be utilized by a route engine 140. The route engine 140 receives a target compound as input and applies reaction transformations derived from the reactions 110 to retrosynthetically generate one or more synthetic routes 150.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims priority to U.S. Provisional Patent Application No. 62 / 640,282, filed Mar. 8, 2018, and U.S. Provisional Patent Application No. 62 / 624,047, filed Jan. 30, 2018, the entireties of which are incorporated herein by reference.

[0002] Statement Regarding Federally Sponsored Research This invention was made with government support under Contract No. W911NF - 16 - C - 0051 awarded by the U.S. Army Research Office. The government has certain rights in this invention.

Background Art

[0003] Retrosynthetic analysis is a problem - solving technique for converting the structure of a target compound along a synthetic pathway that ultimately leads to simple and / or commercially available starting materials (also referred to as “feedstocks”) into a series of progressively simpler structures. Currently, in order to construct such a synthetic pathway retro - synthetically, chemists must rely on known chemical reactions. There is a need for a technique that enables the construction of synthetic pathways that are not constrained by known chemical reactions.

Summary of the Invention

[0004] It should be understood that both the following general description and the following detailed description of the invention are exemplary and explanatory only and not restrictive. A method and a system for determining a synthetic pathway are described.

[0005] A method for identifying one or more synthetic routes for generating a target compound, comprising determining a plurality of known chemical reactions and / or a plurality of novel chemical reactions, determining a plurality of predicted chemical reactions from the plurality of novel chemical reactions based on a trained classifier, generating a plurality of chemical reactions based on the plurality of predicted chemical reactions and the plurality of known chemical reactions, determining at least one target compound, determining a plurality of chemical reaction pathways associated with the at least one target compound, and determining one or more optimal chemical reaction pathways from the plurality of chemical reaction pathways identified for generating the target compound.

[0006] A method for identifying one or more synthetic routes for generating a target compound, comprising training one or more machine learning classifiers based on a portion of a plurality of known chemical reactions, determining one or more known chemical reactions that result in the target compound based on the plurality of known chemical reactions, determining one or more predicted chemical reactions that result in the target compound based on a chemical reaction transformation, wherein the one or more predicted chemical reactions are predicted to succeed by the one or more machine learning classifiers, determining a plurality of synthetic routes in a retrosynthetic manner, each synthetic route resulting in the target compound and at least one synthetic route including at least one of the one or more known chemical reactions and at least one of the one or more predicted chemical reactions, and determining an optimal synthetic route from the plurality of synthetic routes based on a predetermined number of reactions and a cost function.

[0007] This summary is not intended to identify key or essential features of the present disclosure, but is merely intended to summarize certain features and variations thereof. Other details and features are described in the following sections.

Brief Description of the Drawings

[0008] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of the method and system.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9A

Figure 9B

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

DETAILED DESCRIPTION OF THE INVENTION

[0009] As used in this specification and the appended claims, the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. In this specification, ranges may be expressed as "about" one particular value and / or "about" another particular value. When such a range is expressed, in another configuration, one particular value and / or another particular value are included. When a value is expressed as an approximation, it will be understood by the use of the antecedent "about" that a particular value forms another configuration. It will further be understood that each endpoint of these ranges is significant in relation to, and independent of, the other endpoint.

[0010] "Any" or "optionally" means that the event or circumstance described thereafter may or may not occur, and that this description includes both the case where the event or circumstance occurs and the case where it does not occur.

[0011] Throughout the description of this specification and the claims, the word "comprise", and variations of this word (such as "comprising" and "comprises"), mean "including but not limited to", and are not intended to exclude other components, integers, or steps. "Exemplary" means "an example of", and is not intended to convey a display of a preferred or ideal configuration. "Etc." is not used in a limiting sense, but for illustrative purposes.

[0012] When combinations of components, subsets, interactions, groups, etc. are disclosed, specific references to each of the various individual and collective combinations and permutations of these components may not be explicitly described, but each is understood to be specifically contemplated and described herein. This applies to all parts of this application, including but not limited to steps in the described method. Thus, if there are various additional steps that can be performed, it is understood that each of these additional steps may be performed with any specific configuration or combination of configurations of the described method.

[0013] As will be understood by those skilled in the art, hardware, software, or a combination of software and hardware can be implemented. Further, a computer program product on a computer-readable storage medium (e.g., non-transitory) has processor-executable instructions (e.g., computer software) embodied within the storage medium. Any suitable computer-readable storage medium can be utilized, including a hard disk, CD-ROM, optical storage device, magnetic storage device, memresistor, non-volatile random access memory (NVRAM), flash memory, or a combination thereof.

[0014] Throughout this application, reference is made to block diagrams and flowcharts. It will be understood that each block of the block diagrams and flowcharts, as well as combinations of blocks in the block diagrams and flowcharts, can be implemented by processor-executable instructions. These processor-executable instructions may be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, thereby creating a device for implementing the functions specified in the block(s) of the flowchart by processor-executable instructions that execute on the computer or other programmable data processing apparatus.

[0015] These processor-executable instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, thereby creating a manufacture including processor-executable instructions stored in the computer-readable memory that implement the functions specified in the block(s) of the flowchart. The processor-executable instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be executed on the computer or other programmable data processing apparatus to generate a computer-implemented process, thereby providing steps for implementing the functions specified in the block(s) of the flowchart by processor-executable instructions that execute on the computer or other programmable apparatus.

[0016] Accordingly, the blocks of the block diagrams and flowcharts support combinations of devices for performing the specified functions, combinations of steps for performing the specified functions, and program instruction means for performing the specified functions. It will also be understood that each block of the block diagrams and flowcharts, as well as combinations of blocks in the block diagrams and flowcharts, can be implemented by a special-purpose hardware-based computer system for performing the specified function or step, or by a combination of special-purpose hardware and computer instructions.

[0017] The embodiments for carrying out the present invention may refer to a given entity that performs several actions. It should be understood that this language may, in some cases, mean that a system (e.g., a computer) owned and / or controlled by the given entity actually performs the actions.

[0018] In one aspect, methods and systems for generating a synthetic strategy using retrosynthetic analysis are described. A strategy refers to a plan for synthesizing a target compound. Retrosynthetic analysis is a problem-solving technique for converting the structure of a target compound along a pathway that ultimately leads to simple and / or commercially available starting materials (also referred to as "feedstocks"). The conversion of a compound to its synthetic precursor is achieved by applying to the target compound a conversion that is the exact reverse of a certain synthetic reaction. Thereafter, each structure itself derived in the exact opposite direction from the target becomes the target compound for further analysis. The repetition of this process ultimately generates a synthetic route (or simply a route) to the target compound, which has chemical structures as nodes and edges as reactions.

[0019] A target compound can be selected and investigated, and a synthetic route suitable for synthesis can be derived. After selecting a target compound for synthesis, a synthetic plan can be determined that summarizes some or all of the reasonable routes for synthesizing the target compound. Retrosynthesis can be described as a logical disconnection in a strategic bond such that the process gradually leads to the available starting material(s) through several synthetic plans. Each plan thus evolved describes a retrosynthesis-based route. Each disconnection results in a simplified structure. The logic of such disconnections forms the basis of the retrosynthetic analysis of a given target compound. As described herein, the routes can be generated using known chemical reactions and / or computationally generated chemical reactions. Thus, a synthetic tree can be constructed that can summarize some or all of the possible routes for a given target compound.

[0020] A route can be said to be efficient or optimal based on the evaluation of several parameters. For example, when the overall yield of the entire process is the best among all the investigated routes. This depends not only on the number of steps involved in the synthesis but also on the strategy followed. The strategy can involve linear synthesis with only the resulting steps or convergent synthesis with fewer resulting steps. If each cleavage process yields only one executable intermediate and this process proceeds in this manner throughout to a set of starting materials, this process is called linear synthesis. When the intermediate can be cleaved in two or more ways and can yield different intermediates, a branch occurs in this plan. These processes can continue throughout to the starting materials. In such a route, different branches of the synthetic pathway converge towards the intermediate. Such a scheme is called convergent synthesis.

[0021] As shown in Figure 1, the described method and system rely on a plurality of reactions 110 for retrosynthesis. Reactions 110 can consist of both known reactions 120 and predicted reactions 130. Known reactions 120 can be derived from any known reaction source such as a reaction database. The reaction database can include, for example, Reaxys, SciFinder, ChemInform, or OrgSyn, and proprietary reaction databases such as those from in-house electronic laboratory notes. Predicted reactions 130 (computationally generated reactions) can be generated based on a list of known reaction transformations, i.e., so-called "named reactions", such as the MCT (Medicinal Chemist's Toolbox) (Roughley & Jordan, J. Med. Chem. 2011, 3451, which is incorporated herein by reference) that contains a set of reliable reactions commonly used by medicinal chemists, or computationally extracted by a clustering method (J. Chem. Inf. Model., 2009, 49(3), pp593 - 602, which is incorporated herein by reference) for a reaction database to identify generalized reaction transformations. A "reaction transformation" can be a generalization of the bond patterns made and broken between various atomic types. Predicted reactions 130 can be classified as successes or failures through artificial intelligence techniques such as machine learning and classification. For example, one or more of artificial neural networks, support vector machines, boosting and bagging decision trees, k-nearest neighbor techniques, naive Bayes techniques, discriminant analysis, logistic regression, and combinations thereof can be used to classify predicted reactions 130. Both known reactions 120 and predicted reactions 130 can be utilized by a route engine 140. The route engine 140 can receive a target compound as input and apply reaction transformations derived from reactions 110 to reversibly generate one or more synthetic routes 150.

[0022] In one aspect, methods and systems for generating a predicted reaction 130 using artificial intelligence techniques are described. An example of generating a predicted reaction 130 using artificial intelligence techniques is shown in FIG. 2. Known reactions 120 may be used as training data to train a machine learning classifier. Machine learning involves using examples of a given form of data to optimize for the execution of a specific information task (such as classification or regression), and then performing the same task on unknown data of the same type and form. Machine learning includes any of several methods, devices, and / or other features that can identify patterns, categories, statistical relationships, etc., as shown by the training data. The machine (e.g., a computer) learns by identifying, for example, patterns, categories, statistical relationships, etc., shown by the training data. Then, the learning result is used to predict whether new data exhibits the same patterns, categories, statistical relationships. The machine learning classifier can be one or more of an artificial neural network, a support vector machine, boosted and bagged decision trees, k-nearest neighbor techniques, naive Bayes techniques, discriminant analysis, logistic regression, and combinations thereof.

[0023] To train the machine learning classifier, the known reaction 120 may be processed to serve as training data by encoding the known reaction 120 at 210. Encoding of the known reaction may include encoding all atoms of the reactants according to a fixed set of properties. The properties can include, for example, the following. i. Each atom is classified into one of a plurality of categories (e.g., 78 categories) based on its neighboring atoms (CH4, CH3, C aromatic, etc.). ii. A fixed-length vector of 156 (2×78) integers as a histogram of the categories.

[0024] The classification system of atom types described in Scott A. Wildman, Gordon M. Crippen, Prediction of Physicochemical Parameters by Atomic Contributions, J. Chem. Inf. Comput. Sci., 1999, 39, pp. 868 - 873 is incorporated herein by reference.

[0025] An atom class can be defined as the atom species, its properties, and its immediate neighboring atom species and properties with their bonding types. For the encoding of known reactions 120, a sparse vector of atom classes can be used. By considering all atoms in known reactions 120 (e.g., in the Reaxys database that results in 27,429 classes), the number of classes can be extracted. Atom classes that occur less than a certain threshold number of times can be excluded. This threshold number of times can be, for example, 10, 20, 30, 40, 50, 60, 70, 80, and 90, etc.

[0026] Figure 3 illustrates an exemplary reaction involved in the MCT - type "isocyanate reaction with nucleophile". In this example, a specific instance of a molecule having an isocyanate functional group (1 - isothiocyanato - 3,5 - bis(trifluoromethyl)benzene) is reacted with an amine nucleophile (N1,N1 - dimethylcyclohexane - 1,2 - diamine) to obtain a single product having a thiourea functional group (1 - (3,5 - bis(trifluoromethyl)phenyl)-3-(2-(dimethylamino)cyclohexyl)thiourea). This specific reaction is encoded as a sparse vector containing a histogram of the atom classes present in each of the two reactants shown. This encoding can be used as an input for the training of a machine - learning classifier, along with information regarding the yield and / or reaction conditions.

[0027] Returning to FIG. 2, in step 220, some or all of the known reactions 120 are defined as positive or negative. Positive examples can be defined as all reactions from the known reactions 120 that have a yield greater than a threshold value (e.g., 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, and 90%, etc.). Negative examples can be defined as reactions from the known reactions 120 that have a yield less than a threshold value (e.g., 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, and 90%, etc.) when the reactants are applicable but the reported products are from different reaction types.

[0028] The encoded reactions identified as positive or negative can be split into a training dataset and a test dataset. The training dataset can be used in step 230 to train one or more machine learning classifiers. For example, 80% of the encoded reactions may be used for training and 20% for testing.

[0029] In one aspect, for each chemical transformation, a machine learning classifier can be created and trained at 230. The methods and systems described herein can perform step 230 in various ways and contexts. In one example, the methods and systems described herein can, for the training dataset, (1) extract a feature set from the training dataset that includes the statistically significant features of the positive examples in the training dataset and the statistically significant features of the negative examples in the training dataset, and then (2) use the feature set to construct a machine learning-based classification model that can indicate whether a new item of data contains information within a specific reaction category related to the training dataset, thereby training a machine learning-based classifier.

[0030] As used herein, the term "feature" can refer to any characteristic of an item of data that can be used to determine whether that item of data falls within one or more specific categories of chemical reactions. Examples of such features include, without limitation, an aromatic carbon bonded to two other aromatic carbons, a carbon having two bonded hydrogens, an oxygen having a double bond to a carbon, a solvent, a catalyst, a reagent, a reaction temperature, a reaction time, and combinations thereof.

[0031] The methods and systems described herein can extract a feature set from a training data set in various ways. In some examples, a weight may be associated with each extracted feature to indicate its relative importance with respect to other features. For example, the methods and systems can (1) determine the occurrence frequencies of various features in both positive and negative examples within the training data set, (2) rank these positive and negative features, for example, based on the occurrence frequencies, and then (3) select the highest-ranked features to include in the feature set. In this example, the weight associated with each feature can be the occurrence frequency of that particular feature.

[0032] As detailed above, after the methods and systems have generated a feature set for a particular training data set, the methods and systems can generate a machine learning-based classification model based on the feature set. As used herein, the term "machine learning-based classification model" can refer to a complex mathematical model for data classification that is generated using machine learning techniques. In one example, this machine learning-based classifier can include a map of support vectors representing boundary features. In this example, these boundary features may be selected from and / or represent the highest-ranked features within a particular feature set.

[0033] The present method and system can construct a machine learning-based classification model (e.g., a machine learning classifier) for each chemical transformation determined from the encoded reaction 210 using a feature set extracted from a training data set. In some examples, multiple machine learning-based classification models may be combined into a single machine learning-based classification model. Similarly, a machine learning-based classifier can represent a single classifier containing one or more machine learning-based classification models, and / or multiple classifiers each containing one or more machine learning-based classification models.

[0034] At 240, a trained machine learning classifier can be tested using a test data set. The test output of the trained machine learning classifier can be analyzed to evaluate the performance of the trained machine learning classifier. The performance of the trained machine learning classifier can be evaluated by multiple metrics. By way of example, the performance of the trained machine learning classifier can be evaluated by five metrics (TP = true positive, FP = false positive, TN = true negative, and FN = false negative): 1) accuracy = (TP + TN) / (TP + FP + FN + TN), 2) positive precision = TP / (TP + FP), 3) negative precision = TN / (TN + FN), 4) positive sensitivity = TP / (TP + FN), and 5) negative sensitivity = TN / (TN + FP).

[0035] In one aspect, all trained machine learning classifiers may be used regardless of performance. The trained machine learning classifier generates predictions with a correct probability during use. During use, a probability value for accepting or rejecting the classification of the predicted reaction may be selected by the user.

[0036] Returning to FIG. 1, a trained machine learning classifier(s) can be used to determine whether to include or exclude a predicted reaction 130 in the construction of a synthetic pathway. A plurality of reactants from the encoded (known) reaction 120 may be input into a machine learning classifier(s) that may be configured to assemble the reactants into one or more predicted reactions 130. The trained machine learning classifier(s) may be configured to generate a predicted reaction 130 before the pathway engine 140 receives an input or “on-the-fly” when the pathway engine 140 determines one or more pathways. In one aspect, the trained machine learning classifier(s) may be part of the pathway engine 140.

[0037] The pathway engine 140 can receive a target compound (e.g., a given compound of a user) as an input and apply reaction conversions derived from reaction 110 to reversibly generate one or more synthetic pathways 150. The target compound can have any chemical structure and may be input via alphanumeric input and / or a chemical structure diagram. The target compound should be recognized as the compound to be achieved at the end of one or more chemical reactions.

[0038] As shown in FIG. 4, the pathway engine 140 uses a target compound 410 (and / or downstream / upstream reactants) to identify a reaction containing the target compound 410 (and / or downstream / upstream reactants), and searches for a reaction 110 (which consists of both a known reaction 120 and a predicted reaction 130 if the known reaction 120 and the predicted reaction 130 have been generated in advance), and can reversely generate a potential chemical reaction pathway for generating the target compound 410 (and / or downstream / upstream reactants) by applying a reaction transformation. In one aspect, the pathway engine 140 can generate a predicted reaction 130 at 430 by applying the target compound 410 (and / or downstream / upstream reactants) to one or more known reaction transformations (e.g., MCT transformation). The pathway engine 140 can determine whether the target compound 410 contains a minimum structural element (or substructure) identified for the product in one of the common reaction transformations. The predicted reaction 130 can be provided to one or more machine learning classifiers to evaluate whether the predicted reaction 130 involving the reagent is successful. If it is predicted that the predicted reaction 130 is successful, the predicted reaction 130 can be included in pathway generation. If it is predicted that the predicted reaction 130 fails, the predicted reaction 130 can be excluded from pathway generation.

[0039] At 430, one or more parameters 440 can be identified to modify the application of reaction conversion. The one or more parameters 440 may include one or more pathway modifiers such as feedstock data and equipment data (e.g., chemical apparatuses). The feedstock data may include data indicating reagents and / or preferred reagents available for use in a chemical reaction. The equipment data may include data indicating equipment and / or preferred equipment available for use in a chemical reaction. The equipment data can be obtained from the modular chemical reaction system described in FIGS. 12-19 and / or from the apparatus 2000 described in FIG. 20. For example, the equipment data may indicate one or more operating parameters of the modular chemical reaction system or the apparatus 2000. Thus, the synthetic pathway generated by the method described herein can be adjusted for execution in the modular chemical reaction system or the apparatus 2000 based on the equipment data provided to the pathway engine 140.

[0040] FIG. 5 provides an exemplary user interface 500 for providing an input to the route engine 140. The user interface 500 may include a user interface element 501 configured to receive a target compound 410, for example, as an alphanumeric value indicating an InChl key, a common name, or a frame ID, and / or through the use of a compound structure editor. The user interface 500 may include a user interface element 502 configured to receive the maximum number of optimal routes, for example, as a numerical value. The user interface 500 may include a user interface element 503 configured to receive the cost for performing any reaction, for example, as a numerical value indicating dollars per mole of the desired compound. The user interface 500 may include a user interface element 504 configured to receive the cost for easy solvent exchange, for example, as a numerical value indicating dollars per mole amount of a particular solvent. The user interface 500 may include a user interface element 505 configured to receive the cost for difficult solvent exchange, for example, as a numerical value indicating dollars per mole amount of a particular solvent. The user interface 500 may include a user interface element 506 configured to receive the yield of a reaction having no yield, for example, as a numerical value indicating a percentage yield. The user interface 500 may include a user interface element 506 configured to receive an indication that more routes should be shown after discovery of the optimal route, for example, as a binary indication (e.g., a checkbox). The user interface 500 may include a user interface element 508 configured to receive compounds (reactants) to be excluded from consideration, for example, as an alphanumeric value indicating a reaction ID, a compound ID, a compound name, or an inchi key. The user interface 500 may include a user interface element 509 configured to receive the number of new reactions to create, for example, as a numerical value. The user interface 500 may include a user interface element 510 configured to receive the maximum depth of the new reactions, for example, as a numerical value.The user interface 500 may include a user interface element 511 configured to receive a display for applying a machine learning classifier, for example, as a binary display (e.g., a checkbox). The user interface 500 may include a user interface element 512 configured to receive a display that only new reactions are to be used in the pathway, for example, as a binary display (e.g., a checkbox). The user interface 500 may include a user interface element 513 configured to receive a display regarding whether the pathway engine 140 should create a new compound, for example, as a binary display (e.g., a checkbox). The user interface 500 may include a user interface element 514 configured to receive a display regarding whether the pathway engine 140 should create a new reaction that already exists within the network, for example, as a binary display (e.g., a checkbox).

[0041] Returning to FIG. 4, at 450, the pathway engine 140 can map reactants generated from potential chemical reaction pathways to a fixed reaction network using the Morgan algorithm. The Morgan algorithm can create a unique name (or code) for each compound of a reaction and therefrom determine whether each compound already exists within the fixed reaction network. The Morgan algorithm classifies the co - atoms of a compound and selects the atoms labeled as invariant. The classification uses the concept of considering the proximity number (connectivity) of an atom and performs this in an iterative manner (extended connectivity). Based on specific rules, the Morgan algorithm generates an ambiguous and unique numbering of the compounds (e.g., the generated reactants) within the network.

[0042] At 460, for each compound (as a reactant) with one more reaction to the target compound 410 (and / or downstream / upstream reactants), steps 430 and 450 are repeated until the maximum number of new reactions is reached, and a pathway network can be constructed for each new pathway. As an example, the maximum number of new reactions can be 100,000 or less, 200,000 or less, 300,000 or less, 400,000 or less, 500,000 or less, 600,000 or less, 700,000 or less, 800,000 or less, 900,000 or less, and 1,000,000 or less, etc. Thus, the pathway engine can generate one or more chemical reaction sequences designed to result in the production of the target compound 410. The chemical reaction sequences can be referred to as pathways. The pathway network of the target compound 410 may be represented in a tree data structure and display output.

[0043] FIG. 6 shows an exemplary tree data structure 600 consisting of a plurality of pathways. The target compound 410 may be positioned at the center of the tree data structure 600. Each edge may include a reaction, and each node may include a compound (reactant). As shown, edge 610 represents a reaction derived from the known reaction 120, and node 620 represents the compound (reactant) involved in the reaction of edge 610. Edge 630 represents a reaction derived from the predicted reaction 130, and node 640 represents the compound (reactant) involved in the reaction of edge 630. Nodes 650 contained within the region represent chemical intermediates, while nodes 660 contained within the region represent purchasable supply source compounds. Thus, nodes 660 within the region can serve as the initial compounds in a series of chemical reactions that trace the pathway (a series of chemical reactions) to the starting (target) compound 410.

[0044] Returning to FIG. 4, when the maximum number of reactions produced retro-synthetically from the target compound 410 is reached, at 470, the pathway engine 140 can determine the optimal pathway. The pathway engine 140 can use a Dijkstra-like algorithm to determine the optimal pathway by utilizing a fast search of the pathway network.

[0045] The route engine 140 can determine an optimal route at 470 according to a two - stage approach. In the first stage, the route engine 140 can determine compounds that can generate a target compound with k or fewer reactions (at most k reactions). In the second stage, the route engine 140 can determine the minimum - cost route to the target compound 410. The route with the minimum cost may be specified as the optimal route. A plurality of routes with costs below a threshold may be specified as the optimal routes. The second stage can determine the optimal route without considering reaction telescoping. Reaction telescoping occurs when two or more reactions appear in the reaction sequence without a work - up or solvent - exchange step.

[0046] As shown in FIG. 7, in the first stage, the route engine 140 can start with a starting (target) compound and identify a chemical reaction 710 that produces the target compound 410. The route engine 140 can determine the reactants 720 of these reactions 710 and tag the reactants 720 to the target compound 410 at a distance of 1. The route engine 140 can determine the reactions that produce the reactants 720 and repeat this process from the reactants 720 by tagging those reactants to the target compound 410 at a distance of 2. This process can be repeated by tagging each reactant until a distance k from the target compound 410 is reached. Each reactant is tagged only once until a distance k is reached. Reactions and reactants that do not have a path to the target compound 410 are excluded from consideration. Reactions and reactants that exceed k are excluded from consideration. Stage 1 can be used to limit the feedstocks and reactions to be considered.

[0047] As shown in FIG. 8, in the second stage, the path engine 140 can determine the minimum cost path. The path engine 140 can initialize a prioritized queue having reactions that can be activated from the feedstock. If all the reactants required for the reaction are the feedstock, the reaction can be activated. The reaction cost can be determined as the total feedstock cost divided by the yield. The path engine 140 can determine the active reaction having the minimum cost and identify the next reaction activated by the product of the active reaction having the minimum cost. The next reaction can be added to the prioritized queue, and the process can be repeated until the target compound 410 is reached. Each reaction is considered only once. As shown in FIG. 8, Reaction A, Reaction B, Reaction C, and Reaction D each utilize a feedstock for the reactants. Reaction A utilizes reactants C1 and C2. Reactant C1 has a determined cost of 1, and reactant C2 has a determined cost of 3. The yield of Reaction A is 0.5. The total cost of Reaction A is determined by (1 + 3) / 0.5, and the cost is 8. The next reaction after Reaction A is Reaction C. Reaction C utilizes reactant C4. Reactant C4 has a determined cost of 8. The yield of Reaction C is 0.8. The total cost of Reaction C is determined by 8 / 0.8, and the cost is 10. The result of Reaction C is the starting (target) compound 410. The total cost of the Reaction A - Reaction C path is 8 + 10 = 18.

[0048] Reaction B utilizes reactant C3. Reactant C3 has a determined cost of 6. The yield of reaction B is 0.9. The total cost of reaction B is determined by 6 / 0.9, and the cost is 6.6. The next reaction after reaction B is reaction D. Reaction D utilizes reactant C5. Reactant C5 has a determined cost of 6.6. The yield of reaction D is 0.6. The total cost of reaction D is determined by 6.6 / 0.6, and the cost is 10.9. The result of reaction D is the starting (target) compound 410. The total cost of the reaction B - reaction D route is 6.6 + 10.9 = 17.5. In stage 2, the route engine 140 can select the route with the lowest cost by comparing the total costs. As shown in FIG. 8, the reaction B - reaction D route has a lower cost (17.5) than the reaction A - reaction C (18). Therefore, the route engine 140 can determine the reaction B - reaction D route as the route with the minimum cost.

[0049] The route engine 140 can determine the cost of a route in various ways. The cost of a route can be the cost of the reaction to produce the starting (target) compound 410, plus the sum of all solvent exchange costs (e.g., all costs in dollars per mole) to the financial (e.g., monetary) cost of producing the starting (target) compound 410. The cost of a reaction can be the sum of the financial (e.g., monetary) costs of the reactants including reagents divided by the yield of the reaction, plus the fixed financial (e.g., monetary) cost for carrying out the reaction. The financial (e.g., monetary) cost of solvent exchange between two reactions or reaction steps can be a fixed cost. The route(s) with the minimum cost can be identified as the optimal route(s).

[0050] In one aspect, the route engine 140 can determine the cost according to the following formula.

Number

[0051] Returning to FIG. 1, the optimal route determined by the route engine 140 can be graphically understood by a chemist as the optimal synthetic route 150 and a reaction tree described verbatim along with the names of the compounds, or specified as any output in a computational schematic diagram using a common exchange format such as JavaScript Object Notation (JSON) or Extensible Markup Language (XML).

[0052] FIG. 9A shows a computational method 900 for identifying one or more existing or novel chemical synthesis routes for generating a target compound, the method including, at 901, determining a plurality of known chemical reactions and / or a plurality of novel chemical reactions. The plurality of novel reactions can be extrapolated from generalized known chemical transformations.

[0053] The method 900 can include, at 902, determining a plurality of predicted chemical reactions from the plurality of novel chemical reactions based on a trained classifier. The trained classifier may be trained with data derived from a plurality of chemical reactions known to succeed and a plurality of chemical reactions known to fail, which are examples of a given chemical transformation.

[0054] The method 900 can include, at 903, generating a plurality of chemical reactions based on the plurality of predicted chemical reactions and the plurality of known chemical reactions. Each chemical transformation of the plurality of chemical reactions can represent the conversion of one compound to another compound.

[0055] The method 900 can include, at 904, determining at least one target compound.

[0056] The method 900 can include, at 905, determining a plurality of chemical reaction routes associated with at least one target compound. Each chemical reaction route can include one or more chemical reactions of the plurality of chemical reactions that generate the target compound.

[0057] Method 900 may include, at 906, determining one or more optimal chemical reaction pathways from a plurality of chemical reaction pathways identified to generate a target compound. At least one of the one or more optimal chemical reaction pathways may include at least one known reaction transformation and at least one predicted reaction transformation.

[0058] Method 900 may further include training a classifier with a training dataset, where the training dataset includes one or more of a chemical reaction database, an estimated yield, or a predicted yield of one or more chemical reactions. Training the classifier with the training dataset may include receiving a dataset including one or more chemical reactions based on one or more chemical transformations, where each of the one or more chemical reactions includes at least one reactant, and each reactant consists of one or more atoms. For each reactant, Method 900 may be able to classify the one or more atoms into categories based on neighboring atoms, bond order, and / or the number of hydrogen atoms present. For each reactant, Method 900 may be able to determine a vector based on a histogram of the categories. Method 900 determines a training dataset consisting of a) vectors of reactions related to a particular transformation and b) vectors of reactions related to the particular transformation but resulting in products of different reaction types, exposes a portion of the training dataset to the classifier to train the classifier, and exposes another portion of the training dataset to the trained classifier to test the trained classifier.

[0059] Exposing another portion of the training dataset to the trained classifier to test the trained classifier may include evaluating the performance of the trained classifier based on one or more measurement criteria. The one or more measurement criteria may include one or more of accuracy, positive precision, negative precision, positive sensitivity, or negative sensitivity.

[0060] Method 900 may further include generating a tree data structure, where the target compound is the root node of the tree data structure. Method 900 may further include adding a plurality of branches to the tree data structure, where each branch of the plurality of branches includes one of the plurality of synthetic routes.

[0061] Determining a plurality of synthetic routes related to a target compound may be based on one or more parameters. The one or more parameters may include one or more of available feedstocks, available chemicals, or available equipment.

[0062] Determining one or more optimal synthetic routes from the plurality of synthetic routes may be based on one or more parameters. The one or more parameters include one or more of available feedstocks, available chemicals, available equipment, yield, financial cost, time, reaction conditions, or likelihood of reaction success. Determining one or more optimal synthetic routes from the plurality of synthetic routes may include determining all compounds that can reach the target in a maximum of a predetermined number of steps and determining the minimum-cost synthetic route to the target compound without considering telescoping of conversions.

[0063] Determining the minimum-cost route may include evaluating a cost function. The cost function may include the following.

Number

[0064] FIG. 9B shows a method 910 for identifying one or more synthetic routes for synthesizing a target compound, which includes, at 911, training one or more machine learning classifiers based on a portion of a plurality of known chemical reactions. The plurality of known chemical reactions can be derived from one or more of a chemical reaction database, an estimated yield, or a predicted yield of one or more chemical reactions. Training one or more machine learning classifiers based on a portion of a plurality of known chemical reactions includes receiving a dataset including one or more chemical reactions based on one or more chemical transformations, each of the one or more chemical reactions including at least one reactant, each reactant consisting of one or more atoms; classifying the one or more atoms into categories for each reactant based on neighboring atoms, bond order, and / or number of hydrogen atoms present; determining a vector for each reactant based on a histogram of the categories; determining a training dataset consisting of a) vectors of reactions related to a specific transformation and b) vectors of reactions related to the specific transformation but resulting in products of different reaction types; exposing a portion of the training dataset to the classifier to train the classifier; and exposing another portion of the training dataset to the trained classifier to test the trained classifier, which may include evaluating the performance of the trained classifier based on one or more metrics. The one or more metrics may include one or more of accuracy, positive precision, negative precision, positive sensitivity, or negative sensitivity.

[0065] The method 910 may include, at 912, determining one or more known chemical reactions that result in the target compound based on the plurality of known chemical reactions.

[0066] The method 910 may include, at 913, determining one or more predicted chemical reactions that result in the target compound based on a chemical reaction transformation. The one or more predicted chemical reactions may be predicted to succeed by one machine learning classifier.

[0067] Method 910 may include, at 914, determining multiple synthetic routes retro-synthetically. Each synthetic route can lead to a target compound, and at least one synthetic route includes at least one of one or more known chemical reactions and at least one of one or more predicted chemical reactions. Determining multiple synthetic routes retro-synthetically can be based on one or more parameters. The one or more parameters can include one or more of available feedstocks, available chemicals, or available equipment.

[0068] Method 910 may include, at 915, determining an optimal synthetic route from the multiple synthetic routes based on a predetermined number of reactions and a cost function. Determining an optimal synthetic route from the multiple synthetic routes based on a predetermined number of reactions and a cost function can be further based on one or more parameters. The one or more parameters can include one or more of available feedstocks, available chemicals, available equipment, yield, financial cost, reaction conditions, or the likelihood of reaction success. Determining an optimal synthetic route from the multiple synthetic routes based on a predetermined number of reactions and a cost function can include determining all compounds that can reach the target in a maximum of a predetermined number of steps and determining the minimum-cost synthetic route to the target compound without considering telescoping of conversions. The cost function can include the following.

Number

[0069] Method 910 may further include generating a tree data structure, where the target compound is the root node of the tree data structure. Method 910 may further include adding multiple branches to the tree data structure, where each branch of the multiple branches includes one of the multiple synthetic routes.

[0070] Figure 10 shows the route for producing diazepam derived from the described method and system. The optimal route generated without using a machine learning classifier to classify the predicted reactions leads to a well-known two-step synthesis route contained in the Reaxys database. The route illustrated in Figure 10 was generated using the described method and system that utilized a machine learning classifier. As shown, the first step of the optimal route is the acylation of 2-amino-5-chlorobenzophenone, which results in 5-chloro-2-(chloroacetylamino)benzophenone. The reaction of the first step was obtained from known reactions (e.g., Reaxys). The second step of the optimal route is the amide N-alkylation under the recommended reaction conditions generated by the route engine 140 and determined to be successful by the trained machine learning classifier. The result of the second reaction is 2-(2-chloro-N-methyl-acetamido)-5-chlorobenzophenone. The third step of the optimal route is a cyclization reaction of the ring that results in diazepam. The reaction of the third step was obtained from known reactions (e.g., Reaxys). The route was executed on a multi-step flow synthesizer, and diazepam was obtained in a yield of 78% on a scale of 161 mg.

[0071] Figure 11 shows the route for making imatinib derived from the described method and system. The route illustrated in Figure 10 was generated using the described method and system utilizing a machine learning classifier. As shown, the first step of the optimal route is the bromination of p-toluic acid, which results in 4-bromomethylbenzoic acid. The reaction for the first step was obtained from known reactions (e.g., Reaxys). The second step of the optimal route is an amide synthesis from an acid reaction, generated by the route engine 140 and determined to be successful by the trained machine learning classifier. The result of the second reaction is 4-(bromomethyl)-N-(4-methyl-3-((4-(pyridin-3-yl)pyrimidin-2-yl)amino)phenyl)benzamide. The third step of the optimal route is an alkylation reaction that results in imatinib. The reaction for the third step was generated by the route engine 140 and determined to be successful by the trained machine learning classifier. The route was executed on a multi-step flow synthesizer, and imatinib was obtained in a 91% yield on an 8.4 g scale.

[0072] In various aspects, and with reference to FIGS. 12-19, a modular chemical reaction system 10 is disclosed herein. The complete disclosure of this apparatus can be found in PCT / US2018 / 026557, filed Apr. 6, 2018, entitled "Modular Systems For Performing Multistep Chemical Reactions, And Methods Of Using Same", the entire contents of which are incorporated herein by reference. System 10 may have a substrate layer 20 and a surface mount layer 40 including a plurality of modules 50 further disclosed herein. System 10 may further comprise a plurality of sealing elements 90.

[0073] In use, and as schematically shown in FIG. 12, the modular chemical reaction system 10 is contemplated to provide automated chemical synthesis and monitoring capabilities that can be incorporated into an encompassing system for the design, simulation, screening, execution, analysis, and modification / optimization of chemical reactions. As further disclosed herein, the system 10 of the present disclosure is contemplated to provide modularity that enables rapid reconfiguration (optionally, rearrangement) of system components to quickly change the pathway of fluid flow associated with multiple varying reactions. In some aspects, reconfiguration means selecting alternative pathways within a system having defined pathways as well as pre-positioned modules and / or analytical devices. In these aspects, it is contemplated that the defined pathways can be separated by valve modules disclosed herein, which can be adjusted to modify the fluid flow within or between the defined pathways. In other aspects, reconfiguration can include physically adding new modules or analytical devices to the system 10 of the present disclosure. Additionally, or alternatively, reconfiguration can include removing or replacing at least one module or analytical device disclosed herein. The system 10 of the present disclosure is further contemplated to provide a framework for performing multiple chemical reactions using a single configuration of reaction modules. Further, the system 10 of the present disclosure is contemplated to provide monitoring capabilities during the execution of chemical reactions that were previously not achievable. Further, the system 10 of the present disclosure is contemplated to control and / or optimize reaction conditions based on feedback received from various modules and analytical devices when a reaction occurs.

[0074] In an exemplary aspect, and with reference to FIGS. 13-16, the substrate layer 20 may have a substrate 22 and a plurality of flow components (e.g., flow connectors 26) positioned within the substrate. In these aspects, the substrate 22 may have an outer surface 24. Optionally, in an exemplary aspect, the substrate 22 may include a plurality of substrate bodies that are selectively positioned in parallel to establish the framework of parallel fluid passages disclosed herein. Although the substrate bodies are generally described herein as being parallel, it is contemplated that the substrate bodies may be positioned in any desired configuration, including vertical and angled configurations. Alternatively, it is contemplated that the substrate 22 may be a single continuous platform structure. In an exemplary aspect, the substrate layer 20 (and the manifold layer further disclosed herein) may be configured for selective attachment to an underlying grid support structure that defines a plurality of openings for receiving fasteners to secure the substrate layer and / or the manifold layer to the grid support structure.

[0075] Optionally, each module 50 of the plurality of modules may have at least a first inlet 51 and a first outlet 53 as shown in FIG. 13. However, it is contemplated that some modules may be configured to store material and / or may alternatively include only an inlet 51 or an outlet 53.

[0076] In an additional aspect, a plurality of modules 50 of the surface mounting layer 40 may be selectively mounted on the outer surface 24 (e.g., the upper surface) of the substrate 22 in a lying-on relationship over a plurality of flow components (e.g., flow connectors 26). In these aspects, it is contemplated that the plurality of modules 50 may include a plurality of flow modules 52 that receive fluid forming a portion of the fluid pathway within the system 10. Each flow module 52 of the plurality of flow modules may further be positioned in fluid communication with at least one of the plurality of flow components (e.g., flow connector 26) at respective interfaces 30 shown in FIG. 13. In a further aspect, a plurality of sealing elements 90 may be configured to establish a fluid-tight seal at each interface 30 between one of the plurality of flow modules 52 and one of the plurality of flow components (e.g., flow connector 26). As further disclosed herein, at least a portion 52 of the plurality of flow modules and at least a portion of the plurality of flow components (e.g., flow connector 26) can cooperate to establish a fluid flow pathway 12 (e.g., a first fluid flow pathway) for performing at least one step of a chemical reaction or a series of chemical reactions. As further disclosed herein, it is contemplated that the configuration of the flow modules and flow components may be selectively modified to produce a second fluid flow pathway different from the first fluid flow pathway. Optionally, in an exemplary aspect, the fluid flow pathway may be a liquid flow pathway. In these aspects, it is contemplated that the sealing element 90 may be configured to establish a liquid-tight seal between the flow module 52 and the flow connector 26 at each interface 30. In a further exemplary aspect, it is contemplated that the chemical reaction may be a multi-step chemical reaction of a continuous flow.

[0077] In an additional aspect, each flow connector 26 may be configured to selectively form a portion of the fluid flow pathway 12 for performing at least one step of a chemical reaction. Alternatively, each flow connector 26 may be configured to selectively disengage from a flow connector forming the fluid flow pathway such that the flow connector is not in fluid communication with the fluid flow pathway. In an exemplary aspect, each flow connector 26 may have opposing inlet / outlet openings 28 that can function as an inlet or an outlet depending on the direction of fluid flow in a particular flow path configuration. As shown in FIG. 16, it is contemplated that the flow connector 26 can be positioned within a channel 23 extending along the length of the substrate 22. In a further aspect, it is contemplated that the outer surface 24 of the substrate 22 may define connection openings 25 configured to enable securing surface-mounted components (e.g., modules) to the substrate. It is further contemplated that the inlet / outlet openings 28 of the flow connector 26 may project upwardly or downwardly from an adjacent portion of the flow connector to engage an inlet or an outlet of a module or other flow connector disclosed herein.

[0078] In an exemplary aspect, each module 50 of a plurality of modules may have a common base structure that includes a plurality of openings configured to receive fasteners (e.g., bolts or screws) for mounting the module to the outer surface 24 of the substrate 22. In these aspects, it is contemplated that the positions of the openings within the base structure of each module 50 may complement corresponding connection openings 25 defined within the substrate layer 20. The common base structure may further include a common dimensional profile, such as, for example and without limitation, a square profile that may optionally include dimensions of about 1.5 inches in length and width. In some exemplary aspects, the modules 50 of the present disclosure may be mounted directly to the substrate 22 disclosed herein. Alternatively, in other exemplary aspects and as shown in FIG. 16, the modules 50 of the present disclosure may be mounted to a base plate 55, which in turn is mounted to the substrate 22 disclosed herein.

[0079] Optionally, in a further aspect and as shown in FIGS. 14 - 16, the modular chemical reaction system 10 may further comprise a manifold layer 1410. In these aspects, the manifold layer 1410 may include at least one manifold body 1420 underlying the substrate layer 20. Optionally, the manifold body 1420 may include a plurality of manifold bodies that are selectively positioned in parallel to establish the framework of parallel fluid passages disclosed herein. Alternatively, it is contemplated that the manifold body 1420 may be a single continuous platform structure. In use, it is contemplated that the manifold body 1420 may be oriented perpendicular to the substrate 22 disclosed herein to provide for the conveyance of reaction components between parallel substrates. Alternatively, in another aspect, the manifold body 1420 may be oriented parallel to (or underlying) the substrate body to allow for the bypass of a particular reaction module aligned with the particular substrate body. In an exemplary aspect, it is contemplated that the plurality of flow connectors 26 of the system may include a first plurality of flow connectors 26 positioned within the substrate layer 20 and a second plurality of flow connectors 1430 positioned within the manifold layer 1410. Each flow connector 1430 of the manifold layer 1410 may have opposing inlet / outlet openings 1440 that can function as an inlet or an outlet depending on the direction of fluid flow in a particular flow path configuration. As shown in FIG. 16, it is contemplated that the flow connector 1430 may be positioned within a channel 1630 extending along the length of the manifold body 1420. In a further aspect, it is contemplated that the manifold body 1420 may have an outer surface 1610 that defines connection openings 1620 configured to allow the substrate 22 to be fastened to the manifold body. The inlet / outlet openings 1440 of the flow connector 1430 may further project upwardly or downwardly from an adjacent portion of the flow connector to engage an inlet or an outlet of a module or other flow connector disclosed herein.

[0080] The flow connector 26, substrate layer 1430, and manifold layer of the present disclosure are contemplated to be provided in various varying lengths and shapes that enable connection with other flow connectors and various modules disclosed herein.

[0081] In FIGS. 14 - 16, it is shown as having two layers (substrate layer 20 and manifold layer 1410) under the surface mount layer 40, but the system of the present disclosure is contemplated to have additional layers under the manifold layer 1410 to enable further modification of fluid pathways.

[0082] In additional aspects, and with reference to FIGS. 17 - 18, the plurality of modules 50 may include at least one monitoring module 58 configured to generate at least one output indicative of at least one condition of a chemical reaction. In these aspects, it is contemplated that at least one monitoring module 58 (optionally, a plurality of monitoring modules) may be communicatively coupled to a processing circuit further disclosed herein. Exemplary conditions that may be monitored by at least one monitoring module 58 include, but are not limited to, temperature, pressure, flow rate, identification of products produced by the reaction, consumption rate of reagents, identification of by - products, yield, selectivity, and purity. It is contemplated that the at least one monitoring module may comprise sufficient sensors, hardware, or processing components capable of generating an output corresponding to the experiment being monitored by at least one monitoring module 58.

[0083] In a further exemplary aspect, at least one flow module 52 of the plurality of flow modules may be a process module 54 that can correspond to the position of a step of a chemical reaction. Optionally, each process module 54 disclosed herein can also serve as a monitoring module 58, in which case the process module 54 is configured to provide at least one output to a processing circuit further disclosed herein. Examples of such process modules 54 include a reactor 56 or a separator 60 further disclosed herein. In one aspect, when at least one process module 52 comprises a reactor 56, it is contemplated that the reactor can be a heated tube reactor, a packed bed reactor, or a combination thereof. However, other reactors can be used, provided that they have the surface mounting capabilities disclosed herein. In another aspect, when at least one process module 52 comprises a separator 60, the separator can be a liquid / liquid separator or a gas / liquid separator. In any one aspect, the separator 60 can include a membrane-based liquid-liquid separator further disclosed in the Examples section of this application. In any other aspect, the separator 60 can include a gravity-based liquid-liquid separator further disclosed in the Examples section of this application. In this aspect, and as further described herein, it is contemplated that the gravity-based liquid-liquid separator can be configured to be used under pressures exceeding conventional atmospheric conditions. It is further contemplated that the gravity-based liquid-liquid separator of the present disclosure can include a glass that allows visibility of the separation process. It is further contemplated that the gravity-based liquid-liquid separator of the present disclosure can provide inlet and outlet flow paths that move within a common plane rather than in different conventional planes. In a further aspect, it is contemplated that the separator 60 can comprise a gravity-based gas-liquid separator further disclosed in the Examples section of this application.

[0084] Optionally, in an exemplary configuration, the plurality of flow modules 52 of the system may comprise at least one reactor 56 and at least one separator 60.

[0085] Optionally, in an exemplary aspect, each flow connector 26 of the substrate layer 20 (and, if present, each flow connector 1430 of the manifold layer 1410) is contemplated to have a consistent inner diameter along its entire length (optionally within a range of about 0.04 inches to about 0.08 inches). Optionally, in these aspects, at least one flow module 52 of the system 10 may comprise a reactor 56 and / or a separator 60, and at least one of the fluid inlet 51 and the fluid outlet 53 of the at least one flow module 52 may share a consistent inner diameter with an adjacent flow connector 26 of the plurality of flow connectors. Optionally, in a further exemplary aspect, 1430 (optionally each flow connector) of the plurality of flow connectors, which is at least a portion of the flow connector 26, may comprise Hastelloy C276. In contrast to known flow connectors having variable inner diameters at various locations, the flow connectors of the present disclosure are contemplated to provide improved performance by minimizing dead space and providing improved fluid flow (particularly in liquid reactions).

[0086] Optionally, in a further exemplary aspect, the plurality of modules 50 of the molecular chemical reaction system 10 may comprise at least one controller module 64. Optionally, in these aspects, each controller module 64 disclosed herein may also serve as a monitoring module 58, in which case the controller module 64 is also configured to provide at least one output to a processing circuit further disclosed herein. In an exemplary aspect, it is contemplated that each controller module 64 may be positioned in fluid communication or thermal communication with the fluid flow pathway 12 and configured to achieve, maintain, and / or measure one or more desired conditions of the chemical reaction. Optionally, the plurality of modules 50 of the system 10 may include at least one process module 54 and at least one controller module 64. Exemplary controller modules 64 include, for example and without limitation, check valves, T-shaped filters, flow controllers, pressure sensing modules, pressure relief valves, backpressure controllers, tube adapters, valves, pumps, flow selectors, control valve modules, temperature monitoring modules, temperature control modules, heaters, coolers, or combinations thereof. In an exemplary aspect, at least one controller module 64 may be positioned in fluid communication and / or thermal communication with a portion of the fluid flow pathway and may include a sensor (e.g., a temperature, pressure, or flow sensor) in thermal communication with a portion of the fluid flow pathway configured to generate an output indicative of at least one characteristic of the fluid (e.g., a liquid) within the controller module (and in this case, also the flow module). For example, as shown in FIG. 18, the temperature module 70 may include a temperature sensor 71 and optionally may also include heating and / or cooling elements 72 known in the art and further disclosed herein. In other exemplary aspects, it is contemplated that at least one controller module 64 may be configured to effect an adjustment of at least one property of the fluid within the fluid flow pathway. For example, the valve module 74 may be configured to move between at least a first position and a second position to modify the flow of fluid through the fluid flow pathway.Optionally, each valve module 74 may be communicatively coupled to a process circuit further disclosed herein to enable selective monitoring and / or control of valve positioning and may include a servo motor and a position sensor (e.g., an encoder).

[0087] In an exemplary aspect, it is contemplated that system 10 may comprise at least one analytical device 1700. In these aspects, each analytical device 1700 may be positioned to operatively communicate with fluid flow pathway 12 through at least one module 50. As used in this context, the term "operative communication" may refer to any form of communication necessary to enable analysis by the analytical device 1700 disclosed herein. It is further contemplated that each analytical device 1700 may be configured to generate at least one output indicative of at least one characteristic of a chemical reaction when the reaction occurs. In a further aspect, each analytical device 1700 may comprise a UV-Vis spectrometer, a near-infrared (NIR) spectrometer, a Raman spectrometer, a Fourier transform infrared (FT-IR) spectrometer, a nuclear magnetic resonance (NMR) spectrometer, or a mass spectrometer (MS). More generally, it is contemplated that the analytical device 1700 can be any conventional process analytical technology (PAT) device suitable for use in at least one step of a chemical reaction or series of chemical reactions. One or more analytical devices may be disposed along the flow path of system 10, and it is further contemplated that each of the analytical devices may transmit output analysis to a processing circuit to monitor or further optimize one step of the chemical reaction or series of chemical reactions being performed. In an exemplary aspect, the plurality of modules 50 may comprise at least one analysis module 80 having at least a second outlet 84 positioned to operatively communicate with the analytical device 1700 disclosed herein. Optionally, in these aspects, it is contemplated that the analysis module 80 may be positioned upstream of at least one other flow module of the plurality of flow modules. However, in other aspects, it is contemplated that the analysis module 80 may be positioned at a location corresponding to the end or completion of the reaction. In some exemplary aspects, it is contemplated that the analysis module 80 may be communicatively coupled to the analytical device 1700. In these aspects, it is contemplated that the analysis module 80 may function as the monitoring module 58 disclosed herein.

[0088] In further exemplary aspects, system 10 may comprise a processing circuit 110. In these aspects, it is contemplated that the processing circuit 110 may be communicatively coupled to at least one module 50 of the plurality of modules (e.g., at least one monitoring module 58) and at least one analysis device 1700. It is further contemplated that the processing circuit 110 may be configured to receive at least one output from at least one module (e.g., monitoring module 58). Optionally, the processing circuit 110 may receive multiple outputs from multiple modules (e.g., monitoring modules) sequentially or simultaneously. Optionally, the processing circuit 110 may use at least one output to adjust the operation of at least one module 50 (e.g., process module 54 and / or regulator module 64) to optimize a chemical reaction or a portion of a chemical reaction. Additionally, or alternatively, it is further contemplated that the processing circuit 110 may be configured to receive at least one output from at least one analysis device 1700. Optionally, the processing circuit 110 may receive multiple outputs from multiple analysis devices sequentially or simultaneously. Optionally, the processing circuit 110 may use at least one output to adjust the operation of at least one module 50 (e.g., process module 54 and / or regulator module 64) to optimize a chemical reaction or a portion of a chemical reaction. In an exemplary aspect, the processing circuit may be able to receive outputs from at least one module (e.g., monitoring module) and at least one analysis device simultaneously or sequentially when a reaction occurs.

[0089] In additional aspects, the processing circuit may adjust specific reaction parameters in response to outputs received from the monitoring module 58 and / or the analysis device 1700, based on pre-set conditions stored within the processing circuit (i.e., within the memory of the processing circuit), or based on adjustments made through user input (i.e., via a user interface positioned to communicate with the processing circuit).

[0090] In some embodiments, the user can manually trigger a change in any one of the modules by changing one or more parameters in the processing circuit based on the output from one or more of the monitoring modules and / or one or more of the analysis devices disclosed herein.

[0091] In some embodiments, the processing circuit of the present disclosure (optionally in the form of a controller) can be used to automatically organize changes to one or more of the modules of the system based on the output from one or more of the monitoring modules and / or one or more of the analysis devices disclosed herein, where the changes are based on pre-set triggers (such as a predetermined threshold temperature or yield parameter) that can optionally be stored in the memory of the processing circuit. For example, if the temperature of a given reaction exceeds a pre-set threshold temperature, the processing circuit can send an instruction / command to the corresponding temperature controller to lower the temperature of the reactor for that particular reaction until the temperature drops below the threshold temperature value.

[0092] An exemplary schematic flow diagram of system 10 is provided in FIG. 17. Each successive box corresponds to a respective module 50 and is shown in succession, although it is understood that the modules need not be in direct contact with each other. The solid arrows within the successive boxes represent the flow of fluid within the flow pathways disclosed herein, while the dashed arrows represent communication between system components. Module 50a receives an inlet supply of fluid, and underlying flow connectors deliver the fluid to an adjacent separator module 60. Separator module 60 is shown in thermal communication with monitoring module 58 and in fluid communication with reactor 56 and module 50b, each of which receives a different separation product. Monitoring module 58 can monitor one or more conditions during the separation step. Optionally, in one embodiment, monitoring module 58 is configured to monitor the temperature during the separation step and may be a temperature module 70 configured to provide additional heat or cooling to maintain a desired or selected temperature as disclosed herein. Module 50c represents another inlet source that delivers additional fluid to reactor 56. The reaction products within reactor 56 are delivered to module 50d, which is in fluid communication with analysis module 80, which in turn is operatively in communication with analysis device 1700 as disclosed herein. Module 50d is also in fluid communication with valve 74, and this valve can be selectively adjusted to direct the fluid either to 50e or module 50f. As further disclosed herein, it is contemplated that at least a portion of the modules of the present disclosure can be communicatively coupled to processing circuitry 110 that can be used to provide active feedback and / or modification to surface-mounted system components.

[0093] FIG. 19 shows an exemplary configuration in which surface-mounted components of the present system can be communicatively coupled to a processing circuit such as a computing device 1900 (optionally multiple computing devices) further disclosed herein. Non-limiting examples of the computing device 1900 include desktop computers, laptop computers, central servers, mainframe computers, tablets, and smartphones. In an exemplary aspect, the computing device 1900 may be positioned in the vicinity of the system 10. For example, in various exemplary aspects and as shown in FIG. 17, at least one computing device 1900 of the system may be selectively surface-mounted as disclosed herein or alternatively positioned in the vicinity of surface-mounted components, and it is contemplated that it may be the control module 1702. In these aspects, it is contemplated that multiple control modules 1702 may be selectively positioned within the system 10 to form the desired feedback loop disclosed herein. The computing device 1900 may be configured to generate, receive, store, and / or transmit device data related to the modular chemical reaction system. For example, the computing device 1900 can receive such device data from one or more of the process module 54, regulator module 64, monitoring module 58, valve 74, and / or analysis device 1700. The computing device 1900 can provide such device data to the path engine 140 and / or a computing device associated with the path engine 140. The computing device 1900 may further be configured to receive one or more synthesis paths from the path engine 140 and cause the execution of one or more synthesis paths on the modular chemical reaction system.

[0094] As shown in FIG. 19, it is contemplated that the computing device 1900 may include a processing unit 1904 (e.g., a CPU) in communication with a memory 1906. In an exemplary aspect, the processing unit 1904 may be communicatively coupled to at least one module 50 of the system 10 using conventional wired (e.g., cable, USB) or wireless (Wifi, Bluetooth) communication protocols. Additionally or alternatively, it is contemplated that the processing unit 1904 may be communicatively coupled to at least one analysis device 1700 using conventional wired (e.g., cable, USB) or wireless (Wifi, Bluetooth) communication protocols. It is contemplated that the processing unit 1904 may be communicatively coupled to at least one monitoring module 58 (e.g., a plurality of monitoring modules) further disclosed herein. In an exemplary aspect, the processing unit 1904 may be communicatively coupled to at least one process module 54. Additionally or alternatively, in a further exemplary aspect, the processing unit 1904 may be communicatively coupled to at least one controller module 64 such as a temperature module 70 or a valve 74.

[0095] Optionally, the computing device 1900 may include a wireless transceiver 1908 (e.g., a WiFi or Bluetooth wireless) configured to wirelessly transmit and receive information. In an exemplary aspect, it is contemplated that the wireless transceiver 1908 may be communicatively coupled to a remote computing device 1902 such as a tablet, a smartphone, or another computing device located remotely from the system. In these aspects, the remote computing device 1902 may be configured to provide remote user input or monitor the progress of an ongoing reaction based on output received from the computing device 1900 (optionally, through a WiFi, cellular network, or cloud-based system). The remote computing device may include a processing unit 1910.

[0096] FIG. 17 also includes an exemplary illustrative communication schematic of system 10. As shown, it is contemplated that a plurality of modules of the present system can be communicatively coupled to a processing circuit, shown herein as control module 1702. During the execution of at least one step of a reaction using the system of the present disclosure, it is contemplated that one or more monitoring modules 58 and one or more analysis devices 100 can be configured to provide outputs to a process circuit further disclosed herein. In the illustrated embodiment, monitoring module 58, reactor module 56, separator 60, analysis module 80, valve module 74, and analysis device 1700 are all communicatively coupled to control module 1702, thereby enabling direct monitoring of various reaction conditions and characteristics as the reaction occurs. However, in other exemplary configurations, only one module may be communicating with the processing circuit. Optionally, control module 1702 (alone or in combination with remote computing devices disclosed herein) can be further configured to selectively adjust the operation of at least one module (e.g., a process module (reactor 56, separator 60) or a controller module (valve 74)) to optimize a chemical reaction. Exemplary characteristics and conditions that can be optimized using the feedback loop of the present disclosure include, for example and without limitation, one or more of pressure, temperature, identification of the product produced, reagent consumption rate, identification of by-products, product yield, selectivity, and purity.

[0097] In an exemplary aspect, at least a portion of a plurality of modules can cooperate with at least a portion of a plurality of flow components to generate a first configuration that forms a first fluid flow pathway for performing at least one step of a first chemical reaction. After completion of the first chemical reaction, the plurality of modules and flow components within the substrate layer can be configured for selective rearrangement to a second configuration that generates a second fluid flow pathway for performing at least one step of a second chemical reaction within a minimal switching period. In these aspects, it is contemplated that the second configuration of the modules and flow components can include at least one module that did not define a portion of the first fluid flow pathway. It is further contemplated that the modules and flow components that define the second fluid flow pathway can include at least a portion of the modules and flow components that defined the first fluid flow pathway. The number of modules included in the second fluid flow pathway can be less than, equal to, or greater than the number of modules included in the first fluid flow pathway. Optionally, in an exemplary aspect, the positions of the plurality of modules and the plurality of flow connectors relative to the substrate (and the manifold layer) can remain unchanged within the first and second fluid flow pathways. In these aspects, it is contemplated that the first fluid flow pathway can be modified by changing the flow position within the valve (but not adjusting the mounting position of the valve module relative to the substrate), thereby adjusting the flow pathway. Optionally, such a modification can enable bypassing a portion of the first fluid pathway (e.g., a process module) and / or directing fluid to other modules (e.g., process modules) that were not previously in fluid communication with the first fluid flow pathway. Although not essential, in some optional aspects, it is contemplated that the fluid flow pathway can be selectively adjusted by removing, adding, or replacing modules.Accordingly, in some exemplary embodiments, the modified second fluid flow pathway can be created by adjusting the flow of fluid within the valve module and removing, adding, or replacing at least one module of the system. It is contemplated that for the addition or removal of modules disclosed herein, the position and / or number and / or type of the flow connectors can be adjusted to accommodate changes in the fluid flow pathway.

[0098] In further exemplary embodiments, it is contemplated that the minimal switching period can enable the sequential execution of multiple chemical reactions within a limited time frame that is much shorter than what is possible with conventional reaction structures. Optionally, the minimal switching period can range from about 30 minutes to about 4 hours, or more typically from about 1 hour to about 2 hours, depending on the complexity of the reaction.

[0099] Optionally, system 10 of the present disclosure may include a plurality of controller modules 64. In an exemplary embodiment, the first and second configurations of the plurality of modules and the plurality of flow components may each include first and second arrangements of the controller modules, and it is contemplated that the first and second arrangements of the controller modules may differ from each other with respect to at least one of the positioning of the modules and the type of the modules. Optionally, in some exemplary embodiments, each arrangement of the controller modules may be contemplated to include at least five of the following: check valve, T-shaped filter, flow controller, pressure sensing module, pressure sensing module, pressure relief valve, pressure controller, tube adapter, valve, pump, control valve module, temperature monitoring module, heater, or cooler. Optionally, in these embodiments, the second configuration may include at least one module type that is not present in the first configuration. It is further contemplated that the second configuration may include more or fewer controller modules than are included in the first configuration.

[0100] In further exemplary embodiments, it is contemplated that the systems of the present disclosure may enable the simultaneous execution of multiple or distinct reaction steps. For example, in one exemplary use, a product or byproduct separated from a process module (e.g., a separation module after a separation step) can be delivered to different modules (and distinct downstream flow paths) for further analysis and / or processing (reaction, separation) disclosed herein.

[0101] Optionally, system 10 of the present disclosure may comprise a plurality of analytical devices. In an exemplary embodiment, a first configuration of the plurality of analytical devices may operatively communicate with a first fluid flow pathway, but it is contemplated that the plurality of modules and flow components within the substrate layer may be configured for selective rearrangement to establish operative communication between a second configuration of the plurality of analytical devices and a second fluid flow pathway. In these embodiments, it is contemplated that the first and second configurations of the plurality of analytical devices may each include at least two of the following: a UV-Vis spectrometer, a near-infrared (NIR) spectrometer, a Raman spectrometer, a Fourier transform infrared (FT-IR) spectrometer, a nuclear magnetic resonance (NMR) spectrometer, or a mass spectrometer (MS). Optionally, in these embodiments, the second configuration of the analytical devices may include at least one analytical device type not present in the first configuration. It is further contemplated that the second configuration may include more or fewer analytical devices than those included in the first configuration.

[0102] An exemplary method of using the systems of the present disclosure may include introducing at least one reagent (e.g., a liquid reagent) into a fluid flow pathway of the system and then performing a chemical reaction using the at least one reagent (e.g., a liquid reagent).

[0103] Optionally, in some embodiments, at least one process module includes a plurality of process modules, and the chemical reaction may be a multi-step chemical synthesis that includes a plurality of sequential steps. In these embodiments, it is contemplated that each step of the plurality of sequential steps may correspond to the flow of reagents within each respective process module.

[0104] In a further embodiment, the method may include modifying a fluid flow pathway to create a second fluid flow pathway that is different from the first fluid flow pathway disclosed herein. As further described herein, the second fluid flow pathway may differ from the first fluid flow pathway in terms of the number of flow modules, the number of monitoring modules, the location of the monitoring modules, the number of monitoring modules, the number of process modules, the type of process modules, the routing of the process modules, the location of the process modules, the number of controller modules, the type of controller modules, the location of the controller modules, the number of analysis modules, the location of the analysis modules, the direction of flow, and combinations thereof. Further, the method may include performing a second chemical reaction using the modified fluid flow pathway that includes additional process modules.

[0105] Optionally, modifying the first fluid flow pathway may include adjusting the flow of liquid through at least one valve module between a plurality of modules without the need to adjust the position of any module with respect to the substrate layer (or manifold layer). Optionally, it is contemplated that a valve may be used to adjust the fluid (e.g., liquid) flow path of a chemical reaction without the need to adjust the position and / or orientation of the surface-mounted components and / or flow connectors disclosed herein. Additionally, or alternatively, in another embodiment, modifying the first fluid flow pathway may include implementing additional process modules on the outer surface of the substrate. In these embodiments, it is contemplated that the additional process modules may be reactors or separators as disclosed herein. The method may further include establishing fluid communication between the additional process modules and the fluid flow pathway.

[0106] In a further aspect, the method may include receiving at least one output from at least one analysis device using a processing circuit disclosed herein. In these aspects, the method may further include using a process circuit to adjust the operation of at least one module, such as a process module or a controller module, to optimize a chemical reaction. Additionally, or alternatively, the method may include receiving at least one output from a monitoring module (e.g., a process module or a controller module equipped with sensors) disclosed herein using a processing circuit. The method may further include using a processing circuit to adjust the operation of at least one module based on the at least one received output to optimize a chemical reaction. Optionally, the monitoring and optimization of the chemical reaction may occur at a location within the system corresponding to an intermediate step of the chemical reaction. It is further contemplated that the monitoring and optimization of the chemical reaction can be performed when the reaction occurs.

[0107] As further disclosed herein, it is contemplated that the monitoring module and the analysis module can be selectively positioned at various locations along the reaction flow pathway depending on the specific reaction step / location and conditions / characteristics that the user desires to monitor.

[0108] In a further exemplary aspect, it is contemplated that the system of the present disclosure can function as a fully integrated platform for performing and modifying chemical reactions. Optionally, each of the modules of the system may be communicatively coupled to a computing device 1900 and used to monitor and adjust each of the modules within the system based on feedback from analysis tools including software executed by a processing unit 1904. In an exemplary aspect, and as further disclosed herein, the system 10 may comprise a user interface for inputting instructions for configuring a chemical reaction, and the processing unit may be configured to determine appropriate modifications to achieve a selected configuration and then effectuate automated modification of a plurality of modules as needed to achieve the selected configuration.

[0109] In use, it is contemplated that the system of the present disclosure can enable the performance of multi-step chemical synthesis reactions in a continuous manner that was not previously achievable. It is further contemplated that the system of the present disclosure can enable the performance of modular liquid flow reactions that were not achievable using other surface-mounted reactor systems. It is further contemplated that the system of the present disclosure can provide intermediate processing steps in a manner that was not previously achievable (during intermediate steps of a reaction), where previously such processing was only executable at the end of the reaction pathway. Additionally, it is contemplated that the system of the present disclosure can provide a reaction using less volume of reagents, shorter residence times, and / or shorter heating times compared to previous chemical reactions.

[0110] In another aspect, an integrated method is also disclosed herein for discovering potentially new synthetic routes using the above-described retrosynthetic method, along with a system that can rapidly and inexpensively screen and optimize such chemical reactions. Exemplary apparatus includes a plurality of reaction vessels, a dispensing subsystem, at least one reactor module, an analysis subsystem, an automation subsystem, and a control circuit. The dispensing subsystem delivers reagents to a plurality of reaction vessels containing a plurality of reaction mixtures having varying reaction conditions. At least one reactor module drives a plurality of reactions within the plurality of reaction vessels. The analysis subsystem analyzes the compositions contained within the plurality of reaction vessels. The automation subsystem selectively moves the plurality of reaction vessels from a position proximal to the dispensing subsystem to at least one reactor module based on experimental design parameters. Also, the control circuit identifies optimal reaction conditions for a target final product based on the analysis. The complete disclosure of this apparatus can be found in PCT / US2018 / 040421, filed Jun. 29, 2018, entitled "Apparatus for reaction screening and optimization, and methods thereof", the entire contents of which are incorporated herein by reference.

[0111] In various specific embodiments, the apparatus includes a plurality of reaction vessels, a dispensing subsystem, at least one reactor module, an automation subsystem, and a control circuit. The reaction vessels may be provided within or contained within a substrate. The dispensing subsystem delivers reagents to the plurality of reaction vessels with a plurality of reaction mixtures having varying reaction conditions. At least one reactor module drives the plurality of reactions within the plurality of reaction vessels according to varying reaction conditions. For example, at least one reactor module includes an energy emitter that provides an energy output towards the plurality of reaction vessels, thereby driving the plurality of reactions. The varying reaction conditions may include, among other variations, temperature, time, reagent concentration, and reagents may be included. The analysis subsystem analyzes the composition of the reaction mixtures (e.g., reactants, by-products, final products, and by-products) contained within the plurality of reaction vessels after the reaction has started and optionally at any point during a set of reaction times. The analysis can be performed at a rate of about and / or up to one reaction (or more) per second. The automation subsystem selectively moves the plurality of reaction vessels from a position proximal to the dispensing subsystem to at least one reactor module based on experimental design parameters (e.g., defining varying reaction conditions). The control circuit provides the experimental design parameters to the dispensing subsystem and the automation subsystem to feedback control the plurality of reactions within a threshold period and identify the optimal reaction conditions for the target final product based on the analysis of the composition received from the analysis subsystem.

[0112] In a more specific embodiment, feedback control is provided by the control circuit adjusting the varying reaction conditions of a plurality of additional reactions based on comparing the previous reaction results with the yield of the optimal reaction product stored in the analysis subsystem. For example, the control circuit provides the adjusted varying reaction conditions to the dispensing subsystem and the automation subsystem as revised experimental design parameters, which may be instantaneous or nearly instantaneous.

[0113] Multiple reaction mixtures may be exposed to the same or different additional reaction conditions (e.g., the same temperature, the same exposure time, or various combinations of temperature and / or exposure time). As a specific example, the varying reaction conditions may include exposure to different temperatures over different periods. At least one reactor module may include a plurality of reactor modules, or one reaction module having different zones that drive a plurality of reactions in parallel at a plurality of different temperatures, and each of the reactor modules includes a thermal energy radiator that provides thermal energy towards at least a portion of the plurality of reaction mixtures. In such an exemplary embodiment, the reaction vessels are selectable independently of each other, and the automation subsystem selectively moves a first one of the plurality of reaction vessels to a first position associated with at least one reactor module, a second one of the plurality of reaction vessels to a second position associated with at least one reactor module, and at the completion of each respective reaction, selectively moves each of the first and second ones of the plurality of reaction vessels to a position proximal to the analysis subsystem. In other embodiments, the reaction vessels or a subset thereof may be located on a substrate, and the substrate (as a whole) moves to the reactor module and is exposed to temperature.

[0114] The automation subsystem can move a reaction vessel, reaction mixture, substrate, or other component (e.g., a cap) to various positions associated with the apparatus. The reaction mixture can move from a position proximal to the dispensing subsystem to at least one reactor module to drive a reaction. The automation subsystem can, in addition, move the reaction mixture (all or selected) back to the dispensing subsystem for addition of additional reagents and / or to the analysis subsystem. For example, the automation subsystem can move the reaction mixture from at least one reactor module to a position proximal to the analysis subsystem, and the analysis subsystem can emit an analysis beam towards each of a plurality of reaction vessels substantially parallel to the upper portion of the reaction vessel. In a more specific embodiment, the control circuit and the automation subsystem seal each of a plurality of reaction vessels before a plurality of reactions are driven in the reaction vessels, and unseal each of the plurality of reaction vessels during the reaction to introduce other reagents for sampling the reaction mixture and / or before analysis of the composition of the reaction mixture (e.g., reactants, by-products, final products, and by-products, etc.).

[0115] Further, the apparatus may optionally include one or more dispensing chambers used for dispensing reaction vessels and caps to the automation subsystem.

[0116] The dispensing system can include an inkjet printer, a liquid dispenser, and combinations thereof. For example, the inkjet printer may have a printer head such as an 8-channel printer head, a 9-channel printer head, or a 96-channel printer head used for dispensing reagents to the reaction vessel.

[0117] The analysis subsystem may include a liquid chromatography mass spectrometer (LC-MS), a direct analysis in real time (DART) mass spectrometer (MS), a spectroscopic imaging device, and combinations thereof. For example, the components of a DART-MS can provide a beam of gas directed sequentially at each reaction mixture and convey sampling of each reaction mixture continuously to another component of the DART-MS. The beam can be provided directed towards the top of the reaction vessel, at an angle, for example, between 0 and 45 degrees relative to normal. The beam can result in, or cause, a detectable audio frequency that can be used to verify whether an analysis is being performed. In some particular embodiments, the apparatus further includes a sensor circuit that provides a detectable audio frequency signal to a control circuit in response to analysis beam sampling of each reaction mixture, and the control circuit compares the detected audio frequency signal to a threshold audio frequency to verify therefrom whether an analysis is occurring. In other embodiments, the apparatus includes an imaging circuit used to take a visual image of (e.g., each) reaction vessel, from which it can be verified whether an analysis is occurring.

[0118] Other related and specific embodiments of the present disclosure are directed to an apparatus including a plurality of reaction vessels that are individually selectable and separable, at least one reactor module, an analysis subsystem, an automation subsystem, and a control circuit. The plurality of reaction vessels contain reagents therein according to experimental design parameters of a plurality of reaction mixtures having varying reaction conditions. The at least one reactor module drives the plurality of reactions within the plurality of reaction vessels according to varying reaction conditions, the varying reaction conditions including exposure to different temperatures over different periods. The analysis subsystem selectively provides an analysis beam towards the plurality of reaction mixtures and analyzes the results therefrom at a rate of approximately one reaction per second, such as at a rate of up to one reaction per second or more, to analyze the composition of the reaction mixtures (e.g., reactants, by-products, final products, and by-products) contained within the plurality of reaction vessels at any point after the reaction has started and during any of a set of reaction times. The automation subsystem seals the plurality of reaction vessels, selectively moves the plurality of reaction vessels to and from the at least one reactor module over different periods based on the experimental design parameters, unseals the plurality of reaction vessels, and selectively moves the reaction mixtures proximal to the analysis subsystem after the reaction. The control circuit provides the experimental design parameters to the automation subsystem to control the reactions within the plurality of reaction vessels and identifies optimal reaction conditions for a target final product based on the analysis of the composition received from the analysis subsystem.

[0119] In certain aspects, the automation circuit includes a movable arm and a dispensing chamber. The dispensing chamber contains caps for the plurality of reaction vessels. The movable arm and the dispensing chamber dispense caps for the plurality of reaction vessels and use the dispensed caps to seal the plurality of reaction vessels. As further described herein, the movable arm may include a head assembly used for selection of reaction vessels and a set of interconnected links and power junctions used for movement of the head assembly.

[0120] In certain embodiments, the apparatus described above may further include a dispensing subsystem that delivers reagents to a plurality of reaction vessels for a plurality of reaction mixtures having varying reaction conditions. The automation subsystem can selectively move the plurality of reaction vessels from a position proximal to the dispensing subsystem to at least one reactor module. The control circuit also provides design-of-experiment parameters to the dispensing subsystem, which include reagent identification, the concentration of the reagent in each of the plurality of reaction vessels, and other varying reaction conditions.

[0121] Certain embodiments according to the present disclosure are directed to a method of using the apparatus described above. The method can include providing a plurality of design-of-experiment parameters to a dispensing subsystem and an automation subsystem via a control circuit to control a plurality of reactions within a plurality of reaction vessels. The method further includes delivering different amounts of reagents by the dispensing subsystem and according to the design-of-experiment parameters to respective ones of the plurality of reaction vessels. The subsystem can selectively move the plurality of reaction vessels from a position proximal to the dispensing subsystem to at least one reactor module in which the plurality of reactions are driven. For example, the plurality of reactions are driven within the plurality of reaction vessels according to varying reaction conditions including exposure to different temperatures and different durations defined by the design-of-experiment parameters and by at least one reactor module. The method further includes analyzing the compositions contained within the plurality of reaction vessels at a rate of about (e.g., at most or more than) one reaction per second and identifying, based on this analysis, reaction conditions that are optimal for a target final product.

[0122] As described above, in some embodiments, the method further includes selectively moving a plurality of reaction vessels to a position proximal to the analysis subsystem in response to a plurality of reactions that are driven to completion. The analysis subsystem provides a beam of gas that can be directed movably to each of the plurality of reaction vessels. The beam of gas can be directed at an angle substantially parallel to the upper portion of the plurality of reaction vessels, and the beam of gas carries a sampling of the reaction mixture to the analysis subsystem for analyzing the composition contained within the reaction vessel based on the ions generated therefrom.

[0123] In various related embodiments, the method includes delivering different amounts of reagent by providing a plurality of reaction mixtures having different concentrations of reagent to different reaction vessels of the plurality of reaction vessels according to experimental design parameters. The reagents can be provided simultaneously or at different times throughout the experiment.

[0124] Identifying the optimal reaction conditions for the target final product may further include identifying optimized experimental design parameters selected from the group consisting of reagents, reagent concentrations, temperature, time, stoichiometry, and combinations thereof. The optimal reaction conditions can be further optimized by providing feedback. For example, the method can provide adjusted and varying reaction conditions for a plurality of additional reactions designed to reach revised optimal reaction conditions for the target final product based on the analysis of the composition contained within the reaction vessel, and provide the adjusted and varying reaction conditions as revised experimental design parameters to the dispensing subsystem and the automation subsystem. Using the revised experimental design parameters, the apparatus can perform additional tests and further optimize the reaction conditions from the analysis of the composition therefrom.

[0125] FIG. 20 illustrates an example of an apparatus for performing reaction screening and optimization according to various embodiments. Apparatus 2000 includes a plurality of reaction vessels 2012, a control circuit 2002, a dispensing subsystem 2004, an automation subsystem 2006, at least one reactor module 2008, and an analysis subsystem 2010. Apparatus 2000 can be used for the synthesis design of a target final product. More specifically, it can explore a plurality of synthetic routes having varying reaction conditions and be used for screening or optimizing reaction conditions to reach the target final product.

[0126] Different experimental design parameters 2001 can be input into the control circuit 2002 of apparatus 2000 and used to explore a plurality of synthetic routes having varying reaction conditions to reach the target final product. The experimental design parameters 2001 may include one or more synthetic routes generated by a route engine 140. The experimental design parameters 2001 may also include equipment data provided to the route engine 140 for consideration during the generation of the synthetic routes. The experimental design parameters, which may also be referred to as DOE information, may include a plurality of reaction conditions having different combinations of values. Exemplary varying reaction conditions may include, among other variations, when a reagent is added, the reagent, the concentration of the reagent, or the stoichiometry, time, and temperature, and the values may include different actions or values of the conditions of the experiment (e.g., 50 degrees and 2000 degrees). Some DOE information according to the present disclosure can preclude the use of optimizing one reaction condition at a time. For example, DOE information regarding four experimental design parameters (n <n>) can be reduced from 256 possibilities to 32 experiments or reaction mixtures. As can be understood, the DOE information can be designed and stored as data within the memory circuit of the control circuit 2002.

[0127] The control circuit 2002 receives the experimental design parameters 2001 and provides at least a portion of these experimental design parameters (e.g., a set of reaction conditions) to other components of the apparatus 2000 (such as the dispensing subsystem 2004 and the automation subsystem 2006, etc.) to control the reaction based on the varied reaction conditions. For example, the experimental design parameters 2001 can define the varied reaction conditions and may include a list of compounds and solvents, stoichiometric ranges, time and temperature conditions, and normalized volumes. The DOE information may include a table containing the experiments to be performed or may be provided as such. In certain embodiments, a file may be generated by the control circuit 2002 and transmitted to the dispensing subsystem 2004 for reagent dispensing. For example, the control circuit 2002 can provide the dispensing subsystem 2004 with combinations of reagents at specific concentrations and can provide the automation subsystem 2006 with the specification of the time for which the reaction mixture is to be exposed (or the specific time for which each reaction mixture is to be exposed to a specific temperature or other type of energy used to drive the reaction). The automation subsystem 2006 may be provided with information about at least one reactor module 2008 (or a zone thereof), such as the temperature(s) at which one reactor module 2008 is configured to expose the reaction mixture, and / or which module or zone, and / or for how long each reaction vessel is to be provided.

[0128] The plurality of reaction vessels 2012 are configured to contain reagents that contribute to a reaction designed to produce a target end product. Various types of reaction vessels 2012, such as individual vials or wells, can be used. In some embodiments, the reaction vessel 2012 may be disposed within or form part of a substrate 2014, such as a plate having wells formed thereon and / or a plate having a space (e.g., a hole) sized to receive vials therein. The substrate 2014 can take various forms. For example, the substrate 2014 can be flat and may include a tape incorporating wells, an absorbent material for collecting and mixing reagents, such as Teflon® or stainless steel mesh, or may be formed as wells for containing mixtures in a plurality of containers. As another example, catalytic chemistry can be studied by using a palladium or other reactive metal mesh. According to various embodiments, the reaction vessels 2012 can be selectable independently of each other (e.g., vials) and selectively moved for different synthetic routes. In other embodiments, at least one subset of the reaction vessels 2012 are linked together (e.g., wells on a plate) for a synthetic route and moved together.

[0129] The dispensing subsystem 2004 delivers reagents to a plurality of reaction vessels 2012 of a plurality of reaction mixtures having varying reaction conditions based on the varying conditions defined by the experimental design parameters 2001. More specifically, the plurality of reaction mixtures may include a set of reagents in different amounts or concentrations, and / or different reagents. An exemplary dispensing subsystem 2004 includes an inkjet printer or a liquid dispenser. As further illustrated and described herein, an inkjet printer delivers reagents based on inkjet printing. An exemplary inkjet printer can dispense volumes from picoliters to microliters onto a microliter plate using a multi-channel print head such as a 9-channel, 12-channel, 96-channel, etc. Each print head can contain a specific reagent. The inkjet printer can print reaction mixtures, for example, at a rate of one reaction per second. Additionally, the reagents may be loaded directly into the apparatus 2000. For example, pre-weighted reagents loaded into matrix tubes may be input into the apparatus 2000. The pre-weighted reagents may be barcoded for tracking of the reagent position and optionally formatted in a 96-tube tray holder sealed with an inter-slit septum cap that can be mounted directly on the print head of an inkjet printer. An exemplary dispenser includes an inkjet printer and a print head.

[0130] However, embodiments are not limited to inkjet printers and can include a variety of different dispensing subsystems. For example, the dispensing subsystem can include a liquid dispenser that can be used for filling plates and / or vials presented by the automation subsystem 2006, and / or a manual dispenser (e.g., a pipette).

[0131] The apparatus 2000 includes at least one reactor module 2008 having an energy emitter, such as a thermal energy tool or radiator, that provides an energy output (e.g., heat) towards the reaction mixture to drive a plurality of reactions. Examples of energy emitters include heaters, ovens, microwave sources, or light. Each reactor module has at least one zone configured to provide a specific temperature or otherwise drive the reactions in a different manner (e.g., provide different light or microwaves). For example, at least one reactor module 2008 drives the reactions within a plurality of reaction vessels 2012 according to varying reaction conditions. In some embodiments, the apparatus 2000 includes one reactor module having one zone or is otherwise configured to provide a single temperature. Alternatively, and / or in addition, one reactor module may have a plurality of zones and / or the apparatus may include a plurality of reactor modules, each having one or more zones and used to provide a plurality of different temperatures (e.g., two or more, six, ninety-six, etc.). In such an exemplary embodiment, at least one reactor module 2008 can drive the reactions within the reaction vessels 2012 by exposing the reaction mixture to different temperatures and optionally for different periods of time. The different periods of time can be provided via an automated subsystem 2006 that moves at least one of the reaction vessels 2012 from at least one reactor module 2008 at the end of the different periods of time. Multiple reactions can be driven in parallel and at multiple different temperatures (or other types of energy) using different zones or different reactor modules. As further illustrated and described herein, the reactor module can contain at least one subset of at least the reaction vessels 2012 provided to the reactor module by the automated subsystem 2006.

[0132] The automated subsystem 2006 can selectively move the reaction vessel 2012 and / or the reaction mixture within the reaction vessel 2012 based on the experimental design parameters 2001. More specifically, the automated subsystem 2006 moves the reaction vessel 2012 from a position proximal to the dispensing subsystem 2004 to at least one reactor module 2008 to drive the reaction. As further illustrated herein, the automated subsystem 2006 may include a movable arm (e.g., a robotic arm) and other movable components used for the selective movement of the reaction vessel 2012 and / or the reaction mixture. In some particular embodiments, the movement may include the selective movement of the reaction mixture (e.g., the vessel) to different reactant modules or zones, or over different periods. In such a manner, the reaction mixture dispensed by the dispensing subsystem 2004 is moved to at least one reactor module 2008 to drive the reaction therein, optionally over different periods. The automated subsystem 2006 can further move the reaction mixture to a position proximal to the analysis subsystem 2010 to analyze the composition contained therein, although the embodiments are not limited thereto, and the movement may occur using other mechanisms further described herein. The composition may include reactants, by-products, final products, and by-products, as well as various combinations thereof.

[0133] As a specific example to be further described below, in an apparatus having individually selectable reaction vessels and a plurality of reactor modules or zones for providing a plurality of temperatures, the varied reaction conditions can include exposure to different temperatures over different times. The automation subsystem 2006 selectively moves a first subset of the plurality of reaction vessels to a first position associated with at least one reactor module 2008 to expose the first subset of reaction vessels to a first temperature, and moves a second subset of the reaction vessels to a second position of at least one reactor module 2008 to expose the second subset of vessels to a second temperature different from the first temperature. At the completion of each reaction, or as otherwise defined by the experimental design parameters 2001, each of the reaction vessels in the first and second subsets is moved to a position proximal to the analysis subsystem 2010. The movement can be performed by the automation subsystem 2006 and / or additional components such as a conveyor belt further described herein.

[0134] According to some embodiments, the automation subsystem 2006 can seal and / or unseal the reaction mixture within the reaction vessel 2012 (based on control by the control circuit 2002). For example, prior to driving a plurality of reactions within the reaction vessel 2012 by the automation subsystem 2006, each of the plurality of reaction vessels 2012 can be sealed and, during the reaction to introduce other reagents for sampling the reaction mixture, or prior to analysis of the composition, opened based on the experimental design parameters 2001. For example, the automation subsystem 2006 can include a movable arm and a dispensing chamber. The dispensing chamber can contain a plurality of caps for the reaction vessels 2012. The movable arm, together with the dispensing chamber, can dispense caps to each of the plurality of reaction vessels 2012 and use the caps to seal the reaction vessels. The movable arm can include or have access to tools for subsequently unsealing the caps, as further illustrated herein.

[0135] The analysis subsystem 2010 analyzes the compositions contained within a plurality of reaction vessels 2012 after the reaction has started (and at any point during a set of reaction times defined by the experimental design parameters 2001). The compositions can be analyzed for specific purposes or a set of purposes, such as, for example, product yield, selectivity, cost, purity, m / z values, and various combinations thereof. As an example, the final product is analyzed for yield, purity, and cost to generate revised reaction conditions for further optimizing one or more of the objectives. The analysis can be performed at a rate of approximately one reaction per second (e.g., up to and including one or more reactions per second, and / or within the aforementioned range). Exemplary analysis subsystems include liquid chromatography-mass spectrometers (LC-MS), such as those via a 96-well plate or via a UV plate reader (the plate either not containing vials or containing transparent vials), spectroscopic imaging (e.g., UV-Vis vials, FT-IR cells, etc.), and direct analysis in a real-time (DART) mass spectrometer (MS) via individualized vials, as well as various combinations thereof. In various specific embodiments, the analysis subsystem 2010 includes a DART source (e.g., DART-MS) that provides a beam of gas sequentially directed at each reaction mixture surface and transports a sample of each reaction mixture to the MS of the DART-MS. The analysis beam is an ionization source (e.g., a beam of gas in the case of DART-MS) and, in certain embodiments, is radiated towards each of the plurality of reaction vessels in a manner approximately parallel to (e.g., at an angle relative to normal) the upper portion of the reaction vessel 2012, although the embodiments are not limited thereto. The beam of gas can be directed towards the upper portion of the plurality of reaction vessels 2012, and the beam of gas transports sampling of the reaction mixture contained within the reaction vessel to another component of the analysis subsystem 2010 (e.g., the MS) for analysis based on the ions generated therefrom. The angle can include zero degrees with normal extending towards the ceiling. In this manner, the reaction vessel 2012 is opened, as in the case of liquids from 5 - 10i up to a maximum of 20ul (or the maximum volume of the vial), and the DART head is directed directly towards the MS through the vial.The beam can be directed at an angle of 0 to 45 degrees relative to the normal of the reaction vessel 2012.

[0136] In some embodiments, the angle of the gas beam can generate a detectable audio frequency signal. In such exemplary embodiments, the apparatus 2000 may optionally include a sensor circuit that outputs a signal to the control circuit 2002 in response to the detectable audio frequency signal. The sensor circuit can provide a signal in response, and this signal can be used to verify whether the analysis beam is sampling (or not sampling) each reaction mixture. For example, the control circuit 2002 can compare the detected audio frequency signal with a threshold audio signal (indicating sampling) and verify therefrom whether an analysis is taking place. In other embodiments, the apparatus 2000 includes an imaging circuit used to capture a visual image of the reaction vessel 2012, and from this visual image, it can be verified whether an analysis is taking place.

[0137] In certain embodiments, for purposes such as selectivity and yield definition of a target final product, the final product or other composition may be compared to the target final product or target composition. The analysis subsystem 2010 provides an analysis of the composition to the control circuit 2002. The control circuit 2002 identifies the optimal reaction conditions for the target final product (from among the varying reaction conditions). More specifically, the optimal reaction conditions can include a set of reaction conditions among the varying reaction conditions for reaching the target final product, which can include reagents, reagent concentrations, temperature, time, stoichiometry, and combinations thereof. As described above, the control circuit 2002 may further provide feedback control of multiple reactions within a threshold time. The feedback control adjusts the varying reaction conditions of multiple additional reactions based on a comparison of previous reaction results with the yield of the optimal reaction product stored in the analysis subsystem 2010, and provides the adjusted varying reaction conditions as revised experimental design parameters (e.g., a new set of multiple reaction conditions) to the dispensing subsystem 2004 and the automation subsystem 2006, or can be provided thereby. The threshold period can include instantaneous or near-instantaneous control in some particular embodiments. The adjusted varying conditions may be for multiple additional reactions designed to achieve revised optimal reaction conditions for the target final product and / or other target compositions (e.g., one or more objectives can be optimized). The control circuit 2002 can provide feedback control, e.g., the adjusted varying reaction conditions, as revised experimental design parameters to the dispensing subsystem 2004 and the automation subsystem 2006. The apparatus 2000 uses the revised experimental design parameters to perform additional tests and further optimize the reaction conditions from the analysis of the compositions therefrom.

[0138] Feedback control can use machine learning to provide adjusted and varying conditions. For example, control circuit 2002 is trained with data on molecular properties such as the ability to inhibit an enzyme, the ability to act as an antibacterial agent, the ability to catalyze a particular reaction, and predicting whether a molecule has relevant properties. Over time, control circuit 2002 updates its training to predict which reaction conditions and / or their values affect a particular goal. Control circuit 2002 is updated over time and uses this training to provide adjusted and varying reaction conditions for one or more goals as described above, further optimizing the reaction conditions.

[0139] As a specific example, and consistent with the specific examples provided above, the plurality of reaction vessels 2012 includes individual separable reaction vessels. The automation subsystem 2006 positions the reaction vessels 2012 on a substrate 2014 proximal to the dispensing subsystem 2004. The dispensing subsystem 2004 dispenses different amounts of reagents into each of the plurality of reaction vessels according to the experimental design parameters 2001. The plurality of reaction vessels 2012 having reaction mixtures are sealed via the automation subsystem 2006, such as via the caps described above and further illustrated. The automation subsystem 2006 selectively moves the reaction vessels 2012 from the substrate 2014 proximal to the dispensing subsystem 2004 to at least one reactor module 2008. The automation subsystem 2006 moves a particular container to different zones or reactor modules associated with different temperatures. For example, a first subset of the plurality of reaction vessels is moved to a first zone and / or a first reactor module that drives the reaction within the first subset of reaction vessels by exposing the reaction mixture to a first temperature (e.g., 50°C). A second subset of the reaction vessels is moved to a second zone and / or a second reactor module that exposes the second subset of the reaction vessels to a second temperature (e.g., 75°C). A third subset is moved to a third zone and / or a third reactor module and exposed to a third temperature. Embodiments are not limited to three zones, reactor modules, and / or temperatures, and may include more or less than three, such as one, two, four, five, six, twenty, etc. zones, reactor modules, and / or temperatures.

[0140] In addition, in various embodiments, each reaction mixture of the subset may be exposed to a respective temperature for different periods of time. For example, the automated subsystem 2006 selectively moves (e.g., removes from exposure to temperature) reaction vessels at different times based on the design of experiments parameters 2001 from at least one reactor module 2008. Using the example provided above, at the end of a first period (e.g., 2 minutes), the first reaction vessel within the first subset is removed from the first zone and / or the first reactor module, and at the end of a second period (e.g., 2 minutes and 20 seconds), the second reaction vessel within the first subset is removed from the first zone and / or the first reactor module. Embodiments are not limited thereto, and in response to a plurality of reactions driven towards completion, a plurality of reaction vessels may be moved to a position proximal to the analysis subsystem 2010 simultaneously or at different times. For example, the automated subsystem 2006 can open a plurality of reaction vessels 2012 and selectively move the reaction mixture proximal to the analysis subsystem 2010. The analysis subsystem 2010 can then analyze the composition in comparison to the target end product. In various embodiments, the reaction vessel 2012 can be opened by removing the cap of the reaction vessel 2012 (e.g., removing the cap that seals the reaction vessel 2012) or by puncturing the seal of the reaction vessel 2012. For example, the reaction vessel 2012 may include a seal having a pierceable location that can be pierced to facilitate removal and analysis of the product.

[0141] The movement can be performed by the automation subsystem 2006. For example, due to interference of DART-MS, the reaction vessel 2012 may be placed on a substrate 2014 such as a 96-well plate. The automation subsystem 2006 caps the reaction vessel 2012, places the capped reaction vessel in at least one reactor module 2008 as defined by the DOE information, and then removes them from at least one reactor module 2008. The automation subsystem 2006 removes the cap of the reaction vessel 2012 (or positions it at a position where the cap is removed), and sequentially places the reaction vessels with the caps removed in front of the DART inlet. For example, the automation subsystem 2006 may place the reaction vessels with the caps removed on a conveyor that sequentially transports the reaction vessels, as further illustrated herein, in front of the DART inlet.

[0142] According to some embodiments, one or more of the synthetic reaction pathways may include adding reagents at different times. In such embodiments, one or more reaction vessels are removed from at least one reactor module 2008 in an open or uncapped state, returned to the dispensing subsystem 2004 for dispensing of one or more additional reagents, optionally capped again, and returned to one of at least one reactor module 2008 for further driving of the reaction. The automation subsystem 2006 selectively moves the reaction vessels from at least one reactor module 2008 and / or the dispensing subsystem 2004 to a position in front of the DART-MS. In another embodiment, the reaction vessel is returned to the substrate 2014 or an additional substrate, such as a well plate, and then the substrate is moved in the X-Y stage to position the vial in front of the DART-MS.

[0143] The above examples describe the use of DART-MS, but embodiments are not limited to DART-MS, varying reaction conditions including different temperatures and times, and / or reaction vessels that can be individually moved. For example, as described above, the reaction mixture may be dispensed into individual reaction vessels with caps and reacted with the caps on. The automated subsystem 2006 can replace reaction vessels that are uncapped or otherwise opened (e.g., perforated) onto or with the substrate 2014, and the reaction mixture can be sampled directly by LC-MS. In other embodiments, the reaction vessels are not individually selectable and / or movable vials. For example, the reagent may be dispensed directly onto a substrate 2014 having wells such as a microliter plate. The substrate 2014 (e.g., a plate) may be a conventional solid plate, or the plate may be compatible with a UV plate reader. In some embodiments, the apparatus 2000 is operated in a screening mode in which all wells are exposed to the same temperature and the same time. In the screening mode, variations in the input reagents can be tested to identify which chemistries function. The dispensing subsystem 2004 dispenses the reagent into the well plate. For example, the plate is transported to at least one reactor module 2008 for processing (if necessary) and then placed in the LC-MS autosampler. In other embodiments, the reagent is dispensed into a transparent microtiter plate. The reaction mixture is reacted with a set of reaction conditions and placed in a plate reader for rapid UV / Vis evaluation. In other specific embodiments, the (individual) reaction vessels 2012 include transparent vials into which the reagent is dispensed, reacted (optimized) individually, and then exchanged onto the transparent plate for the above-described UV / Vis analysis.

[0144] FIG. 21 is a block diagram showing an environment 2100 that includes a non-limiting example of a client 2106 connected via a server 2102 and a network 2104. In one aspect, the analysis device 1700, the control module 1702, the computing device 1900, the remote computing device 1902, and / or the device 2000 (and any of its sub-components) may include one or more of the server 2102 and / or the client 2106. In one aspect, some or all of the steps of any of the described methods may be performed on the computing devices described herein. The server 2102 may include one or more computers configured to store one or more path engines 140, reactions 110, machine learning classifiers, synthetic pathways 150, and the like. The client 2106 may include one or more computers configured to operate a user interface 500 (e.g., via a web browser), such as a laptop computer or a desktop computer. A plurality of clients 2106 may be connected to the server(s) 2102 through a network 2104, such as the Internet. A user of the client 2106 may connect to the path engine 140 using the user interface 500.

[0145] Server 2102 and client 2106 may be digital computers that generally include a processor 2108, a memory system 2110, an input / output (I / O) interface 2112, and a network interface 2114 with respect to the hardware architecture. These components (2108, 2110, 2112, and 2114) are communicatively coupled via a local interface 2116. The local interface 2116 may be, for example, but not limited to, one or more buses or other wired or wireless connections known in the art. The local interface 2116 may have additional elements (omitted for simplicity) such as a controller, buffer (cache), driver, repeater, and receiver to enable communication. Further, the local interface may include address, control, and / or data connections to enable proper communication between the aforementioned components.

[0146] Processor 2108 may be a hardware device for executing software, particularly software stored in memory system 2110. Processor 2108 can be any custom-made or commercially available processor, a central processing unit (CPU), an auxiliary processor among several processors associated with server 2102 and client 2106, a semiconductor-based microprocessor (in the form of a microchip or chipset), or generally any device for executing software instructions. When server 2102 or client 2106 is operating, processor 2108 is configured to execute software stored in memory system 2110, communicate data to and from memory system 2110, and generally control the operation of server 2102 and client 2106 according to the software.

[0147] Using the I / O interface 2112, user input can be received from and / or system output can be provided to one or more devices or components. The user input may be provided, for example, via a keyboard and / or a mouse. The system output may be provided via a display device and a printer (not shown). The I / O interface 2112 may include, for example, a serial port, a parallel port, a Small Computer System Interface (SCSI), an IR interface, an RF interface, and / or a Universal Serial Bus (USB) interface.

[0148] Using the network interface 2114, transmission and reception can be performed from and to an external server 2102 or a client 2106 on the network 2104. The network interface 2114 may include, for example, a 10BaseT Ethernet adapter, a 100BaseT Ethernet adapter, a LAN PHY Ethernet adapter, a Token Ring adapter, a wireless network adapter (e.g., WiFi), or any other suitable network interface device. The network interface 2114 may include an address, control, and / or data connection to enable proper communication on the network 2104.

[0149] The memory system 2110 may include either one or a combination of volatile memory elements (e.g., random access memory (RAM) such as DRAM, SRAM, SDRAM, etc.) and non-volatile memory elements (e.g., ROM, hard drive, tape, CDROM, DVDROM, etc.). Further, the memory system 2110 may incorporate electronic, magnetic, optical, and / or other types of storage media. It should be noted that the memory system 2110 may have a distributed architecture where various components are located apart from each other but can be accessed by the processor 2108.

[0150] The software within the memory system 2110 may include one or more software programs, each of which includes an ordered list of executable instructions for performing a logical function. In the example of FIG. 21, the software within the memory system 2110 of the server 2102 can include a routing engine 140 and a suitable operating system (O / S) 2118. In the example of FIG. 21, the software within the memory system 2110 of the client 2106 can include a user interface 500 and a suitable operating system (O / S) 2118. The operating system 2118 essentially controls the execution of other computer programs such as the operating system 2118, the user interface 500, etc., and provides scheduling, input-output control, file and data management, memory management, and communication control, as well as related services.

[0151] For illustrative purposes, application programs and other executable program components (such as operating system 2118) are illustrated herein as separate blocks, but it is recognized that such programs and components may exist at various times within different storage components of server 2102 and / or client 2106. The implementation of routing engine 140 and / or user interface 500 may be stored on or transmitted through some form of computer-readable medium. Any of the methods of the present disclosure can be executed by computer-readable instructions embodied on a computer-readable medium. The computer-readable medium can be any available medium accessible by a computer. By way of example, and not limitation, the computer-readable medium may include "computer storage media" and "communication media". "Computer storage media" can include volatile and non-volatile removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Exemplary computer storage media can include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0152] Although specific configurations have been described, the configurations herein are not intended to be limiting, but rather are intended to be possible configurations in all respects, and thus are not intended to limit this scope to the specific configurations described.

[0153] Unless otherwise specified, no method described in this specification is intended to be construed as requiring that its steps be performed in a particular order. Thus, if a claim for a method does not actually recite the order in which the steps are to be followed, or if the steps are not otherwise limited to a particular order in the claims or specification, then in no way is it intended to imply any order. This holds true for any possible ambiguous criteria for interpretation, including logical issues regarding the arrangement of steps or the sequence of operations, straightforward interpretations derived from grammar systems or punctuation, and the number or type of configurations described in this specification.

[0154] It will be apparent to those skilled in the art that various modifications and variations can be made without departing from the scope or spirit. Other configurations will be apparent to those skilled in the art by considering the specification and practice described herein. The specification and configurations described herein are to be regarded as merely exemplary, and the true scope and spirit are intended to be indicated by the following claims.< / n>

Claims

1. A computer-executed computational method for identifying one or more existing or new chemical synthesis routes for generating a target compound, comprising: determining, by the computer, a plurality of known chemical reactions based on a first one or more sets of chemical reactions; determining, by the computer, a plurality of computationally generated chemical reactions different from the plurality of known chemical reactions based on at least one target compound and generalized known chemical transformations; applying, by the computer, a trained classifier to each of the plurality of computationally generated chemical reactions to classify, from the plurality of computationally generated chemical reactions, one or more computationally generated chemical reactions as successful computationally generated chemical reactions, wherein the trained classifier includes a machine learning model executed by the computer and is trained using training data including one or more chemical reactions classified as successful and one or more chemical reactions classified as failed; generating, by the computer, a plurality of chemical reactions based on the one or more successful computationally generated chemical reactions and the plurality of known chemical reactions, wherein each chemical transformation of the plurality of chemical reactions represents the conversion of one compound to another compound; determining, by the computer, a plurality of chemical synthesis routes related to the at least one target compound based on the at least one target compound, wherein each chemical synthesis route includes one or more of the plurality of chemical reactions and each chemical synthesis route of the plurality of chemical synthesis routes generates the target compound; identifying, by the computer, chemical synthesis routes among the plurality of chemical synthesis routes for which the corresponding cost is less than a threshold; outputting the identified chemical synthesis route for synthesizing the at least one target compound by executing the identified chemical synthesis route; A method comprising the above.

2. training, by the computer, a classifier with a training dataset, the training dataset including one or more of a chemical reaction database, an estimated yield, or a predicted yield of the first one or more sets of chemical reactions, the method of claim 1 further comprising training.

3. training the classifier with the training dataset comprises receiving a dataset including the plurality of known chemical reactions, each of the plurality of known chemical reactions including at least one reactant, each reactant consisting of one or more atoms, receiving; for each reactant, classifying the one or more atoms into categories based on neighboring atoms, bond order, and / or number of hydrogen atoms present; for each reactant, determining a vector based on a histogram of the categories; determining a training dataset consisting of a) a vector of a reaction related to a specific transformation and b) a vector of a reaction related to the specific transformation but resulting in a product of a different reaction type; exposing a portion of the training dataset to the classifier to train the classifier; exposing another portion of the training dataset to the trained classifier to test the trained classifier, the method of claim 2 comprising.

4. exposing another portion of the training dataset to the trained classifier to test the trained classifier includes evaluating the performance of the trained classifier based on one or more measurement criteria, the method of claim 3 comprising.

5. the method of claim 4, wherein the one or more measurement criteria include one or more of accuracy, positive precision, negative precision, positive sensitivity, or negative sensitivity.

6. The method according to claim 1, further comprising generating, by the computer, a tree data structure, wherein the target compound is the root node of the tree data structure. **Claim 7** The method according to claim 6, further comprising adding, by the computer, a plurality of branches to the tree data structure, each branch of the plurality of branches including one of the plurality of chemical synthesis routes. **Claim 8** The method according to claim 1, wherein determining the plurality of chemical synthesis routes associated with the target compound is based on one or more parameters. **Claim 9** The method according to claim 8, wherein the one or more parameters include one or more of available feedstocks, available chemicals, or available equipment. **Claim 10** The method according to claim 1, wherein determining the one or more optimal chemical synthesis routes from the plurality of chemical synthesis routes is based on one or more parameters. **Claim 11** The method according to claim 10, wherein the one or more parameters include one or more of available feedstocks, available chemicals, available equipment, yield, financial cost, time, reaction conditions, or likelihood of reaction success. **Claim 12** Determining the one or more optimal chemical synthesis routes from the plurality of chemical synthesis routes comprises determining all compounds that can reach the target in a maximum of a predetermined number of steps, and determining the minimum cost chemical synthesis route to the target compound from among the plurality of chemical synthesis routes including routes excluding workup or solvent exchange steps, the method according to claim 1. **Claim 13** The method according to claim 12, wherein determining the minimum cost chemical synthesis route comprises evaluating a cost function. **Claim 14** The method according to claim 13, wherein the cost function includes the following. [Equation 1]

15. The method according to claim 1, further comprising performing one of the one or more chemical synthesis routes to synthesize the at least one target compound.

16. The method according to claim 1, wherein the plurality of known chemical reactions and the plurality of computationally generated chemical reactions are disjoint sets.

17. The method according to claim 1, wherein the first one or more sets of the chemical reactions are a reaction database.

18. The method according to claim 1, wherein the trained classifier is based on a vector of reactions related to a particular transformation.

19. A method performed by a computer, comprising: training, by the computer, one or more machine learning classifiers based on a portion of a plurality of known chemical reactions; determining, by the computer, one or more known chemical reactions that result in a target compound based on the plurality of known chemical reactions; determining, by the computer, one or more predicted chemical reactions that result in the target compound based on a chemical reaction transformation, wherein the one or more predicted chemical reactions are predicted to succeed by the one or more machine learning classifiers; determining, by the computer, a plurality of chemical synthesis routes in a retrosynthetic manner, each chemical synthesis route resulting in the target compound and at least one chemical synthesis route including at least one of the one or more known chemical reactions and at least one of the one or more predicted chemical reactions; determining, by the computer, an optimal chemical synthesis route from the plurality of chemical synthesis routes based on a predetermined number of reactions and a cost function; A method comprising: outputting the optimal chemical synthesis route for the synthesis of the target compound by executing the optimal chemical synthesis route. Claim 20 The method according to claim 19, wherein the plurality of known chemical reactions are derived from one or more of a chemical reaction database, an estimated yield, or a predicted yield of the one or more chemical reactions. Claim 21 Training one or more machine learning classifiers based on a portion of the plurality of known chemical reactions, Receiving a dataset comprising one or more chemical reactions based on one or more chemical transformations, each of the one or more chemical reactions comprising at least one reactant, each reactant comprising one or more atoms; For each reactant, classifying the one or more atoms into categories based on neighboring atoms, bond order, and / or the number of hydrogen atoms present; For each reactant, determining a vector based on a histogram of the categories; Determining a training dataset consisting of a) vectors of reactions related to a particular transformation and b) vectors of reactions related to the particular transformation but resulting in products of different reaction types; Exposing a portion of the training dataset to the classifier to train the classifier; Exposing another portion of the training dataset to the trained classifier to test the trained classifier, the method according to claim 19. Claim 22 Exposing another portion of the training dataset to the trained classifier to test the trained classifier includes evaluating the performance of the trained classifier based on one or more measurement criteria, the method according to claim 21. Claim 23 The method according to claim 22, wherein the one or more measurement criteria include one or more of accuracy, positive precision, negative precision, positive sensitivity, or negative sensitivity.

Images