Methods for determining target functional compounds, including target biodegradability

Abstract

The present invention relates to a method for determining a synthetic specification including a target biodegradability. A target biodegradability indicating a biodegradation characteristic of a functional compound is provided. A digital representation of a potential target synthetic specification is provided. A habitat is provided indicating habitat descriptor values ​​for habitat descriptors. A habitat-based model adapted to determine the biodegradability of the functional compound in the habitat is provided. The biodegradability of the potential target functional compound is determined based on the provided model and digital representation. The determined biodegradability is then compared to the target biodegradability and either i) the potential target functional compound is determined as the target functional compound, or ii) a new potential target synthetic specification for the potential target functional compound is provided and the determination of biodegradability is repeated using the new potential target synthetic specification.

Description

[Technical Field]

[0001] FIELD OF THE INVENTION The present invention relates to a method, an apparatus, and a computer program product for determining a target functional compound, including a target biodegradability. Furthermore, the present invention relates to a training method, a training apparatus, and a training computer program for training a data-driven biodegradation model that can be used by the method, the apparatus, and the computer program product for determining a target functional compound. Furthermore, the present invention relates to a method and an apparatus for providing an interface for providing a target functional compound. [Background technology]

[0002] Background of the Invention Functional compounds, generally referring to small molecules, are widely used in industrial products and / or everyday items due to their wide range of application properties. Uses of functional compounds include, among others, excipients, plasticizers, stabilizers, inhibitors, odorants, fragrances, nutrients, catalysts, radiation absorbers, lubricants, and surfactants. However, this widespread application also results in a large amount of waste containing the functional compounds used. Non-degradable waste poses problems when disposed of in undesignated environments. In particular, the accumulation of chemicals in the environment, such as the accumulation of phosphates that leads to algae blooms, is undesirable. Therefore, there is not only a need for functional compounds that degrade, but also a need to consider knowledge of the biodegradability of functional compounds at an early stage of the product design process. In particular, it would be advantageous to be able to predict functional compounds that provide specific biodegradability and are suitable for the intended application already during the design process. Therefore, it would be advantageous to provide a possibility to predict functional compounds, including biodegradability, suitable for an application in an accurate and computationally inexpensive manner. Summary of the Invention [Problem to be solved by the invention]

[0003] Summary of the Invention It is an object of the present invention to provide a method, an apparatus, and a computer program product that allows for accurate determination and allows for determination of target functional compounds, including target biodegradability, with low computational cost. It is also an object of the present invention to provide a training method, a training apparatus, and a computer program product that can be used in the method, the apparatus, and the computer program product and that can provide a biodegradation model that can be trained to provide good determination accuracy by utilizing fewer computational resources. [Means for solving the problem]

[0004] In a first aspect of the present invention, a computer-implemented method for determining a target functional compound comprising a target biodegradability is provided, the method comprising: a) providing a target biodegradability, the biodegradability indicating a biodegradation characteristic of the functional compound; b) providing a digital representation of a potential target functional compound; c) providing biodegradation habitats, the biodegradation habitats indicating habitat descriptor values ​​of habitat descriptors that affect the biodegradation of the functional compound in each habitat, the habitat descriptors indicating environmental characteristics of the habitat; and d) providing a biodegradation model based on the provided biodegradation habitats, the biodegradation model indicating the biodegradation of the functional compound in each biodegradation habitat. a digital representation of the functional compound, the digital representation being adapted to determine the biodegradability of the functional compound provided thereto, wherein the biodegradation model is a data-driven model parameterized for a biodegradation habitat such that the biodegradation model determines the biodegradability of the functional compound based on the digital representation of the functional compound; e) determining the biodegradability of the potential target functional compound based on the provided biodegradation model and the digital representation; and f) comparing the determined biodegradability of the potential target functional compound with a target biodegradability, and based on the comparison, i) determining the potential target functional compound as the target functional compound, or ii) providing a new potential target functional compound and repeating the determination of biodegradability using the new potential target functional compound.

[0005] Because the biodegradation model is specifically tailored to determine the biodegradability of potential target functional compounds for specific biodegradation habitats characterized by respective habitat descriptor values ​​that affect the biodegradability of the functional compound in each habitat, the biodegradability of functional compounds, particularly potential target functional compounds, for each habitat can be determined with great accuracy. Furthermore, because the biodegradation model is specifically trained for one or more specific biodegradation habitats, less training data is required, making the biodegradation model more flexible for determining the biodegradability of new functional compounds that are not part of the training dataset. In this manner, accurate determination of the biodegradability of potential target functional compounds is provided in a computationally inexpensive manner. Because the determination of target functional compounds is based on accurate and computationally inexpensive determination of biodegradability, the method also enables accurate and computationally inexpensive determination of target synthesis specifications that represent target functional compounds containing respective target biodegradability. Furthermore, whereas currently utilized testing methods for testing the biodegradability of functional compounds are very time-consuming and can take months or years to obtain results, the above-described method allows for essentially immediate provision of results, particularly for potentially suitable functional compounds. Thus, not only can the technical requirements for determining biodegradability be reduced, but also the time required to design new biodegradable products can be significantly shortened. Furthermore, by providing an easy possibility to take into account the accurate determination of biodegradability already during the product design process, it is possible to design products in such a way that waste can be avoided. In particular, it can be ensured that the functional compounds used in the products will biodegrade in the respective expected environment, for example, the marine habitat.

[0006] The development of new chemical products tailored to application requirements is a major challenge in the modern chemical industry. In recent years, additional requirements have arisen regarding the environmental impact of chemical products along their life cycle. One important aspect of environmental impact is the prevention of chemical accumulation in the environment and bioaccumulation. Chemical accumulation is an increasing problem and can be avoided if functional compounds are biodegradable. Bioaccumulation, the gradual accumulation of compounds in living organisms, can be avoided if functional compounds are biodegradable. A series of standardized tests are currently used to evaluate biodegradation. Various biodegradation tests exist using specific conditions (e.g., ISO 13432, ISO 14852, ISO 14855, ISO 17556, and OECD 301). Standardized tests often balance time-efficient testing (as short as 14 days and as long as 24 months) with real-life conditions. In fact, to speed up testing, temperatures higher than those in real-life conditions are often used. Companies developing new functional compounds must invest significant resources in self-assessment and certification of their product sustainability. The entire biodegradability evaluation, including laboratory space and equipment, is costly and time-consuming. Therefore, it is necessary to identify the biodegradability of new materials early in the development process. The proposed method for determining biodegradability as disclosed herein enables new materials to be developed more quickly and efficiently. Biodegradability can be determined at an early stage, even before the functional compound is synthesized. This makes it possible to determine whether the functional compound is suitable for market launch, which leads to a shorter time to market. This also allows for reduced waste generation, since there is no need to synthesize the functional compound to determine its application performance. The proposed method provides a digital twin of the measurement of the biodegradability of the functional compound.

[0007] Furthermore, standard measurements and tests of biodegradability are often time-consuming, including waiting times of up to several months or even years. Particularly when developing new functional compounds for each application, such time-consuming tests can severely limit the development process. In this regard, the present invention makes it possible to provide results for new functional compounds immediately, significantly reducing the time after which the results are available.

[0008] Furthermore, because the number of potentially suitable functional compounds for a particular application is enormous, and many of them are often not fully researched, technical product engineers today are given the technical task of finding functional compounds that are not only suitable for a particular application but also satisfy the respective target properties. In particular, to find each functional compound that may be suitable for the application, they must synthesize and test a huge number of possible functional compounds or search through vast data sets and libraries in which potential functional compounds are stored. Even when using sophisticated experimental design, it is still necessary to synthesize and experimentally test a very large number of possible functional compounds. In this regard, the above-described method can help users, such as technical product engineers, to automatically and much more quickly find potentially suitable functional compounds. In particular, by using the above-described method, users only need to synthesize and test potentially suitable functional compounds that are determined to be highly likely to satisfy the respective target properties, in particular the target biodegradability. Therefore, unnecessary synthesis and testing of functional compounds can be avoided. Therefore, the method allows users to quickly and more efficiently perform the technical task of finding functional compounds suitable for a technical application.

[0009] The method refers to a computer-implemented method and therefore may be performed by a general or specialized computer adapted to perform the method, for example, by executing a respective computer program. The method is adapted to determine target functional compounds, including target biodegradability.

[0010] In general, a biodegradable functional compound refers to a functional compound that can be decomposed by biological processes. In particular, a biodegradable functional compound can refer to a functional compound that can be assimilated by bacteria and / or fungi to produce an environmentally friendly product, i.e., decomposed into non-polluting residues. Generally, biodegradability refers to the biodegradation properties of a functional compound. In particular, biodegradability refers to a measure of the degradation, or decomposition, of a functional compound caused by a biological process, i.e., a process involving biological materials, particularly microorganisms, involved in the degradation process. Therefore, biodegradability does not refer to a purely chemical decomposition process that does not involve microbial activity. Biodegradability is an intrinsic property of a functional compound. In this context, the intrinsic property of a functional compound refers to a property of a functional compound that is caused by and therefore reflects the properties of the functional compound, i.e., its structure, composition, etc., in relation to a particular context. In particular, biodegradability reflects the properties of a functional compound when present in a particular biologically active environment. Target biodegradability can refer to any quantification of the biodegradability of a functional compound. For example, the target biodegradability may refer to only one value, such as the half-life of the functional compound in a respective habitat, or may refer to more than one value, such as the degradation function of the functional compound over time in a particular habitat. Preferably, the target biodegradability of a functional compound refers to any one of the functional compound's mineralization properties, biotransformation properties, and / or degradation half-life. Preferably, the target biodegradability is provided in the form of a percentage value of biodegradation after a predetermined time frame.

[0011] Biodegradable compounds can be designed to break down through the action of living organisms upon disposal. Biodegradability can relate to the environmental fate and / or behavior of a compound. Biodegradability can relate to the extent to which a compound can be broken down by microorganisms such as bacteria, fungi, or algae. Biodegradability can depend on physical factors such as chemical structure, molecular weight, crosslink density, branching, crystallinity, or solubility, as well as the component composition of the compound in the exposure conditions, such as the habitat, such as soil, compost, or aquatic systems. With respect to the exposure conditions, the microorganism, the substrate characteristics, such as nutrient concentration, temperature, pH, pO2, ionic conditions, or toxicity, affect biodegradability. Biodegradability can be measured based on measured mass loss (mg / hour), dissolved organic carbon (organic carbon concentration / hour, DOC), oxygen consumption (e.g., by pressure measurement, e.g., Pa / hour), or carbon dioxide production over time (e.g., by pressure measurement, e.g., Pa / hour).

[0012] Many measurement standards have been developed to quantify biodegradability in terms of measured properties of compounds. Various measurement methods have been defined to determine biodegradability under predefined laboratory conditions. For example, the "Ready biodegradability" (July 17, 1992) for wastewater OECD test No. 301 describes six methods for determining biodegradability. Furthermore, ASTM D5988-18, "Standard test method for determining aerobic biodegradation of plastic materials in soil," describes the measurement of carbon dioxide evolved by microorganisms as a function of exposure time, thus determining the degree of biodegradability compared to a reference material. Furthermore, ISO 17556:2019, "Plastics—Determination of the ultimate aerobic biodegradability of plastic materials in soil by monitoring the oxygen demand in a respirometer or the amount of carbon dioxide evolved," determines the optimal rate of biodegradation of plastic materials in test soil by controlling the oxygen consumption or carbon dioxide production.Further, for example, ISO 14855-1:2012, "Determination of the ultimate aerobic biodegradability of plastic materials under controlled composting conditions—method by analysis of evolved carbon dioxide—Part 1: General method," and ASTM D5338-15, "Standard test method for determining aerobic biodegradation of plastic materials under controlled composting conditions, incorporating thermophilic temperatures," determine the ultimate aerobic biodegradability (the complete decomposition of chemicals or organic materials by microorganisms in the presence of oxygen) of organic-based plastics under controlled composting conditions by measuring the percentage of carbon converted to carbon dioxide and the degree of decomposition of the plastic at the end of the test. ASTM D6400-21, "Standard specification for labeling of plastics designed to be aerobically composted in municipal or industrial facilities," additionally includes elemental analysis, plant germination (phytotoxicity), and mesh filtration of the resulting particles. ISO 17088:2021 "Plastics - Organic recycling - Specifications for compostable plastics" includes an assessment of the negative consequences for the composting process and equipment, and the adverse effects on the quality of the resulting compost, including the presence of high levels of restricted metals and other harmful elements.

[0013] For aerobic biodegradation, ISO 18830:2016 "Plastics - Determination of aerobic biodegradation of non-floating plastic materials in a seawater / sandy sediment interface - Method by measuring the oxygen demand in a closed respirometer" and ISO 19679:2020 "Plastics - Determination of aerobic biodegradation of non-floating plastic materials in a seawater / sediment interface - Method by analysis of evolved carbon dioxide" have been developed. Biodegradation assessment is measured by oxygen demand or CO2 evolution. Further standards include, for example, ISO 14853:2016 "Plastics - Determination of the ultimate anaerobic biodegradation of plastic materials in an aqueous system - Method by measurement of biogas production", ISO 23977-1:2020 "Plastics - Determination of the aerobic biodegradation of plastic materials exposed to seawater - Part 1: Method by analysis of evolved carbon dioxide", and ISO 23977-2:2020 "Plastics - Determination of the aerobic biodegradation of plastic materials exposed to seawater - Part 2: Method by measuring the oxygen demand in a closed respirometer".

[0014] The biodegradation properties quantified for a compound may depend on the measurement method and conditions used, the measurement environment, and measurements related to the degradation process, such as mass loss, DOC, oxygen consumption, or carbon dioxide production over time. The measurement method and measured properties may be provided as metadata for each measurement point related to biodegradability.

[0015] Generally, functional compounds can be any functional compound. Functional compounds generally have application properties for technical purposes, i.e., perform a function in chemical products. For example, a compound that provides UV protection in a sunscreen is a functional compound. Functional compounds can include active ingredients, i.e., components that provide the functionality of the functional compound. Additionally, active ingredients can provide the biological activity of the functional compound. For example, functional compounds can refer to antifungal agents, fragrance chemicals, UV absorbers, food additives, vitamins, nutrients, dyes, and surfactants. Functional compounds are generally characterized by their chemical structure. However, different chemical structures can also exist within a single functional compound. For example, functional compounds can be composed of building blocks that are molecules that undergo tautomerization, protonation, or deprotonation. Functional compounds can be composed of two or more stereoisomers. Thus, a functional compound composed of one type of molecule can be associated with one or more chemical structures, e.g., one protonated structure and one uncharged structure, and / or two stereoisomers. Thus, in general, a functional compound may include all molecules related to a single chemical formula through isomerization, such as (de)protonation, tautomerization, and stereoisomerism. Furthermore, a functional compound may refer to any functional compound that can be described by one or more chemical structures. In one embodiment, the chemical structures may be related to a single chemical formula.

[0016] Preferably, the functional compound is composed of small molecules. Preferably, the functional compound has a molecular mass of less than 10,000 g / mol. More preferably, the compound has a molecular weight of less than 800 g / mol, and even more preferably less than 400 g / mol. Furthermore, the functional compound preferably exists in the environment in a form that allows the molecule of the functional compound to be completely described using a simple structural formula containing relevant information. A simple molecular structure refers to a molecule that can be clearly described by the covalent bonds between the atoms of the molecule. Examples of cases where this is not the case are systems that have a dynamic equilibrium between several forms, such as monomers and oligomers, as in the case of some inorganic acids, or ionic species with highly localized charges that interact strongly with the solvent, for example, via hydrogen bonds. Preferably, the functional compound has at least one of the following properties: having an effect on an organism, being suitable for influencing the structure, or being suitable for influencing the function of an organism. In one embodiment, the functional compound comprises at least one of the following functional groups: ether group, hydroxyl group, peroxo group, hydroperoxide group, carboxyl group, carboxyl group derivative, carbonyl group, amine group, imine group, hydrazine group, urea group, urethane group, thiourethane group, nitrile group, azide group, azo group, cyanate group, isocyanate group, isocyanide group, pyridine group, alkane group, alkene group, alkyne group, phenyl group, ketone group, thioketone group, aldehyde group, thioaldehyde group, acetal group, ketal group, oxime group, hydrazone group, nitro group, nitroso group, thiol group, sulfide group, disulfide group, sulfonic acid derivative, sulfinic acid derivative, sulfate group, sulfate group derivative, sulfone group, sulfoxide group, sulfhydryl group, sulfide group, phosphorane group, phosphate group, phosphate derivative. phosphonates, phosphine groups, silane groups, silazane groups, silicone groups, borate groups, borane groups, halide groups, or combinations thereof. Preferably, the functional compound corresponds to one of the following compound classes: carboxyl group derivatives, ether groups, amine groups, hydroxy groups, carbonyl groups, alkane groups, alkene groups, benzene derivatives, pyridine derivatives, halide groups.

[0017] In a first step, the method includes providing a target biodegradability indicating the biodegradation characteristics of the functional compound. In particular, providing may refer to, for example, receiving the target biodegradability from a user's input using a respective input unit. Furthermore, providing may also refer to accessing a storage unit in which the target biodegradability is already stored. Furthermore, providing may also include, for example, receiving the target biodegradability from another source via a network connection and providing the received biodegradability. Generally, the target biodegradability may refer to a single target value, such as the target half-life of the functional compound in a particular habitat, or may refer to a range of values ​​that the functional compound should meet in a particular habitat. Furthermore, the target biodegradability may also refer to any type of target function, such as the time sequence of biodegradation. For example, the target biodegradability may indicate that the target functional compound should have a first range of biodegradability values ​​during a first time range, and then a second range of target biodegradability values ​​during a subsequent time range. Such more complex target biodegradability may be advantageous when it is desired that the functional compound not biodegrade in a particular habitat for some time, e.g., the average use time of the functional compound, and then rapidly biodegrade in the same or another habitat.

[0018] The method includes providing a digital representation of a potential target functional compound. In particular, providing may refer to receiving the digital representation from a user input, for example, using a respective input unit. Furthermore, providing may refer to accessing a storage unit in which the digital representation is already stored. The digital representation of the functional compound may be any representation that defines the functional compound and / or provides information that allows deriving respective characterization parameters, for example physicochemical properties of the functional compound. Preferably, the digital representation includes indications for the characterization parameters that refer to the chemical structure of the functional compound. Based on the digital representation, physicochemical properties may optionally be derived and used.

[0019] In a preferred embodiment, the digital representation is a chemical structure and / or synthesis specification for the functional compound. As mentioned above, the functional compound may also include two or more chemical structures. In this case, the digital representation preferably provides a chemical structure associated with and / or indicating one or more structural formulas and the quantitative ratio of the two or more structural formulas present in the functional compound. Preferably, the at least two structural formulas provided by the digital representation for the functional compound correspond to related structural formulas through chemical equilibrium. Generally, the synthesis specification includes instructions on how to produce a particular related functional compound. For example, the synthesis specification, if applicable, may refer to ingredients, starting products, and / or manufacturing conditions that result in the synthesis of the functional compound in a manufacturing process. Thus, the synthesis specification is always associated with the functional compound produced when the synthesis specification is executed, for example, using suitable laboratory or industrial equipment. In particular, the synthesis specification may be considered a recipe for how to produce the related functional compound. Furthermore, if at least one synthesis specification is known for the functional compound, it is preferable to provide the synthesis specification as part of the digital representation. However, in some cases, the target functional compound is first determined, and then the synthesis specification for the target functional compound is determined. This method can be particularly applied to potential target compounds for which the synthetic specifications are not yet known.

[0020] Because the structural formula of a functional compound can be influenced by its environment, it is preferable that the chemical structure provided by the digital representation be environment-dependent. For example, in an aqueous medium, a particular molecule may tend to exist in a protonated form with a 1:3 unprotonated to protonated ratio. In this case, a digital representation of such a molecule using a single chemical structure may not be sufficient. Such a molecule may be represented by a digital representation that includes a quantitative ratio indicating the equilibrium between different structures associated with a single chemical formula, where two or more structures are in chemical equilibrium. The digital representation may be referred to as a statistical representation because it incorporates the statistical frequency of molecules associated with each structure. To outline the concept, an example equilibrium for morpholine and one of its protonated structures is illustrated by morpholine + H (25%) ⇔ protonated morpholine (75%). Both morpholine and protonated morpholine may be the result of introducing morpholine to water at a specific pH value that favors protonated morpholine; for example, the ratio may be 1:3 protonated morpholine to morpholine. Thus, a digital representation of introducing morpholine into water can refer to a structural specification of morpholine and protonated morpholine, including the respective amounts or ratios of amounts of two or more structural formulae present in the functional compound. An example of a chemical structure specification can be the number and type of atoms and their respective connectivity. Another example includes using SMILES and / or SMARTS to represent the chemical structure of the functional compound.

[0021] Furthermore, the digital representation can also be a chemical graph of the functional compound. A chemical graph is a representation of the structural formula of a compound from the perspective of graph theory. For example, a chemical graph can be a labeled graph whose vertices correspond to atoms of the compound and whose edges correspond to chemical bonds. The digital representation can then refer to a graph in which the atoms of the molecule are the nodes and the atomic bonds of the molecule are the edges of the graph.

[0022] Preferably, the digital representation includes characterization parameters, in particular physicochemical properties of the potential target functional compound. In particular, the physicochemical properties of the functional compound can be quantified by the physicochemical parameters. Preferably, the digital representation directly includes the physicochemical parameters, preferably with reference to a descriptor. In particular, the physicochemical parameters refer to parameters that quantify the physicochemical properties of the functional compound. In this context, the term "physicochemical properties" refers to the physical and / or chemical properties of the functional compound. However, the digital representation can also be provided to enable deriving the physicochemical properties, for example, in the form of a descriptor, for example, by providing a representation of potential target synthetic specifications, where the respective physicochemical properties are already stored or can be determined, for example, by calculation of the respective descriptor. Preferably, the digital representation refers to at least one of the synthetic specifications, structural formula, brand name, IUPAC name, chemical identifier, and CAS number of the functional compound.

[0023] The potential target synthetic specification may also be considered as a starting synthetic specification indicating for which functional compound or in which region of the potential functional compound space biodegradability should first be determined in a search for synthetic specifications that will result in functional compounds having a target biodegradability. Generally, the digital representation of the potential target synthetic specification may be provided by a user or automatically, e.g., according to predetermined rules or arbitrarily. For example, a user may select a promising potential target synthetic specification as a starting point. However, any target synthetic specification may also be used, or a set of rules may be used to provide potential target synthetic specifications without user intervention. Preferably, the potential target synthetic specification is provided based on rules that take into account constraints on the potential target synthetic specification space, i.e., the target functional compound space.

[0024] Preferably, the physicochemical parameters refer to at least one of the following: compositional descriptors, count descriptors, lists of structural fragments, fingerprints, graph invariants, 3D descriptors, and / or higher-dimensional descriptors, which represent parameters quantifying the physicochemical properties of the functional compound. In a preferred embodiment, the descriptors refer to 3D descriptors, in particular quantum chemical descriptors. Furthermore, the inventors have found that molar mass in particular describes the biodegradation of functional compounds very accurately. Therefore, it is particularly preferred that the physicochemical parameters include the molar mass of the functional compound. Possible physicochemical parameters are defined in more detail below.

[0025] The constituent descriptors may refer to any of the following: potential, molecular weight, charge, spin, boiling point, melting point, enthalpy of fusion, dissociation constant, Hansen parameters, protic, polar and dispersive contributions, Abraham parameters, retention index, total polar surface area, acceptor binding constant, Michaelis-Menten constant, inhibitor constant, mutagenicity, LD50, bioconcentration, toxicity, biodegradation profile and viscosity.

[0026] The count descriptor may refer to any of the following: sum of atomic electronegativities, sum of atomic polarizabilities, number of atoms and non-hydrogen atoms, number of H, B, C, N, O, P, S, Hal, and heavy atoms, number of hydrogen donor and hydrogen acceptor atoms, number of bonds, number of non-hydrogen or multiple bonds, number of double, triple, and aromatic bonds, number of functional groups, functional group ratio, sum of bond orders, aromatic ratio, number of rings or cycles, number of unpaired electrons, number of rotatable bonds, rotatable bond fraction, and number of conformers.

[0027] The physicochemical parameters referring to a list of structural fragment descriptors may refer to at least one of a list of molecular fractions, a list of functional groups, a list of bonds, and a list of atoms. The fingerprint descriptors preferably include at least one of a MACCS key, preferably in bit format or total amount format, a Morgan fingerprint and other circular fingerprints, preferably in bit format or total amount format, a topological twist, an atom pair, an infrared spectrum and related spectra, a fingerprint number, a PubChem fingerprint, a substructure fingerprint, and a Klekota-Roth fingerprint. The graph invariance / topology index descriptors preferably include at least one of a topostructural index and a topochemical index. Furthermore, molecular graph representations can be used as descriptors.

[0028] In a preferred embodiment, the physicochemical parameters of the functional compounds are 3D descriptors comprising at least one of the following: molecular volume, average volume per atom, molecular area, area as average per atom, solvent accessible surface, dispersion energy, dielectric energy, H donors, H acceptors, polar and non-polar surface areas, atomically resolved H donors, H acceptors, polar and non-polar surface areas, shape, sphericity, dipole and higher order electric moments, polarizability, dielectric energy, proticity, polar and non-polar surface areas, orbital energies and orbital gaps, ionization energy, electron affinity, hardness, electronegativity, electrophilicity, excitation energy and intensity, infrared and ultraviolet absorption bands, reactivity measurements, redox potential, bond reference points, partial charges, charge surface area, atomic orbital contributions, bond order, atomic radius. In particular, the physicochemical parameters of the functional compounds preferably refer to 3D descriptors comprising at least one of the following: molecular volume, average volume per atom, molecular area, area as average per atom, solvent accessible surface, dispersion energy, dielectric energy, H donors, H acceptors, polar and / or non-polar surface area, atomically resolved H donors, H acceptors, polar and / or non-polar surface area, shape, sphericity, cone angle, polarizability, dielectric energy, proticity, polar and / or non-polar surface area, excitation energy and intensity, infrared and / or UV absorption bands, reactivity measurements, particle charge and / or charge surface area. Preferably, the high-dimensional descriptors utilized may include at least one of the following: configurational partition function, solubility, vapor pressure, activity coefficient, diffusion coefficient, partition coefficient, surface activity, rotational constant, moment of inertia, radius of gyration, density, viscosity, conformer-weighted volume and area, conformer-weighted H donor, H acceptor, proticity, polar and / or non-polar surface area, charge distribution, configurational dipole moment, molecular refraction. Preferably, high-dimensional descriptors utilized include at least one of the following: solubility, vapor pressure and activity coefficient, surface activity, conformer-weighted H donor, H acceptor, proticity, polar and non-polar surface area, and charge distribution.

[0029] The physicochemical parameters of the functional compounds can be encoded in a molecular graph representation, e.g., a molecular fingerprint such as an extended connectivity fingerprint, one-hot encoding, word embedding, or graph-level embedding. For example, a machine learning feature model can be utilized to generate a predetermined molecular fingerprint comprising a predetermined amount of characterization parameters. Such a machine learning model can be trained using a respective molecular database, either supervised or unsupervised. Preferably, a graph neural network is utilized as the feature model. Preferably, the molecular graph representation reflects similarities in the properties of the functional compounds. In one embodiment, the machine learning-based feature model can be utilized as part of a biodegradation model to determine respective molecular graph representations from the digital representations of the functional compounds, which can then be utilized as input to a second machine learning model as part of the biodegradation model to determine biodegradation based on the molecular graph representations.

[0030] The method further includes providing a biodegradation habitat, where the biodegradation habitat indicates a habitat descriptor value of a habitat descriptor that affects the biodegradation of the functional compound in the respective habitat. In particular, providing may refer to receiving the biodegradation habitat from a user's input, for example, using a respective input unit. Furthermore, providing may also refer to accessing a storage unit in which the biodegradation habitat is already stored. Furthermore, providing may also refer to pre-configuring the biodegradation habitat. For example, if the method is used in a very specific situation in which only one specific biodegradation habitat is sensible, the respective biodegradation habitat can be pre-configured and does not need to be provided as a specific input. Furthermore, providing may also include directly receiving the habitat descriptor value of the habitat descriptor from another source, for example, via a network connection, and providing the received habitat descriptor value of the habitat descriptor as the biodegradation habitat. The provided biodegradation habitat may refer to a general habitat, for example, a marine habitat, and then the respective habitat descriptor value of the habitat descriptor for this habitat is already stored on the respective storage, where it can be accessed. However, the provided biodegradation habitat may also directly include respective habitat descriptor values ​​of the biodegradation habitat to provide further specification of the biodegradation habitat. Furthermore, providing the biodegradation habitat may include providing a digital representation of the biodegradation habitat, which may then indicate respective habitat descriptor values ​​of habitat descriptors that affect the biodegradability of the functional compound in each habitat. In a further preferred embodiment, the habitat is derived from a digital representation of a potential target composite specification. For example, a biodegradation habitat may be indicated by the aggregation of each potential target functional compound under normal conditions.

[0031] In general, habitat descriptors indicate the environmental characteristics of a habitat. In particular, the environmental characteristics of a biodegradation habitat can affect biological activity in the respective habitat, for example, the presence, growth, or absence of specific bacteria. Therefore, the environmental characteristics defined by the habitat descriptors also indirectly affect the biodegradation of functional compounds in the respective habitat. For example, if a functional compound is biodegradable by specific bacteria that require a specific salt concentration, the functional compound will biodegrade quickly in a habitat that provides such a salt concentration, such as a marine habitat, but will biodegrade much more slowly in a habitat that does not have the appropriate salt concentration, such as wastewater.

[0032] Preferably, the biodegradation habitat refers to any one of a marine habitat, a wastewater habitat, a calcareous habitat, a compost habitat, or a soil habitat. In a preferred embodiment, the biodegradation habitat refers to a marine habitat, and the habitat descriptor refers to at least one of salinity, sedimentation type, oxygen level, location, sample depth, water temperature, nutrient concentration, pH value, environment type, and microbial community. In a more preferred embodiment, the biodegradation habitat refers to a lake habitat, and the habitat descriptor refers to at least one of salinity, sedimentation type, oxygen level, location, sample depth, water temperature, nutrient concentration, pH value, environment type, and microbial community. In a particularly preferred embodiment, the biodegradation habitat refers to wastewater, and the habitat descriptor refers to at least one of water temperature, microbial community, sludge concentration, nutrient concentration, pH value, test duration, and enzyme environment. Preferably, in the case of a wastewater habitat, the biodegradability model is trained based on biodegradability determined using standard tests determined by the OECD 301 and OECD 302 norms. Furthermore, the habitat descriptor values ​​of this habitat preferably refer to habitat descriptor values ​​determined by the OECD 301 and OECD 302 norms. In a more preferred embodiment, the biodegradation habitat refers to soil, and the habitat descriptors refer to at least one of temperature, sand content, pH value, moisture content, nutrient concentration, microbial community, and enzyme environment. In a more preferred embodiment, the biodegradation habitat refers to compost, and the habitat descriptors refer to at least one of temperature, compost activity, pH value, moisture content, humidity, compost maturity, compost composition, compost origin, nutrient concentration, microbial community, and enzyme environment. In the case of marine habitats, the following parameters may affect biodegradation: salinity, sediment, water temperature, bacterial culture, etc. In some examples, the marine habitat descriptors may be stored in a database together with geolocation. Generally, habitat can also refer to the habitat of the standard test utilized to determine the biodegradability of the functional compound. For example, standard tests such as those defined by ISO 13432, ISO 14852, ISO 14855, ISO 17556, OECD 301, and OECD 302 also define the specific habitat in which biodegradation occurs.Thus, providing a biodegradation habitat can also include providing one of the standard tests, e.g., selecting it via user input, in which case the habitat descriptor refers to the test, i.e., the test environment, and thus to a particular characteristic of the test habitat. Furthermore, the habitat can also be defined by the biodegradation of a reference functional compound or other reference chemical. In this case, the habitat can be provided by providing the reference and its biodegradation. In this case, the reference and its biodegradation represent the habitat descriptor.

[0033] The method further includes providing a biodegradation model based on the provided biodegradation habitat. In particular, providing a biodegradation model preferably refers to selecting a biodegradation model based on the provided biodegradation habitat. For example, multiple biodegradation models may be stored in the biodegradation storage, each trained for one or more different biodegradation habitats. Preferably, each biodegradation model is trained specifically for a different value or range of values ​​of the habitat descriptor values ​​of the biodegradation habitat. Based on the provided biodegradation habitats exhibiting habitat descriptor values, a respective appropriate biodegradation model may then be selected from the multiple biodegradation models. For example, a biodegradation model is appropriate if the exhibited habitat descriptor value is within the range of habitat descriptor values ​​for which the biodegradation model is trained. For example, a respective lookup table may be provided that allows easy comparison between the exhibited habitat descriptor value and the range of descriptor values ​​for which the biodegradation model stored in the storage is trained, so that an appropriate biodegradation model can be directly selected. However, in another embodiment, providing a biodegradation model based on the provided biodegradation habitat may also refer to user selection of a biodegradation model. For example, the user may be provided with a preselection of biodegradation models that refer to the provided biodegradation habitats, and then be allowed to select the respective biodegradation model to be used. Generally, possible stored biodegradation models refer to biodegradation models that have already been parameterized based on respective training data sets for one or more habitats. Since the training data sets used to parameterize the biodegradation models are historical data, as will be described in more detail below, the biodegradation models can be trained, and thus generated, and stored in the respective databases at any time before and after determining the specific biodegradability of a specific functional compound. However, training, and therefore generation of a biodegradation model, can also, of course, be performed when it is determined that a specific biodegradation model for a specific habitat is needed.

[0034] The biodegradation model can be parameterized based on a training dataset that includes measured biodegradation in each habitat associated with each formulation in the training dataset. The measured biodegradation can be measured for each habitat using a predetermined biodegradation test method, such as any of the test methods described above. Thus, the biodegradation model represents the measured biodegradability of the training formulations.

[0035] The provided biodegradation model is then adapted to determine the biodegradability of the functional compound in each biodegradation habitat. In particular, the biodegradation model is a data-driven model parameterized for the biodegradation habitat to determine the biodegradability of the functional compound based on the digital representation. Preferably, the biodegradation model is trained to determine biodegradation based on the characterization parameters of the functional compound indicated by the digital representation. Additionally or alternatively, the biodegradation model can be trained to determine biodegradation based on the chemical structure, preferably based on the chemical formula and amount of two or more structural formulas present in the functional compound, or the ratio of each chemical formula, as described above. The term "to" here should be interpreted as meaning that when the physicochemical parameters of the functional compound are provided as input, the parameterization adapts the biodegradation model, thereby enabling the biodegradation model to provide biodegradability for the habitat. For example, the biodegradation model relates the physicochemical parameters of the functional compound to biodegradability for the past digital representation of the functional compound and the past digital representation of the habitat. This allows the digital representation of the functional compound to be determined based on the target biodegradability. The term "data-driven" is used herein to emphasize that the model is primarily based on respective data inputs and not, for example, on intuition, personal experience, or knowledge. Preferably, the biodegradation model refers to a machine learning-based model based on known machine learning algorithms, such as neural networks, regression models, classification algorithms, etc. Regression models based on neural networks, linear regression, random forests, boosted trees, lasso, ridge regression, and MARS algorithms, among others, are suitable for most applications in this regard, while random forests, logistic regression, and SVM algorithms, among others, have been found to be suitable for classification models. Generally, the biodegradation model is parameterized during a training process in which a digital representation of a functional compound, or one or more characterization parameters and / or chemical structures derived from the digital representation, are utilized along with the corresponding biodegradability for a specific biodegradation habitat, as described above.Based on such a training dataset specific to a biodegradation habitat, e.g., a particular habitat descriptor range and / or value, known training methods can be used to determine the respective parameters of the data-driven model such that the biodegradation model can also determine the biodegradability of functional compounds that are not part of the training dataset.

[0036] In one embodiment, the biodegradation model is a two-stage machine learning model including two machine learning algorithms, where the output of the first stage is the input of the second stage, and both machine learning algorithms are trained simultaneously using the same training dataset. Preferably, the first stage is trained to determine one or more characterization parameters from the digital representation, and then the second stage is trained to utilize the one or more characterization parameters to determine biodegradability. In a preferred embodiment, the first stage is based on a graph neural network trained to determine a molecular graph representation, e.g., a molecular fingerprint, of the functional compound as described above based on the digital representation, and the second stage is based on a random forest algorithm to determine the respective biodegradation based on the molecular graph representation and, optionally, habitat descriptors.

[0037] Furthermore, in a preferred embodiment, the biodegradation model can also be adapted to determine the biodegradability of the functional compound further based on habitat descriptor values ​​as input. In particular, the biodegradation model can be trained using a training dataset including: a) a digital representation of the functional compound, preferably including or showing, for example, the functional compound's physicochemical parameters, structural formula, etc.; and b) the associated biodegradability for a specific habitat, as described above, resulting in a biodegradation model that indirectly takes the specific habitat into account. However, the training dataset can also optionally include specific habitat descriptor values ​​for each habitat. In this case, the biodegradation model can be provided with the habitat descriptor values ​​as input in addition to the functional compound and / or derivable characterization parameters as described above, and the biodegradation model can then be trained to determine biodegradability further based on the habitat descriptor values. This has the advantage that biodegradability can be determined even more accurately, especially when biodegradability is strongly dependent on the specific habitat descriptor values ​​of the habitat. For example, in marine habitats, temperature or salinity can vary greatly in different regions of the world, which can lead to different biodegradability for some functional compounds. Therefore, for such cases, it may be advantageous to provide the habitat descriptor values ​​directly as inputs to the biodegradation model. However, instead of providing habitat descriptor values ​​as inputs to the biodegradation model, it is also possible to train two different biodegradation models and indirectly treat different areas as different habitats.

[0038] The method further includes determining the biodegradability of the potential target functional compound based on the provided biodegradation model and digital representation. In particular, as described above, the digital representation of the potential target compound, the amount of chemical formula, and / or characterization parameters provided by or derivable from the digital representation of the functional compound can be provided as input characterization parameters to the biodegradation model. The biodegradation model then provides the biodegradability of the potential target functional compound as an output. If the digital representation does not directly include the respective inputs, e.g., physicochemical parameters, determining the biodegradability can also include first determining the respective inputs, e.g., structural formulas, the amount of two or more structural formulas present in the functional compound, and / or characterization parameters, e.g., as described above. Such determined inputs can then be provided to the biodegradation model.

[0039] The determination of biodegradability using a biodegradation model can be considered a virtual measurement of biodegradability. In particular, the biodegradation model is based on measurement data, e.g., the measured biodegradability of the functional compound used to train the biodegradation model. Thus, the biodegradation model includes information provided by these previous measurements. Furthermore, physicochemical parameters may also refer to measured properties of the functional compound in some cases. Thus, the biodegradability of a new functional compound determined using a biodegradation model can also be considered to be based at least in part on measurement results.

[0040] In the following step, the determined biodegradability of the potential target functional compound is compared with the target biodegradability. Based on the comparison, it is determined whether the potential target functional compound is determined as a target functional compound, in which case the iteration can stop at this point. Furthermore, based on the comparison, it can also be determined to provide a new potential target functional compound and repeat the determination of biodegradability using the new potential target functional compound. In particular, the new potential target functional compound is provided in the form of a new digital representation, as described above. Thus, at this point, an iteration is performed in which the determination of biodegradability using the biodegradation model and the characterization parameters of the potential target functional compound is repeated until one potential target functional compound is determined as a target functional compound. In particular, the comparison can include determining whether the determined biodegradability of the potential target functional compound is within a predetermined range around the target biodegradability, in which case the target can be considered met and the potential target functional compound is determined as a target functional compound. If the determined biodegradability is outside the predetermined range around the target biodegradability, it is determined that the target is not met, and a new potential target functional compound that can meet the target biodegradability is provided.

[0041] In general, the iterations performed may refer to any or directed search of the space of potential target functional compounds. For example, new potential target functional compounds may be simply and arbitrarily selected from a large number of potential target functional compounds generated in silico. However, specific rules for generating new potential target functional compounds may also be applied based on a comparison between the determined biodegradability and potential target functional compounds, with or without considering simultaneous optimization of additional target properties of the functional compounds. In general, known methods for generating new potential target functional compounds and / or new potential target functional compounds may be utilized, for example, data-driven generative models of molecules may be used.

[0042] Then, as described above, iterations can be performed over the steps of determining the biodegradability of the new potential target functional compound by utilizing the digital representations of the biodegradation habitat and the new potential target functional compound. Optionally, for example, determining characterization parameters from the digital representation of the new potential target synthetic specification can also be part of the iterations if the characterization parameters are not already provided in the digital description of the new potential target functional compound. Furthermore, it is preferred that the same biodegradation model be used in all iteration steps to determine biodegradability. However, in some cases, different biodegradation models can also be used in different iteration steps. For example, if other characterization parameters are utilized for the new potential target functional compound, a different biodegradation model may be more appropriate.

[0043] After the iterations stop, for example, after a potential target functional compound has been determined as the target functional compound, or if a new potential target functional compound cannot be selected or generated, the results of the iterations can be provided to the user. For example, if none of the potential target functional compounds meets the target biodegradability, the user can be notified that the target functional compound determination failed. If the target functional compound can be determined, the target functional compound can be provided to the user as output. For example, the determined target functional compound can then be provided to an output unit or a computing unit for further processing. Preferably, providing the target functional compound leads to further processing to determine potential synthetic specifications for the target functional compound. This can be done, for example, by querying a database with stored synthetic specifications or using a data-driven forward synthetic planning tool.

[0044] Preferably, processing the target functional compound includes determining a target synthesis specification, e.g., as described above, and determining control signals for controlling a production process based on the determined target synthesis specification. Preferably, the production process refers to a process for producing the target functional compound utilizing the target synthesis specification. Furthermore, it is preferred that the target synthesis specification references a machine-executable synthesis specification for the target functional compound, such that the control signals can directly reference the control of respective laboratory or process equipment that enables execution of the synthesis specification to produce the functional compound. In one embodiment, providing the target synthesis specification for the target functional compound includes providing control signals adapted to control an industrial plant to produce the target functional compound in accordance with the target synthesis specification.

[0045] In a preferred embodiment, the method further includes providing connectivity information as a digital representation of the functional compound and determining model inputs, e.g., structural formula, characterization parameters, from the connectivity information. In particular, the connectivity information includes information about atoms, chemical bonds between them, and stereochemistry of the functional compound. The method then includes determining the chemical structure, structural formula, and / or characterization parameters from the connectivity information.

[0046] In one embodiment, a target application for the functional compound is further provided, indicating the intended application of the target functional compound, and a biodegradation habitat is provided based on the target application. The target application for the functional compound may indicate the intended application context of the functional compound, for example, if the functional compound is intended for use as an excipient, plasticizer, stabilizer, inhibitor, odorant, fragrance component, nutrient component, catalyst, radiation absorber, lubricant, or surfactant. Such a target application indicates a specific biodegradation habitat. For example, in the case of a pesticide in agricultural applications, it may be interesting to know whether the functional compound will biodegrade in soil. In another example, if the target application indicates the use of the functional compound as a surfactant in personal care products, the functional compound will most likely be found in wastewater sooner or later. Thus, each target application indicates a respective biodegradation habitat. In this regard, a predetermined list may be provided on the storage device in which each target application and its corresponding biodegradation habitat are stored. Target applications for the functional compound may then be provided, for example, by providing a list of target applications to a user and allowing the user to select individual target applications, with each individual target application being connected to one or more biodegradation habitats. A target functional compound can then be determined for each biodegradation habitat to which the target application is connected, or again, the user can select each biodegradation habitat to which the target application is connected. Additionally or alternatively, information indicating the intended end-of-life treatment of the functional compound can be provided. For example, the end-of-life treatment can indicate whether the functional compound is intended to biodegrade in a particular environment or whether it should be subjected to a particular treatment, for example, in a bioreactor. Thus, the intended end-of-life treatment information can also be utilized to determine a biodegradation habitat for the functional compound, as described above.

[0047] In one embodiment, further information indicating the accessible surface area of ​​the functional compound in its intended form is provided, and the biodegradation model is further trained to determine biodegradability based on the accessible surface area, and the method further includes further determining biodegradability based on the accessible surface area. For example, the information may indicate whether the intended product is provided in a solid, crushed, foamed, pelleted, or any other form. Preferably, the information indicates the surface area of ​​the product per mass or the geometric shape of the smallest independent part of the product. Generally, the biodegradability of a functional compound is an intrinsic property of the functional compound, but the precise timing of biodegradation of a product containing a functional compound may also depend, for example, on the surface area accessible by microbial components of the habitat involved in biodegradation. Therefore, further determining biodegradability based on the surface area of ​​a product containing a functional compound allows for more accurate prediction of the biodegradability of the final product, thereby also allowing for more accurate determination of a target functional compound suitable for the final product.

[0048] In one embodiment, target technical application properties of the target functional compound are provided, and potential target functional compounds are provided based on the provided target technical application properties so that the potential target functional compounds satisfy the provided target technical application properties. In particular, the technical application properties may refer to any property of the functional compound and / or a substance at least partially comprising the functional compound, thereby enabling the evaluation of the technical application properties of each functional compound provided after synthesis. Preferably, the technical application properties include at least one of mechanical properties, optical properties, physicochemical properties, chemical properties, and biological properties. Generally, the mechanical properties may refer to any of adhesion, tensile strength, stiffness, hardness, shrinkage, elongation, tear, tear strength, rebound, compressibility, abrasion, leakage, morphology, tactile properties, stress at break, elongation at break, particle size distribution, and packing. Generally, the optical properties may include any of color, turbidity, opacity, gloss, reflection, appearance, absorption, scattering, color intensity, cloud point, matteness, optical density, spectrum, and refractive index. Furthermore, the physicochemical properties may refer to any of density, viscosity, K value, molar weight, dispersity, particle size distribution, solubility, partition coefficient, interfacial properties, surface tension, dispersibility, storage stability, odor, separation, coagulation, electrical conductivity, electrical capacity, surface area, flow time, vapor pressure, VOC, solids content, hygroscopicity, miscibility, thixotropy, phase transition properties, corrosion inhibition, solvent separation, coagulation, impact sensitivity, loss on drying, reaction angle, electrostatic charge, minimum film formation temperature, and charge density. Chemical properties may refer to functional group count, atom type count, functional group density, atom type density, chemical resistance, reaction timing, crystallinity, reaction temperature, reaction pressure, decomposition, thermal decomposition, photolysis, acidity, pK aThe biological properties may include any of the following: pH, moisture / water content, flammability, burning rate, spontaneous combustion, flash point, flammable gas production, response to fire, deflagration rate, by-product production, salinity, heat resistance, oxidizing properties, reducing properties, reactivity, ash content, stability, chelating capacity, calorific value, and saponification value. Furthermore, the biological properties may include any of the following: biodegradability, biological resistance, toxicity, biotransformation, ecotoxicology, sensitization, bacterial count, enzyme activity, environmental distribution, bioaccumulation, and biological exposure. In a preferred embodiment, the technical application property may further refer to biodegradability, e.g., biodegradability in another habitat. For example, a first target biodegradability may refer to a marine habitat, and a second target biodegradability, i.e., the technical application property in this case, may refer to wastewater.

[0049] Then, potential target functional compounds are provided to satisfy the provided target technical application properties. For example, a database in which functional compounds and corresponding technical application properties are already stored can be utilized, and a target functional compound that satisfies the provided target technical application properties can be selected from the database. In general, functional compounds that satisfy the target technical application properties can be considered to form a potential target functional compound space that can be searched during an iterative process to find a target functional compound. Then, a first potential target functional compound can be selected from the selected target functional compounds that satisfy the target technical application properties.

[0050] In one embodiment, providing a new potential target functional compound is based on modifying the provided target application property and providing a new potential target functional compound so that the potential target functional compound satisfies the modified target application property. In particular, if a new potential target functional compound must be provided, comparing the determined biodegradability with the target biodegradability indicates that the determined biodegradability of the current potential target functional compound does not satisfy the target biodegradability. In such cases, a new potential target functional compound can be provided so that the new potential target functional compound still satisfies the target technical application property, if such a respective functional compound exists. However, in many cases, it may be impossible to provide such a new potential target functional compound, or it may not be technically prudent to provide such a new potential target functional compound that still satisfies the target technical application property. In these cases, it may be advantageous to modify the target technical application property, for example, to utilize a less strict target technical application property, such as modifying the target technical application property to refer to a range of values ​​instead of a single specific value, or to refer to a wider range of values ​​if a range of values ​​is referred to. A new potential target functional compound can then be selected or generated to satisfy the modified target application property.

[0051] In one embodiment, providing potential target functional compounds based on the provided target technical application properties includes utilizing a decision model adapted to determine the technical application properties of the functional compounds based on a digital representation of the functional compounds, the decision model being a data-driven model parameterized to determine the technical application properties associated with the functional compounds based on the digital representation including characterization parameters of the functional compounds. The decision model may refer to any known data-driven decision model that enables determining technical application properties based on a digital representation of a functional compound including characterization parameters. In general, the decision model preferably follows the same principles as those described above with respect to the biodegradability model. In fact, the decision model may be based on or utilize the same machine learning algorithm and training method, only using different training data, i.e., training data including another respective technical application property of the functional compounds instead of biodegradability. Thus, all of the embodiments described above with respect to the biodegradation model may also be implemented with respect to a decision model for determining technical application properties. Using such a decision model has the advantage that iterations can be performed not only on the biodegradability of the functional compounds but also on one or more additional technical application properties in a fast and computationally inexpensive manner, thereby resulting in target functional compounds that satisfy not only the target biodegradability but also one or more additional target technical application properties.

[0052] In one embodiment, the method further includes providing a biodegradation test method, where the provided biodegradation test method represents a standardized biodegradation test method for experimentally determining the biodegradability of a chemical substance, and further providing a biodegradation model based on the provided biodegradation test method. Generally, multiple standardized biodegradation test methods exist for testing the biodegradability of chemical substances. For example, such test methods can be found in DIN or ISO standards. Furthermore, by providing a biodegradation test method and a biodegradation model trained using the provided biodegradation test method, it is possible to determine biodegradation by utilizing each test method, for example, that can be easily compared with each measured biodegradation. In particular, in this embodiment, the biodegradation model is preferably trained based on a dataset, and the test method(s) by which biodegradation was determined are clearly specified so that the biodegradation model can be specifically trained for one or more test methods.

[0053] In one embodiment, habitat descriptor values ​​for the habitat descriptors are stored in association with respective geographic locations, and providing a biodegradation habitat refers to providing the geographic location of the habitat and retrieving the habitat descriptor value for that geographic location from storage. The geographic location may refer to, for example, coordinates or other area identifiers. For example, the geographic location may refer to a city name, a country name, a country region name, a sea area name, a geographic feature, etc. Based on such geographic location, each habitat and / or habitat descriptor, for example, an average value or a minimum and maximum value of the habitat descriptor, may be stored. Thus, by providing a geographic location, each habitat descriptor value for that geographic location may be provided. An advantage of this is that the user does not need to know the exact habitat or the exact habitat descriptor value of a certain area. Thus, the user can simply provide a location where the target functional compound is expected to be biodegradable in that area.

[0054] In one embodiment, the characterization parameters that may be indicated by the digital representation of the functional compound may refer to at least one of recipe parameters from the synthesis of the functional compound, compositional descriptors, count descriptors, lists of structural fragments, fingerprints, graph invariants, 3D descriptors, and / or high-dimensional descriptors that indicate the chemical properties of the functional compound. The respective connections of the digital representation with characterization parameters, e.g., previously calculated, or further information about the functional compound, may already be stored and connected to the respective digital representation. For example, if the digital representation refers to a brand name, the components corresponding to the brand name, their respective structural formulas and amounts, and / or physicochemical parameters may already be stored, e.g., in the brand name owner's storage.

[0055] In one embodiment, the method further includes providing a biodegradation test method, wherein the provided biodegradation test method represents a standardized biodegradation test method for experimentally determining the biodegradability of a chemical substance, and wherein a biodegradation model is further provided based on the provided biodegradation test method. For example, the test method may be any of the following standardized test methods: ISO 13432, ISO 14852, ISO 14855, ISO 17556, OECD 301, and OECD 302.

[0056] In a further aspect, an interface method for providing an interface is presented, the interface method including: a) receiving a target biodegradability, a digital representation, and a habitat as input via a user interface, and providing the received target biodegradability, digital representation, and habitat to a processor executing the above-described method; and b) providing a target functional compound as a result, the result being received from the processor executing the above-described method.

[0057] In a further aspect, a computer-implemented training method for training a data-driven based biodegradation model to parameterize the biodegradation model is presented, the training method comprising: a) providing training data related to a predetermined biodegradation habitat, the training data including: i) digital representations of a plurality of training functional compounds, and ii) biodegradability for each biodegradation habitat associated with each training functional compound; b) providing a data-driven based trainable biodegradation model; c) training the provided data-driven based biodegradation model based on the provided training data, such that the trained biodegradation model is adapted to determine biodegradability of the functional compounds based on the digital representations of the functional compounds; and d) providing a trained biodegradation model.

[0058] In a further aspect, an apparatus for determining a target functional compound comprising a target biodegradability is provided, the apparatus comprising: a) a target biodegradability providing unit for providing a target biodegradability, wherein the biodegradability indicates a biodegradation characteristic of the functional compound; b) a digital representation providing unit for providing a digital representation of a potential target functional compound; c) a habitat providing unit for providing a biodegradation habitat, wherein the biodegradation habitat indicates habitat descriptor values ​​of habitat descriptors that affect the biodegradation of the functional compound in each habitat, the habitat descriptors indicating environmental characteristics of the habitat; and d) a model providing unit for providing a biodegradation model based on the provided biodegradation habitat, wherein the biodegradation model indicates a biodegradation characteristic of each biodegradation habitat. The method comprises: a model providing unit adapted to determine the biodegradability of a functional compound in a degradation habitat, wherein the biodegradation model is a data-driven model parameterized for the biodegradation habitat so as to determine the biodegradability of the functional compound based on the digital representation; e) a biodegradability determining unit for determining the biodegradability of a potential target functional compound based on the selected biodegradation model and the digital representation; and f) an iterative control unit for comparing the determined biodegradability of the potential target functional compound with a target biodegradability, wherein the iterative control unit, based on the comparison, either i) determines the potential target functional compound as the target functional compound, or ii) provides a new potential target functional compound and repeats the determination of biodegradability using the new potential target functional compound.

[0059] In a further aspect, an interface device for providing an interface is presented, comprising: a) an input interface unit for receiving a target biodegradability, a starting digital representation, and a habitat as input via a user interface and providing the received target biodegradability, starting digital representation, and habitat to the above-mentioned device; and b) a result interface for providing a habitat descriptor value of the functional compound as a result, the result being received from the above-mentioned device.

[0060] In a further aspect, a training device for training a data-driven based biodegradation model for parameterizing the biodegradation model is presented, the training device comprising: a) a training data providing unit for providing training data related to a predetermined biodegradation habitat, the training data including: i) digital representations of a plurality of training functional compounds, and ii) biodegradability for each biodegradation habitat associated with each training functional compound; b) a trainable model providing unit for providing a data-driven based trainable biodegradation model; c) a training unit for training the provided data-driven based biodegradation model based on the provided training data, such that the trained biodegradation model is adapted to determine the biodegradability of the functional compounds based on the digital representations; and d) a trained model providing unit for providing a trained biodegradation model.

[0061] In a further aspect of the present invention, there is provided the use of the method described above, wherein the method is used to determine target functional compounds, including target biodegradability for any of the following: i) functional compounds referring to nutritional ingredients, ii) functional compounds referring to UV absorbers used in skin protection, iii) formulation additives used in personal care applications, iv) functional compounds used in aroma applications, v) functional compounds used as plasticizers, vi) functional compounds used as lubricants, and vii) functional compounds used as active ingredients.

[0062] In a further aspect of the present invention, a system is provided, the system including: i) a control signal including a synthesis specification for a functional compound indicating one or more ingredients for producing the functional compound, the control signal being generated according to the method described above; and ii) one or more ingredients indicated by the synthesis specification in the control signal.

[0063] In a further aspect of the present invention, there is provided the use of a control signal generated according to the above-described method for controlling a production process, in particular a production process involving the production of a functional compound.

[0064] In a further aspect of the present invention, a control signal is provided, the control signal being generated according to the method described above. Preferably, the control signal comprises a machine-executable synthesis specification for producing a target functional compound.

[0065] In a further aspect, there is provided a computer program product for determining target functional compounds having target biodegradability, the computer program product comprising program code means for causing the above-described apparatus to perform the above-described method.

[0066] In a further aspect, there is provided a computer program product for training a biodegradation model, the computer program product comprising program code means for causing an apparatus as described above to perform the method as described above.

[0067] It is to be understood that the above-mentioned method, the above-mentioned device and the above-mentioned computer program product have similar and / or identical preferred embodiments, in particular those defined in the dependent claims. Furthermore, the above-mentioned training method, the above-mentioned training device and the above-mentioned training computer program product also have similar and / or preferred embodiments, in particular those defined in the dependent claims.

[0068] It should be understood that a preferred embodiment of the invention can also be any combination of the dependent claims or the above-mentioned embodiments with the respective independent claims.

[0069] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. [Brief explanation of the drawings]

[0070] [Figure 1] FIG. 1 is a schematic, exemplary illustration of one embodiment of a system comprising an apparatus for determining target synthesis specifications indicative of target functional compounds, including target biodegradability. [Figure 2] FIG. 1 shows, by way of example only, a flow chart of a method for determining a target synthesis specification indicative of a target functional compound, including a target biodegradability. [Figure 3] FIG. 1 shows, schematically and exemplarily, a flow chart of a method for training a biodegradation model for determining the biodegradability of a functional compound. [Figure 4] FIG. 1 is a schematic, exemplary flow chart of a preferred and more detailed embodiment of a method for determining target synthesis specifications indicative of target functional compounds, including target biodegradability. [Figure 5] FIG. 1 is a schematic, exemplary flow chart of a preferred and more detailed embodiment of a method for determining target synthesis specifications indicative of target functional compounds, including target biodegradability. [Figure 6] FIG. 1 shows, in a schematic and exemplary manner, a block diagram of a system architecture for a system and apparatus for determining target synthesis specifications indicative of target functional compounds, including target biodegradability. [Figure 7] FIG. 1 shows, in a schematic and exemplary manner, a block diagram of a system architecture for a system and apparatus for determining target synthesis specifications indicative of target functional compounds, including target biodegradability. [Figure 8] FIG. 1 shows, in a schematic and exemplary manner, a block diagram of a system architecture for a system and apparatus for determining target synthesis specifications indicative of target functional compounds, including target biodegradability. DETAILED DESCRIPTION OF THE INVENTION

[0071] Detailed Description of the Embodiments 1 shows a schematic and exemplary embodiment of a system 100 comprising an apparatus 110 for determining a target synthesis specification indicative of a target functional compound having a target biodegradability. The system 100 further comprises a training apparatus 130 for training a biodegradation model utilized in the apparatus 110, a database 140 in which results of the determination of the target synthesis specification may be stored, and a production system 120 for producing a product comprising the determined target functional compound, which may be controlled, inter alia, utilizing the determined target synthesis specification of the target functional compound.

[0072] The apparatus 110 comprises a target biodegradability providing unit 111, a digital representation providing unit 112, a habitat providing unit 113, a model providing unit 114, a biodegradability determining unit 115, an iterative control unit 116, and an output and / or control unit 117, which may optionally be adapted to output the determined target functional compound, may be adapted to cause the determination of a synthesis specification, and optionally may also be adapted to provide a control signal for controlling the production process of the production system 120 based on the determined synthesis specification.

[0073] The target biodegradability-providing unit 111 is adapted to provide a target biodegradability indicative of a desired biodegradation characteristic of the functional compound. The target biodegradability-providing unit 111 may, for example, refer to an input unit through which a user can input the respective target biodegradability. Furthermore, the target biodegradability-providing unit 111 may refer to or be part of a user interface that allows a user to interact with the device 110 to provide the target biodegradability. However, the target biodegradability-providing unit 111 may also, for example, refer to or be communicatively coupled to a storage unit in which a target biodegradability for a particular application is already stored.

[0074] The digital representation providing unit 112 is adapted to provide digital representations indicative of potential target functional compounds. The digital representation providing unit 112 may, for example, refer to an input unit through which a user can input the respective digital representation. Furthermore, the digital representation providing unit 112 may refer to or be part of a user interface that allows a user to interact with the device 110 and / or the database 140. However, the digital representation providing unit 112 may also refer to or be communicatively coupled to a storage unit in which the digital representations of the functional compounds are already stored. Generally, the digital representations may directly include, for example, chemical structures, structural formulas, and respective amounts, and / or characterization parameters of the functional compounds. However, for example, instead of directly providing the characterization parameters, only known synthesis specifications and / or molecular structures of the functional compounds may be provided. In this case, it is preferable that the digital representation providing unit 112 is further adapted to determine respective other information and / or parameters, for example, chemical structures, structural formulas, and respective amounts of two or more structural formulas present in the functional compound, and / or characterization parameters from the synthesis specifications and / or molecular structures. In particular, the digital representation providing unit 112 may be adapted to determine the chemical structures, structural formulas and respective amounts of two or more structural formulas present in the functional compound, for example by accessing a database in which respective information for a plurality of functional compounds is already stored, and / or to determine characterization parameters, and then the digital representation providing unit 112 is adapted to provide a digital representation comprising the respectively determined further information, such as the characterization parameters, to, for example, the determining unit 115.

[0075] The habitat providing unit 113 is adapted to provide a biodegradation habitat. The habitat providing unit 113 may, for example, refer to an input unit through which a user can input a respective biodegradation habitat. For example, a user interface may be provided that allows the user to select from a plurality of predefined biodegradation habitats. In a preferred embodiment, the habitat providing unit 113 may be communicatively coupled to or reference a user interface that allows the user to indicate a geographic location, for example, by marking a location on a map, by indicating coordinates, or by providing a region name, such as a political or geological region, and the habitat providing unit may then be adapted to provide a biodegradation habitat based on the geographic location. For example, if the geolocation indicates a particular ocean region, such as the North Sea or the Atlantic Ocean, the habitat providing unit may be adapted to determine a marine habitat as the biodegradation habitat.

[0076] Generally, the biodegradation habitats indicate habitat descriptor values ​​of habitat descriptors that affect the biodegradation of functional compounds in the respective habitats. In particular, the habitat descriptors indicate environmental characteristics of the habitat; for example, for a marine habitat, salt concentration may strongly affect the biodegradation of functional compounds in the marine habitat. Generally, the chemical effect of the habitat descriptor on the functional compound is not important in this application, since biodegradability is determined. Thus, it is the effect of the habitat descriptor on the ecology of the habitat, particularly the microbial community of the habitat, that indirectly affects biodegradability. Typical specific habitat descriptor values ​​for each habitat may be stored in the database. However, for example, if it is known that the habitat descriptor values ​​for each habitat deviate from the typical habitat descriptor values, the user may also enter each specific habitat descriptor value.

[0077] The model providing unit 114 is adapted to provide a biodegradation model based on the provided biodegradation habitat. In particular, the model providing unit 114 is preferably adapted to select a biodegradation model from a plurality of biodegradation models already stored in the database. For example, the biodegradation model may be trained on training data corresponding to one or more specific biodegradation habitats. These specific biodegradation habitats may be defined with respect to specific habitat descriptor values ​​or ranges of values ​​that define for which biodegradation habitat each biodegradation model is suitable. For example, a look-up table may be provided that allows the model providing unit to select which biodegradation model is suitable based on the biodegradation habitat, e.g., based on the habitat descriptor values ​​of the biodegradation habitat. However, the model providing unit 114 may also configure or reference an input unit from which a biodegradation model may be provided, e.g., by user selection or user input indicating which biodegradation model should be used.

[0078] The biodegradation model is a data-driven model parameterized to determine the biodegradability of a functional compound based on a digital representation, particularly the chemical structure, structural formula, and amount of two or more structural formulas present in the functional compound, and / or the characterization parameters of the functional compound. Optionally, the biodegradation model can also be trained to further utilize habitat descriptor values ​​provided as input. In a preferred embodiment, the data-driven model refers to a machine learning model that utilizes, for example, a regression model-based algorithm or a classifier model-based algorithm. The regression model-based algorithm can be based on any of a neural network algorithm, a linear regression algorithm, a LASSO algorithm, a ridge regression algorithm, a MARS algorithm, a random forest algorithm, and a boosted tree algorithm. The classifier model algorithm can be based on any of a random forest algorithm, a logistic regression algorithm, and an SVM algorithm. The inventors have found that neural network, linear regression, random forest, and MARS-based algorithms are particularly suitable for most applications.

[0079] The biodegradation model can be trained, for example, using a training device 130. In particular, the training device 130 includes a training data providing unit 131 for providing training data for training the data-driven biodegradation model. The training data includes a) digital representations of a plurality of training functional compounds and b) biodegradability associated with each training functional compound in one or more different habitats. Optionally, the training dataset may further include habitat descriptor values ​​for the specific habitats in which the biodegradability of each of the functional compounds has been determined. Preferably, in the training data, the biodegradability provided for each training functional compound refers to biodegradability measured according to the same measurement method. However, biodegradability may also be provided for different measurement methods, in which case it is preferable to clearly indicate which biodegradability is associated with which measurement method so that the biodegradation model can be trained to distinguish between the different measurement methods. Generally, the training data can be designed to cover a predetermined habitat space of the biodegradation model to be trained, the habitat space being defined by the range of values ​​of each habitat descriptor for which the biodegradation model is trained. For example, the training data can be designed to cover a predetermined functional compound type for a predetermined habitat. Known methods for designing and optimizing training data for a given habitat space can be used to ensure that the habitat space is adequately covered by the training data and that random outliers are avoided.

[0080] Further, the training device 130 includes a model providing unit 132 adapted to provide a data-driven, trainable biodegradation model, e.g., a biodegradation model including parameters that can be set during a training process to train the biodegradation model. For example, the trainable biodegradation model may be already stored in a storage unit that the model providing unit 132 can access to provide it. Further, the training device 130 includes a training unit 133 for training the provided data-driven biodegradation model based on the provided training data. In particular, training may refer to varying the parameters of the biodegradation model based on the digital representation, in particular based on input parameters, e.g., the chemical structures, structural formulas, and amounts of two or more structural formulas present in the functional compound, and / or any of the characterization parameters of the functional compound, based on the respective training data until the biodegradation model is adapted to determine the biodegradability of the functional compound. Generally, any known training algorithm for training a data-driven, in particular machine learning-based, model may be utilized. Preferably, during the training of the biodegradation model, the input parameters of the functional compounds that have the most influence on biodegradability in each habitat are also determined, and then the model is trained based on these most influential input parameters, for example, the most influential characterization parameters. To determine these most influential input parameters, for example, cluster analysis or PCA analysis tools can be used. Furthermore, learned representations based on molecular graphs can be used as input for the predictive model. In particular, the input parameters can be used to determine the application space of the training data, which is then defined by the input parameters of the functional compounds and the habitat descriptors covered by the data. The determination of the most influential input parameters and / or habitat descriptors can then be performed as a dimensionality reduction of the application space. An algorithm can then be applied to optimize the training data within the application space, for example, to cover the application space with as little training data as possible.

[0081] The training device 130 then comprises a trained model providing unit 134 adapted to provide the trained biodegradation model to, for example, a storage unit in which trained biodegradation models for different habitats and / or different types of functional compounds and / or characterization parameters, respectively, are stored. However, the trained model providing unit 134 may also be adapted to provide the trained biodegradation model directly to, for example, the biodegradation model providing unit 114 of the device 110.

[0082] In all cases, the biodegradation model providing unit 114 is then adapted to provide a suitable trained biodegradation model to the biodegradability determining unit 115. The biodegradability determining unit 115 can then utilize the biodegradation model and the provided digital representation to determine the biodegradability. In particular, the biodegradability determining unit 115 can be adapted to utilize input parameters, e.g., any of the chemical structures, structural formulas, and amounts of two or more structural formulas present in the functional compound, and / or characterization parameters indicated by the digital representation as input to the trained biodegradation model so as to provide as output a decision on the biodegradability it was trained on, as already mentioned above.

[0083] The apparatus further includes an iterative control unit 116 adapted to control the iterative process for determining the target synthesis specification. In particular, the iterative control unit 116 is adapted to compare the determined biodegradability of the potential target functional compound with the target biodegradability. Based on this comparison, the iterative control unit 116 is then adapted to determine whether further iterative steps are necessary to determine the target functional compound or whether the iteration has reached an end, in particular, whether the potential target functional compound can be set as the target functional compound. Preferably, the comparison of the determined biodegradability of the potential target functional compound with the target biodegradability refers to determining whether the determined biodegradability is within a predetermined range around the biodegradability, for example, by determining whether the difference between the determined biodegradability and the target biodegradability is less than a predetermined threshold. However, the comparison may also refer to a more complex mathematical function, and the condition for determining a potential target functional compound as a target functional compound may refer to any condition based on the comparison of the determined biodegradability with the target biodegradability. Generally, if a predetermined condition is met, for example, if the determined biodegradability is within a predetermined range around the target biodegradability, the iterative control unit 116 determines that the potential target functional compound is a target functional compound.

[0084] If the above condition is not met, for example, if the determined biodegradability is not within a predetermined range around the target biodegradability, the iteration control unit 116 is adapted to determine that a further iteration step is necessary. In this case, the iteration control unit 116 is adapted to provide a new potential target functional compound and repeat the determination of biodegradability using the new potential target functional compound, particularly based on a digital representation of the new potential target functional compound. For example, the new potential target functional compound, particularly in the form of a respective digital representation, can be provided in a database in which multiple potential target synthetic specifications are already stored, from which the iteration control unit 116 can select a new potential target functional compound arbitrarily or according to a predetermined rule. Such a rule can, for example, be a function of a comparison of the determined biodegradability with the target biodegradability of the potential target functional compound. For example, the function can refer to the size of the difference between the determined biodegradability and the target biodegradability; the smaller the difference, the more similar the portion of the new potential target functional compound is in the potential target functional compound. In such a case, these rules may allow the iterative control unit 116 to be adapted to select a new potential target functional compound that is more similar to the potential target functional compound if the determined biodegradability of the potential target functional compound is already similar to the target functional compound, or that is less similar if the difference between the determined biodegradability and the target biodegradability is large. However, completely different rules may also be applied. Furthermore, the iterative control unit 116 may also be adapted to generate new potential target synthetic specifications, for example, based on the potential target functional compound and predetermined rules, or arbitrarily. Again, the same principles as those described above may be applied to the rules.

[0085] Furthermore, the iteration control unit 116 may also be adapted to apply an iteration stop criterion that indicates failure to find a suitable target functional compound for each target biodegradability. For example, the iteration control unit 116 may be adapted to apply a stop criterion that refers to a predetermined number of iteration steps, i.e., that refers to determining a predetermined number of new potential target synthetic specifications. However, other stop criterions may also be utilized.

[0086] An output unit, e.g., a display, may then be adapted to output the determined target functional compound in the form of, e.g., a visual representation of the functional compound, an identification of the functional compound, a chemical formula representing the functional compound, a chemical structure of the functional compound, etc. Furthermore, the output unit may additionally or alternatively be adapted to provide the determined target functional compound to a database 140 for storing each determined target functional compound in association with a respective target biodegradability for future use. Optionally, the apparatus 110 may comprise a control unit 117 adapted to provide a control signal based on the determined target functional compound to control the production process of the production system 120. In particular, the control unit 117 may be adapted to trigger the determination of a synthesis specification for the target functional compound based on a respective known method if the synthesis specification is not known. The control signal then preferably indicates a machine-executable synthesis specification for the target functional compound to be generated based on the determined synthesis specification to produce a target functional compound that satisfies the target biodegradability. However, the control unit 117 may also be adapted to control the production process of another product based on the determined target functional compound, for example, to provide control signals indicating machine-executable synthesis specifications for another product that utilizes or includes the respective target functional compound.

[0087] FIG. 2 schematically and exemplarily shows a flowchart of a method for determining a target functional compound having a target biodegradability. The method 200 includes a first step 210 of providing a target biodegradability. Furthermore, in step 220, a digital representation of a potential target functional compound is provided. In particular, the provision of the target biodegradability and the digital representation may follow the principles described above with respect to the target biodegradability providing unit 111 and the digital representation providing unit 112, respectively. Furthermore, in step 230, biodegradation habitats are provided, indicating habitat descriptor values ​​of habitat descriptors that affect the biodegradation of the functional compound in each habitat. For example, the principles described above with respect to the habitat providing unit 113 may also be applied to this step 230. Furthermore, in step 240, a biodegradation model is provided, adapted to determine the biodegradability of the functional compound based on the digital representation. As already described in more detail above, providing a biodegradation model may also refer to the selection of a biodegradation model based on the provided biodegradation habitat. Furthermore, the biodegradation model is preferably a data-driven model parameterized for the biodegradation habitat, so as to be able to determine the biodegradability of the functional compound based on the characterization parameters of the functional compound. Generally, steps 210, 220, 230, and 240 can be performed in any order or simultaneously. In the following step 250, biodegradability is determined based on the provided digital representation and biodegradation model of the potential target functional compound. In step 260, the determined biodegradability of the potential target functional compound is then compared to the target biodegradability. Based on this comparison, the potential target functional compound is determined as the target functional compound, or a new potential target functional compound is provided and the determination of biodegradability is repeated using the new potential target functional compound. In optional step 270 after the target synthesis specification has been determined using the above steps, the determined target functional compound and target biodegradability can be provided to a user via an output unit.Further, in step 270, synthesis specifications for the target functional compound may be determined and then utilized to generate control signals that allow for control of the production process of a product, e.g., the target functional compound or a product containing the target functional compound, as already described in detail above.

[0088] FIG. 3 schematically and exemplarily illustrates a flowchart of a method for training a data-driven biodegradation model, for example, as utilized in the method 200 described with reference to FIG. 2 . Generally, the method 300 may be performed by each unit of the training device 130, for example, as described with reference to FIG. 1 . The method 300 includes a step 310 of providing training data for training the data-driven biodegradation model. The training data includes a) digital representations of a plurality of training functional compounds and b) biodegradability associated with each training functional compound in each biodegradation habitat, for example, for a particular habitat descriptor value. Optionally, the training dataset may further include each particular habitat descriptor value. In particular, the training data may be provided according to the principles described above with reference to the training data providing unit 131 described with reference to FIG. 1 . The method further includes a step 320 of providing a data-driven trainable biodegradation model, for example, a machine learning-based biodegradation model such as a neural network. Generally, steps 310 and 320 may be performed in any order or simultaneously. The method 300 then further includes step 330 of training the provided data-driven biodegradation model based on the provided training data, e.g., by varying parameters in the data-driven trainable biodegradation model, such that the trained biodegradation model is adapted to determine the biodegradability of the functional compound based on the digital representation of the functional compound. In step 340, the trained biodegradation model can then be provided, e.g., by storing the trained biodegradation model in storage or by directly providing the trained biodegradation model to the device 130, as described with respect to FIG. 1.

[0089] In the following, a more detailed preferred embodiment of the above-mentioned method and corresponding device will be described. A schematic and exemplary flowchart of an exemplary and preferred embodiment of the method is provided by FIG. 4. In this exemplary embodiment, the method begins by requesting, for example, via a user interface, target values ​​for the target application, in particular, the target biodegradability. Furthermore, in a next step, optimization is initiated by providing a target functional compound. Optionally, constraints on the functional compound can be taken into account in this process, for example, if the user provides such constraints. The constraints may refer, for example, to constraints on the production of the functional compound, constraints on the starting materials to be used in the synthesis of the functional compound, etc. Furthermore, additional application conditions may be requested, in particular, to indicate the biodegradation habitat of the target functional compound. Furthermore, the additional application conditions may also indicate further information about the target functional compound that should be satisfied. For example, the requested additional application conditions may refer to geographic locations indicating where the functional compound is expected to be biodegradable. Based on these geographic locations, biodegradation habitats and respective habitat descriptors can be determined, for example, by utilizing a database in which each associated biodegradation habitat and biodegradation physicochemical parameter is already stored. Based on the above steps, optimization for determining a target functional compound, i.e., a target synthesis specification, can be initiated. In the first step of optimization, characterization parameter values ​​can be derived from the provided functional compound. However, deriving the characterization parameters can refer to accessing storage in which the respective characterization parameter values ​​for each potential target functional compound are already stored. Furthermore, if the provided digital representation of the potential target functional compound already includes the characterization parameters, this step can also be omitted. Based on the required additional application conditions, in particular the biodegradation habitat, a respective decision model, i.e., a biodegradation model, can be provided. Based on the provided decision model and the digital representation of the potential target functional compound, a target application, i.e., a biodegradability value, for the potential target functional compound can be provided.In the next step, it is determined whether the determined performance value, i.e., the determined biodegradability, meets the target value, i.e., the target biodegradability, within predetermined limits. If not, i.e., if this condition is not met, the functional compound is modified and a new potential target functional compound is optionally determined, taking into account the previously provided constraints. Then, the iteration can start anew for the potential target functional compound. At a certain point, if the determined performance value meets the target value within its limits, i.e., if the respective condition is met, the potential target functional compound is determined as a target functional compound and provided, for example, to a user or to a control unit for production of the respective determined target functional compound.

[0090] FIG. 5 illustrates a further preferred embodiment of the above-described method for determining a target composition specification having a predetermined target biodegradability. In this embodiment, in addition to the target biodegradability, it is desired that the target functional compound also satisfy a further target value, i.e., a target technical application property. The additional target technical application property may refer to any technical application property, such as additional biodegradability in another habitat or another technical application property. In general, the method follows the same principles as those described above with reference to FIG. 4. However, due to the additional target value, additional conditions must be met during optimization. Therefore, only the main differences from the above-described method will be pointed out below. In particular, in this preferred embodiment, the optimization module not only optimizes for the first target value, i.e., the target biodegradability, but also for a second target value. Preferably, a decision model adapted to determine the value of the technical application property based on the characterization parameters is utilized for the second target value as well. Therefore, in addition to the above-described method for the second target application, a second decision model is provided, which enables the application property value to be determined based on the characterization parameters for the second target application. The second determination model may be based on the same algorithm as the biodegradation model, but is simply trained using a different data set to determine another property of the functional compound.Then, the comparison refers not only to determining whether the determined biodegradability meets the target biodegradability within a limit, but also to determining whether the determined second application property value meets the target second application property value within a limit.A predetermined rule may be used to determine when the iteration continues, that is, a new functional compound is provided, and a potential target functional compound is determined as the target functional compound for that condition.For example, the user may predetermine a weighting value to weight which conditions must be met to what extent.For example, it may be more important for the user that biodegradability is met, but other target application properties are not so important.In this case, the limits on which the second target application property can be met may be set wider, or the importance of meeting this condition may be lessened. In this regard, Pareto optimization methods may be used to find the optimal tradeoff between different goals. Then, at a certain point in the iteration, if it is determined that the condition is met and satisfies a predetermined rule, each potential target synthesis specification is determined as the target synthesis specification and may be provided as an output to a user or used to generate a control file for producing each target functional compound.

[0091] FIG. 6 shows a block diagram of an exemplary system architecture of an automated laboratory system 1000 for synthesizing functional compounds, including a laboratory equipment control device 1102, a network 1150, a synthesis specification, i.e., recipe, module 1100 / 1110, and a client device 1108. The automated laboratory system includes a laboratory equipment control device layer 1152 as part of the laboratory equipment control device 1102, a synthesis specification module layer 1154 associated with the synthesis specification module, and a remote control or client layer 1156 associated with the client device 1108. The laboratory equipment control device layer can be divided into several hierarchical layers: a hardware layer, a middleware layer, and an interface layer. The hardware layer specifically relates to hardware resources, such as sensors and actuators, for controlling the synthesis of functional compounds. The middleware relates to any of the known middleware for laboratory or plant synthesis operations. One example is LABS / QM, which provides various abstractions over hardware, networks, and operating systems, such as low-level device control and message passing. The communication layer relates to communication protocols, one of which may be REST, which may be implemented over different transport protocols (i.e., UDP, TCP, telemetry) that allow the exchange of messages between the laboratory equipment control device and the laboratory equipment devices. Such a software architecture makes it possible to control and monitor laboratory equipment without the need to interact with hardware.

[0092] The synthesis specification module layer 1154 may include a mass storage layer, a computing layer, and an interface layer. As described in detail above, the storage layer is configured to provide mass storage for a data-driven biodegradation model for providing a recipe, i.e., a synthesis specification, of a functional compound that meets a target biodegradability. In particular, the functions performed by the device described above may be provided as program code stored in the mass storage. Furthermore, synthesis specifications for multiple functional compounds may be stored in the mass storage. Such data may be stored in a structured database, such as an SQL database, a distributed file system, such as HDFS, or a NoSQL database, such as HBase or MongoDB. The computing layer may include an application layer that customizes functionality provided by standard cloud services to execute computing processes based on target properties. Such functions may include determining a digital representation of a target functional compound based on the target biodegradability and the biodegradation model, generating a synthesis specification from the digital representation of the target functional compound, and providing the synthesis specification as control data to a laboratory equipment control device.

[0093] The interface layer may implement a web service, a network interface as UDP or TCP, or a web socket interface. For communication with laboratory equipment control devices, a REST API is implemented.

[0094] The client layer 1156 provides an interface to an end user. For the end user, the client layer 1156 can execute a client-side web application that provides an interface to the composite specification module layer 1154 or the laboratory equipment control device layer 1152. The user can be provided with a UI for selecting a target biodegradability and a biodegradation habitat for the target biodegradability, which can also include a range of biodegradability values. In other examples, the user can be provided with a UI for selecting two or more target biodegradabilities and their respective values. The application can be configured to allow the user to remotely monitor and control the laboratory equipment control device and operation. In other examples, the client device layer and composite specification module layer can be incorporated into a single device. The alternatives described herein are merely illustrative and should not be construed as limiting.

[0095] 7 shows a block diagram of an exemplary system architecture of a system and apparatus for generating a biodegradation model for determining biodegradability, namely, a network 2150 and a model generation module 2100 / 2110, which may be considered as or comprise a training model apparatus, a synthesis specification module 1100 / 1110, and a client device 2108. The system for generating a biodegradation model includes a model generation module layer 2154 as part of the model generation module and a client layer 2156 associated with the client device 2108.

[0096] The model generation module layer 2154 may include a mass storage layer, a computing layer, and an interface layer. The storage layer is configured to provide mass storage for the data-driven biodegradation model described above. Furthermore, the mass storage is configured to store the synthetic specifications of the functional compound and the measured biodegradability of one or more habitats. Such data may be stored in a structured database, such as an SQL database, a distributed file system, such as HDFS, or a NoSQL database, such as HBase or MongoDB. The computing layer may include an application layer that customizes the functionality provided by standard cloud services to execute the computing process for generating a biodegradation model for determining the biodegradability of the functional compound. Such functions may include receiving, in a model generation module, digital representations of at least one unmeasured functional compound, each digital representation associated with a synthetic specification for at least two previously measured functional compounds, and at least one measurement data of biodegradability in at least one habitat for each of the at least two previously measured functional compounds, and training a model according to the training principles described above based on a similarity measure between the digital representations of the at least two previously measured functional compounds, the measurement data of biodegradability in at least one habitat for each of the at least two previously measured functional compounds, and preferably between the digital representations associated with the synthetic specification for each of the at least two previously measured functional compounds and the digital representations associated with the synthetic specification for each of the at least one unmeasured functional compound, and providing a biodegradation model via an output interface. The model generation module layer may be configured to deploy the generated model and synthetic specification database to the synthetic specification module layer, which may include storing the generated model and synthetic specification database in a mass storage device associated with the synthetic specification module.

[0097] The model generation module layer may be further configured to determine, from the synthesis specification and / or molecular structure, a digital representation of the functional compound associated with the synthesis specification. The digital representation may include a set of characterization parameters associated with the synthesis specification and / or molecular structure of each measured functional compound. One way to derive these characterization parameters may be by applying the SMILES algorithm or any other principle already described above. When a model is generated based on a digital representation derived from a recipe, the relationship between the synthesis specification and / or molecular structure and the characterization parameters may be stored in a mass storage device associated with the model generation module. In such a case, deploying the model includes providing the relationship.

[0098] The interface layer may implement a web service, a network interface such as UDP or TCP, or a web socket interface. In this example, a REST API is implemented for communication with client devices. The client layer 2156 provides access to a mass storage device containing synthetic specifications for functional compounds and at least one biodegradability for at least two functional compounds. The client layer also provides an interface to an end user. For end users, the client layer 2156 can execute a client-side web application that provides an interface to the model generation module layer 2154 or to a mass storage device associated with the client layer. A user may be provided with a UI for selecting a test method and / or habitat for which biodegradability will be determined. A user may further be provided with a UI for selecting synthetic specification data. The user interface may also provide options for uploading selected data to the model generation module layer and, optionally, starting model generation.

[0099] FIG. 8 illustrates an exemplary system 700 for producing a chemical product based on a synthesis specification generated in accordance with the present invention. In this example, the system includes a user interface 710 and a processor 720 associated with a control unit 740. The user interface 710 and the processor 720 may be associated with or implemented in accordance with the principles described above, and may be particularly adapted to execute a computer-implemented method for determining a target functional compound and / or synthesis specification based on a determined biodegradability, as described above. The control unit 740 may be configured, for example, to receive control data generated in accordance with the present invention, particularly control data generated based on a synthesis specification for a functional compound including a target biodegradability. In this example, the control data is provided from a database 730, but in other examples, the control data may be provided from a server or any other computing unit for distributing data. Vessels 750, 752 each contain components of a chemical product, e.g., compounds, catalysts, etc. Typically, there are more than two vessels, but in this example, only two are shown for illustrative purposes. Valves 760, 762 are associated with the vessels 750, 752. Valves 750 and 752 may be controlled to dose the appropriate amount of each component into reaction vessel 770 according to the synthesis specification. A motor 800 for agitator 780 may also be controlled by the control unit according to the synthesis specification. An optional heater 790 may also be controlled according to the synthesis specification. Finally, an outlet valve 810 in fluid communication with the reactor may be controlled by the control unit to provide chemical products to a vessel or test system 820.

[0100] A more detailed example of a possible biodegradation model is provided below. In this example, a machine learning feature model is first utilized to determine molecular features that determine the biodegradability of the molecule. For example, the feature model can be a graph neural network (GNN). The GNN interprets a molecule as a graph, with the atoms of the molecule being nodes and the atomic bonds of the molecule being edges of the graph. The GNN is then configured to utilize this graph to find relevant substructures of the molecule. The feature model is then trained to convert the molecule into a vector of a predetermined amount of features, e.g., 20 features, so that similar molecules are similar in their representation in this predetermined amount of features. Similarity can be determined based on Tanimoto similarity, which is based on Morgan fingerprints. Further details of examples of GNNs that can be used in this case can be found in the literature "Molecular contrastive learning of representations via graph neural networks," Wang, Y., Wang, J., Cao, Z. et al., Nat Mach Intell 4, 279-287 (2022), and "Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast," Wang Y., Magar R., Liang C., and Farmimani AB, J. Chem. Inf. Model. 62, 11, 2713-2725 (2022). A feature vector containing each feature value of the molecule can then be used as a digital representation of the molecule. A random forest model is then used as a biodegradation model and trained to determine biodegradation in each habitat based on the digital representation.

[0101] Both models are then trained together using public training data, e.g., from the NITE database, and biodegradation measurements of each molecule in each habitat can be performed. In this example, over 3,000 data points are used: Measurements are performed using standardized OECD 301 (A-F) test setups in each test habitat, with a measurement error uncertainty of approximately 10%. The molecules used for training in this exemplary training data are organic compounds with a molecular mass of less than 500 g / mol for over 90% of the molecules. As is common in machine learning, various parameters of both models are set to perform best on the available data, i.e., to predict biodegradation as accurately as possible for the data at hand. Standard machine learning training protocols are followed to ensure and test the models' generalizability to other molecules. Because both models are trained simultaneously on the same training data, the biodegradation model can also be considered to include both models and utilize input digital representations, such as molecular graphs or digital representations representing molecular graphs.

[0102] Cross-validation can be used to evaluate the performance of the trained model, particularly the link between the GNN model and the random forest model that maps molecules to their biodegradation values. Thus, in this example, the training data used is divided into a predetermined number of data portions, for example, five portions. From the data portions, multiple random data portions are each used to train a model based on the respective data portion. Then, using at least one data portion, the trained model is applied to the molecules in this data portion, and the results of the biodegradation measurements are compared with known values ​​for biodegradation. This technique makes it possible to simulate how well the model can determine the biodegradability of molecules that it has not been trained on. For this exemplary model, the error averages 19%, taking into account a 10% measurement uncertainty and a 14% median error.

[0103] Furthermore, as an optional extension of the model, a method for quantifying the uncertainty of the model decision can be implemented based on how similar each molecule is to the molecules in the training data used. Furthermore, molecules can also be visualized in two-dimensional graphics based on numerical representations from the GNN model, for example, projecting 20 feature values ​​into 2D space to enable visualization while maintaining a fairly good degree of similarity. For the model trained above, specifically for the 838 molecules used as test input from the NITE database, the average prediction error determined using cross-validation is 19% and the median error is 13%. An example is provided in the table below.

[0104] [Table 1]

[0105] In general, possible training data sources, i.e., data sources that can be used to derive training data for the respective biodegradation models, are, for example, data from the NITE database, data retrieved from literature articles, data retrieved from the Aropha dataset. Furthermore, respective measurements of biodegradation of training molecules may also be performed on a large scale on test samples using standard procedures and methods, for example, as described in OECD 301(A-F).

[0106] Although the biodegradation model above is described as being solely a random forest model, and the digital representation is determined by a GNN model, in other embodiments, the digital representation may be considered to be a molecular structure or graph, or any representation showing a structure or graph, in which case the biodegradation model includes both a random forest model and a GNN, and thus refers to a two-stage machine learning model, where the output of the first model is the input of the second model.

[0107] In the following, further details regarding some of the above-mentioned embodiments are provided. Generally, in some applications, it is desirable to find functional compounds that meet specific technical application properties, such as tensile strength, and also meet requirements regarding biodegradability. For this application, a method such as that described with reference to FIG. 5 is proposed. In this example embodiment suitable for this application, a target requirement for biodegradability may be provided, and target application properties are also provided. Based on the target application properties, a determination model is selected, which preferably associates characterization parameters related to the synthesis specifications with the application properties. In addition, a further model is selected based on the habitat of the functional compound. This biodegradation model associates habitat information and characterization parameters related to the synthesis specifications with biodegradability. Based on the target application requirements, characterization parameters based on the synthesis specifications are determined. In an optional step, additional descriptor values ​​related to the habitat are required based on the selected biodegradation model used. Based on the biodegradation model, biodegradability can be determined. The determined biodegradability is then compared to the target biodegradability. Furthermore, the determination model is used to determine application properties of the functional compound, and the determined application properties are compared to the target properties. If the determined biodegradability meets the target biodegradability and the determined application properties satisfy the target properties, a synthesis specification for the functional compound is provided. The synthesis specification may also refer to or include control data for controlling the plant producing the functional compound. If the target biodegradability and / or target application properties are not met, the target application properties may be reduced and the process may be re-run with reduced target application properties until the biodegradation requirements are met. A tolerance range for the target application properties may be provided. If a functional compound is not found that meets the required targets for biodegradability and target application performance, the process may stop and the user may be notified.

[0108] The potential expression of biodegradability can be one or more of the following: mineralization, which refers to whether the functional compound is completely mineralized or the time until mineralization is achieved; biotransformation, which refers to a change in the chemical structure of the functional compound that results in the loss of a specific property, such as toxicity, or the time until this is achieved; and half-life, which refers to the time until 50% of the functional compound is degraded. Prominent habitats are oceans, wastewater, and soil. In the case of oceans, the following parameters may affect biodegradation: salinity, sediment, water temperature, bacterial culture, etc. In some examples, marine habitat descriptors may be stored in a database along with geographic locations. In that case, the geographic location can be entered, and the values ​​of the parameters associated with this geographic location can be retrieved from the database. In the case of wastewater, the following parameters may affect biodegradation: temperature, bacterial population, type of bacteria, enzyme concentration, and enzymes. In the case of soil, the following parameters may affect biodegradation: temperature, bacterial population, type of bacteria, enzyme concentration, and enzymes.

[0109] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0110] With respect to the processes and methods disclosed herein, the actions performed in the processes and methods may be implemented in different orders. Furthermore, the outlined actions are provided only as examples, and some of the actions may be optional, combined into fewer steps and actions, supplemented with additional actions, or expanded into additional actions, without detracting from the essence of the disclosed embodiments.

[0111] In the claims, the word "comprising" does not exclude other elements or steps and the indefinite article "a" or "an" does not exclude a plurality.

[0112] A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0113] The procedures performed by one or more units or devices, such as providing a digital representation and a biodegradation model, determining biodegradability, providing biodegradability, etc., may be performed by any number of other units or devices. These procedures may be implemented as program code means of a computer program and / or as dedicated hardware.

[0114] The computer program product may be distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, stored / distributed on other media, but may also be distributed in other forms, for example via the Internet or other wired or wireless telecommunications systems.

[0115] Any unit described herein may be a processing unit that is part of a classical computing system. The processing unit may include a general-purpose processor, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other dedicated circuit. Any memory may be physical system memory, which may be volatile, nonvolatile, or a combination of the two. The term "memory" may include any computer-readable storage medium, such as non-volatile mass storage. If the computing system is distributed, processing and / or storage capabilities may also be distributed. A computing system may include multiple structures as "executable components." The term "executable components" is a well-understood structure in the computing field, which may be software, hardware, or a combination thereof. For example, when implemented in software, those skilled in the art will understand that the structure of executable components may include software objects, routines, methods, etc. that can be executed on the computing system. This may include both executable components in the computing system's heap or executable components on a computer-readable storage medium. The structure of the executable components may reside on a computer-readable medium such that, when interpreted by one or more processors of a computing system, e.g., by processor threads, it causes the computing system to perform functions. Such structure may be directly computer-readable by a processor, e.g., where the executable components are binary, or may be structured to be interpretable and / or compiled to generate such a binary, e.g., in a single stage or multiple stages, that is directly interpretable by a processor. In other examples, the structure may be hard-coded or hard-wired logic gates implemented exclusively or nearly exclusively in hardware, e.g., in a field programmable gate array (FPGA), application specific integrated circuit (ASIC), or other dedicated circuitry.Thus, the term “executable component” is a term for structures well understood by those skilled in the computing arts, whether implemented in software, hardware, or a combination. Any embodiments herein are described with reference to operations performed by one or more processing units of a computing system. When such operations are implemented in software, one or more processors direct the operation of the computing system in response to execution of the computer-executable instructions that make up the executable components. A computing system may also include communication channels that enable the computing system to communicate with other computing systems, for example, over a network. A “network” is defined as one or more data links that enable the transmission of electronic data between computing systems and / or modules and / or other electronic devices. When information is transferred or provided to a computing system via a network or another communications connection, e.g., either hardwired, wireless, or a combination of hardwired and wireless, the computing system properly considers the connection to be a carrier medium. A carrier medium may include a network and / or data link that can be used to carry desired program code means in the form of computer-executable instructions or data structures and that can be accessed by a general-purpose computing system or a special-purpose computing system, or a combination thereof. Although not all computing systems require a user interface, in some embodiments a computing system includes a user interface system for use in interfacing with a user. The user interface serves as an input or output mechanism to the user, for example, via a display.

[0116] Those skilled in the art will appreciate that at least portions of the present invention may be implemented in networked computing environments having many types of computing system configurations, including personal computers, desktop computers, laptop computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, cellular phones, PDAs, pagers, routers, switches, data centers, wearable devices such as eyeglasses, etc. The present invention may also be implemented in distributed system environments where local and remote computing systems, linked, for example, through a network, either by hardwired data links, wireless data links, or a combination of hardwired and wireless data links, both perform tasks. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0117] Those skilled in the art will appreciate that at least a portion of the present invention may also be implemented in a cloud computing environment. A cloud computing environment may be distributed, but this is not required. If distributed, a cloud computing environment may be distributed internationally within an organization and / or have components held across multiple organizations. For purposes of this specification and the claims that follow, "cloud computing" is defined as a model that enables on-demand network access to a shared pool of configurable computing resources, such as networks, servers, storage, applications, and services. The definition of "cloud computing" is not limited to any of the many other advantages that may be obtained when such a model is deployed. The computing system in the figures, as described, includes various components or functional blocks that may implement various embodiments disclosed herein. The various components or functional blocks may be implemented on a local computing system or on a distributed computing system that includes elements that reside in the cloud or that implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing systems shown in the figures may include more or fewer components than those shown in the figures, and some of the components may be combined where circumstances warrant.

[0118] Any reference signs in the claims should not be construed as limiting the scope.

[0119] The present invention relates to a method for determining a synthetic specification including a target biodegradability. A target biodegradability indicating the biodegradation characteristics of a functional compound is provided. A digital representation of a potential target synthetic specification is provided, indicating physicochemical properties of the functional compound. A habitat is provided, indicating habitat descriptor values ​​for habitat descriptors. A habitat-based model is provided, adapted to determine the biodegradability of the functional compound in the habitat. The biodegradability of the potential target functional compound is determined based on the provided model and digital representation. The determined biodegradability is then compared to the target biodegradability, and either i) the potential target functional compound is determined as the target functional compound, or ii) a new potential target synthetic specification for the potential target functional compound is provided, and the determination of biodegradability is repeated using the new potential target synthetic specification.

Claims

1. 1. A computer-implemented method for determining a target functional compound having a target biodegradability, the method (200) comprising: Providing a target biodegradability (210), wherein the biodegradability exhibits biodegradation characteristics of a potential target functional compound (210); Providing a digital representation of a potential target functional compound (220); Providing (230) biodegradation habitats, each of the biodegradation habitats exhibiting habitat descriptor values ​​for habitat descriptors that affect the biodegradation of a functional compound in the habitat, the habitat descriptors indicating environmental characteristics of the habitat; providing a biodegradation model based on the provided biodegradation habitats (240), wherein the biodegradation model is adapted to determine the biodegradability of a functional compound in each of the biodegradation habitats, and the biodegradation model is a data-driven model parameterized with respect to the biodegradation habitats to determine the biodegradability of a functional compound based on a digital representation of the functional compound (240); determining (250) the biodegradability of the potential target functional compound based on the provided biodegradation model and the digital representation; comparing (260) the determined biodegradability of the potential target functional compound to the target biodegradability, and based on the comparison, either i) determining the potential target functional compound as the target functional compound, or ii) providing a new potential target functional compound and repeating the determination of biodegradability using the new potential target functional compound; A method comprising:

2. The method of claim 1 , wherein the functional compound has a molecular mass of less than 10,000 g / mol.

3. 10. The method of any one of the preceding claims, wherein the functional compound has at least one of the following properties: having an effect on an organism, being suitable for influencing the structure, or being suitable for influencing the function of an organism.

4. 10. The method of any one of the preceding claims, wherein the functional compound comprises at least one of the following functional groups: a carboxylic acid group, a carboxylic acid derivative group, an ether group, a hydroxyl group, a carbonyl group, an amine group, an ammonium group, an alkyl group, an alkylene group, a phenyl group, an acetal group, a ketal group, a thiol group, a sulfide group, a phosphate group, a halide group, or a combination thereof.

5. 10. The method of any one of the preceding claims, wherein the digital representation comprises or indicates a chemical structure of the functional compound, the chemical structure relating to and / or indicating one or more structural formulae and quantitative ratios of two or more structural formulae.

6. 6. The method of claim 5, wherein at least two of the structural formulas correspond to structural formulas that are related via chemical equilibrium and / or stereochemistry.

7. 10. The method of any one of the preceding claims, further comprising providing a biodegradation test method, wherein the provided biodegradation test method represents a standardized biodegradation test method for experimentally determining biodegradability of chemical substances, and wherein the biodegradation model is further provided based on the provided biodegradation test method.

8. 10. The method of any one of the preceding claims, wherein habitat descriptor values ​​of the habitat descriptors are stored in association with respective geographic locations, and wherein said providing the biodegradable habitat refers to providing a geographic location of the habitat and retrieving the habitat descriptor value for the geographic location from storage.

9. 1. An interface method for providing an interface, comprising: receiving as input via a user interface a target biodegradability, a starting digital representation, and a habitat, and providing said received target biodegradability, digital representation, and said habitat to a processor executing the method (200) of any one of claims 1 to 8; providing the starting digital representation of the functional compound as a result, the result being received from the processor executing the method (200) of any one of claims 1 to 8; An interface method comprising:

10. 1. A computer-implemented training method for training a data-driven biodegradation model to parameterize said biodegradation model, said training method (300) comprising: Providing training data associated with a predetermined biodegradation habitat (310), the training data including: a) a digital representation of a plurality of trained functional compounds; and b) a biodegradability for each of the biodegradation habitats associated with each trained functional compound (310); Providing a data-driven, trainable biodegradation model (320); training (330) the provided data-driven biodegradation model based on the provided training data, such that the trained biodegradation model is adapted to determine biodegradability of the functional compound based on the digital representation of the functional compound; providing the trained biodegradation model (340); A method comprising:

11. 1. An apparatus for determining a target functional compound, including a target biodegradability, the apparatus (110) comprising: a target biodegradability-providing unit (111) for providing a target biodegradability, wherein the biodegradability indicates the biodegradation properties of a potential target functional compound; a digital representation providing unit (112) for providing a digital representation of a potential target functional compound; a habitat providing unit (113) for providing a biodegradation habitat, wherein the biodegradation habitat exhibits habitat descriptor values ​​of habitat descriptors that affect the biodegradation of the functional compound in each of the habitats, the habitat descriptors exhibiting environmental characteristics of the habitat; a model providing unit (114) for providing a biodegradation model based on the provided biodegradation habitats, the biodegradation model being adapted to determine the biodegradability of a functional compound in each of the biodegradation habitats, the biodegradation model being a data-driven model parameterized with respect to the biodegradation habitats so as to determine the biodegradability of a functional compound based on the digital representation of the functional compound; a biodegradability determination unit (115) for determining the biodegradability of the potential target functional compound based on the selected biodegradation model and the digital representation; a repeat control unit (116) for comparing the determined biodegradability of the potential target functional compound with the target biodegradability, and based on the comparison, either i) determining the potential target functional compound as the target functional compound, or ii) providing a new potential target functional compound and repeating the determination of the biodegradability using the new potential target functional compound; An apparatus comprising:

12. 1. An interface device for providing an interface, comprising: an input interface unit for receiving as input via a user interface a target biodegradability, a starting digital representation, and a habitat, and for providing the received target biodegradability, starting digital representation, and the habitat to the device of claim 11; a result interface for providing the habitat descriptor values ​​of the functional compounds as results, the results being received from the device of claim 11; An interface device comprising:

13. A training device for training a data-driven biodegradation model to parameterize said biodegradation model, said training device (120) comprising: a training data providing unit (121) for providing training data associated with a predetermined biodegradation habitat, the training data including: a) digital representations of a plurality of trained functional compounds; and b) biodegradability for each of the biodegradation habitats associated with each trained functional compound; a trainable model providing unit (122) for providing a data-driven based trainable biodegradation model; a training unit (123) for training the provided data-driven biodegradation model based on the provided training data, such that the trained biodegradation model is adapted to determine biodegradability of a functional compound based on the digital representation of the functional compound; a trained model providing unit (124) for providing said trained biodegradation model; A training device comprising:

14. A computer program product for determining target functional compounds with target biodegradability, comprising program code means for causing an apparatus according to claim 11 to carry out the method according to any one of claims 1 to 8.

Images