Prediction of metabolic reactions based on atomic and molecular properties of small-molecule compounds

Specifics of Metabolite-Protein Interactions and Their Computational Analysis and Prediction

Computational approaches to the characterization and prediction of compound-protein interactions have a long research history and are well established, driven primarily by the needs of drug development. While, in principle, many of the computational methods developed in the context of drug development can also be applied directly to the investigation of metabolite-protein interactions, the interactions of metabolites with proteins (enzymes) are characterized by a number of particularities that result from their natural evolutionary origin and their biological and biochemical roles, as well as from a different problem setting when investigating them. In this review, these special aspects will be highlighted and recent research on them and developed computational approaches presented, along with available resources. They concern, among others, binding promiscuity, allostery, the role of posttranslational modifications, molecular steering and crowding effects, and metabolic conversion rate predictions. Recent breakthroughs in the field of protein structure prediction and newly developed machine learning techniques are being discussed as a tremendous opportunity for developing a more detailed molecular understanding of metabolism.

Review of Machine Learning Methods for the Prediction and Reconstruction of Metabolic Pathways

Prediction and reconstruction of metabolic pathways play significant roles in many fields such as genetic engineering, metabolic engineering, drug discovery, and are becoming the most active research topics in synthetic biology. With the increase of related data and with the development of machine learning techniques, there have many machine leaning based methods been proposed for prediction or reconstruction of metabolic pathways. Machine learning techniques are showing state-of-the-art performance to handle the rapidly increasing volume of data in synthetic biology. To support researchers in this field, we briefly review the research progress of metabolic pathway reconstruction and prediction based on machine learning. Some challenging issues in the reconstruction of metabolic pathways are also discussed in this paper.

A deep learning approach to evaluate the feasibility of enzymatic reactions generated by retrobiosynthesis

Retrobiosynthesis allows the designing of novel biosynthetic pathways for the production of chemicals and materials through metabolic engineering, but generates a large number of reactions beyond the experimental feasibility. Thus, an effective method that can reduce a large number of the initially predicted enzymatic reactions has been needed. Here, we present Deep learning-based Reaction Feasibility Checker (DeepRFC) to classify the feasibility of a given enzymatic reaction with high performance and speed. DeepRFC is designed to receive Simplified Molecular-Input Line-Entry System (SMILES) strings of a reactant pair, which is defined as a substrate and a product of a reaction, as an input, and evaluates whether the input reaction is feasible. A deep neural network is selected for DeepRFC as it leads to better classification performance than five other representative machine learning methods examined. For validation, the performance of DeepRFC is compared with another in-house reaction feasibility checker that uses the concept of reaction similarity. Finally, the use of DeepRFC is demonstrated for the retrobiosynthesis-based design of novel one-carbon assimilation pathways. DeepRFC will allow retrobiosynthesis to be more practical for metabolic engineering applications by efficiently screening a large number of retrobiosynthesis-derived enzymatic reactions. DeepRFC is freely available at https://bitbucket.org/kaistsystemsbiology/deeprfc.

Antioxidant Activity of Synthetic Polymers of Phenolic Compounds

In recent years, developing potent antioxidants has been a very active area of research. In this context, phenolic compounds have been evaluated for their antioxidant activity. However, the use of phenolic compounds has also been limited by poor antioxidant activity in several in vivo studies. Polymeric phenols have received much attention owing to their potent antioxidant properties and increased stability in aqueous systems. To be truly effective in biological applications, it is important that these polymers be synthesized using benign methods. In this context, enzyme catalyzed synthesis of polymeric phenols has been explored as an environmentally friendly and safer approach. This review summarizes work in enzymatic syntheses of polymers of phenols. Several assays have been developed to determine the antioxidant potency of these polymeric phenols. These assays are discussed in detail along with structure-property relationships. A deeper understanding of factors affecting antioxidant activity would provide an opportunity for the design of versatile, high performing polymers with enhanced antioxidant activity.

Exploration and Evaluation of Machine Learning-Based Models for Predicting Enzymatic Reactions

Unannotated gene sequences in databases are increasing due to sequencing advances. Therefore, computational methods to predict functions of unannotated genes are needed. Moreover, novel enzyme discovery for metabolic engineering applications further encourages annotation of sequences. Here, enzyme functions are predicted using two general approaches, each including several machine learning algorithms. First, Enzyme-models (E-models) predict Enzyme Commission (EC) numbers from amino acid sequence information. Second, Substrate-Enzyme models (SE-models) are built to predict substrates of enzymatic reactions together with EC numbers, and Substrate-Enzyme-Product models (SEP-models) are built to predict substrates, products, and EC numbers. While accuracy of E-models is not optimal, SE-models and SEP-models predict EC numbers and reactions with high accuracy using all tested machine learning-based methods. For example, a single Random Forests-based SEP-model predicts EC first digits with an Average AUC score of over 0.94. Various metrics indicate that the current strategy of combining sequence and chemical structure information is effective at improving enzyme reaction prediction.

Harnessing biocompatible chemistry for developing improved and novel microbial cell factories

White biotechnology relies on the sophisticated chemical machinery inside living cells for producing a broad range of useful compounds in a sustainable and environmentally friendly way. However, despite the impressive repertoire of compounds that can be generated using white biotechnology, this approach cannot currently fully replace traditional chemical production, often relying on petroleum as a raw material. One challenge is the limited number of chemical transformations taking place in living organisms. Biocompatible chemistry, that is non‐enzymatic chemical reactions taking place under mild conditions compatible with living organisms, could provide a solution. Biocompatible chemistry is not a novel invention, and has since long been used by living organisms. Examples include Fenton chemistry, used by microorganisms for degrading plant materials, and manganese or ketoacids dependent chemistry used for detoxifying reactive oxygen species. However, harnessing biocompatible chemistry for expanding the chemical repertoire of living cells is a relatively novel approach within white biotechnology, and it could potentially be used for producing valuable compounds which living organisms otherwise are not able to generate. In this mini review, we discuss such applications of biocompatible chemistry, and clarify the potential that lies in using biocompatible chemistry in conjunction with metabolically engineered cell factories for cheap substrate utilization, improved cell physiology, efficient pathway construction and novel chemicals production.

A pathway for every product? Tools to discover and design plant metabolism

The vast diversity of plant natural products is a powerful indication of the biosynthetic capacity of plant metabolism. Synthetic biology seeks to capitalize on this ability by understanding and reconfiguring the biosynthetic pathways that generate this diversity to produce novel products with improved efficiency. Here we review the algorithms and databases that presently support the design and manipulation of metabolic pathways in plants, starting from metabolic models of native biosynthetic pathways, progressing to novel combinations of known reactions, and finally proposing new reactions that may be carried out by existing enzymes. We show how these tools are useful for proposing new pathways as well as identifying side reactions that may affect engineering goals.

Computational Methods to Assess the Production Potential of Bio-Based Chemicals

Elevated costs and long implementation times of bio-based processes for producing chemicals represent a bottleneck for moving to a bio-based economy. A prospective analysis able to elucidate economically and technically feasible product targets at early research phases is mandatory. Computational tools can be implemented to explore the biological and technical spectrum of feasibility, while constraining the operational space for desired chemicals. In this chapter, two different computational tools for assessing potential for bio-based production of chemicals from different perspectives are described in detail. The first tool is GEM-Path: an algorithm to compute all structurally possible pathways from one target molecule to the host metabolome. The second tool is a framework for Modeling Sustainable Industrial Chemicals production (MuSIC), which integrates modeling approaches for cellular metabolism, bioreactor design, upstream/downstream processes, and economic impact assessment. Integrating GEM-Path and MuSIC will play a vital role in supporting early phases of research efforts and guide the policy makers with decisions, as we progress toward planning a sustainable chemical industry.

Predicting novel substrates for enzymes with minimal experimental effort with active learning

Enzymatic substrate promiscuity is more ubiquitous than previously thought, with significant consequences for understanding metabolism and its application to biocatalysis. This realization has given rise to the need for efficient characterization of enzyme promiscuity. Enzyme promiscuity is currently characterized with a limited number of human-selected compounds that may not be representative of the enzyme's versatility. While testing large numbers of compounds may be impractical, computational approaches can exploit existing data to determine the most informative substrates to test next, thereby more thoroughly exploring an enzyme's versatility. To demonstrate this, we used existing studies and tested compounds for four different enzymes, developed support vector machine (SVM) models using these datasets, and selected additional compounds for experiments using an active learning approach. SVMs trained on a chemically diverse set of compounds were discovered to achieve maximum accuracies of ~80% using ~33% fewer compounds than datasets based on all compounds tested in existing studies. Active learning-selected compounds for testing resolved apparent conflicts in the existing training data, while adding diversity to the dataset. The application of these algorithms to wide arrays of metabolic enzymes would result in a library of SVMs that can predict high-probability promiscuous enzymatic reactions and could prove a valuable resource for the design of novel metabolic pathways.

Predicting the Metabolic Sites by Flavin-Containing Monooxygenase on Drug Molecules Using SVM Classification on Computed Quantum Mechanics and Circular Fingerprints Molecular Descriptors

As an important enzyme in Phase I drug metabolism, the flavin-containing monooxygenase (FMO) also metabolizes some xenobiotics with soft nucleophiles. The site of metabolism (SOM) on a molecule is the site where the metabolic reaction is exerted by an enzyme. Accurate prediction of SOMs on drug molecules will assist the search for drug leads during the optimization process. Here, some quantum mechanics features such as the condensed Fukui function and attributes from circular fingerprints (called Molprint2D) are computed and classified using the support vector machine (SVM) for predicting some potential SOMs on a series of drugs that can be metabolized by FMO enzymes. The condensed Fukui function fA- representing the nucleophilicity of central atom A and the attributes from circular fingerprints accounting the influence of neighbors on the central atom. The total number of FMO substrates and non-substrates collected in the study is 85 and they are equally divided into the training and test sets with each carrying roughly the same number of potential SOMs. However, only N-oxidation and S-oxidation features were considered in the prediction since the available C-oxidation data was scarce. In the training process, the LibSVM package of WEKA package and the option of 10-fold cross validation are employed. The prediction performance on the test set evaluated by accuracy, Matthews correlation coefficient and area under ROC curve computed are 0.829, 0.659, and 0.877 respectively. This work reveals that the SVM model built can accurately predict the potential SOMs for drug molecules that are metabolizable by the FMO enzymes.

Characterising Complex Enzyme Reaction Data

The relationship between enzyme-catalysed reactions and the Enzyme Commission (EC) number, the widely accepted classification scheme used to characterise enzyme activity, is complex and with the rapid increase in our knowledge of the reactions catalysed by enzymes needs revisiting. We present a manual and computational analysis to investigate this complexity and found that almost one-third of all known EC numbers are linked to more than one reaction in the secondary reaction databases (e.g., KEGG). Although this complexity is often resolved by defining generic, alternative and partial reactions, we have also found individual EC numbers with more than one reaction catalysing different types of bond changes. This analysis adds a new dimension to our understanding of enzyme function and might be useful for the accurate annotation of the function of enzymes and to study the changes in enzyme function during evolution.

MINEs: open access databases of computationally predicted enzyme promiscuity products for untargeted metabolomics

BACKGROUND

In spite of its great promise, metabolomics has proven difficult to execute in an untargeted and generalizable manner. Liquid chromatography-mass spectrometry (LC-MS) has made it possible to gather data on thousands of cellular metabolites. However, matching metabolites to their spectral features continues to be a bottleneck, meaning that much of the collected information remains uninterpreted and that new metabolites are seldom discovered in untargeted studies. These challenges require new approaches that consider compounds beyond those available in curated biochemistry databases.

DESCRIPTION

Here we present Metabolic In silico Network Expansions (MINEs), an extension of known metabolite databases to include molecules that have not been observed, but are likely to occur based on known metabolites and common biochemical reactions. We utilize an algorithm called the Biochemical Network Integrated Computational Explorer (BNICE) and expert-curated reaction rules based on the Enzyme Commission classification system to propose the novel chemical structures and reactions that comprise MINE databases. Starting from the Kyoto Encyclopedia of Genes and Genomes (KEGG) COMPOUND database, the MINE contains over 571,000 compounds, of which 93% are not present in the PubChem database. However, these MINE compounds have on average higher structural similarity to natural products than compounds from KEGG or PubChem. MINE databases were able to propose annotations for 98.6% of a set of 667 MassBank spectra, 14% more than KEGG alone and equivalent to PubChem while returning far fewer candidates per spectra than PubChem (46 vs. 1715 median candidates). Application of MINEs to LC-MS accurate mass data enabled the identity of an unknown peak to be confidently predicted.

CONCLUSIONS

MINE databases are freely accessible for non-commercial use via user-friendly web-tools at http://minedatabase.mcs.anl.gov and developer-friendly APIs. MINEs improve metabolomics peak identification as compared to general chemical databases whose results include irrelevant synthetic compounds. Furthermore, MINEs complement and expand on previous in silico generated compound databases that focus on human metabolism. We are actively developing the database; future versions of this resource will incorporate transformation rules for spontaneous chemical reactions and more advanced filtering and prioritization of candidate structures. Graphical abstractMINE database construction and access methods. The process of constructing a MINE database from the curated source databases is depicted on the left. The methods for accessing the database are shown on the right.

Prediction of overall in vitro microsomal stability of drug candidates based on molecular modeling and support vector machines. Case study of novel arylpiperazines derivatives

Other than efficacy of interaction with the molecular target, metabolic stability is the primary factor responsible for the failure or success of a compound in the drug development pipeline. The ideal drug candidate should be stable enough to reach its therapeutic site of action. Despite many recent excellent achievements in the field of computational methods supporting drug metabolism studies, a well-recognized procedure to model and predict metabolic stability quantitatively is still lacking. This study proposes a workflow for developing quantitative metabolic stability-structure relationships, taking a set of 30 arylpiperazine derivatives as an example. The metabolic stability of the compounds was assessed in in vitro incubations in the presence of human liver microsomes and NADPH and subsequently quantified by liquid chromatography-mass spectrometry (LC-MS). Density functional theory (DFT) calculations were used to obtain 30 models of the molecules, and Dragon software served as a source of structure-based molecular descriptors. For modeling structure-metabolic stability relationships, Support Vector Machines (SVM), a non-linear machine learning technique, were found to be more effective than a regression technique, based on the validation parameters obtained. Moreover, for the first time, general sites of metabolism for arylpiperazines bearing the 4-aryl-2H-pyrido[1,2-c]pyrimidine-1,3-dione system were defined by analysis of Q-TOF-MS/MS spectra. The results indicated that the application of one of the most advanced chemometric techniques combined with a simple and quick in vitro procedure and LC-MS analysis provides a novel and valuable tool for predicting metabolic half-life values. Given the reduced time and simplicity of analysis, together with the accuracy of the predictions obtained, this is a valid approach for predicting metabolic stability using structural data. The approach presented provides a novel, comprehensive and reliable tool for investigating metabolic stability, factors that affect it, and the proposed structures of metabolites at the same time. The performance of the DFT-SVM-based approach provides an opportunity to implement it in a standard drug development pipeline.

Sampling with poling-based flux balance analysis: optimal versus sub-optimal flux space analysis of Actinobacillus succinogenes

BACKGROUND

Flux balance analysis is traditionally implemented to identify the maximum theoretical flux for some specified reaction and a single distribution of flux values for all the reactions present which achieve this maximum value. However it is well known that the uncertainty in reaction networks due to branches, cycles and experimental errors results in a large number of combinations of internal reaction fluxes which can achieve the same optimal flux value.

RESULTS

In this work, we have modified the applied linear objective of flux balance analysis to include a poling penalty function, which pushes each new set of reaction fluxes away from previous solutions generated. Repeated poling-based flux balance analysis generates a sample of different solutions (a characteristic set), which represents all the possible functionality of the reaction network. Compared to existing sampling methods, for the purpose of generating a relatively "small" characteristic set, our new method is shown to obtain a higher coverage than competing methods under most conditions. The influence of the linear objective function on the sampling (the linear bias) constrains optimisation results to a subspace of optimal solutions all producing the same maximal fluxes. Visualisation of reaction fluxes plotted against each other in 2 dimensions with and without the linear bias indicates the existence of correlations between fluxes. This method of sampling is applied to the organism Actinobacillus succinogenes for the production of succinic acid from glycerol.

CONCLUSIONS

A new method of sampling for the generation of different flux distributions (sets of individual fluxes satisfying constraints on the steady-state mass balances of intermediates) has been developed using a relatively simple modification of flux balance analysis to include a poling penalty function inside the resulting optimisation objective function. This new methodology can achieve a high coverage of the possible flux space and can be used with and without linear bias to show optimal versus sub-optimal solution spaces. Basic analysis of the Actinobacillus succinogenes system using sampling shows that in order to achieve the maximal succinic acid production CO₂ must be taken into the system. Solutions involving release of CO₂ all give sub-optimal succinic acid production.

A systems approach to predict oncometabolites via context-specific genome-scale metabolic networks

Altered metabolism in cancer cells has been viewed as a passive response required for a malignant transformation. However, this view has changed through the recently described metabolic oncogenic factors: mutated isocitrate dehydrogenases (IDH), succinate dehydrogenase (SDH), and fumarate hydratase (FH) that produce oncometabolites that competitively inhibit epigenetic regulation. In this study, we demonstrate in silico predictions of oncometabolites that have the potential to dysregulate epigenetic controls in nine types of cancer by incorporating massive scale genetic mutation information (collected from more than 1,700 cancer genomes), expression profiling data, and deploying Recon 2 to reconstruct context-specific genome-scale metabolic models. Our analysis predicted 15 compounds and 24 substructures of potential oncometabolites that could result from the loss-of-function and gain-of-function mutations of metabolic enzymes, respectively. These results suggest a substantial potential for discovering unidentified oncometabolites in various forms of cancers.

Cancer and metabolism have been considered to be associated for a long period since Otto Warburg observed that tumor cells consume glucose and convert most of it to lactate, despite the presence of oxygen. However, the role of the Warburg effect in oncogenesis had been under doubt because no solid links between genetic variations in metabolic genes and cancer had been observed until recent days. When with the development of sequencing technologies, researchers found mutations in IDH1, IDH2 (isocitrate dehydrogenase) in medium-grade glioma and acute leukemia. As these mutated metabolic genes initiate unexpected enzymatic reactions, cancer cells show altered concentration of particular metabolites, here called “oncometabolites”. The oncometabolites regulate the epigenetic controls of cell differentiations. In this study, we predict potential oncometabolites that might originate from loss or gain-of-function mutations in nine types of cancer from massive scale cancer mutation data with a systems biology approach.

Cytochrome P450 site of metabolism prediction from 2D topological fingerprints using GPU accelerated probabilistic classifiers

Background

The prediction of sites and products of metabolism in xenobiotic compounds is key to the development of new chemical entities, where screening potential metabolites for toxicity or unwanted side-effects is of crucial importance. In this work 2D topological fingerprints are used to encode atomic sites and three probabilistic machine learning methods are applied: Parzen-Rosenblatt Window (PRW), Naive Bayesian (NB) and a novel approach called RASCAL (Random Attribute Subsampling Classification ALgorithm). These are implemented by randomly subsampling descriptor space to alleviate the problem often suffered by data mining methods of having to exactly match fingerprints, and in the case of PRW by measuring a distance between feature vectors rather than exact matching. The classifiers have been implemented in CUDA/C++ to exploit the parallel architecture of graphical processing units (GPUs) and is freely available in a public repository.

Results

It is shown that for PRW a SoM (Site of Metabolism) is identified in the top two predictions for 85%, 91% and 88% of the CYP 3A4, 2D6 and 2C9 data sets respectively, with RASCAL giving similar performance of 83%, 91% and 88%, respectively. These results put PRW and RASCAL performance ahead of NB which gave a much lower classification performance of 51%, 73% and 74%, respectively.

Conclusions

2D topological fingerprints calculated to a bond depth of 4-6 contain sufficient information to allow the identification of SoMs using classifiers based on relatively small data sets. Thus, the machine learning methods outlined in this paper are conceptually simpler and more efficient than other methods tested and the use of simple topological descriptors derived from 2D structure give results competitive with other approaches using more expensive quantum chemical descriptors. The descriptor space subsampling approach and ensemble methodology allow the methods to be applied to molecules more distant from the training data where data mining would be more likely to fail due to the lack of common fingerprints. The RASCAL algorithm is shown to give equivalent classification performance to PRW but at lower computational expense allowing it to be applied more efficiently in the ensemble scheme.

Computational tools for modeling xenometabolism of the human gut microbiota

The gut microbiota is increasingly being recognized as a key site of metabolism for drugs and other xenobiotic compounds that are relevant to human health. The molecular complexity of the gut microbiota revealed by recent metagenomics studies has highlighted the need as well as the challenges for system-level modeling of xenobiotic metabolism in the gut. Here, we outline the possible pathways through which the gut microbiota can modify xenobiotics and review the available computational tools towards modeling complex xenometabolic processes. We put these diverse computational tools and relevant experimental findings into a unified perspective towards building holistic models of xenobiotic metabolism in the gut.

Metabolism site prediction based on xenobiotic structural formulas and PASS prediction algorithm

A new ligand-based method for the prediction of sites of metabolism (SOMs) for xenobiotics has been developed on the basis of the LMNA (labeled multilevel neighborhoods of atom) descriptors and the PASS (prediction of activity spectra for substances) algorithm and applied to predict the SOMs of the 1A2, 2C9, 2C19, 2D6, and 3A4 isoforms of cytochrome P450. An average IAP (invariant accuracy of prediction) of SOMs calculated by the leave-one-out cross-validation procedure was 0.89 for the developed method. The external validation was made with evaluation sets containing data on biotransformations for 57 cardiovascular drugs. An average IAP of regioselectivity for evaluation sets was 0.83. It was shown that the proposed method exceeds accuracy of SOM prediction by RS-Predictor for CYP 1A2, 2D6, 2C9, 2C19, and 3A4 and is comparable to or better than SMARTCyp for CYP 2C9 and 2D6.

In silico enzymatic synthesis of a 400,000 compound biochemical database for nontargeted metabolomics

Current methods of structure identification in mass-spectrometry-based nontargeted metabolomics rely on matching experimentally determined features of an unknown compound to those of candidate compounds contained in biochemical databases. A major limitation of this approach is the relatively small number of compounds currently included in these databases. If the correct structure is not present in a database, it cannot be identified, and if it cannot be identified, it cannot be included in a database. Thus, there is an urgent need to augment metabolomics databases with rationally designed biochemical structures using alternative means. Here we present the In Vivo/In Silico Metabolites Database (IIMDB), a database of in silico enzymatically synthesized metabolites, to partially address this problem. The database, which is available at http://metabolomics.pharm.uconn.edu/iimdb/, includes ~23,000 known compounds (mammalian metabolites, drugs, secondary plant metabolites, and glycerophospholipids) collected from existing biochemical databases plus more than 400,000 computationally generated human phase-I and phase-II metabolites of these known compounds. IIMDB features a user-friendly web interface and a programmer-friendly RESTful web service. Ninety-five percent of the computationally generated metabolites in IIMDB were not found in any existing database. However, 21,640 were identical to compounds already listed in PubChem, HMDB, KEGG, or HumanCyc. Furthermore, the vast majority of these in silico metabolites were scored as biological using BioSM, a software program that identifies biochemical structures in chemical structure space. These results suggest that in silico biochemical synthesis represents a viable approach for significantly augmenting biochemical databases for nontargeted metabolomics applications.

QSAR classification of metabolic activation of chemicals into covalently reactive species

Metabolic activation of chemicals into covalently reactive species might lead to toxicological consequences such as tissue necrosis, carcinogenicity, teratogenicity, or immune-mediated toxicities. Early prediction of this undesirable outcome can help in selecting candidates with increased chance of success, thus, reducing attrition at all stages of drug development. The ensemble modelling of mixed features was used for the development of a model to classify the metabolic activation of chemicals into covalently reactive species. The effects of the quality of base classifiers and performance measure for sorting were examined. An ensemble model of 13 naive Bayes classifiers was built from a diverse set of 1,479 compounds. The ensemble model was validated internally with five-fold cross validation and it has achieved sensitivity of 67.4% and specificity of 93.4% when tested on the training set. The final ensemble model was made available for public use.

Computational prediction of metabolism: sites, products, SAR, P450 enzyme dynamics, and mechanisms

Metabolism of xenobiotics remains a central challenge for the discovery and development of drugs, cosmetics, nutritional supplements, and agrochemicals. Metabolic transformations are frequently related to the incidence of toxic effects that may result from the emergence of reactive species, the systemic accumulation of metabolites, or by induction of metabolic pathways. Experimental investigation of the metabolism of small organic molecules is particularly resource demanding; hence, computational methods are of considerable interest to complement experimental approaches. This review provides a broad overview of structure- and ligand-based computational methods for the prediction of xenobiotic metabolism. Current computational approaches to address xenobiotic metabolism are discussed from three major perspectives: (i) prediction of sites of metabolism (SOMs), (ii) elucidation of potential metabolites and their chemical structures, and (iii) prediction of direct and indirect effects of xenobiotics on metabolizing enzymes, where the focus is on the cytochrome P450 (CYP) superfamily of enzymes, the cardinal xenobiotics metabolizing enzymes. For each of these domains, a variety of approaches and their applications are systematically reviewed, including expert systems, data mining approaches, quantitative structure–activity relationships (QSARs), and machine learning-based methods, pharmacophore-based algorithms, shape-focused techniques, molecular interaction fields (MIFs), reactivity-focused techniques, protein–ligand docking, molecular dynamics (MD) simulations, and combinations of methods. Predictive metabolism is a developing area, and there is still enormous potential for improvement. However, it is clear that the combination of rapidly increasing amounts of available ligand- and structure-related experimental data (in particular, quantitative data) with novel and diverse simulation and modeling approaches is accelerating the development of effective tools for prediction of in vivo metabolism, which is reflected by the diverse and comprehensive data sources and methods for metabolism prediction reviewed here. This review attempts to survey the range and scope of computational methods applied to metabolism prediction and also to compare and contrast their applicability and performance.