Extended Functional Groups (EFG): An Efficient Set for Chemical Characterization and Structure-Activity Relationship Studies of Chemical Compounds

The state-of-the-art machine learning model for Plasma Protein Binding Prediction: computational modeling with OCHEM and experimental validation

Plasma protein binding (PPB) is closely related to pharmacokinetics, pharmacodynamics and drug toxicity. Existing models for predicting PPB often suffer from low prediction accuracy and poor interpretability, especially for high PPB compounds, and are most often not experimentally validated. Here, we carried out a strict data curation protocol, and applied consensus modeling to obtain a model with a coefficient of determination of 0.90 and 0.91 on the training set and the test set, respectively. This model (available on the OCHEM platform https://ochem.eu/article/29) was further retrospectively validated for a set of 63 poly-fluorinated molecules and prospectively validated for a set of 25 highly diverse compounds, and its performance for both these sets was superior to that of the other previously reported models. Furthermore, we identified the physicochemical and structural characteristics of high and low PPB molecules for further structural optimization. Finally, we provide practical and detailed recommendations for structural optimization to decrease PPB binding of lead compounds.

RDCanon: A Python Package for Canonicalizing the Order of Tokens in SMARTS Queries

SMARTS is a widely used language in cheminformatics for defining substructural queries for database lookups, reaction templates for chemical transformations, and other applications. As an extension to SMILES, many SMARTS patterns can represent the same query. Despite this, no canonicalization algorithm invariant of the line notation sequence or atomic numbering is publicly available. Here, we introduce RDCanon, an open-source Python package that can be used to standardize SMARTS queries. RDCanon is designed to ensure that the sequence of atomic queries remains consistent for all graphs representing the same substructure query and to ensure a canonical sequence of primitives within each individual atom query; furthermore, the algorithm can be applied to canonicalize the order of reactants, agents, and products and their atom map numbers in reaction SMARTS templates. As part of its canonicalization algorithm, RDCanon provides a mechanism in which the canonicalized SMARTS is optimized for speed against specific molecular databases. Several case studies are provided to showcase improved efficiency in substructure matching and retrosynthetic analysis.

CRD: A de novo design algorithm for the prediction of cognate protein receptors for small molecule ligands

While predicting a ligand that binds to a protein is feasible with current methods, the opposite, i.e., the prediction of a receptor for a ligand remains challenging. We present an approach for predicting receptors of a given ligand that uses de novo design and structural bioinformatics. We have developed the algorithm CRD, comprising multiple modules combining fragment-based sub-site finding, a machine learning function to estimate the size of the site, a genetic algorithm that encodes knowledge on protein structures and a physics-based fitness scoring scheme. CRD includes a pseudo-receptor design component followed by a mapping component to identify proteins that might contain these sites. CRD recovers the sites and receptors of several natural ligands. It designs similar sites for similar ligands, yet to some extent can distinguish between closely related ligands. CRD correctly predicts receptor classes for several drugs and might become a valuable tool for drug discovery.

Dataset Design for Building Models of Chemical Reactivity

Models can codify our understanding of chemical reactivity and serve a useful purpose in the development of new synthetic processes via, for example, evaluating hypothetical reaction conditions or in silico substrate tolerance. Perhaps the most determining factor is the composition of the training data and whether it is sufficient to train a model that can make accurate predictions over the full domain of interest. Here, we discuss the design of reaction datasets in ways that are conducive to data-driven modeling, emphasizing the idea that training set diversity and model generalizability rely on the choice of molecular or reaction representation. We additionally discuss the experimental constraints associated with generating common types of chemistry datasets and how these considerations should influence dataset design and model building.

Quantifying Functional-Group-like Structural Fragments in Molecules and Its Applications in Drug Design

A functional group in a molecule is a structural fragment consisting of a few atoms or a single atom that imparts reactivity to a molecule. Hence, defining functional groups is crucial in chemistry to predict the properties and reactivities of molecules. However, there is no established method in the literature for defining functional groups based on reactivity parameters. In this work, we addressed this issue by designing a set of predefined structural fragments along with reactivity parameters like electron conjugation and ring strain. This approach uses bond orders and atom connectivities to quantify the presence of these fragments within an organic molecule based on a given input molecular coordinate. To assess the effectiveness of this approach, we performed a case study to show the benefits of using these newly designed structural fragments instead of traditional fingerprint-based methods for grouping potential COX1/COX2 inhibitors by screening an approved drug library against aspirin molecule. The structural fragment-based model for ternary classification of rat oral LD₅₀ of chemicals showed performance similar to the fingerprint-based models. In evaluating the regression model performance for aqueous solubility, log(S), predictions, our approach outperformed the fingerprint-based model.

MORTAR: a rich client application for in silico molecule fragmentation

Developing and implementing computational algorithms for the extraction of specific substructures from molecular graphs (in silico molecule fragmentation) is an iterative process. It involves repeated sequences of implementing a rule set, applying it to relevant structural data, checking the results, and adjusting the rules. This requires a computational workflow with data import, fragmentation algorithm integration, and result visualisation. The described workflow is normally unavailable for a new algorithm and must be set up individually. This work presents an open Java rich client Graphical User Interface (GUI) application to support the development of new in silico molecule fragmentation algorithms and make them readily available upon release. The MORTAR (MOlecule fRagmenTAtion fRamework) application visualises fragmentation results of a set of molecules in various ways and provides basic analysis features. Fragmentation algorithms can be integrated and developed within MORTAR by using a specific wrapper class. In addition, fragmentation pipelines with any combination of the available fragmentation methods can be executed. Upon release, three fragmentation algorithms are already integrated: ErtlFunctionalGroupsFinder, Sugar Removal Utility, and Scaffold Generator. These algorithms, as well as all cheminformatics functionalities in MORTAR, are implemented based on the Chemistry Development Kit (CDK).

ReLMole: Molecular Representation Learning Based on Two-Level Graph Similarities

Molecular representation is a critical part of various prediction tasks for physicochemical properties of molecules and drug design. As graph notations are common in expressing the structural information of chemical compounds, graph neural networks (GNNs) have become the mainstream backbone model for learning molecular representation. However, the scarcity of task-specific labels in the biomedical domain limits the power of GNNs. Recently, self-supervised pretraining for GNNs has been leveraged to deal with this issue, while the existing pretraining methods are mainly designed for graph data in general domains without considering the specific data properties of molecules. In this paper, we propose a representation learning method for molecular graphs, called ReLMole, which is featured by a hierarchical graph modeling of molecules and a contrastive learning scheme based on two-level graph similarities. We assess the performance of ReLMole on two types of downstream tasks, namely, the prediction of molecular properties (MPs) and drug-drug interaction (DDIs). ReLMole achieves promising results for all the tasks. It outperforms the baseline models by over 2.6% on ROC-AUC averaged across six MP prediction tasks, and it improves the F1 value by 7-18% in DDI prediction for unseen drugs compared with other self-supervised models.

In Silico Structure-Based Approach for Group Efficiency Estimation in Fragment-Based Drug Design Using Evaluation of Fragment Contributions

The notion of a contribution of a specific group in an organic molecule's property and/or activity is both common in our thinking and is still not strictly correct due to the inherent non-additivity of free energy with respect to molecular fragments composing a molecule. The fragment- based drug discovery (FBDD) approach has proven to be fruitful in addressing the above notions. The main difficulty of the FBDD, however, is in its reliance on the low throughput and expensive experimental means of determining the fragment-sized molecules binding. In this article we propose a way to enhance the throughput and availability of the FBDD methods by judiciously using an in silico means of assessing the contribution to ligand-receptor binding energy of fragments of a molecule under question using a previously developed in silico Reverse Fragment Based Drug Discovery (R-FBDD) approach. It has been shown that the proposed structure-based drug discovery (SBDD) type of approach fills in the vacant niche among the existing in silico approaches, which mainly stem from the ligand-based drug discovery (LBDD) counterparts. In order to illustrate the applicability of the approach, our work retrospectively repeats the findings of the use case of an FBDD hit-to-lead project devoted to the experimentally based determination of additive group efficiency (GE)-an analog of ligand efficiency (LE) for a group in the molecule-using the Free-Wilson (FW) decomposition. It is shown that in using our in silico approach to evaluate fragment contributions of a ligand and to estimate GE one can arrive at similar decisions as those made using the experimentally determined activity-based FW decomposition. It is also shown that the approach is rather robust to the choice of the scoring function, provided the latter demonstrates a decent scoring power. We argue that the proposed approach of in silico assessment of GE has a wider applicability domain and expect that it will be widely applicable to enhance the net throughput of drug discovery based on the FBDD paradigm.

What Features of Ligands Are Relevant to the Opening of Cryptic Pockets in Drug Targets?

Small-molecule drug design aims to identify inhibitors that can specifically bind to a functionally important region on the target, i.e., an active site of an enzyme. Identification of potential binding pockets is typically based on static three-dimensional structures. However, small molecules may induce and select a dynamic binding pocket that is not visible in the apo protein, which presents a well-recognized challenge for structure-based drug discovery. Here, we assessed whether it is possible to identify features in molecules, which we refer to as inducers, that can induce the opening of cryptic pockets. The volume change between apo and bound protein conformations was used as a metric to differentiate chemical features in inducers vs. non-inducers. Based on the dataset of holo–apo pairs, classification models were built to determine an optimum threshold. The model analysis suggested that inducers preferred to be more hydrophobic and aromatic. The impact of sulfur was ambiguous, while phosphorus and halogen atoms were overrepresented in inducers. The fragment analysis showed that small changes in the structures of molecules can strongly affect the potential to induce a cryptic pocket. This analysis and developed model can be used to design inducers that can potentially open cryptic pockets for undruggable proteins.

Screening of 6000 Compounds for Uncoupling Activity: A Comparison Between a Mechanistic Biophysical Model and the Structural Alert Profiler Mitotox

Protonophoric uncoupling of phosphorylation is an important factor when assessing chemicals for their toxicity, and has recently moved into focus in pharmaceutical research with respect to the treatment of diseases such as cancer, diabetes, or obesity. Reliably identifying uncoupling activity is thus a valuable goal. To that end, we screened more than 6000 anionic compounds for in vitro uncoupling activity, using a biophysical model based on ab initio COSMO-RS input parameters with the molecular structure as the only external input. We combined these results with a model for baseline toxicity (narcosis). Our model identified more than 1250 possible uncouplers in the screening dataset, and identified possible new uncoupler classes such as thiophosphoric acids. When tested against 423 known uncouplers and 612 known inactive compounds in the dataset, the model reached a sensitivity of 83% and a specificity of 96%. In a direct comparison, it showed a similar specificity than the structural alert profiler Mitotox (97%), but much higher sensitivity than Mitotox (47%). The biophysical model thus allows for a more accurate screening for uncoupling activity than existing structural alert profilers. We propose to use our model as a complementary tool to screen large datasets for protonophoric uncoupling activity in drug development and toxicity assessment.

Highly Accurate Filters to Flag Frequent Hitters in AlphaScreen Assays by Suggesting their Mechanism

AlphaScreen is one of the most widely used assay technologies in drug discovery due to its versatility, dynamic range and sensitivity. However, a presence of false positives and frequent hitters contributes to difficulties with an interpretation of measured HTS data. Although filters do exist to identify frequent hitters for AlphaScreen, they are frequently based on privileged scaffolds. The development of such filters is time consuming and requires deep domain knowledge. Recently, machine learning and artificial intelligence methods are emerging as important tools to advance drug discovery and chemoinformatics, including their application to identification of frequent hitters in screening assays. However, the relative performance and complementarity of the Machine Learning and scaffold-based techniques has not yet been comprehensively compared. In this study, we analysed filters based on the privileged scaffolds with filters built using machine learning. Our results demonstrate that machine-learning methods provide more accurate filters for identification of frequent hitters in AlphaScreen assays than scaffold-based methods and can be easily redeveloped once new data are measured. We present highly accurate models to identify frequent hitters in AlphaScreen assays.

CATMoS: Collaborative Acute Toxicity Modeling Suite

BACKGROUND

Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests. In silico models built using existing data facilitate rapid acute toxicity predictions without using animals.

OBJECTIVES

The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop in silico models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (LD50 value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals [LD50 (LD50≤50mg/kg)], and nontoxic chemicals (LD50>2,000mg/kg).

METHODS

An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches.

RESULTS

The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with in vivo results.

DISCUSSION

CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for in vivo rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.

Trade-off Predictivity and Explainability for Machine-Learning Powered Predictive Toxicology: An in-Depth Investigation with Tox21 Data Sets

Selecting a model in predictive toxicology often involves a trade-off between prediction performance and explainability: should we sacrifice the model performance to gain explainability or vice versa. Here we present a comprehensive study to assess algorithm and feature influences on model performance in chemical toxicity research. We conducted over 5000 models for a Tox21 bioassay data set of 65 assays and ∼7600 compounds. Seven molecular representations as features and 12 modeling approaches varying in complexity and explainability were employed to systematically investigate the impact of various factors on model performance and explainability. We demonstrated that end points dictated a model's performance, regardless of the chosen modeling approach including deep learning and chemical features. Overall, more complex models such as (LS-)SVM and Random Forest performed marginally better than simpler models such as linear regression and KNN in the presented Tox21 data analysis. Since a simpler model with acceptable performance often also is easy to interpret for the Tox21 data set, it clearly was the preferred choice due to its better explainability. Given that each data set had its own error structure both for dependent and independent variables, we strongly recommend that it is important to conduct a systematic study with a broad range of model complexity and feature explainability to identify model balancing its predictivity and explainability.

Recent advances in constraint and machine learning-based metabolic modeling by leveraging stoichiometric balances, thermodynamic feasibility and kinetic law formalisms

Understanding the governing principles behind organisms' metabolism and growth underpins their effective deployment as bioproduction chassis. A central objective of metabolic modeling is predicting how metabolism and growth are affected by both external environmental factors and internal genotypic perturbations. The fundamental concepts of reaction stoichiometry, thermodynamics, and mass action kinetics have emerged as the foundational principles of many modeling frameworks designed to describe how and why organisms allocate resources towards both growth and bioproduction. This review focuses on the latest algorithmic advancements that have integrated these foundational principles into increasingly sophisticated quantitative frameworks.

ChemFLuo: a web-server for structure analysis and identification of fluorescent compounds

BACKGROUND

Fluorescent detection methods are indispensable tools for chemical biology. However, the frequent appearance of potential fluorescent compound has greatly interfered with the recognition of compounds with genuine activity. Such fluorescence interference is especially difficult to identify as it is reproducible and possesses concentration-dependent characteristic. Therefore, the development of a credible screening tool to detect fluorescent compounds from chemical libraries is urgently needed in early stages of drug discovery.

RESULTS

In this study, we developed a webserver ChemFLuo for fluorescent compound detection, based on two large and high-quality training datasets containing 4906 blue and 8632 green fluorescent compounds. These molecules were used to construct a group of prediction models based on the combination of three machine learning algorithms and seven types of molecular representations. The best blue fluorescence prediction model achieved with balanced accuracy (BA) = 0.858 and area under the receiver operating characteristic curve (AUC) = 0.931 for the validation set, and BA = 0.823 and AUC = 0.903 for the test set. The best green fluorescence prediction model achieved the prediction accuracy with BA = 0.810 and AUC = 0.887 for the validation set, and BA = 0.771 and AUC = 0.852 for the test set. Besides prediction model, 22 blue and 16 green representative fluorescent substructures were summarized for the screening of potential fluorescent compounds. The comparison with other fluorescence detection tools and theapplication to external validation sets and large molecule libraries have demonstrated the reliability of prediction model for fluorescent compound detection.

CONCLUSION

ChemFLuo is a public webserver to filter out compounds with undesirable fluorescent properties, which will benefit the design of high-quality chemical libraries for drug discovery. It is freely available at http://admet.scbdd.com/chemfluo/index/.

Scopy: an integrated negative design python library for desirable HTS/VS database design

BACKGROUND

High-throughput screening (HTS) and virtual screening (VS) have been widely used to identify potential hits from large chemical libraries. However, the frequent occurrence of 'noisy compounds' in the screened libraries, such as compounds with poor drug-likeness, poor selectivity or potential toxicity, has greatly weakened the enrichment capability of HTS and VS campaigns. Therefore, the development of comprehensive and credible tools to detect noisy compounds from chemical libraries is urgently needed in early stages of drug discovery.

RESULTS

In this study, we developed a freely available integrated python library for negative design, called Scopy, which supports the functions of data preparation, calculation of descriptors, scaffolds and screening filters, and data visualization. The current version of Scopy can calculate 39 basic molecular properties, 3 comprehensive molecular evaluation scores, 2 types of molecular scaffolds, 6 types of substructure descriptors and 2 types of fingerprints. A number of important screening rules are also provided by Scopy, including 15 drug-likeness rules (13 drug-likeness rules and 2 building block rules), 8 frequent hitter rules (four assay interference substructure filters and four promiscuous compound substructure filters), and 11 toxicophore filters (five human-related toxicity substructure filters, three environment-related toxicity substructure filters and three comprehensive toxicity substructure filters). Moreover, this library supports four different visualization functions to help users to gain a better understanding of the screened data, including basic feature radar chart, feature-feature-related scatter diagram, functional group marker gram and cloud gram.

CONCLUSION

Scopy provides a comprehensive Python package to filter out compounds with undesirable properties or substructures, which will benefit the design of high-quality chemical libraries for drug design and discovery. It is freely available at https://github.com/kotori-y/Scopy.

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Risk assessment of newly synthesised chemicals is a prerequisite for regulatory approval. In this context, in silico methods have great potential to reduce time, cost, and ultimately animal testing as they make use of the ever-growing amount of available toxicity data. Here, KnowTox is presented, a novel pipeline that combines three different in silico toxicology approaches to allow for confident prediction of potentially toxic effects of query compounds, i.e. machine learning models for 88 endpoints, alerts for 919 toxic substructures, and computational support for read-across. It is mainly based on the ToxCast dataset, containing after preprocessing a sparse matrix of 7912 compounds tested against 985 endpoints. When applying machine learning models, applicability and reliability of predictions for new chemicals are of utmost importance. Therefore, first, the conformal prediction technique was deployed, comprising an additional calibration step and per definition creating internally valid predictors at a given significance level. Second, to further improve validity and information efficiency, two adaptations are suggested, exemplified at the androgen receptor antagonism endpoint. An absolute increase in validity of 23% on the in-house dataset of 534 compounds could be achieved by introducing KNNRegressor normalisation. This increase in validity comes at the cost of efficiency, which could again be improved by 20% for the initial ToxCast model by balancing the dataset during model training. Finally, the value of the developed pipeline for risk assessment is discussed using two in-house triazole molecules. Compared to a single toxicity prediction method, complementing the outputs of different approaches can have a higher impact on guiding toxicity testing and de-selecting most likely harmful development-candidate compounds early in the development process.

Structural Analysis and Identification of False Positive Hits in Luciferase-Based Assays

Luciferase-based bioluminescence detection techniques are highly favored in high-throughput screening (HTS), in which the firefly luciferase (FLuc) is the most commonly used variant. However, FLuc inhibitors can interfere with the activity of luciferase, which may result in false positive signals in HTS assays. In order to reduce the unnecessary cost of time and money, an in silico prediction model for FLuc inhibitors is highly desirable. In this study, we built an extensive data set consisting of 20 888 FLuc inhibitors and 198 608 noninhibitors, and then developed a group of classification models based on the combination of three machine learning (ML) algorithms and four types of molecular representations. The best prediction model based on XGBoost and ECFP4 and MOE2d descriptors yielded a balanced accuracy (BA) of 0.878 and an area under the receiver operating characteristic curve (AUC) value of 0.958 for the validation set, and a BA of 0.886 and an AUC of 0.947 for the test set. Three external validation sets, including set 1 (3231 FLuc inhibitors and 69 783 noninhibitors), set 2 (695 FLuc inhibitors and 75 913 noninhibitors), and set 3 (1138 FLuc inhibitors and 8155 noninhibitors), were used to verify the predictive ability of our models. The BA values for the three external validation sets given by the best model are 0.864, 0.845, and 0.791, respectively. In addition, the important features or structural fragments related to FLuc inhibitors were recognized by the Shapley additive explanations (SHAP) method along with their influences on predictions, which may provide valuable clues to detecting undesirable luciferase inhibitors. Based on the important and explanatory features, 16 rules were proposed for detecting FLuc inhibitors, which can achieve a correction rate of 70% for FLuc inhibitors. Furthermore, a comparison with existing prediction rules and models for FLuc inhibitors used in virtual screening verified the high reliability of the models and rules proposed in this study. We also used the model to screen three curated chemical databases, and almost 10% of the molecules in the evaluated databases were predicted as inhibitors, highlighting the potential risk of false positives in luciferase-based assays. Finally, a public web server called ChemFLuc was developed (http://admet.scbdd.com/chemfluc/index/), and it offers a free available service to predict potential FLuc inhibitors.

Enhancing reaction-based de novo design using a multi-label reaction class recommender

Reaction-based de novo design refers to the in-silico generation of novel chemical structures by combining reagents using structural transformations derived from known reactions. The driver for using reaction-based transformations is to increase the likelihood of the designed molecules being synthetically accessible. We have previously described a reaction-based de novo design method based on reaction vectors which are transformation rules that are encoded automatically from reaction databases. A limitation of reaction vectors is that they account for structural changes that occur at the core of a reaction only, and they do not consider the presence of competing functionalities that can compromise the reaction outcome. Here, we present the development of a Reaction Class Recommender to enhance the reaction vector framework. The recommender is intended to be used as a filter on the reaction vectors that are applied during de novo design to reduce the combinatorial explosion of in-silico molecules produced while limiting the generated structures to those which are most likely to be synthesisable. The recommender has been validated using an external data set extracted from the recent medicinal chemistry literature and in two simulated de novo design experiments. Results suggest that the use of the recommender drastically reduces the number of solutions explored by the algorithm while preserving the chance of finding relevant solutions and increasing the global synthetic accessibility of the designed molecules.

RxnBLAST: molecular scaffold and reactive chemical environment feature extractor for biochemical reactions

Motivation

Molecular scaffolds are useful in medicinal chemistry to describe, discuss and visualize series of chemical compounds, biochemical transformations and associated biological properties.

Results

Here, we present RxnBLAST as a web-based tool for analyzing scaffold transformations and reactive chemical environment features in bioreactions. RxnBLAST extracts chemical features from bioreactions including atom–atom mapping, reaction centers, rules and functional groups to help understand chemical compositions and reaction patterns. Core-to-Core is proposed, which can be utilized in scaffold networks and for constructing a reaction space, as well as providing guidance for subsequent biosynthesis efforts.

Availability and implementation

RxnBLAST is available at: http://design.rxnfinder.org/rxnblast/.

Flexible heuristic algorithm for automatic molecule fragmentation: application to the UNIFAC group contribution model

A priori calculation of thermophysical properties and predictive thermodynamic models can be very helpful for developing new industrial processes. Group contribution methods link the target property to contributions based on chemical groups or other molecular subunits of a given molecule. However, the fragmentation of the molecule into its subunits is usually done manually impeding the fast testing and development of new group contribution methods based on large databases of molecules. The aim of this work is to develop strategies to overcome the challenges that arise when attempting to fragment molecules automatically while keeping the definition of the groups as simple as possible. Furthermore, these strategies are implemented in two fragmentation algorithms. The first algorithm finds only one solution while the second algorithm finds all possible fragmentations. Both algorithms are tested to fragment a database of 20,000+ molecules for use with the group contribution model Universal Quasichemical Functional Group Activity Coefficients (UNIFAC). Comparison of the results with a reference database shows that both algorithms are capable of successfully fragmenting all the molecules automatically. Furthermore, when applying them on a larger database it is shown, that the newly developed algorithms are capable of fragmenting structures previously thought not possible to fragment.

Leveraging heterogeneous data from GHS toxicity annotations, molecular and protein target descriptors and Tox21 assay readouts to predict and rationalise acute toxicity

Despite the increasing knowledge in both the chemical and biological domains the assimilation and exploration of heterogeneous datasets, encoding information about the chemical, bioactivity and phenotypic properties of compounds, remains a challenge due to requirement for overlap between chemicals assayed across the spaces. Here, we have constructed a novel dataset, larger than we have used in prior work, comprising 579 acute oral toxic compounds and 1427 non-toxic compounds derived from regulatory GHS information, along with their corresponding molecular and protein target descriptors and qHTS in vitro assay readouts from the Tox21 project. We found no clear association between the results of a FAFDrugs4 toxicophore screen and the acute oral toxicity classifications for our compound set; and a screen using a subset of the ToxAlerts toxicophores was also of limited utility, with only slight enrichment toward the toxic set (odds ratio of 1.48). We then investigated to what degree toxic and non-toxic compounds could be separated in each of the spaces, to compare their potential contribution to further analyses. Using an LDA projection, we found the largest degree of separation using chemical descriptors (Cohen’s d of 1.95) and the lowest degree of separation between toxicity classes using qHTS descriptors (Cohen’s d of 0.67). To compare the predictivity of the feature spaces for the toxicity endpoint, we next trained Random Forest (RF) acute oral toxicity classifiers on either molecular, protein target and qHTS descriptors. RFs trained on molecular and protein target descriptors were most predictive, with ROC AUC values of 0.80–0.92 and 0.70–0.85, respectively, across three test sets. RFs trained on both chemical and protein target descriptors combined exhibited similar predictive performance to the single-domain models (ROC AUC of 0.80–0.91). Model interpretability was improved by the inclusion of protein target descriptors, which allow the identification of specific targets (e.g. Retinal dehydrogenase) with literature links to toxic modes of action (e.g. oxidative stress). The dataset compiled in this study has been made available for future application.

Luciferase Advisor: High-Accuracy Model To Flag False Positive Hits in Luciferase HTS Assays

Firefly luciferase is an enzyme that has found ubiquitous use in biological assays in high-throughput screening (HTS) campaigns. The inhibition of luciferase in such assays could lead to a false positive result. This issue has been known for a long time, and there have been significant efforts to identify luciferase inhibitors in order to enhance recognition of false positives in screening assays. However, although a large amount of publicly accessible luciferase counterscreen data is available, to date little effort has been devoted to building a chemoinformatic model that can identify such molecules in a given data set. In this study we developed models to identify these molecules using various methods, such as molecular docking, SMARTS screening, pharmacophores, and machine learning methods. Among the structure-based methods, the pharmacophore-based method showed promising results, with a balanced accuracy of 74.2%. However, machine-learning approaches using associative neural networks outperformed all of the other methods explored, producing a final model with a balanced accuracy of 89.7%. The high predictive accuracy of this model is expected to be useful for advising which compounds are potential luciferase inhibitors present in luciferase HTS assays. The models developed in this work are freely available at the OCHEM platform at http://ochem.eu .

Matched Molecular Pair Analysis on Large Melting Point Datasets: A Big Data Perspective

A matched molecular pair (MMP) analysis was used to examine the change in melting point (MP) between pairs of similar molecules in a set of ∼275k compounds. We found many cases in which the change in MP (ΔMP) of compounds correlates with changes in functional groups. In line with the results of a previous study, correlations between ΔMP and simple molecular descriptors, such as the number of hydrogen bond donors, were identified. In using a larger dataset, covering a wider chemical space and range of melting points, we observed that this method remains stable and scales well with larger datasets. This MMP-based method could find use as a simple privacy-preserving technique to analyze large proprietary databases and share findings between participating research groups.

An algorithm to identify functional groups in organic molecules

Background

The concept of functional groups forms a basis of organic chemistry, medicinal chemistry, toxicity assessment, spectroscopy and also chemical nomenclature. All current software systems to identify functional groups are based on a predefined list of substructures. We are not aware of any program that can identify all functional groups in a molecule automatically. The algorithm presented in this article is an attempt to solve this scientific challenge.

Results

An algorithm to identify functional groups in a molecule based on iterative marching through its atoms is described. The procedure is illustrated by extracting functional groups from the bioactive portion of the ChEMBL database, resulting in identification of 3080 unique functional groups.

Conclusions

A new algorithm to identify all functional groups in organic molecules is presented. The algorithm is relatively simple and full details with examples are provided, therefore implementation in any cheminformatics toolkit should be relatively easy. The new method allows the analysis of functional groups in large chemical databases in a way that was not possible using previous approaches.

Electronic supplementary material

The online version of this article (doi:10.1186/s13321-017-0225-z) contains supplementary material, which is available to authorized users.

Public (Q)SAR Services, Integrated Modeling Environments, and Model Repositories on the Web: State of the Art and Perspectives for Future Development

Thousands of (Quantitative) Structure-Activity Relationships (Q)SAR models have been described in peer-reviewed publications; however, this way of sharing seldom makes models available for the use by the research community outside of the developer's laboratory. Conversely, on-line models allow broad dissemination and application representing the most effective way of sharing the scientific knowledge. Approaches for sharing and providing on-line access to models range from web services created by individual users and laboratories to integrated modeling environments and model repositories. This emerging transition from the descriptive and informative, but "static", and for the most part, non-executable print format to interactive, transparent and functional delivery of "living" models is expected to have a transformative effect on modern experimental research in areas of scientific and regulatory use of (Q)SAR models.

ToxCast EPA in Vitro to in Vivo Challenge: Insight into the Rank-I Model

The ToxCast EPA challenge was managed by TopCoder in Spring 2014. The goal of the challenge was to develop a model to predict the lowest effect level (LEL) concentration based on in vitro measurements and calculated in silico descriptors. This article summarizes the computational steps used to develop the Rank-I model, which calculated the lowest prediction error for the secret test data set of the challenge. The model was developed using the publicly available Online CHEmical database and Modeling environment (OCHEM), and it is freely available at http://ochem.eu/article/68104. Surprisingly, this model does not use any in vitro measurements. The logic of the decision steps used to develop the model and the reason to skip inclusion of in vitro measurements is described. We also show that inclusion of in vitro assays would not improve the accuracy of the model.

Special Issue: Chemoinformatics

Chemoinformatics techniques were originally developed for the construction and searching of large archives of chemical structures but they were soon applied to problems in drug discovery and are now playing an increasingly important role in many additional areas of chemistry. This Special Issue contains seven original research articles and four review articles that provide an introduction to several aspects of this rapidly developing field.

Identification of Small-Molecule Frequent Hitters of Glutathione S-Transferase–Glutathione Interaction

In high-throughput screening (HTS) campaigns, the binding of glutathione S-transferase (GST) to glutathione (GSH) is used for detection of GST-tagged proteins in protein-protein interactions or enzyme assays. However, many false-positives, so-called frequent hitters (FH), arise that either prevent GST/GSH interaction or interfere with assay signal generation or detection. To identify GST-FH compounds, we analyzed the data of five independent AlphaScreen-based screening campaigns to classify compounds that inhibit the GST/GSH interaction. We identified 53 compounds affecting GST/GSH binding but not influencing His-tag/Ni2+-NTA interaction and general AlphaScreen signals. The structures of these 53 experimentally identified GST-FHs were analyzed in chemoinformatic studies to categorize substructural features that promote interference with GST/GSH binding. Here, we confirmed several existing chemoinformatic filters and more importantly extended them as well as added novel filters that specify compounds with anti–GST/GSH activity. Selected compounds were also tested using different antibody-based GST detection technologies and exhibited no interference clearly demonstrating specificity toward their GST/GSH interaction. Thus, these newly described GST-FH will further contribute to the identification of FH compounds containing promiscuous substructures. The developed filters were uploaded to the OCHEM website ( http://ochem.eu ) and are publicly accessible for analysis of future HTS results.

Lowe D, Williams AJ. The development of models to predict melting and pyrolysis point data associated with several hundred thousand compounds mined from PATENTS

BACKGROUND

Melting point (MP) is an important property in regards to the solubility of chemical compounds. Its prediction from chemical structure remains a highly challenging task for quantitative structure-activity relationship studies. Success in this area of research critically depends on the availability of high quality MP data as well as accurate chemical structure representations in order to develop models. Currently, available datasets for MP predictions have been limited to around 50k molecules while lots more data are routinely generated following the synthesis of novel materials. Significant amounts of MP data are freely available within the patent literature and, if it were available in the appropriate form, could potentially be used to develop predictive models.

RESULTS

We have developed a pipeline for the automated extraction and annotation of chemical data from published PATENTS. Almost 300,000 data points have been collected and used to develop models to predict melting and pyrolysis (decomposition) points using tools available on the OCHEM modeling platform (http://ochem.eu). A number of technical challenges were simultaneously solved to develop models based on these data. These included the handing of sparse data matrices with >200,000,000,000 entries and parallel calculations using 32 × 6 cores per task using 13 descriptor sets totaling more than 700,000 descriptors. We showed that models developed using data collected from PATENTS had similar or better prediction accuracy compared to the highly curated data used in previous publications. The separation of data for chemicals that decomposed rather than melting, from compounds that did undergo a normal melting transition, was performed and models for both pyrolysis and MPs were developed. The accuracy of the consensus MP models for molecules from the drug-like region of chemical space was similar to their estimated experimental accuracy, 32 °C. Last but not least, important structural features related to the pyrolysis of chemicals were identified, and a model to predict whether a compound will decompose instead of melting was developed.

CONCLUSIONS

We have shown that automated tools for the analysis of chemical information have reached a mature stage allowing for the extraction and collection of high quality data to enable the development of structure-activity relationship models. The developed models and data are publicly available at http://ochem.eu/article/99826.