Visualization and Interpretation of Support Vector Machine Activity Predictions

Topological regression as an interpretable and efficient tool for quantitative structure-activity relationship modeling

Quantitative structure-activity relationship (QSAR) modeling is a powerful tool for drug discovery, yet the lack of interpretability of commonly used QSAR models hinders their application in molecular design. We propose a similarity-based regression framework, topological regression (TR), that offers a statistically grounded, computationally fast, and interpretable technique to predict drug responses. We compare the predictive performance of TR on 530 ChEMBL human target activity datasets against the predictive performance of deep-learning-based QSAR models. Our results suggest that our sparse TR model can achieve equal, if not better, performance than the deep learning-based QSAR models and provide better intuitive interpretation by extracting an approximate isometry between the chemical space of the drugs and their activity space.

In silico prediction of ocular toxicity of compounds using explainable machine learning and deep learning approaches

The accurate identification of chemicals with ocular toxicity is of paramount importance in health hazard assessment. In contemporary chemical toxicology, there is a growing emphasis on refining, reducing, and replacing animal testing in safety evaluations. Therefore, the development of robust computational tools is crucial for regulatory applications. The performance of predictive models is heavily reliant on the quality and quantity of data. In this investigation, we amalgamated the most extensive dataset (4901 compounds) sourced from governmental GHS-compliant databases and literature to develop binary classification models of chemical ocular toxicity. We employed 12 molecular representations in conjunction with six machine learning algorithms and two deep learning algorithms to create a series of binary classification models. The findings indicated that the deep learning method GCN outperformed the machine learning models in cross-validation, achieving an impressive AUC of 0.915. However, the top-performing machine learning model (RF-Descriptor) demonstrated excellent performance with an AUC of 0.869 on the test set and was therefore selected as the best model. To enhance model interpretability, we conducted the SHAP method and attention weights analysis. The two approaches offered visual depictions of the relevance of key descriptors and substructures in predicting ocular toxicity of chemicals. Thus, we successfully struck a delicate balance between data quality and model interpretability, rendering our model valuable for predicting and comprehending potential ocular-toxic compounds in the early stages of drug discovery.

A radiogenomic multimodal and whole-transcriptome sequencing for preoperative prediction of axillary lymph node metastasis and drug therapeutic response in breast cancer: a retrospective, machine learning and international multicohort study

BACKGROUND

Axillary lymph nodes (ALN) status serves as a crucial prognostic indicator in breast cancer (BC). The aim of this study was to construct a radiogenomic multimodal model, based on machine learning and whole-transcriptome sequencing (WTS), to accurately evaluate the risk of ALN metastasis (ALNM), drug therapeutic response and avoid unnecessary axillary surgery in BC patients.

METHODS

In this study, conducted a retrospective analysis of 1078 BC patients from The Cancer Genome Atlas (TCGA), The Cancer Imaging Archive (TCIA), and Foshan cohort. These patients were divided into the TCIA cohort ( N =103), TCIA validation cohort ( N =51), Duke cohort ( N =138), Foshan cohort ( N =106), and TCGA cohort ( N =680). Radiological features were extracted from BC radiological images and differentially expressed gene expression was calibrated using technology. A support vector machine model was employed to screen radiological and genetic features, and a multimodal model was established based on radiogenomic and clinical pathological features to predict ALNM. The accuracy of the model predictions was assessed using the area under the curve (AUC) and the clinical benefit was measured using decision curve analysis. Risk stratification analysis of BC patients was performed by gene set enrichment analysis, differential comparison of immune checkpoint gene expression, and drug sensitivity testing.

RESULTS

For the prediction of ALNM, rad-score was able to significantly differentiate between ALN- and ALN+ patients in both the Duke and Foshan cohorts ( P <0.05). Similarly, the gene-score was able to significantly differentiate between ALN- and ALN+ patients in the TCGA cohort ( P <0.05). The radiogenomic multimodal nomogram demonstrated satisfactory performance in the TCIA cohort (AUC 0.82, 95% CI: 0.74-0.91) and the TCIA validation cohort (AUC 0.77, 95% CI: 0.63-0.91). In the risk sub-stratification analysis, there were significant differences in gene pathway enrichment between high and low-risk groups ( P <0.05). Additionally, different risk groups may exhibit varying treatment responses ( P <0.05).

CONCLUSION

Overall, the radiogenomic multimodal model employs multimodal data, including radiological images, genetic, and clinicopathological typing. The radiogenomic multimodal nomogram can precisely predict ALNM and drug therapeutic response in BC patients.

De Novo Generation and Identification of Novel Compounds with Drug Efficacy Based on Machine Learning

One of the main challenges in small molecule drug discovery is finding novel chemical compounds with desirable activity. Traditional drug development typically begins with target selection, but the correlation between targets and disease remains to be further investigated, and drugs designed based on targets may not always have the desired drug efficacy. The emergence of machine learning provides a powerful tool to overcome the challenge. Herein, a machine learning-based strategy is developed for de novo generation of novel compounds with drug efficacy termed DTLS (Deep Transfer Learning-based Strategy) by using dataset of disease-direct-related activity as input. DTLS is applied in two kinds of disease: colorectal cancer (CRC) and Alzheimer's disease (AD). In each case, novel compound is discovered and identified in in vitro and in vivo disease models. Their mechanism of actionis further explored. The experimental results reveal that DTLS can not only realize the generation and identification of novel compounds with drug efficacy but also has the advantage of identifying compounds by focusing on protein targets to facilitate the mechanism study. This work highlights the significant impact of machine learning on the design of novel compounds with drug efficacy, which provides a powerful new approach to drug discovery.

Generalizability Improvement of Interpretable Symbolic Regression Models for Quantitative Structure-Activity Relationships

In the pursuit of optimal quantitative structure-activity relationship (QSAR) models, two key factors are paramount: the robustness of predictive ability and the interpretability of the model. Symbolic regression (SR) searches for the mathematical expressions that explain a training data set. Thus, the models provided by SR are globally interpretable. We previously proposed an SR method that can generate interpretable expressions by humans. This study introduces an enhanced symbolic regression method, termed filter-induced genetic programming 2 (FIGP2), as an extension of our previously proposed SR method. FIGP2 is designed to improve the generalizability of SR models and to be applicable to data sets in which cost-intensive descriptors are employed. The FIGP2 method incorporates two major improvements: a modified domain filter to eradicate diverging expressions based on optimal calculation and the introduction of a stability metric to penalize expressions that would lead to overfitting. Our retrospective comparative analysis using 12 structure-activity relationship data sets revealed that FIGP2 surpassed the previously proposed SR method and conventional modeling methods, such as support vector regression and multivariate linear regression in terms of predictive performance. Generated mathematical expressions by FIGP2 were relatively simple and not divergent in the domain of function. Taken together, FIGP2 can be used for making interpretable regression models with predictive ability.

Screening and Validation of Odorants against Influenza A Virus Using Interpretable Regression Models

Influenza is a respiratory infection caused by the influenza virus that is prevalent worldwide. One of the most contagious variants of influenza is influenza A virus (IAV), which usually spreads in closed spaces through aerosols. Preventive measures such as novel compounds are needed that can act on viral membranes and provide a safe environment against IAV infection. In this study, we screened compounds with common fragrances that are generally used to mask unpleasant odors but can also exhibit antiviral activity against a strain of IAV. Initially, a set of 188 structurally diverse odorants were collected, and their antiviral activity was measured in vapor phase against the IAV solution. Regression models were built for the prediction of antiviral activity using this set of odorants by taking into account their structural features along with vapor pressure and partition coefficient (n-octanol/water). The models were interpreted using a feature weighting approach and Shapley Additive exPlanations to rationalize the predictions as an additional validation for virtual screening. This model was used to screen odorants from an in-house odorant data set consisting of 2020 odorants, which were later evaluated using in vitro experiments. Out of 11 odorants proposed using the final model, 8 odorants were found to exhibit antiviral activity. The feature interpretation of screened odorants suggested that they contained hydrophilic substructures, such as hydroxyl group, which might contribute to denaturation of proteins on the surface of the virus. These odorants should be explored as a preventive measure in closed spaces to decrease the risk of infections of IAV.

Extended Connectivity Fingerprints as a Chemical Reaction Representation for Enantioselective Organophosphorus-Catalyzed Asymmetric Reaction Prediction

Predicting the outcomes of organic reactions using data-driven approaches aids in the acceleration of research. In laboratory-scale experiments, only a small number of reaction data can be accessed for machine learning model construction, where reaction representations play a pivotal role in the success of model construction. Nevertheless, representation comparison for a small data set is not adequate. Herein, focusing on the enantioselectivity of phosphoric-acid-catalyzed reactions, various two-dimensional and three-dimensional reaction representations (descriptors) were compared. Overall, the concatenated form of the extended connectivity fingerprints showed the best predictive capability for the two types of data sets: high-throughput experimental data and manually collected literature data sets. Furthermore, highlighting the substructure contribution to the prediction outcome was shown to be informative for guiding catalyst development.

Calculation of Exact Shapley Values for Support Vector Machines with Tanimoto Kernel Enables Model Interpretation

The support vector machine (SVM) algorithm is popular in chemistry and drug discovery. SVM models have black box character. Their predictions can be interpreted through feature weighting or the model-agnostic Shapley additive explanations (SHAP) formalism that locally approximates Shapley values (SVs) originating from game theory. We introduce an algorithm termed SV-expressed Tanimoto similarity (SVETA) for the exact calculation of SVs to explain SVM models employing the Tanimoto kernel, the gold standard for the assessment of molecular similarity. For a model system, the exact calculation of SVs is demonstrated. In an SVM-based compound classification task from drug discovery, only a limited correlation between exact SV and SHAP values is observed, prohibiting the use of approximate values for rationalizing predictions. For exemplary test compounds, atom-based mapping of prioritized features delineates coherent substructures that closely resemble those obtained by analyzing independently derived random forest models, thus providing consistent explanations.

•

SVETA: new methodology for explaining support vector machine (SVM) predictions

•

Tanimoto similarity-based SVM models are popular in chemistry

•

SVETA enables the calculation of exact Shapley values for rationalizing SVM models

•

SVETA-based feature mapping provides intuitive explanations of SVM decisions

Machine Learning in Chemoinformatics and Medicinal Chemistry

In chemoinformatics and medicinal chemistry, machine learning has evolved into an important approach. In recent years, increasing computational resources and new deep learning algorithms have put machine learning onto a new level, addressing previously unmet challenges in pharmaceutical research. In silico approaches for compound activity predictions, de novo design, and reaction modeling have been further advanced by new algorithmic developments and the emergence of big data in the field. Herein, novel applications of machine learning and deep learning in chemoinformatics and medicinal chemistry are reviewed. Opportunities and challenges for new methods and applications are discussed, placing emphasis on proper baseline comparisons, robust validation methodologies, and new applicability domains. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 5 is August 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Evolution of Support Vector Machine and Regression Modeling in Chemoinformatics and Drug Discovery

The support vector machine (SVM) algorithm is one of the most widely used machine learning (ML) methods for predicting active compounds and molecular properties. In chemoinformatics and drug discovery, SVM has been a state-of-the-art ML approach for more than a decade. A unique attribute of SVM is that it operates in feature spaces of increasing dimensionality. Hence, SVM conceptually departs from the paradigm of low dimensionality that applies to many other methods for chemical space navigation. The SVM approach is applicable to compound classification, and ranking, multi-class predictions, and –in algorithmically modified form– regression modeling. In the emerging era of deep learning (DL), SVM retains its relevance as one of the premier ML methods in chemoinformatics, for reasons discussed herein. We describe the SVM methodology including strengths and weaknesses and discuss selected applications that have contributed to the evolution of SVM as a premier approach for compound classification, property predictions, and virtual compound screening.

Explainable Machine Learning for Property Predictions in Compound Optimization

The prediction of compound properties from chemical structure is a main task for machine learning (ML) in medicinal chemistry. ML is often applied to large data sets in applications such as compound screening, virtual library enumeration, or generative chemistry. Albeit desirable, a detailed understanding of ML model decisions is typically not required in these cases. By contrast, compound optimization efforts rely on small data sets to identify structural modifications leading to desired property profiles. In this situation, if ML is applied, one usually is reluctant to make decisions based on predictions that cannot be rationalized. Only few ML methods are interpretable. However, to yield insights into complex ML model decisions, explanatory approaches can be applied. Herein, methodologies for better understanding of ML models or explaining individual predictions are reviewed and current challenges in integrating ML into medicinal chemistry programs as well as future opportunities are discussed.

Explainable machine learning predictions of dual-target compounds reveal characteristic structural features

Compounds with defined multi-target activity play an increasingly important role in drug discovery. Structural features that might be signatures of such compounds have mostly remained elusive thus far. We have explored the potential of explainable machine learning to uncover structural motifs that are characteristic of dual-target compounds. For a pharmacologically relevant target pair-based test system designed for our study, accurate prediction models were derived and the influence of molecular representation features of test compounds was quantified to explain the predictions. The analysis revealed small numbers of specific features whose presence in dual-target and absence in single-target compounds determined accurate predictions. These features formed coherent substructures in dual-target compounds. From computational analysis of specific feature contributions, structural motifs emerged that were confirmed to be signatures of different dual-target activities. Our findings demonstrate the ability of explainable machine learning to bridge between predictions and intuitive chemical analysis and reveal characteristic substructures of dual-target compounds.

Interpretation of Ligand-Based Activity Cliff Prediction Models Using the Matched Molecular Pair Kernel

Activity cliffs (ACs) are formed by two structurally similar compounds with a large difference in potency. Accurate AC prediction is expected to help researchers' decisions in the early stages of drug discovery. Previously, predictive models based on matched molecular pair (MMP) cliffs have been proposed. However, the proposed methods face a challenge of interpretability due to the black-box character of the predictive models. In this study, we developed interpretable MMP fingerprints and modified a model-specific interpretation approach for models based on a support vector machine (SVM) and MMP kernel. We compared important features highlighted by this SVM-based interpretation approach and the SHapley Additive exPlanations (SHAP) as a major model-independent approach. The model-specific approach could capture the difference between AC and non-AC, while SHAP assigned high weights to the features not present in the test instances. For specific MMPs, the feature weights mapped by the SVM-based interpretation method were in agreement with the previously confirmed binding knowledge from X-ray co-crystal structures, indicating that this method is able to interpret the AC prediction model in a chemically intuitive manner.

Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics

Machine learning is widely applied in drug discovery research to predict molecular properties and aid in the identification of active compounds. Herein, we introduce a new approach that uses model-internal information from compound activity predictions to uncover relationships between target proteins. On the basis of a large-scale analysis generating and comparing machine learning models for more than 200 proteins, feature importance correlation analysis is shown to detect similar compound binding characteristics. Furthermore, rather unexpectedly, the analysis also reveals functional relationships between proteins that are independent of active compounds and binding characteristics. Feature importance correlation analysis does not depend on specific representations, algorithms, or metrics and is generally applicable as long as predictive models can be derived. Moreover, the approach does not require or involve explainable or interpretable machine learning, but only access to feature weights or importance values. On the basis of our findings, the approach represents a new facet of machine learning in drug discovery with potential for practical applications.

Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations

Compounds with defined multi-target activity (promiscuity) play an increasingly important role in drug discovery. However, the molecular basis of multi-target activity is currently only little understood. In particular, it remains unclear whether structural features exist that generally characterize promiscuous compounds and set them apart from compounds with single-target activity. We have devised a test system using machine learning to systematically examine structural features that might characterize compounds with multi-target activity. Using this system, more than 860,000 diagnostic predictions were carried out. The analysis provided compelling evidence for the presence of structural characteristics of promiscuous compounds that were dependent on given target combinations, but not generalizable. Feature weighting and mapping identified characteristic substructures in test compounds. Taken together, these findings are relevant for the design of compounds with desired multi-target activity.

Predicting Isoform-Selective Carbonic Anhydrase Inhibitors via Machine Learning and Rationalizing Structural Features Important for Selectivity

Carbonic anhydrases (CAs) catalyze the physiological hydration of carbon dioxide and are among the most intensely studied pharmaceutical target enzymes. A hallmark of CA inhibition is the complexation of the catalytic zinc cation in the active site. Human (h) CA isoforms belonging to different families are implicated in a wide range of diseases and of very high interest for therapeutic intervention. Given the conserved catalytic mechanisms and high similarity of many hCA isoforms, a major challenge for CA-based therapy is achieving inhibitor selectivity for hCA isoforms that are associated with specific pathologies over other widely distributed isoforms such as hCA I or hCA II that are of critical relevance for the integrity of many physiological processes. To address this challenge, we have attempted to predict compounds that are selective for isoform hCA IX, which is a tumor-associated protein and implicated in metastasis, over hCA II on the basis of a carefully curated data set of selective and nonselective inhibitors. Machine learning achieved surprisingly high accuracy in predicting hCA IX-selective inhibitors. The results were further investigated, and compound features determining successful predictions were identified. These features were then studied on the basis of X-ray structures of hCA isoform-inhibitor complexes and found to include substructures that explain compound selectivity. Our findings lend credence to selectivity predictions and indicate that the machine learning models derived herein have considerable potential to aid in the identification of new hCA IX-selective compounds.

Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions

Difficulties in interpreting machine learning (ML) models and their predictions limit the practical applicability of and confidence in ML in pharmaceutical research. There is a need for agnostic approaches aiding in the interpretation of ML models regardless of their complexity that is also applicable to deep neural network (DNN) architectures and model ensembles. To these ends, the SHapley Additive exPlanations (SHAP) methodology has recently been introduced. The SHAP approach enables the identification and prioritization of features that determine compound classification and activity prediction using any ML model. Herein, we further extend the evaluation of the SHAP methodology by investigating a variant for exact calculation of Shapley values for decision tree methods and systematically compare this variant in compound activity and potency value predictions with the model-independent SHAP method. Moreover, new applications of the SHAP analysis approach are presented including interpretation of DNN models for the generation of multi-target activity profiles and ensemble regression models for potency prediction.

Interpretation of Compound Activity Predictions from Complex Machine Learning Models Using Local Approximations and Shapley Values

In qualitative or quantitative studies of structure-activity relationships (SARs), machine learning (ML) models are trained to recognize structural patterns that differentiate between active and inactive compounds. Understanding model decisions is challenging but of critical importance to guide compound design. Moreover, the interpretation of ML results provides an additional level of model validation based on expert knowledge. A number of complex ML approaches, especially deep learning (DL) architectures, have distinctive black-box character. Herein, a locally interpretable explanatory method termed Shapley additive explanations (SHAP) is introduced for rationalizing activity predictions of any ML algorithm, regardless of its complexity. Models resulting from random forest (RF), nonlinear support vector machine (SVM), and deep neural network (DNN) learning are interpreted, and structural patterns determining the predicted probability of activity are identified and mapped onto test compounds. The results indicate that SHAP has high potential for rationalizing predictions of complex ML models.

Learning To Predict Reaction Conditions: Relationships between Solvent, Molecular Structure, and Catalyst

Reaction databases provide a great deal of useful information to assist planning of experiments but do not provide any interpretation or chemical concepts to accompany this information. In this work, reactions are labeled with experimental conditions, and network analysis shows that consistencies within clusters of data points can be leveraged to organize this information. In particular, this analysis shows how particular experimental conditions (specifically solvent) are effective in enabling specific organic reactions (Friedel-Crafts, Aldol addition, Claisen condensation, Diels-Alder, and Wittig), including variations within each reaction class. Network analysis shows data points for reactions tend to break into clusters that depend on the catalyst and chemical structure. This type of clustering, which mimics how a chemist reasons, is derived directly from the network. Therefore, the findings of this work could augment synthesis planning by providing predictions in a fashion that mimics human chemists. To numerically evaluate solvent prediction ability, three methods are compared: network analysis (through the k-nearest neighbor algorithm), a support vector machine, and a deep neural network. The most accurate method in 4 of the 5 test cases is the network analysis, with deep neural networks also showing good prediction scores. The network analysis tool was evaluated by an expert panel of chemists, who generally agreed that the algorithm produced accurate solvent choices while simultaneously being transparent in the underlying reasons for its predictions.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Advances with support vector machines for novel drug discovery

INTRODUCTION

Novel drug discovery remains an enormous challenge, with various computer-aided drug design (CADD) approaches having been widely employed for this purpose. CADD, specifically the commonly used support vector machines (SVMs), can employ machine learning techniques. SVMs and their variations offer numerous drug discovery applications, which range from the classification of substances (as active or inactive) to the construction of regression models and the ranking/virtual screening of databased compounds. Areas covered: Herein, the authors consider some of the applications of SVMs in medicinal chemistry, illustrating their main advantages and disadvantages, as well as trends in their utilization, via the available published literature. The aim of this review is to provide an up-to-date review of the recent applications of SVMs in drug discovery as described by the literature, thereby highlighting their strengths, weaknesses, and future challenges. Expert opinion: Techniques based on SVMs are considered as powerful approaches in early drug discovery. The ability of SVMs to classify active or inactive compounds has enabled the prioritization of substances for virtual screening. Indeed, one of the main advantages of SVMs is related to their potential in the analysis of nonlinear problems. However, despite successes in employing SVMs, the challenges of improving accuracy remain.

Support Vector Machine Classification and Regression Prioritize Different Structural Features for Binary Compound Activity and Potency Value Prediction

In computational chemistry and chemoinformatics, the support vector machine (SVM) algorithm is among the most widely used machine learning methods for the identification of new active compounds. In addition, support vector regression (SVR) has become a preferred approach for modeling nonlinear structure-activity relationships and predicting compound potency values. For the closely related SVM and SVR methods, fingerprints (i.e., bit string or feature set representations of chemical structure and properties) are generally preferred descriptors. Herein, we have compared SVM and SVR calculations for the same compound data sets to evaluate which features are responsible for predictions. On the basis of systematic feature weight analysis, rather surprising results were obtained. Fingerprint features were frequently identified that contributed differently to the corresponding SVM and SVR models. The overlap between feature sets determining the predictive performance of SVM and SVR was only very small. Furthermore, features were identified that had opposite effects on SVM and SVR predictions. Feature weight analysis in combination with feature mapping made it also possible to interpret individual predictions, thus balancing the black box character of SVM/SVR modeling.

Shallow Representation Learning via Kernel PCA Improves QSAR Modelability

Linear models offer a robust, flexible, and computationally efficient set of tools for modeling quantitative structure-activity relationships (QSARs) but have been eclipsed in performance by nonlinear methods. Support vector machines (SVMs) and neural networks are currently among the most popular and accurate QSAR methods because they learn new representations of the data that greatly improve modelability. In this work, we use shallow representation learning to improve the accuracy of L1 regularized logistic regression (LASSO) and meet the performance of Tanimoto SVM. We embedded chemical fingerprints in Euclidean space using Tanimoto (a.k.a. Jaccard) similarity kernel principal component analysis (KPCA) and compared the effects on LASSO and SVM model performance for predicting the binding activities of chemical compounds against 102 virtual screening targets. We observed similar performance and patterns of improvement for LASSO and SVM. We also empirically measured model training and cross-validation times to show that KPCA used in concert with LASSO classification is significantly faster than linear SVM over a wide range of training set sizes. Our work shows that powerful linear QSAR methods can match nonlinear methods and demonstrates a modular approach to nonlinear classification that greatly enhances QSAR model prototyping facility, flexibility, and transferability.

Comparison of the Predictive Performance and Interpretability of Random Forest and Linear Models on Benchmark Data Sets

The ability to interpret the predictions made by quantitative structure-activity relationships (QSARs) offers a number of advantages. While QSARs built using nonlinear modeling approaches, such as the popular Random Forest algorithm, might sometimes be more predictive than those built using linear modeling approaches, their predictions have been perceived as difficult to interpret. However, a growing number of approaches have been proposed for interpreting nonlinear QSAR models in general and Random Forest in particular. In the current work, we compare the performance of Random Forest to those of two widely used linear modeling approaches: linear Support Vector Machines (SVMs) (or Support Vector Regression (SVR)) and partial least-squares (PLS). We compare their performance in terms of their predictivity as well as the chemical interpretability of the predictions using novel scoring schemes for assessing heat map images of substructural contributions. We critically assess different approaches for interpreting Random Forest models as well as for obtaining predictions from the forest. We assess the models on a large number of widely employed public-domain benchmark data sets corresponding to regression and binary classification problems of relevance to hit identification and toxicology. We conclude that Random Forest typically yields comparable or possibly better predictive performance than the linear modeling approaches and that its predictions may also be interpreted in a chemically and biologically meaningful way. In contrast to earlier work looking at interpretation of nonlinear QSAR models, we directly compare two methodologically distinct approaches for interpreting Random Forest models. The approaches for interpreting Random Forest assessed in our article were implemented using open-source programs that we have made available to the community. These programs are the rfFC package ( https://r-forge.r-project.org/R/?group_id=1725 ) for the R statistical programming language and the Python program HeatMapWrapper [ https://doi.org/10.5281/zenodo.495163 ] for heat map generation.