Anatomy of Potency Predictions Focusing on Structural Analogues with Increasing Potency Differences Including Activity Cliffs.

Potency predictions are popular in compound design and optimization but are complicated by intrinsic limitations. Moreover, even for nonlinear methods, activity cliffs (ACs, formed by structural analogues with large potency differences) represent challenging test cases for compound potency predictions. We have devised a new test system for potency predictions, including AC compounds, that is based on partitioned matched molecular pairs (MMP) and makes it possible to monitor prediction accuracy at the level of analogue pairs with increasing potency differences. The results of systematic predictions using different machine learning and control methods on MMP-based data sets revealed increasing prediction errors when potency differences between corresponding training and test compounds increased, including large prediction errors for AC compounds. At the global level, these prediction errors were not apparent due to the statistical dominance of analogue pairs with small potency differences. Test compounds from such pairs were accurately predicted and determined the observed global prediction accuracy. Shapley value analysis, an explainable artificial intelligence approach, was applied to identify structural features determining potency predictions using different methods. The analysis revealed that numerical predictions of different regression models were determined by features that were shared by MMP partner compounds or absent in these compounds, with opposing effects. These findings provided another rationale for accurate predictions of similar potency values for structural analogues and failures in predicting the potency of AC compounds.

CIRCE: Web-Based Platform for the Prediction of Cannabinoid Receptor Ligands Using Explainable Machine Learning.

The endocannabinoid system, which includes cannabinoid receptor 1 and 2 subtypes (CB1R and CB2R, respectively), is responsible for the onset of various pathologies including neurodegeneration, cancer, neuropathic and inflammatory pain, obesity, and inflammatory bowel disease. Given the high similarity of CB1R and CB2R, generating subtype-selective ligands is still an open challenge. In this work, the Cannabinoid Iterative Revaluation for Classification and Explanation (CIRCE) compound prediction platform has been generated based on explainable machine learning to support the design of selective CB1R and CB2R ligands. Multilayer classifiers were combined with Shapley value analysis to facilitate explainable predictions. In test calculations, CIRCE predictions reached ∼80% accuracy and structural features determining ligand predictions were rationalized. CIRCE was designed as a web-based prediction platform that is made freely available as a part of our study.

DeepCubist: Molecular Generator for Designing Peptidomimetics based on Complex three-dimensional scaffolds.

Mimicking bioactive conformations of peptide segments involved in the formation of protein-protein interfaces with small molecules is thought to represent a promising strategy for the design of protein-protein interaction (PPI) inhibitors. For compound design, the use of three-dimensional (3D) scaffolds rich in sp3-centers makes it possible to precisely mimic bioactive peptide conformations. Herein, we introduce DeepCubist, a molecular generator for designing peptidomimetics based on 3D scaffolds. Firstly, enumerated 3D scaffolds are superposed on a target peptide conformation to identify a preferred template structure for designing peptidomimetics. Secondly, heteroatoms and unsaturated bonds are introduced into the template via a deep generative model to produce candidate compounds. DeepCubist was applied to design peptidomimetics of exemplary peptide turn, helix, and loop structures in pharmaceutical targets engaging in PPIs.

Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets.

In drug discovery, compounds with well-defined activity against multiple targets (multitarget compounds, MT-CPDs) provide the basis for polypharmacology and are thus of high interest. Typically, MT-CPDs for polypharmacology have been discovered serendipitously. Therefore, over the past decade, computational approaches have also been adapted for the design of MT-CPDs or their identification via computational screening. Such approaches continue to be under development and are far from being routine. Recently, different machine learning (ML) models have been derived to distinguish between MT-CPDs and corresponding compounds with activity against the individual targets (single-target compounds, ST-CPDs). When evaluating alternative models for predicting MT-CPDs, we discovered that MT-CPDs could also be accurately predicted with models derived for corresponding ST-CPDs; this was an unexpected finding that we further investigated using explainable ML. The analysis revealed that accurate predictions of ST-CPDs were determined by subsets of structural features of MT-CPDs required for their prediction. These findings provided a chemically intuitive rationale for the successful prediction of MT-CPDs using different ML models and uncovered general-feature subset relationships between MT- and ST-CPDs with activities against different targets.

Explaining Multiclass Compound Activity Predictions Using Counterfactuals and Shapley Values.

Most machine learning (ML) models produce black box predictions that are difficult, if not impossible, to understand. In pharmaceutical research, black box predictions work against the acceptance of ML models for guiding experimental work. Hence, there is increasing interest in approaches for explainable ML, which is a part of explainable artificial intelligence (XAI), to better understand prediction outcomes. Herein, we have devised a test system for the rationalization of multiclass compound activity prediction models that combines two approaches from XAI for feature relevance or importance analysis, including counterfactuals (CFs) and Shapley additive explanations (SHAP). For compounds with different single- and dual-target activities, we identified small compound modifications that induce feature changes inverting class label predictions. In combination with feature mapping, CFs and SHAP value calculations provide chemically intuitive explanations for model decisions.

Systematic Analysis of Covalent and Allosteric Protein Kinase Inhibitors.

In drug discovery, protein kinase inhibitors (PKIs) are intensely investigated as drug candidates in different therapeutic areas. While ATP site-directed, non-covalent PKIs have long been a focal point in protein kinase (PK) drug discovery, in recent years, there has been increasing interest in allosteric PKIs (APKIs), which are expected to have high kinase selectivity. In addition, as compounds acting by covalent mechanisms experience a renaissance in drug discovery, there is also increasing interest in covalent PKIs (CPKIs). There are various reasons for this increasing interest such as the anticipated high potency, prolonged residence times compared to non-competitive PKIs, and other favorable pharmacokinetic properties. Due to the popularity of PKIs for therapeutic intervention, large numbers of PKIs and large volumes of activity data have accumulated in the public domain, providing a basis for large-scale computational analysis. We have systematically searched for CPKIs containing different reactive groups (warheads) and investigated their potency and promiscuity (multi-PK activity) on the basis of carefully curated activity data. For seven different warheads, sufficiently large numbers of CPKIs were available for detailed follow-up analysis. For only three warheads, the median potency of corresponding CPKIs was significantly higher than of non-covalent PKIs. However, for CKPIs with five of seven warheads, there was a significant increase in the median potency of at least 100-fold compared to PKI analogues without warheads. However, in the analysis of multi-PK activity, there was no general increase in the promiscuity of CPKIs compared to non-covalent PKIs. In addition, we have identified 29 new APKIs in X-ray structures of PK-PKI complexes. Among structurally characterized APKIs, 13 covalent APKIs in complexes with five PKs are currently available, enabling structure-based investigation of PK inhibition by covalent-allosteric mechanisms.

Isomeric Activity Cliffs-A Case Study for Fluorine Substitution of Aminergic G Protein-Coupled Receptor Ligands.

Currently, G protein-coupled receptors (GPCRs) constitute a significant group of membrane-bound receptors representing more than 30% of therapeutic targets. Fluorine is commonly used in designing highly active biological compounds, as evidenced by the steadily increasing number of drugs by the Food and Drug Administration (FDA). Herein, we identified and analyzed 898 target-based F-containing isomeric analog sets for SAR analysis in the ChEMBL database-FiSAR sets active against 33 different aminergic GPCRs comprising a total of 2163 fluorinated (1201 unique) compounds. We found 30 FiSAR sets contain activity cliffs (ACs), defined as pairs of structurally similar compounds showing significant differences in affinity (≥50-fold change), where the change of fluorine position may lead up to a 1300-fold change in potency. The analysis of matched molecular pair (MMP) networks indicated that the fluorination of aromatic rings showed no clear trend toward a positive or negative effect on affinity. Additionally, we propose an in silico workflow (including induced-fit docking, molecular dynamics, quantum polarized ligand docking, and binding free energy calculations based on the Generalized-Born Surface-Area (GBSA) model) to score the fluorine positions in the molecule.

Fine-tuning of a generative neural network for designing multi-target compounds.

Exploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

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.

Epilogue to the Gerald Maggiora Festschrift: a tribute to an exemplary mentor, colleague, collaborator, and innovator.

In May 2022, JCAMD published a Special Issue in honor of Gerald (Gerry) Maggiora, whose scientific leadership over many decades advanced the fields of computational chemistry and chemoinformatics for drug discovery. Along the way, he has impacted many researchers in both academia and the pharmaceutical industry. In this Epilogue, we explain the origins of the Festschrift and present a series of first-hand vignettes, in approximate chronological sequence, that together paint a picture of this remarkable man. Whether they highlight Gerry's endless curiosity about molecular life sciences or his willingness to challenge conventional wisdom or his generous support of junior colleagues and peers, these colleagues and collaborators are united in their appreciation of his positive influence. These tributes also reflect key trends and themes during the evolution of modern drug discovery, seen through the lens of people who worked with a visionary leader. Junior scientists will find an inspiring roadmap for creative collegiality and collaboration.

DeepAS - Chemical language model for the extension of active analogue series.

In medicinal chemistry, hit-to-lead and lead optimization efforts produce analogue series (ASs), the analysis of which is of central relevance for the exploration and exploitation of structure-activity relationships (SARs) and generation of candidate compounds. The key question in any chemical optimization effort is which analogue(s) to generate next, for which computational support is typically provided through QSAR analysis and compound potency predictions. In this study, we introduce a new chemical language model for analogue design via deep learning. For this purpose, ASs comprising active compounds are ordered according to increasing potency and the chemical language model predicts preferred R-groups for new analogues on the basis of ordered R-group sequences. Hence, consistent with the principles of deep models for natural language processing, analogues with new R-groups are predicted based upon conditional probabilities taking preceding groups into account. This implicitly accounts for the potency gradient captured by an AS and detectable SAR trends, providing a new concept for analogue design. Herein, we report the AS-based chemical language model, its initial evaluation, and exemplary applications.

Approach for the Design of Covalent Protein Kinase Inhibitors via Focused Deep Generative Modeling.

Deep machine learning is expanding the conceptual framework and capacity of computational compound design, enabling new applications through generative modeling. We have explored the systematic design of covalent protein kinase inhibitors by learning from kinome-relevant chemical space, followed by focusing on an exemplary kinase of interest. Covalent inhibitors experience a renaissance in drug discovery, especially for targeting protein kinases. However, computational design of this class of inhibitors has thus far only been little investigated. To this end, we have devised a computational approach combining fragment-based design and deep generative modeling augmented by three-dimensional pharmacophore screening. This approach is thought to be particularly relevant for medicinal chemistry applications because it combines knowledge-based elements with deep learning and is chemically intuitive. As an exemplary application, we report for Bruton's tyrosine kinase (BTK), a major drug target for the treatment of inflammatory diseases and leukemia, the generation of novel candidate inhibitors with a specific chemically reactive group for covalent modification, requiring only little target-specific compound information to guide the design efforts. Newly generated compounds include known inhibitors and characteristic substructures and many novel candidates, thus lending credence to the computational approach, which is readily applicable to other targets.

Introducing a Chemically Intuitive Core-Substituent Fingerprint Designed to Explore Structural Requirements for Effective Similarity Searching and Machine Learning.

Fingerprint (FP) representations of chemical structure continue to be one of the most widely used types of molecular descriptors in chemoinformatics and computational medicinal chemistry. One often distinguishes between two- and three-dimensional (2D and 3D) FPs depending on whether they are derived from molecular graphs or conformations, respectively. Primary application areas for FPs include similarity searching and compound classification via machine learning, especially for hit identification. For these applications, 2D FPs are particularly popular, given their robustness and for the most part comparable (or better) performance to 3D FPs. While a variety of FP prototypes has been designed and evaluated during earlier times of chemoinformatics research, new developments have been rare over the past decade. At least in part, this has been due to the situation that topological (atom environment) FPs derived from molecular graphs have evolved as a gold standard in the field. We were interested in exploring the question of whether the amount of structural information captured by state-of-the-art 2D FPs is indeed required for effective similarity searching and compound classification or whether accounting for fewer structural features might be sufficient. Therefore, pursuing a "structural minimalist" approach, we designed and implemented a new 2D FP based upon ring and substituent fragments obtained by systematically decomposing large numbers of compounds from medicinal chemistry. The resulting FP termed core-substituent FP (CSFP) captures much smaller numbers of structural features than state-of-the-art 2D FPs. However, CSFP achieves high performance in similarity searching and machine learning, demonstrating that less structural information is required for establishing molecular similarity relationships than is often believed. Given its high performance and chemical tangibility, CSFP is also relevant for practical applications in medicinal chemistry.

Informatics for Chemistry, Biology, and Biomedical Sciences.

Informatics is growing across disciplines, impacting several areas of chemistry, biology, and biomedical sciences. Besides the well-established bioinformatics discipline, other informatics-based interdisciplinary fields have been evolving over time, such as chemoinformatics and biomedical informatics. Other related research areas such as pharmacoinformatics, food informatics, epi-informatics, materials informatics, and neuroinformatics have emerged more recently and continue to develop as independent subdisciplines. The goals and impacts of each of these disciplines have typically been separately reviewed in the literature. Hence, it remains challenging to identify commonalities and key differences. Herein, we discuss in context three major informatics disciplines in the natural and life sciences including bioinformatics, chemoinformatics, and biomedical informatics and briefly comment on related subdisciplines. We focus the discussion on the definitions, historical background, actual impact, main similarities, and differences and evaluate the dissemination and teaching of bioinformatics, chemoinformatics, and biomedical informatics.

Evaluation of multi-target deep neural network models for compound potency prediction under increasingly challenging test conditions.

Machine learning (ML) enables modeling of quantitative structure-activity relationships (QSAR) and compound potency predictions. Recently, multi-target QSAR models have been gaining increasing attention. Simultaneous compound potency predictions for multiple targets can be carried out using ensembles of independently derived target-based QSAR models or in a more integrated and advanced manner using multi-target deep neural networks (MT-DNNs). Herein, single-target and multi-target ML models were systematically compared on a large scale in compound potency value predictions for 270 human targets. By design, this large-magnitude evaluation has been a special feature of our study. To these ends, MT-DNN, single-target DNN (ST-DNN), support vector regression (SVR), and random forest regression (RFR) models were implemented. Different test systems were defined to benchmark these ML methods under conditions of varying complexity. Source compounds were divided into training and test sets in a compound- or analog series-based manner taking target information into account. Data partitioning approaches used for model training and evaluation were shown to influence the relative performance of ML methods, especially for the most challenging compound data sets. For example, the performance of MT-DNNs with per-target models yielded superior performance compared to single-target models. For a test compound or its analogs, the availability of potency measurements for multiple targets affected model performance, revealing the influence of ML synergies.

Adapting the DeepSARM approach for dual-target ligand design.

The structure-activity relationship (SAR) matrix (SARM) methodology and data structure was originally developed to extract structurally related compound series from data sets of any composition, organize these series in matrices reminiscent of R-group tables, and visualize SAR patterns. The SARM approach combines the identification of structural relationships between series of active compounds with analog design, which is facilitated by systematically exploring combinations of core structures and substituents that have not been synthesized. The SARM methodology was extended through the introduction of DeepSARM, which added deep learning and generative modeling to target-based analog design by taking compound information from related targets into account to further increase structural novelty. Herein, we present the foundations of the SARM methodology and discuss how DeepSARM modeling can be adapted for the design of compounds with dual-target activity. Generating dual-target compounds represents an equally attractive and challenging task for polypharmacology-oriented drug discovery. The DeepSARM-based approach is illustrated using a computational proof-of-concept application focusing on the design of candidate inhibitors for two prominent anti-cancer targets.

Prediction of activity cliffs on the basis of images using convolutional neural networks.

An activity cliff (AC) is formed by a pair of structurally similar compounds with a large difference in potency. Accordingly, ACs reveal structure-activity relationship (SAR) discontinuity and provide SAR information for compound optimization. Herein, we have investigated the question if ACs could be predicted from image data. Therefore, pairs of structural analogs were extracted from different compound activity classes that formed or did not form ACs. From these compound pairs, consistently formatted images were generated. Image sets were used to train and test convolutional neural network (CNN) models to systematically distinguish between ACs and non-ACs. The CNN models were found to predict ACs with overall high accuracy, as assessed using alternative performance measures, hence establishing proof-of-principle. Moreover, gradient weights from convolutional layers were mapped to test compounds and identified characteristic structural features that contributed to successful predictions. Weight-based feature visualization revealed the ability of CNN models to learn chemistry from images at a high level of resolution and aided in the interpretation of model decisions with intrinsic black box character.

Systematic assessment of structure-promiscuity relationships between different types of kinase inhibitors.

Given the increasing quest for selective kinase inhibitors, we have systematically investigated structural and structure-promiscuity relationships between promiscuous kinase inhibitors and other types with increasing potential for selective kinase inhibition. Therefore, inhibitors with different modes of action were extracted from X-ray structures of kinase complexes. For more than 18,000 promiscuous kinase inhibitors and 1253 type I1/2, II, and allosteric inhibitors with structurally confirmed mechanisms, analogue space was systematically charted. These inhibitors were active against a total of 426 human kinases. While nearly 80% of the promiscuous inhibitors formed related analogues series, only ~30% of other types of inhibitors were involved in such structural relationships and many of these inhibitors also had multi-kinase activity. Thus, most of the investigated type I1/2, II, and allosteric inhibitors with reported single-kinase activity were distinguished from promiscuous inhibitors, thus indicating potential for kinase selectivity. Structural relationships between promiscuous inhibitors and the subset of other inhibitors were organized in a matrix format including kinase activity profiles, revealing structure-promiscuity relationships for follow-up investigations.

Development of curcumin-based amyloid ß aggregation inhibitors for Alzheimer's disease using the SAR matrix approach.

Amyloid ß (Aß) aggregation inhibitor activity cliff involving a curcumin structure was predicted using the SAR Matrix method on the basis of 697 known Aß inhibitors from ChEMBL (data set 2487). Among the compounds predicted, compound B was found to possess approximately 100 times higher inhibitory activity toward Aß aggregation than curcumin. TEM images indicate that compound B induced the shortening of Aß fibrils and increased the generation of Aß oligomers in a concentration dependent manner. Furthermore, compound K, in which the methyl ester of compound B was replaced by the tert-butyl ester, possessed low cytotoxicity on N2A cells and attenuated Aß-induced cytotoxicity, indicating that compound K would have an ability for preventing neurotoxicity caused by Aß aggregation.

QSAR without borders.

Prediction of chemical bioactivity and physical properties has been one of the most important applications of statistical and more recently, machine learning and artificial intelligence methods in chemical sciences. This field of research, broadly known as quantitative structure-activity relationships (QSAR) modeling, has developed many important algorithms and has found a broad range of applications in physical organic and medicinal chemistry in the past 55+ years. This Perspective summarizes recent technological advances in QSAR modeling but it also highlights the applicability of algorithms, modeling methods, and validation practices developed in QSAR to a wide range of research areas outside of traditional QSAR boundaries including synthesis planning, nanotechnology, materials science, biomaterials, and clinical informatics. As modern research methods generate rapidly increasing amounts of data, the knowledge of robust data-driven modelling methods professed within the QSAR field can become essential for scientists working both within and outside of chemical research. We hope that this contribution highlighting the generalizable components of QSAR modeling will serve to address this challenge.