Toxicity prediction using target, interactome, and pathway profiles as descriptors

In silico methods are essential to the safety evaluation of chemicals. Computational risk assessment offers several approaches, with data science and knowledge-based methods becoming an increasingly important sub-group. One of the substantial attributes of data science is that it allows using existing data to find correlations, build strong hypotheses, and create new, valuable knowledge that may help to reduce the number of resource intensive experiments. In choosing a suitable method for toxicity prediction, the available data and desired toxicity endpoint are two essential factors to consider. The complexity of the endpoint can impact the success rate of the in silico models. For highly complex endpoints such as hepatotoxicity, it can be beneficial to decipher the toxic event from a more systemic point of view. We propose a data science-based modelling pipeline that uses compounds` connections to tissue-specific biological targets, interactome, and biological pathways as descriptors of compounds. Models trained on different combinations of the collected, compound-target, compound-interactor, and compound-pathway profiles, were used to predict the hepatotoxicity of drug-like compounds. Several tree-based models were trained, utilizing separate and combined target, interactome and pathway level variables. The model using combined descriptors of all levels and the random forest algorithm was further optimized. Descriptor importance for model performance was addressed and examined for a biological explanation to define which targets or pathways can have a crucial role in toxicity. Descriptors connected to cytochromes P450 enzymes, heme degradation and biological oxidation received high weights. Furthermore, the involvement of other, less discussed processes in connection with toxicity, such as the involvement of RHO GTPase effectors in hepatotoxicity, were marked as fundamental. The optimized combined model using only the selected descriptors yielded the best performance with an accuracy of 0.766. The same dataset using classical Morgan fingerprints for compound representation yielded models with similar performance measures, as well as the combination of systems biology-based descriptors and Morgan fingerprints. Consequently, adding the structural information of compounds did not enhance the predictive value of the models. The developed systems biology-based pipeline comprises a valuable tool in predicting toxicity, while providing novel insights about the possible mechanisms of the unwanted events.

Validation strategies for target prediction methods

Computational methods for target prediction, based on molecular similarity and network-based approaches, machine learning, docking and others, have evolved as valuable and powerful tools to aid the challenging task of mode of action identification for bioactive small molecules such as drugs and drug-like compounds. Critical to discerning the scope and limitations of a target prediction method is understanding how its performance was evaluated and reported. Ideally, large-scale prospective experiments are conducted to validate the performance of a model; however, this expensive and time-consuming endeavor is often not feasible. Therefore, to estimate the predictive power of a method, statistical validation based on retrospective knowledge is commonly used. There are multiple statistical validation techniques that vary in rigor. In this review we discuss the validation strategies employed, highlighting the usefulness and constraints of the validation schemes and metrics that are employed to measure and describe performance. We address the limitations of measuring only generalized performance, given that the underlying bioactivity and structural data are biased towards certain small-molecule scaffolds and target families, and suggest additional aspects of performance to consider in order to produce more detailed and realistic estimates of predictive power. Finally, we describe the validation strategies that were employed by some of the most thoroughly validated and accessible target prediction methods.

Computational Applications in Secondary Metabolite Discovery (CAiSMD): an online workshop

We report the major conclusions of the online open-access workshop "Computational Applications in Secondary Metabolite Discovery (CAiSMD)" that took place from 08 to 10 March 2021. Invited speakers from academia and industry and about 200 registered participants from five continents (Africa, Asia, Europe, South America, and North America) took part in the workshop. The workshop highlighted the potential applications of computational methodologies in the search for secondary metabolites (SMs) or natural products (NPs) as potential drugs and drug leads. During 3 days, the participants of this online workshop received an overview of modern computer-based approaches for exploring NP discovery in the "omics" age. The invited experts gave keynote lectures, trained participants in hands-on sessions, and held round table discussions. This was followed by oral presentations with much interaction between the speakers and the audience. Selected applicants (early-career scientists) were offered the opportunity to give oral presentations (15 min) and present posters in the form of flash presentations (5 min) upon submission of an abstract. The final program available on the workshop website ( https://caismd.indiayouth.info/ ) comprised of 4 keynote lectures (KLs), 12 oral presentations (OPs), 2 round table discussions (RTDs), and 5 hands-on sessions (HSs). This meeting report also references internet resources for computational biology in the area of secondary metabolites that are of use outside of the workshop areas and will constitute a long-term valuable source for the community. The workshop concluded with an online survey form to be completed by speakers and participants for the goal of improving any subsequent editions.

Predicting the Skin Sensitization Potential of Small Molecules with Machine Learning Models Trained on Biologically Meaningful Descriptors

In recent years, a number of machine learning models for the prediction of the skin sensitization potential of small organic molecules have been reported and become available. These models generally perform well within their applicability domains but, as a result of the use of molecular fingerprints and other non-intuitive descriptors, the interpretability of the existing models is limited. The aim of this work is to develop a strategy to replace the non-intuitive features by predicted outcomes of bioassays. We show that such replacement is indeed possible and that as few as ten interpretable, predicted bioactivities are sufficient to reach competitive performance. On a holdout data set of 257 compounds, the best model (“Skin Doctor CP:Bio”) obtained an efficiency of 0.82 and an MCC of 0.52 (at the significance level of 0.20). Skin Doctor CP:Bio is available free of charge for academic research. The modeling strategies explored in this work are easily transferable and could be adopted for the development of more interpretable machine learning models for the prediction of the bioactivity and toxicity of small organic compounds.

BonMOLière: Small-Sized Libraries of Readily Purchasable Compounds, Optimized to Produce Genuine Hits in Biological Screens across the Protein Space

Experimental screening of large sets of compounds against macromolecular targets is a key strategy to identify novel bioactivities. However, large-scale screening requires substantial experimental resources and is time-consuming and challenging. Therefore, small to medium-sized compound libraries with a high chance of producing genuine hits on an arbitrary protein of interest would be of great value to fields related to early drug discovery, in particular biochemical and cell research. Here, we present a computational approach that incorporates drug-likeness, predicted bioactivities, biological space coverage, and target novelty, to generate optimized compound libraries with maximized chances of producing genuine hits for a wide range of proteins. The computational approach evaluates drug-likeness with a set of established rules, predicts bioactivities with a validated, similarity-based approach, and optimizes the composition of small sets of compounds towards maximum target coverage and novelty. We found that, in comparison to the random selection of compounds for a library, our approach generates substantially improved compound sets. Quantified as the "fitness" of compound libraries, the calculated improvements ranged from +60% (for a library of 15,000 compounds) to +184% (for a library of 1000 compounds). The best of the optimized compound libraries prepared in this work are available for download as a dataset bundle ("BonMOLière").

Similarity-Based Methods and Machine Learning Approaches for Target Prediction in Early Drug Discovery: Performance and Scope

Computational methods for predicting the macromolecular targets of drugs and drug-like compounds have evolved as a key technology in drug discovery. However, the established validation protocols leave several key questions regarding the performance and scope of methods unaddressed. For example, prediction success rates are commonly reported as averages over all compounds of a test set and do not consider the structural relationship between the individual test compounds and the training instances. In order to obtain a better understanding of the value of ligand-based methods for target prediction, we benchmarked a similarity-based method and a random forest based machine learning approach (both employing 2D molecular fingerprints) under three testing scenarios: a standard testing scenario with external data, a standard time-split scenario, and a scenario that is designed to most closely resemble real-world conditions. In addition, we deconvoluted the results based on the distances of the individual test molecules from the training data. We found that, surprisingly, the similarity-based approach generally outperformed the machine learning approach in all testing scenarios, even in cases where queries were structurally clearly distinct from the instances in the training (or reference) data, and despite a much higher coverage of the known target space.

Scope of 3D Shape-Based Approaches in Predicting the Macromolecular Targets of Structurally Complex Small Molecules Including Natural Products and Macrocyclic Ligands

A plethora of similarity-based, network-based, machine learning, docking and hybrid approaches for predicting the macromolecular targets of small molecules are available today and recognized as valuable tools for providing guidance in early drug discovery. With the increasing maturity of target prediction methods, researchers have started to explore ways to expand their scope to more challenging molecules such as structurally complex natural products and macrocyclic small molecules. In this work, we systematically explore the capacity of an alignment-based approach to identify the targets of structurally complex small molecules (including large and flexible natural products and macrocyclic compounds) based on the similarity of their 3D molecular shape to noncomplex molecules (i.e., more conventional, “drug-like”, synthetic compounds). For this analysis, query sets of 10 representative, structurally complex molecules were compiled for each of the 28 pharmaceutically relevant proteins. Subsequently, ROCS, a leading shape-based screening engine, was utilized to generate rank-ordered lists of the potential targets of the 28 × 10 queries according to the similarity of their 3D molecular shapes with those of compounds from a knowledge base of 272 640 noncomplex small molecules active on a total of 3642 different proteins. Four of the scores implemented in ROCS were explored for target ranking, with the TanimotoCombo score consistently outperforming all others. The score successfully recovered the targets of 30% and 41% of the 280 queries among the top-5 and top-20 positions, respectively. For 24 out of the 28 investigated targets (86%), the method correctly assigned the first rank (out of 3642) to the target of interest for at least one of the 10 queries. The shape-based target prediction approach showed remarkable robustness, with good success rates obtained even for compounds that are clearly distinct from any of the ligands present in the knowledge base. However, complex natural products and macrocyclic compounds proved to be challenging even with this approach, although cases of complete failure were recorded only for a small number of targets.