Exploring the Use of Compound-Induced Transcriptomic Data Generated From Cell Lines to Predict Compound Activity Toward Molecular Targets

Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity

Identifying active compounds for a target is a time- and resource-intensive task in early drug discovery. Accurate bioactivity prediction using morphological profiles could streamline the process, enabling smaller, more focused compound screens. We investigate the potential of deep learning on unrefined single-concentration activity readouts and Cell Painting data, to predict compound activity across 140 diverse assays. We observe an average ROC-AUC of 0.744 ± 0.108 with 62% of assays achieving ≥0.7, 30% ≥0.8, and 7% ≥0.9. In many cases, the high prediction performance can be achieved using only brightfield images instead of multichannel fluorescence images. A comprehensive analysis shows that Cell Painting-based bioactivity prediction is robust across assay types, technologies, and target classes, with cell-based assays and kinase targets being particularly well-suited for prediction. Experimental validation confirms the enrichment of active compounds. Our findings indicate that models trained on Cell Painting data, combined with a small set of single-concentration data points, can reliably predict the activity of a compound library across diverse targets and assays while maintaining high hit rates and scaffold diversity. This approach has the potential to reduce the size of screening campaigns, saving time and resources, and enabling primary screening with more complex assays.

Compound Activity Prediction with Dose-Dependent Transcriptomic Profiles and Deep Learning

Predicting compound activity in assays is a long-standing challenge in drug discovery. Computational models based on compound-induced gene expression signatures from a single profiling assay have shown promise toward predicting compound activity in other, seemingly unrelated, assays. Applications of such models include predicting mechanisms-of-action (MoA) for phenotypic hits, identifying off-target activities, and identifying polypharmacologies. Here, we introduce transcriptomics-to-activity transformer (TAT) models that leverage gene expression profiles observed over compound treatment at multiple concentrations to predict the compound activity in other biochemical or cellular assays. We built TAT models based on gene expression data from a RASL-seq assay to predict the activity of 2692 compounds in 262 dose-response assays. We obtained useful models for 51% of the assays, as determined through a realistic held-out set. Prospectively, we experimentally validated the activity predictions of a TAT model in a malaria inhibition assay. With a 63% hit rate, TAT successfully identified several submicromolar malaria inhibitors. Our results thus demonstrate the potential of transcriptomic responses over compound concentration and the TAT modeling framework as a cost-efficient way to identify the bioactivities of promising compounds across many assays.

Benchmarking causal reasoning algorithms for gene expression-based compound mechanism of action analysis

BACKGROUND

Elucidating compound mechanism of action (MoA) is beneficial to drug discovery, but in practice often represents a significant challenge. Causal Reasoning approaches aim to address this situation by inferring dysregulated signalling proteins using transcriptomics data and biological networks; however, a comprehensive benchmarking of such approaches has not yet been reported. Here we benchmarked four causal reasoning algorithms (SigNet, CausalR, CausalR ScanR and CARNIVAL) with four networks (the smaller Omnipath network vs. 3 larger MetaBase™ networks), using LINCS L1000 and CMap microarray data, and assessed to what extent each factor dictated the successful recovery of direct targets and compound-associated signalling pathways in a benchmark dataset comprising 269 compounds. We additionally examined impact on performance in terms of the functions and roles of protein targets and their connectivity bias in the prior knowledge networks.

RESULTS

According to statistical analysis (negative binomial model), the combination of algorithm and network most significantly dictated the performance of causal reasoning algorithms, with the SigNet recovering the greatest number of direct targets. With respect to the recovery of signalling pathways, CARNIVAL with the Omnipath network was able to recover the most informative pathways containing compound targets, based on the Reactome pathway hierarchy. Additionally, CARNIVAL, SigNet and CausalR ScanR all outperformed baseline gene expression pathway enrichment results. We found no significant difference in performance between L1000 data or microarray data, even when limited to just 978 'landmark' genes. Notably, all causal reasoning algorithms also outperformed pathway recovery based on input DEGs, despite these often being used for pathway enrichment. Causal reasoning methods performance was somewhat correlated with connectivity and biological role of the targets.

CONCLUSIONS

Overall, we conclude that causal reasoning performs well at recovering signalling proteins related to compound MoA upstream from gene expression changes by leveraging prior knowledge networks, and that the choice of network and algorithm has a profound impact on the performance of causal reasoning algorithms. Based on the analyses presented here this is true for both microarray-based gene expression data as well as those based on the L1000 platform.

Predicting molecular initiating events using chemical target annotations and gene expression

BACKGROUND

The advent of high-throughput transcriptomic screening technologies has resulted in a wealth of publicly available gene expression data associated with chemical treatments. From a regulatory perspective, data sets that cover a large chemical space and contain reference chemicals offer utility for the prediction of molecular initiating events associated with chemical exposure. Here, we integrate data from a large compendium of transcriptomic responses to chemical exposure with a comprehensive database of chemical-protein associations to train binary classifiers that predict mechanism(s) of action from transcriptomic responses. First, we linked reference chemicals present in the LINCS L1000 gene expression data collection to chemical identifiers in RefChemDB, a database of chemical-protein interactions. Next, we trained binary classifiers on MCF7 human breast cancer cell line derived gene expression profiles and chemical-protein labels using six classification algorithms to identify optimal analysis parameters. To validate classifier accuracy, we used holdout data sets, training-excluded reference chemicals, and empirical significance testing of null models derived from permuted chemical-protein associations. To identify classifiers that have variable predicting performance across training data derived from different cellular contexts, we trained a separate set of binary classifiers on the PC3 human prostate cancer cell line.

RESULTS

We trained classifiers using expression data associated with chemical treatments linked to 51 molecular initiating events. This analysis identified and validated 9 high-performing classifiers with empirical p-values lower than 0.05 and internal accuracies ranging from 0.73 to 0.94 and holdout accuracies of 0.68 to 0.92. High-ranking predictions for training-excluded reference chemicals demonstrating that predictive accuracy extends beyond the set of chemicals used in classifier training. To explore differences in classifier performance as a function of training data cellular context, MCF7-trained classifier accuracies were compared to classifiers trained on the PC3 gene expression data for the same molecular initiating events.

CONCLUSIONS

This methodology can offer insight in prioritizing candidate perturbagens of interest for targeted screens. This approach can also help guide the selection of relevant cellular contexts for screening classes of candidate perturbagens using cell line specific model performance.

Computational analyses of mechanism of action (MoA): data, methods and integration

The elucidation of a compound's Mechanism of Action (MoA) is a challenging task in the drug discovery process, but it is important in order to rationalise phenotypic findings and to anticipate potential side-effects. Bioinformatic approaches, advances in machine learning techniques and the increasing deposition of high-throughput data in public databases have significantly contributed to recent advances in the field, but it is not straightforward to decide which data and methods are most suitable to use in a given case. In this review, we focus on these methods and data and their applications in generating MoA hypotheses for subsequent experimental validation. We discuss compound-specific data such as -omics, cell morphology and bioactivity data, as well as commonly used supplementary prior knowledge such as network and pathway data, and provide information on databases where this data can be accessed. In terms of methodologies, we discuss both well-established methods (connectivity mapping, pathway enrichment) as well as more developing methods (neural networks and multi-omics integration). Finally, we review case studies where the MoA of a compound was successfully suggested from computational analysis by incorporating multiple data modalities and/or methodologies. Our aim for this review is to provide researchers with insights into the benefits and drawbacks of both the data and methods in terms of level of understanding, biases and interpretation - and to highlight future avenues of investigation which we foresee will improve the field of MoA elucidation, including greater public access to -omics data and methodologies which are capable of data integration.

Exploration of the DARTable Genome- a Resource Enabling Data-Driven NAMs for Developmental and Reproductive Toxicity Prediction

The identification of developmental and reproductive toxicity (DART) is a critical component of toxicological evaluations of chemical safety. Adverse Outcome Pathways (AOPs) provide a framework to describe biological processes leading to a toxic effect and can provide insights in understanding the mechanisms underlying toxicological endpoints and aid the development of new approach methods (NAMs). Integrated approaches to testing and assessment (IATA) can be developed based on AOP knowledge and can serve as pragmatic approaches to chemical hazard characterization using NAMs. However, DART effects remain difficult to predict given the diversity of biological mechanisms operating during ontogenesis and consequently, the considerable number of potential molecular initiating events (MIEs) that might trigger a DART Adverse Outcome (DART AO). Consequently, two challenges that need to be overcome to create an AOP-based DART IATA are having sufficient knowledge of relevant biology and using this knowledge to determine the appropriate selection of cell systems that provide sufficient coverage of that biology. The wealth of modern biological and bioinformatics data can be used to provide this knowledge. Here we demonstrate the utility of bioinformatics analyses to address these questions. We integrated known DART MIEs with gene-developmental phenotype information to curate the hypothetical human DARTable genome (HDG, ∼5 k genes) which represents the comprehensive set of biomarkers for DART. Using network analysis of the human interactome, we show that HDG genes have distinct connectivity compared to other genes. HDG genes have higher node degree with lower neighborhood connectivity, betweenness centralities and average shortest path length. Therefore, HDG is highly connected to itself and to the wider network and not only to their local community. Also, by comparison with the Druggable Genome we show how the HDG can be prioritized to identify potential MIEs based on potential to interact with small molecules. We demonstrate how the HDG in combination with gene expression data can be used to select a panel of relevant cell lines (RD-1, OVCAR-3) for inclusion in an IATA and conclude that bioinformatic analyses can provide the necessary insights and serve as a resource for the development of a screening panel for a DART IATA.

A human-based multi-gene signature enables quantitative drug repurposing for metabolic disease

Insulin resistance (IR) contributes to the pathophysiology of diabetes, dementia, viral infection, and cardiovascular disease. Drug repurposing (DR) may identify treatments for IR; however, barriers include uncertainty whether in vitro transcriptomic assays yield quantitative pharmacological data, or how to optimise assay design to best reflect in vivo human disease. We developed a clinical-based human tissue IR signature by combining lifestyle-mediated treatment responses (>500 human adipose and muscle biopsies) with biomarkers of disease status (fasting IR from >1200 biopsies). The assay identified a chemically diverse set of >130 positively acting compounds, highly enriched in true positives, that targeted 73 proteins regulating IR pathways. Our multi-gene RNA assay score reflected the quantitative pharmacological properties of a set of epidermal growth factor receptor-related tyrosine kinase inhibitors, providing insight into drug target specificity; an observation supported by deep learning-based genome-wide predicted pharmacology. Several drugs identified are suitable for evaluation in patients, particularly those with either acute or severe chronic IR.

Recent advances in drug repurposing using machine learning

Drug repurposing aims to find new uses for already existing and approved drugs. We now provide a brief overview of recent developments in drug repurposing using machine learning alongside other computational approaches for comparison. We also highlight several applications for cancer using kinase inhibitors, Alzheimer's disease as well as COVID-19.

Comparison of Chemical Structure and Cell Morphology Information for Multitask Bioactivity Predictions

The understanding of the mechanism-of-action (MoA) of compounds and the prediction of potential drug targets play an important role in small-molecule drug discovery. The aim of this work was to compare chemical and cell morphology information for bioactivity prediction. The comparison was performed using bioactivity data from the ExCAPE database, image data (in the form of CellProfiler features) from the Cell Painting data set (the largest publicly available data set of cell images with ∼30,000 compound perturbations), and extended connectivity fingerprints (ECFPs) using the multitask Bayesian matrix factorization (BMF) approach Macau. We found that the BMF Macau and random forest (RF) performance were overall similar when ECFPs were used as compound descriptors. However, BMF Macau outperformed RF in 159 out of 224 targets (71%) when image data were used as compound information. Using BMF Macau, 100 (corresponding to about 45%) and 90 (about 40%) of the 224 targets were predicted with high predictive performance (AUC > 0.8) with ECFP data and image data as side information, respectively. There were targets better predicted by image data as side information, such as β-catenin, and others better predicted by fingerprint-based side information, such as proteins belonging to the G-protein-Coupled Receptor 1 family, which could be rationalized from the underlying data distributions in each descriptor domain. In conclusion, both cell morphology changes and chemical structure information contain information about compound bioactivity, which is also partially complementary, and can hence contribute to in silico MoA analysis.