Off-targetP ML: an open source machine learning framework for off-target panel safety assessment of small molecules

In silico off-target profiling for enhanced drug safety assessment

Ensuring drug safety in the early stages of drug development is crucial to avoid costly failures in subsequent phases. However, the economic burden associated with detecting drug off-targets and potential side effects through in vitro safety screening and animal testing is substantial. Drug off-target interactions, along with the adverse drug reactions they induce, are significant factors affecting drug safety. To assess the liability of candidate drugs, we developed an artificial intelligence model for the precise prediction of compound off-target interactions, leveraging multi-task graph neural networks. The outcomes of off-target predictions can serve as representations for compounds, enabling the differentiation of drugs under various ATC codes and the classification of compound toxicity. Furthermore, the predicted off-target profiles are employed in adverse drug reaction (ADR) enrichment analysis, facilitating the inference of potential ADRs for a drug. Using the withdrawn drug Pergolide as an example, we elucidate the mechanisms underlying ADRs at the target level, contributing to the exploration of the potential clinical relevance of newly predicted off-target interactions. Overall, our work facilitates the early assessment of compound safety/toxicity based on off-target identification, deduces potential ADRs of drugs, and ultimately promotes the secure development of drugs.

An insulin-like signalling pathway model for Fasciola gigantica

BACKGROUND

The insulin/insulin-like signalling (IIS) pathway is common in mammals and invertebrates, and the IIS pathway is unknown in Fasciola gigantica. In the present study, the IIS pathway was reconstructed in F. gigantica. We defined the components involved in the IIS pathway and investigated the transcription profiles of these genes for all developmental stages of F. gigantica. In addition, the presence of these components in excretory and secretory products (ESPs) was predicted via signal peptide annotation.

RESULTS

The core components of the IIS pathway were detected in F. gigantica. Among these proteins, one ligand (FgILP) and one insulin-like molecule binding protein (FgIGFBP) were analysed. Interestingly, three receptors (FgIR-1/FgIR-2/FgIR-3) were detected, and a novel receptor, FgIR-3, was screened, suggesting novel functions. Fg14-3-3ζ, Fgirs, and Fgpp2a exhibited increased transcription in 42-day-old juveniles and 70-day-old juveniles, while Fgilp, Fgigfb, Fgsgk-1, Fgakt-1, Fgir-3, Fgpten, and Fgaap-1 exhibited increased transcription in metacercariae. FgILP, FgIGFBP, FgIR-2, FgIR-3, and two transcription factors (FgHSF-1 and FgSKN-1) were predicted to be present in FgESPs, indicating their exogenous roles.

CONCLUSIONS

This study helps to elucidate the signal transduction pathway of IIS in F. gigantica, which will aid in understanding the interaction between flukes and hosts, as well as in understanding fluke developmental regulation, and will also lay a foundation for further characterisation of the IIS pathways of trematodes.

Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules

INTRODUCTION

Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.

AREAS COVERED

This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.

EXPERT OPINION

ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.

Reconstruction of the TGF-β signaling pathway of Fasciola gigantica

In the present study, we reconstructed the transforming growth factor beta (TGF-β) signaling pathway for Fasciola gigantica, which is a neglected tropical pathogen. We defined the components involved in the TGF-β signaling pathway and investigated the transcription profiles of these genes for all developmental stages of F. gigantica. In addition, the presence of these components in excretory and secretory products (FgESP) was predicted via signal peptide annotation. The core components of the TGF-β signaling pathway have been detected in F. gigantica; classical and nonclassical single transduction pathways were constructed. Four ligands have been detected, which may mediate the TGF-β signaling pathway and BMP signaling pathway. Two ligand-binding type II receptors were detected, and inhibitory Smad7 was not detected. TLP, BMP-3, BMP-1, and ActRIb showed higher transcription in 42-day juvenile and 70-day juvenile, while ActRIIa, Smad1, ActRIIb, Smad8, KAT2B, and PP2A showed higher transcription in egg. TLM, Ski, Smad6, BMPRI, p70S6K, Smad2, Smad3, TgfβRI, Smad4, and p300 showed higher transcription in metacercariae. Four ligands, 2 receptors and 3 Smads are predicted to be present in the FgESP, suggesting their potential extrinsic function. This study should help to understand signal transduction in the TGF-β signaling pathway in F. gigantica. In addition, this study helps to illustrate the complex mechanisms involved in developmental processes and F. gigantica - host interaction and paves the way for further characterization of the signaling pathway in trematodes.

Identifying Differences in the Performance of Machine Learning Models for Off-Targets Trained on Publicly Available and Proprietary Data Sets

Each year, publicly available databases are updated with new compounds from different research institutions. Positive experimental outcomes are more likely to be reported; therefore, they account for a considerable fraction of these entries. Established publicly available databases such as ChEMBL allow researchers to use information without constrictions and create predictive tools for a broad spectrum of applications in the field of toxicology. Therefore, we investigated the distribution of positive and nonpositive entries within ChEMBL for a set of off-targets and its impact on the performance of classification models when applied to pharmaceutical industry data sets. Results indicate that models trained on publicly available data tend to overpredict positives, and models based on industry data sets predict negatives more often than those built using publicly available data sets. This is strengthened even further by the visualization of the prediction space for a set of 10,000 compounds, which makes it possible to identify regions in the chemical space where predictions converge. Finally, we highlight the utilization of these models for consensus modeling for potential adverse events prediction.

Perspectives of data science in preclinical safety assessment

The data landscape in preclinical safety assessment is fundamentally changing because of not only emerging new data types, such as human systems biology, or real-world data (RWD) from clinical trials, but also technological advancements in data-processing software and analytical tools based on deep learning approaches. The recent developments of data science are illustrated with use cases for the three factors: predictive safety (new in silico tools), insight generation (new data for outstanding questions); and reverse translation (extrapolating from clinical experience to resolve preclinical questions). Further advances in this field can be expected if companies focus on overcoming identified challenges related to a lack of platforms and data silos and assuring appropriate training of data scientists within the preclinical safety teams.