A machine learning pipeline is presented that addresses chemical novelty upfront by employing an XGBoost-based MoA classifier to explicitly prioritize compounds predicted to have mechanisms distinct from known antibiotic classes, combined with graph neural networks for antibacterial activity and toxicity prediction.
Abstract
The rise of antibiotic resistance necessitates the discovery of antibacterial compounds with novel mechanisms of action (MoAs). Recent machine learning approaches have shown promise in antibacterial compound discovery, but often identify derivatives of known antibiotic classes rather than mechanistically novel compounds. Previous approaches applied Tanimoto similarity filters at the end of screening pipelines, but this method has substantial drawbacks: Tanimoto similarity can be misleading in chemical space, and post-hoc filtering does not influence what activity models learn to prioritize. Here, we present a machine learning pipeline that addresses chemical novelty upfront by employing an XGBoost-based MoA classifier to explicitly prioritize compounds predicted to have mechanisms distinct from known antibiotic classes, combined with graph neural networks for antibacterial activity and toxicity prediction. Applied to the Zinc20 database, our approach successfully identified non-toxic antibacterial compounds structurally distinct from known antibiotics. Notably, the majority of these hits exhibited membrane-targeting activity with selectivity for bacterial cells over mammalian cells, suggesting potential for next-generation membrane-active antibiotics. However, we did not identify compounds with novel protein targets. Systematic analysis revealed that this limitation stems from mechanistic bias in training data rather than model architecture. Specifically, our activity model learned to preferentially score compounds similar to specific groups in the training data, thus overrepresenting certain MoA classes including membrane-active compounds. Even substantial model architecture and training data enhancements did not overcome this constraint. Our findings demonstrate that the primary bottleneck for discovering mechanistically novel antibiotics is the scarcity of diverse, mechanistically-annotated training data. This work provides both a methodological framework for mechanism-aware screening and critical insights into data requirements for genuinely novel antibiotic discovery.
The developed XAI framework, together with the pathogen-specific predictive models, the pathogen-selective fragment lists, and their mapping onto the chemical structures, is able to provide a highly valuable and practical guide to the rational design of new antimicrobial agents.
Abdulmujeeb T. Onawole, M. Blaskovich, Johannes Zuegg· ACS Infectious Diseases· 0 citations
An explainable machine-learning framework was developed to predict antibacterial activity of natural products using data from the NPASS 3.0 database and showed the highest overall contributions, while LogP was the most influential conventional molecular descriptor.
Deepthi Goteti· Natural Resources for Human...· 0 citations
Natural products remain an important source of chemically diverse molecules for anticancer drug discovery, but the large number of compounds reported in natural product databases makes systematic experimental screening difficult. Computational approaches can assist this process by identifying structural patterns associ...
H. Shaheen· Natural Resources for Human...· 0 citations
The rapid increase in antimicrobial resistance has created an urgent demand for efficient methods to discover novel antimicrobial compounds. Traditional laboratory screening methods are expensive, time consuming, and often infeasible for evaluating large chemical libraries. Computational approaches using machine learni...
R. Rajan, K. S. Sunil, V. S. Muhammed Naseef et al.· International Conference Inn...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.