2026-10-12T13:52:20Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33716551 2026-09-13T21:03:33Z category_19 category_21 category_272 category_873 category_45 category_734 category_931 portal_63 item_type_3 month_year_09_2026

Fragment-Based Explainable AI for Pathogen-Selective Antimicrobial Drug Design Abdulmujeeb T. Onawole (10641517) Mark A. T. Blaskovich (8804579) Johannes Zuegg (1580692) Pharmacology Biotechnology Environmental Sciences not elsewhere classified Chemical Sciences not elsewhere classified Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified structurally divergent library staphylococcus aureus </ escherichia coli </ different microbial classes candida albicans </ throughput screening compounds novel compound libraries correctly predicted compounds new antimicrobial agents based explainable ai based contribution scores core scaffolds responsible allowing medicinal chemists specific predictive models selective fragment lists developed xai framework specific pathogens selective fragments selecting compounds predictive performance novel antimicrobials 000 compounds three models models trained antimicrobial potential sme ), rational design practical guide negative effect negative ), highly valuable fungal ). external validation evaluation tool enrichment factors efficient development comparative analysis chemical structures 000 high The rise and extent of antimicrobial resistance demand computational tools that go beyond simple predictions of antimicrobial activity to deliver applicable medicinal chemistry insights for an accelerated and more efficient development of novel antimicrobials. Here, we present a fragment-based explainable artificial intelligence (XAI) framework, based on Relational Graph Convolutional Network (R-GCN) models trained with over 127,000 compounds from the Community for Open Antimicrobial Drug Discovery (CO-ADD) database and ChEMBL, targeting <i>Staphylococcus aureus</i> (Gram-positive), <i>Escherichia coli</i> (Gram-negative), and <i>Candida albicans</i> (fungal). External validation on 100,000 high-throughput screening compounds from the European Chemical Biology Database (ECBD) demonstrated the predictive performance of the three models and their utility in selecting compounds from a structurally divergent library, with enrichment factors up to 19-fold. Using substructure mask explanation (SME), we further decompose each prediction into fragment-based contribution scores and map them onto the chemical structures, allowing medicinal chemists to identify which scaffolds and substituents have a positive or negative effect on the activity against specific pathogens. From correctly predicted compounds, we further extracted pathogen-selective XAI fragments representing the core scaffolds responsible for activity, allowing a comparative analysis of these selective fragments between the different microbial classes and providing an evaluation tool for the antimicrobial potential of novel compound libraries. 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. 2026-09-13T00:00:00Z Dataset Dataset 10.1021/acsinfecdis.6c00325.s003 https://figshare.com/articles/dataset/Fragment-Based_Explainable_AI_for_Pathogen-Selective_Antimicrobial_Drug_Design/33716551 CC BY-NC 4.0