AI-driven Discovery of Morphomolecular Signatures in Toxicology

• Type of Material: Article
• Authors: Guillaume Jaume, Harvard University; Thomas Peeters, Harvard University; Andrew H. Song, Harvard University; Rowland Pettit, Harvard University; Drew F.K. Williamson, Emory University; Lukas Oldenburg, Harvard University; Anurag Vaidya, Harvard University; Simone de Brot, University of Bern; Richard J. Chen, Harvard University; Jean-Philippe Thiran, EPFL; Long Phi Le, Harvard University; Georg Gerber, Harvard University; Faisal Mahmood, Harvard University
• Language: English
• Date: 2024-07-23
• Publisher: NIH
• Publication Version: Preprint (Prior to Peer Review)
• Copyright Statement: The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.
• License: Creative Commons Attribution-NonCommercial 4.0 International
• Final Published Version (URL): https://doi.org/10.1101/2024.07.19.604355
• Title of Journal or Parent Work: bioRxiv
• Start Page: 604355
• Grant/Funding Agency: BWH & MGH Pathology; BWH President’s Scholar fund; German Academic Exchange; Massachusetts Life Sciences Center; NSF; BWH President’s Fund
• Grant/Funding Information: This work was supported in part by BWH & MGH Pathology, BWH President’s Fund, Massachusetts Life Sciences Center, NIGMS R35GM138216 (F.M.), and BWH President’s Scholar fund (G.G.) and NIGMS R35GM149270 (G.G.). R.J.C. was also supported by the NSF Graduate Fellowship. L.O. was supported by the German Academic Exchange (DAAD) Fellowship.
• Keywords: toxicogenomics; drug toxicity; biomarkers; in vitro assays
• Subject - Topics: Toxicology; Drug development

Abstract

Early identification of drug toxicity is essential yet challenging in drug development. At the preclinical stage, toxicity is assessed with histopathological examination of tissue sections from animal models to detect morphological lesions. To complement this analysis, toxicogenomics is increasingly employed to understand the mechanism of action of the compound and ultimately identify lesion-specific safety biomarkers for which in vitro assays can be designed. However, existing works that aim to identify morphological correlates of expression changes rely on qualitative or semi-quantitative morphological characterization and remain limited in scale or morphological diversity. Artificial intelligence (AI) offers a promising approach for quantitatively modeling this relationship at an unprecedented scale. Here, we introduce GEESE, an AI model designed to impute morphomolecular signatures in toxicology data. Our model was trained to predict 1,536 gene targets on a cohort of 8,231 hematoxylin and eosin-stained liver sections from Rattus norvegicus across 127 preclinical toxicity studies. The model, evaluated on 2,002 tissue sections from 29 held-out studies, can yield pseudo-spatially resolved gene expression maps, which we correlate with six key drug-induced liver injuries (DILI). From the resulting 25 million lesion-expression pairs, we established quantitative relations between up and downregulated genes and lesions. Validation of these signatures against toxicogenomic databases, pathway enrichment analyses, and human hepatocyte cell lines asserted their relevance. Overall, our study introduces new methods for characterizing toxicity at an unprecedented scale and granularity, paving the way for AI-driven discovery of toxicity biomarkers.