Mechanistically Interpretable Toxicity Prediction Through Multimodal Integration of Structure and Transcriptomics
Cattebeke, G.; Vermeersch, A.-S.; Cappoen, D.; Deforce, D.; Nieuwerburgh, F. V.
Show abstract
Advances in computational toxicology increasingly emphasize the need for models that deliver both scalable predictive performance and mechanistic insights. Nevertheless, most approaches fall short of capturing the underlying mechanisms that drive toxicity. Herein, we describe a scalable multimodal modeling framework that integrates chemical fingerprints with high-throughput transcriptomic dose-response profiles across three human cell lines to predict activity for 41 curated Tox21 assay endpoints. Using gradient-boosted decision trees and nested compound-aware cross-validation, 13 assays achieved robust performance (mean AUPRC > 0.75), spanning nuclear receptor signaling, stress-response pathways, and xenobiotic metabolism. SHAP-based feature attribution analysis showed that predictions depend on both structural motifs and transcriptional programs, in a manner consistent with established mechanistic relationships between chemical structure, nuclear receptor biology, and adaptive cellular responses. These findings illustrate how structure-HTTr dose-response signature integration enables models that are accurate and mechanistically grounded, shifting computational toxicology toward transparent and biologically informed chemical risk evaluation.
Matching journals
The top 14 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Tales of 1,008 Small Molecules: Phenomic Profiling through Live-cell Imaging in a Panel of Reporter Cell Lines 92%
- A scalable platform for efficient CRISPR-Cas9 chemical-genetic screens of DNA damage-inducing compounds 92%
- Evaluation of Connectivity Map shows limited reproducibility in drug repositioning 91%
Similar papers in this journal
- AnimalGAN: A Generative Adversarial Network Model Alternative to Animal Studies for Clinical Pathology Assessment 95%
- Predicting compound activity from phenotypic profiles and chemical structures 94%
- A novel preclinical secondary pharmacology resource illuminates target-adverse drug reaction associations of marketed drugs 92%
Similar papers in this journal
- Longitudinal wastewater sampling in buildings reveals temporal dynamics of metabolites 92%
- A machine learning and network framework to discover new indications for small molecules 90%
- dGPredictor: Automated fragmentation method for metabolic reaction free energy prediction and de novo pathway design 90%
Similar papers in this journal
- Predicting Toxicity and Bioactivity of the Chemical Exposome: A Case Study for the Blood Exposome Database 96%
- Merging Bioactivity Predictions from Cell Morphology and Chemical Fingerprint Models Using Similarity to Training Data 95%
- qHTSWaterfall: 3-dimensional visualization software for quantitative high-throughput screening (qHTS) data 92%
Similar papers in this journal
- A Method To Calibrate Chemical Agnostic Quantitative Adverse Outcome Pathways On Multiple Chemical Dose-Response Data 92%
- Cell Painting and chemical structure read-across can complement each other for rat acute oral toxicity prediction in chemical early de-risking 91%
- Systematic analysis of protein targets associated with adverse events of drugs from clinical trials and post-marketing reports 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.