Back

Multimodal Cross-Attentive Graph-Based Framework for Predicting In Vivo Endocrine Disruptors

Santos, E. S. d. A.; Felizardo, G. S. S.; da Silva, A. C. G.; Martin, H.-J.; Muratov, E. N.; Braga, R. d. C.; Neves, B. J.

2025-09-19 pharmacology and toxicology
10.1101/2025.09.16.676584 bioRxiv
Show abstract

Endocrine hazard assessment needs models that are accurate and mechanistically transparent. We present a multimodal cross-attentive graph framework that fuses molecular graphs with adverse-outcome-pathway (AOP)-anchored assay signals to predict organism-level outcomes in the OECD Hershberger and uterotrophic assays. In Tier-1, multitask GNNs learn ER/AR molecular-initiating and key events across 46 ToxCast/Tox21 assays. In Tier-2, a cross-attentive multimodal GNN integrates Tier-1 pathway signals with molecular graphs, achieving AUROC{square}={square}0.90 (Hershberger) and 0.96 (uterotrophic). External validation on literature compounds showed 84% concordance (Hershberger 15/18; uterotrophic 22/26). Bidirectional cross-attention links molecular substructures to pathway assays and vice-versa, while counterfactual perturbations rank assays and structural motifs most responsible for each decision. The framework couples high accuracy with assay-traceable explanations, supporting targeted testing within the Integrated Approaches.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.