AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

BiGMINT: Biologically-guided Hierarchical Multimodal Integration for Modeling Multiple Compound Activities in Drug Discovery

Pushpak Pati, Bo Li, Abbas Rayabat Khan, Tomé Albuquerque, Steffen Jaensch, Amina Mollaysa, Walid M. Abdelmoula, Samantha J. Allen, Joke Reumers, Helai P. Mohammad, Scott Oloff, Tommaso Mansi and 3 more

CVPR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein interface and docking prediction

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace mean pooling with attention-based MIL aggregation of HCI patch featuresHCI-only baseline (MTL) · U2OSmean AUCROC (%): 69.40 -> 71.17Improved
use multi-task learning instead of multi-label learningHCI-only baseline (MIL) · U2OSmean AUCROC (%): 67.95 -> 71.17Improved
add chemoproteomics-guided cross-attention aggregation of HCI patches (ablation)BiGMINT · U2OSmean AUCROC (%): 77.72 -> 78.23Improved
add chemoproteomics-guided cross-attention aggregation of HCI patches (ablation)BiGMINT · iNeuronmean AUCROC (%): 75.80 -> 76.51Improved
add PPI-derived task-task interaction (TTI) prior (ablation)BiGMINT · U2OSmean AUCROC (%): 77.02 -> 78.23Improved
add PPI-derived task-task interaction (TTI) prior (ablation)BiGMINT · iNeuronmean AUCROC (%): 74.94 -> 76.51Improved
add TTI prior to HCI-only MIL model (ablation)MIL -> MTL (HCI only) · U2OSmean AUCROC (%): 71.17 -> 72.09Improved
add TTI prior (ablation)BiGMINT · U2OS taskstasks improved: 114/170 tasks improved; +12% tasks with AUCROC >=0.8Improved
use outer-product fusion instead of other fusion operators (ablation)BiGMINT · U2OS and iNeuronmean AUCROCImproved
combine HCI and chemoproteomics by concatenation instead of unimodal modelsmultimodal baseline · U2OSmean AUCROC (%): 71.17 -> 73.65Improved
use alignment-based pretraining (CLOOME, MolPhenix) instead of integrationmultimodal baselines · U2OSmean AUCROC (%): 63.49 and 70.17 vs BiGMINT 78.23Hurt
use BiGMINT instead of optimistic per-task best-modality selection (MM-Union)U2OS/iNeuron · tasks with AUCROC >= 0.8number of tasks covered: +56% (U2OS), +5% (iNeuron)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy