AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design

Lisa Schneckenreiter, Sohvi Luukkonen, Lukas Friedrich, Daniel Kuhn, Günter Klambauer

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 0 citations (OpenAlex)

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
add ligand-based data to structure-based training (ablation)ConGLUDe · LIT-PCBAAUROC: 53.06 -> 66.25Improved
add structure-based data to ligand-based training (ablation)ConGLUDe · LIT-PCBAAUROC: 67.94 -> 66.25Mixed
add ligand-based data to structure-based training (ablation)ConGLUDe · DUD-EAUROC: 83.88 -> 82.04Hurt
add structure-based data to ligand-based training (ablation)ConGLUDe · DUD-EAUROC: 67.11 -> 82.04Improved
add structure-based data to ligand-based training (ablation)ConGLUDe · Kinobeads target fishingAUROC: 45.2 -> 65.6Improved
add ligand-based data to structure-based training (ablation)ConGLUDe · Kinobeads target fishingAUROC: 63.2 -> 65.6Improved
add molecule-to-binding-site loss L_m2b (ablation)ConGLUDe · ASD pocket selectiontop-1 DCC success rate: 0.10 -> 0.35Improved
add geometric loss L_geometric (ablation)ConGLUDe · ASD pocket selectiontop-1 DCC success rate: 0.01 -> 0.35Improved
add geometric loss L_geometric (ablation)ConGLUDe · LIT-PCBAAUROC: 64.17 -> 66.25Improved
add molecule-to-protein loss L_m2p (ablation)ConGLUDe · LIT-PCBAAUROC: 64.80 -> 66.25Improved
add molecule-to-protein loss L_m2p (ablation)ConGLUDe · Kinobeads target fishingAUROC: 65.4 -> 65.6No clear effect
add ConGLUDe ligand-conditioning over unconditioned VN-EGNN rankingVN-EGNN · ASD pocket selectiontop-1 DCC success rate: 0.28 -> 0.35Improved

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