Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
Bowen Gao, Bo Qiang, Haichuan Tan, Yinjun Jia, Minsi Ren, Minsi Lu, Jingjing Liu, Wei-Ying Ma, Yanyan Lan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add RDKit conformations (ablation) | DrugCLIP · DUD-E zero-shot | BEDROC (%): 38.13 -> 45.81 | Improved |
| add HomoAug on top of RDKit conformations (ablation) | DrugCLIP · DUD-E zero-shot | BEDROC (%): 45.81 -> 50.52 | Improved |
| add HomoAug on top of RDKit conformations (ablation) | DrugCLIP · DUD-E zero-shot | AUROC (%): 81.05 -> 80.93 | No clear effect |
| add HomoAug on top of RDKit conformations (ablation) | DrugCLIP · DUD-E zero-shot | EF@1%: 29.12 -> 31.89 | Improved |
| finetune on DUD-E | DrugCLIP · DUD-E | AUROC (%): 80.93 -> 96.59 | Improved |
| finetune on DUD-E | DrugCLIP · DUD-E | RE@0.5%: 73.97 -> 118.10 | Improved |
| add atom embeddings from last transformer layer (ablation) | DrugCLIP · DUD-E | BEDROC (%): 50.52 -> 44.72 | Hurt |
| add atom embeddings from second-last layer (ablation) | DrugCLIP · DUD-E | AUROC (%): 80.93 -> 82.79 | Mixed |
| DrugCLIP vs Glide target fishing | DrugCLIP · CASF-2016 target fishing | accuracy @1: 14.98 -> 24.07 | Improved |
| DrugBA for target fishing (ablation) | DrugBA · CASF-2016 target fishing | accuracy @1: 24.07 -> 0.37 | Hurt |
| DrugCLIP vs Glide in expert preference | DrugCLIP · 5 pockets human evaluation | molecules chosen by experts: 8 vs 2 on 5kdt | Mixed |
| training data PDBBind vs BioLip vs ChEMBL (ablation) | DrugCLIP-S/M/L · DUD-E and LIT-PCBA | performance | Mixed |
Later papers that compared with this method
3 later accepted papers report DrugCLIP as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- SubDyve: Subgraph-Driven Dynamic Propagation for Virtual Screening Enhancement Controlling False Positive (ICLR 2026 · better on 4 of 4 shared results)
- Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning (ICML 2025 · better on 5 of 5 shared results)
- S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search (NeurIPS 2024 · better on 8 of 8 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DrugHash: Hashing Based Contrastive Learning for Virtual Screening (AAAI 2025 · similarity 0.90)
- Knowledge Enhanced Representation Learning for Drug Discovery (AAAI 2024 · similarity 0.89)
- Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning (ICML 2025 · similarity 0.89)
- AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation (NeurIPS 2025 · similarity 0.88)
- PharmacoMatch: Efficient 3D Pharmacophore Screening via Neural Subgraph Matching (ICLR 2025 · similarity 0.88)
- DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction (NeurIPS 2025 · similarity 0.87)
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.
