Research map / Graph learning / Graph self-supervised learning
ToDD: Topological Compound Fingerprinting in Computer-Aided Drug Discovery
Andac Demir, Baris Coskunuzer, Yulia Gel, Ignacio Segovia-Dominguez, Yuzhou Chen, Bulent Kiziltan
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 |
|---|---|---|---|
| use ToDD-ViT instead of best baseline (PS + ROCS) | ToDD · Cleves-Jain | EF 2%: 20.5 -> 39.6 | Improved |
| use ToDD-ViT instead of best baseline | ToDD · Cleves-Jain | EF 10%: 6.4 -> 9.9 | Improved |
| use ToDD-RF instead of ToDD-ViT | ToDD · Cleves-Jain | EF 2%: 39.6 -> 35.2 | Hurt |
| use ToDD-RF instead of ToDD-ViT | ToDD · Cleves-Jain | ROC-AUC: 0.90 -> 0.94 | Improved |
| use ToDD-RF instead of best baseline ROCS | ToDD · Cleves-Jain | ROC-AUC: 0.83 -> 0.94 | Improved |
| use ToDD-RF instead of best baseline DeepScore | ToDD · DUD-E Diverse average | EF 1%: 47.9 -> 73.7 | Improved |
| use ToDD-ConvNeXt instead of ToDD-RF | ToDD · DUD-E Diverse CP3A4 | EF 1%: 67.6 -> 28.8 | Hurt |
| use ToDD-ConvNeXt instead of ToDD-RF | ToDD · DUD-E Diverse AMPC | EF 1%: 42.9 -> 46.2 | Improved |
| use ToDD-ConvNeXt instead of ToDD-RF | ToDD · DUD-E Diverse GCR | EF 1%: 78.9 -> 46.0 | Hurt |
| use ToDD-ConvNeXt instead of best baseline | ToDD · DUD-E Diverse average | EF 1%: 47.9 -> 58.9 | Improved |
| combine atomic mass, partial charge and bond type modalities versus single modality (ablation) | ToDD · Cleves-Jain and DUD-E | EF | Improved |
| replace multiparameter persistence fingerprints with Morgan fingerprints (ablation) | ToDD · all DUD-E targets | EF | Hurt |
Closest papers by meaning
- AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation (NeurIPS 2025 · similarity 0.86)
- M²N: A Progressive Macro-to-Micro 3D Modeling Scheme for Unveiling Drug-Target Affinity (AAAI 2025 · similarity 0.85)
- Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism (NeurIPS 2024 · similarity 0.85)
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks (ICLR 2024 · similarity 0.85)
- Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning (ICML 2025 · similarity 0.85)
- DrugHash: Hashing Based Contrastive Learning for Virtual Screening (AAAI 2025 · similarity 0.85)
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.
