Research map / Probabilistic and scientific modeling / Molecules and proteins
CASTER: Predicting Drug Interactions with Chemical Substructure Representation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CASTER instead of MolVAE | DDI prediction · BIOSNAP | ROC-AUC: 0.892\pm0.009 -> 0.910 ± 0.005 | Helped |
| Use CASTER instead of MolVAE | DDI prediction · BIOSNAP | PR-AUC: 0.877 \pm 0.009 -> 0.887 \pm 0.008 | Helped |
| Use CASTER instead of DeepDDI | DDI prediction · BIOSNAP | F1: 0.817\pm0.007 -> 0.843 \pm 0.005 | Helped |
| Use CASTER instead of MolVAE | DDI prediction · DrugBank (DDI) | ROC-AUC: 0.852\pm0.006 -> 0.861 \pm 0.005 | Helped |
| Use CASTER instead of Mol2Vec | DDI prediction · DrugBank (DDI) | PR-AUC: 0.828 \pm 0.006 -> 0.829 \pm 0.003 | Helped |
| Use CASTER instead of Mol2Vec | DDI prediction · DrugBank (DDI) | F1: 0.775\pm0.004 -> 0.796 \pm 0.007 | Helped |
| Increase the amount of unlabelled pretraining data | CASTER · BIOSNAP and DrugBank (DDI), limited labelled data | DDI prediction accuracy | Helped |
| Represent drug pairs with frequent chemical substructures rather than classic fixed-sized fingerprints | DDI prediction · DDI prediction task | predictive value | Helped |
Closest papers by meaning
- Motif-Oriented Representation Learning with Topology Refinement for Drug-Drug Interaction Prediction (AAAI 2025 · similarity 0.88)
- Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction (NeurIPS 2024 · similarity 0.88)
- ExDDI: Explaining Drug-Drug Interaction Predictions with Natural Language (AAAI 2025 · similarity 0.88)
- Dual-Channel Learning Framework for Drug-Drug Interaction Prediction via Relation-Aware Heterogeneous Graph Transformer (AAAI 2024 · similarity 0.87)
- Blend the Separated: Mixture of Synergistic Experts for Data-Scarcity Drug-Target Interaction Prediction (AAAI 2025 · similarity 0.86)
- MOTIVE: A Drug-Target Interaction Graph For Inductive Link Prediction (NeurIPS 2024 · 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.