EBD-DTI: Episodic Bridge Diffusion for Zero-Shot Cold-Start Drug-Target Interaction Prediction
Liu, J.; Le, J.; Wei, C.; Liu, M.; Yin, Z.
Show abstract
Predicting drug-target interactions (DTI) for entirely unseen drugs or proteins--the cold-start problem--remains a critical challenge in computational drug discovery. While sequence-based methods naturally support zero-shot generalization, they often ignore relational topology, and existing graph-based approaches either rely on global diffusion that blurs the boundary between inductive and transductive evaluation or require a few known interaction samples at test time (few-shot). We present EBD-DTI, a framework that enables zero-shot inference in graph-based DTI models without requiring any known interactions for unseen entities. The key innovation is episodic cold-start training : at each epoch, a random subset of training entities is masked and treated as pseudo-cold, forcing the model to learn cold-start inference with explicit gradient supervision. A bridge-conditioned local subgraph, together with multi-hop diffusion, provides cold entities with relational context from their nearest observed neighbors. Experiments on three benchmarks (BioSNAP, BindingDB, and DrugBank) demonstrate that EBD-DTI achieves competitive or superior performance compared to state-of-the-art methods under strict zero-shot evaluation, with episodic training improving AUC by up to 12%.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ProteinBERT: A universal deep-learning model of protein sequence and function 96%
- DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug-target interactions 96%
- Cross-Modality and Self-Supervised Protein Embedding for Compound-Protein Affinity and Contact Prediction 96%
Similar papers in this journal
- Interpreting Neural Networks for Biological Sequences by Learning Stochastic Masks 95%
- Accelerating protein engineering with fitness landscape modeling and reinforcement learning 94%
- TrustAffinity: accurate, reliable and scalable out-of-distribution protein-ligand binding affinity prediction using trustworthy deep learning 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.