Mechanism-Aware Protein-Protein Interaction Prediction via Contact-Guided Dual Attention on Protein Language Models
Deng, S.; Wan, X.; Mu, Z.; HUANG, S.-Y.; Yan, C.
Show abstract
Robust prediction of protein-protein interactions (PPIs) requires models that generalize beyond the training distribution. Here, we present PLMDA-PPI, a mechanism-aware framework that incorporates biophysical inductive biases into a dual-attention architecture with residue-level contact supervision applied to protein language model embedded geometric representations. This design enables the model to jointly learn global interaction likelihoods and the residue pairs mediating interactions, producing interpretable, mechanism-grounded predictions. PLMDA-PPI demonstrates strong out-of-distribution generalization, substantially outperforming lightweight deep learning models (D-SCRIPT, Topsy-Turvy, TT3D, and TUnA) and achieving comparable or even superior performance to computationally intensive methods (AF2Complex, RF2-Lite, and RF2-PPI) derived from AlphaFold2 and RoseTTAFold2, while requiring orders of magnitude fewer computational resources. These results show that incorporating mechanistic priors as architectural inductive biases enhances generalization, interpretability, and computational efficiency, providing a principled foundation for AI-driven prediction of complex biological interactions.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction 98%
- High-accuracy protein complex structure modeling based on sequence-derived structure complementarity 98%
- DeepRank: A deep learning framework for data mining 3D protein-protein interfaces 97%
Similar papers in this journal
- Improved inter-protein contact prediction using dimensional hybrid residual networks and protein language models 97%
- GraphCPLMQA: Assessing protein model quality based on deep graph coupled networks using protein language model 97%
- Cracking the black box of deep sequence-based protein-protein interaction prediction 96%
Similar papers in this journal
- ProBASS: a language model with sequence and structural features for predicting the effect of mutations on binding affinity 96%
- Unsupervised protein embeddings outperform hand-crafted sequence and structure features at predicting molecular function 96%
- PIPENN: Protein Interface Prediction with an Ensemble of Neural Nets 96%
Similar papers in this journal
Similar papers in this journal
- Rapid and accurate protein structure database search using inverse folding model and contrastive learning 97%
- ProAffinity-GNN: A Novel Approach to Structure-based Protein-Protein Binding Affinity Prediction via a Curated Dataset and Graph Neural Networks 96%
- To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map 96%
"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.