Repurposing PeTriBERT for Protein Protein Interaction Prediction with Sequence Structure Fusion
Wavreille, A.; Krouk, G.; Dumortier, B.
Show abstract
Recent advances in artificial intelligence have enabled models to capture protein sequence and structural features. We present PeTriPPI2, a hybrid framework for protein--protein interaction (PPI) prediction that combines sequence embeddings from ESM-2 with structural representations from PeTriBERT, an encoder originally designed for inverse folding. We evaluate this sequence--structure approach on the Pinder dataset. On a test set of 2,342 protein pairs, the selected checkpoint achieves 0.898 accuracy, 0.917 precision, 0.876 recall, and 0.896 F1 score for the interacting class (AUROC 0.963). Compared with SpatialPPIv2 on the same test data, PeTriPPI2 has higher precision (0.917 versus 0.886) but lower recall (0.876 versus 0.942) and F1 score (0.896 versus 0.913). Component ablations indicate that both the sequence and structural pathways contribute to this configuration.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- From Atoms to Fragments: A Coarse Representation for Functional and Efficient Protein Design 96%
- Cross-Modality and Self-Supervised Protein Embedding for Compound-Protein Affinity and Contact Prediction 96%
- Unsupervised protein embeddings outperform hand-crafted sequence and structure features at predicting molecular function 96%
Similar papers in this journal
- ProteinGLUE: A multi-task benchmark suite for self-supervised protein modeling. 96%
- Evaluating the Significance of Embedding-Based Protein Sequence Alignment with Clustering and Double Dynamic Programming for Remote Homology 95%
- A fully open-source framework for deep learning protein real-valued distances 94%
Similar papers in this journal
- MULAN: Multimodal Protein Language Model for Sequence and Structure Encoding 96%
- DeepRank-GNN-esm: A Graph Neural Network for Scoring Protein-Protein Models using Protein Language Model 95%
- SAINT-Angle: self-attention augmented inception-inside-inception network and transfer learning improve protein backbone torsion angle prediction 94%
Similar papers in this journal
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.