SPPIDER-seq: Sequence-based partner-aware predictor of protein-protein interaction sites
Porollo, A.; Jadhav, O.; Alvarez, A.; Chen, J.
Show abstract
MotivationSequence-based protein-protein interaction (PPI) site predictors typically analyze proteins in isolation, neglecting partner-specific context that is critical for interface specificity, particularly in transient and disordered interactions. ResultsWe introduce SPPIDER-seq, a partner-aware PPI site prediction framework that combines pretrained ESM-2 embeddings with a cross-attention architecture to enable residue-level conditioning on interacting partners. We curated non-redundant protein-peptide interaction datasets from BioLiP and used them to train and benchmark two complementary models: a receptor-centric model optimized for structured interfaces and a peptide-centric model tailored to disordered, motif-driven binding. On blind benchmarks, SPPIDER-seq achieved AUROC values up to 0.797 and MCC values up to 0.269, outperforming AlphaFold3 on peptide-mediated and disordered interfaces while remaining complementary on globular complexes. Application to 341 TP53 interaction partners revealed coherent, partner-specific interface patterns across both structured and intrinsically disordered regions. Availability and ImplementationSPPIDER-seq models, datasets, and the Python code are freely available on the web at: https://github.com/aporollo-lab/SPPIDER-seq and archived on Zenodo at DOI: 10.5281/zenodo.19835990, corresponding to GitHub release v2.0-manuscript. ContactDr. Aleksey Porollo - porollay@ucmail.uc.edu Dr. Jichao Chen - jichao.chen@cchmc.org Supplementary InformationAvailable online with the manuscript.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Rhapsody: Pathogenicity prediction of human missense variants based on protein sequence, structure and dynamics 96%
- Unsupervised protein embeddings outperform hand-crafted sequence and structure features at predicting molecular function 96%
- Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery 95%
Similar papers in this journal
- COLLAPSE: A representation learning framework for identification and characterization of protein structural sites 95%
- Neural Network-Derived Potts Models for Structure-Based Protein Design using Backbone Atomic Coordinates and Tertiary Motifs 94%
- ConforFold Recovers Alternative Protein Conformations Beyond MSA Subsampling 94%
Similar papers in this journal
- Disobind: a sequence-based, partner-dependent contact map and interface residue predictor for intrinsically disordered regions 97%
- DynamicGT: a dynamic-aware geometric transformer model to predict protein binding interfaces in flexible and disordered regions 95%
- Inferring protein sequence-function relationships with large-scale positive-unlabeled learning 95%
Similar papers in this journal
- Getting to know each other: PPIMem, a novel approach for predicting transmembrane protein-protein complexes 94%
- Towards mechanistic models of mutational effects: Deep Learning on Alzheimer's Aβ peptide 93%
- Systematic Investigation of Machine Learning on Limited Data: A Study on Predicting Protein-Protein Binding Strength 92%
"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.