Cracking the black box of deep sequence-based protein–protein interaction prediction
Top Cited Papers
Open Access
- 22 January 2024
- journal article
- review article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (2)
Abstract
Identifying protein–protein interactions (PPIs) is crucial for deciphering biological pathways. Numerous prediction methods have been developed as cheap alternatives to biological experiments, reporting surprisingly high accuracy estimates. We systematically investigated how much reproducible deep learning models depend on data leakage, sequence similarities and node degree information, and compared them with basic machine learning models. We found that overlaps between training and test sets resulting from random splitting lead to strongly overestimated performances. In this setting, models learn solely from sequence similarities and node degrees. When data leakage is avoided by minimizing sequence similarities between training and test set, performances become random. Moreover, baseline models directly leveraging sequence similarity and network topology show good performances at a fraction of the computational cost. Thus, we advocate that any improvements should be reported relative to baseline methods in the future. Our findings suggest that predicting PPIs remains an unsolved task for proteins showing little sequence similarity to previously studied proteins, highlighting that further experimental research into the ‘dark’ protein interactome and better computational methods are needed.Keywords
All Related Versions
This publication has 62 references indexed in Scilit:
- Improving the generalizability of protein-ligand binding predictions with AI-BindNature Communications, 2023
- Recent advances in predicting protein–protein interactions with the aid of artificial intelligence algorithmsCurrent Opinion in Structural Biology, 2022
- D-SCRIPT translates genome to phenome with sequence-based, structure-aware, genome-scale predictions of protein-protein interactionsCell Systems, 2021
- Conjoint Feature Representation of GO and Protein Sequence for PPI Prediction Based on an Inception RNN Attention NetworkMolecular Therapy Nucleic Acids, 2020
- Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction2020
- DeepPPI: Boosting Prediction of Protein–Protein Interactions with Deep Neural NetworksJournal of Chemical Information and Modeling, 2017
- Think Locally, Act Globally: Highly Balanced Graph Partitioning2013
- Flaws in evaluation schemes for pair-input computational predictionsNature Methods, 2012
- Large-Scale Prediction of Human Protein−Protein Interactions from Amino Acid Sequence Based on Latent Topic FeaturesJournal of Proteome Research, 2010
- Methods for the detection and analysis of protein–protein interactionsProteomics, 2007