PiNUI: A Dataset of Protein-Protein Interactions for Machine Learning
Dubourg-Felonneau, G.; Wesego, D. M.; Akiva, E.; Varadan, R.
Show abstract
We introduce a novel dataset named PiNUI: Protein Interactions with Nearly Uniform Imbalance. PiNUI is a dataset of Protein-Protein Interactions (PPI) specifically designed for Machine Learning (ML) applications that offer a higher degree of representativeness of real-world PPI tasks compared to existing ML-ready PPI datasets. We achieve such by increasing the data size and quality, and minimizing the sampling bias of negative interactions. We demonstrate that models trained on PiNUI almost always outperform those trained on conventional PPI datasets when evaluated on various general PPI tasks using external test sets. PiNUI is available here.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- RAPPPID: Towards Generalisable Protein Interaction Prediction with AWD-LSTM Twin Networks 96%
- FAPM: Functional Annotation of Proteins using Multi-Modal Models Beyond Structural Modeling 95%
- Pair-EGRET: enhancing the prediction of protein-proteininteraction sites through graph attention networks and protein language models 95%
Similar papers in this journal
- ProteinPrompt: a webserver for predicting protein-protein interactions 95%
- Improving protein function prediction by learning and integrating representations of protein sequences and function labels 94%
- KSMoFinder - Knowledge graph embedding of proteins and motifs for predicting kinases of human phosphosites 94%
Similar papers in this journal
Similar papers in this journal
- ProteinWeaver: A Webtool to Visualize Ontology-Annotated Protein Networks 94%
- Classification of protein binding ligands using structural dispersion of binding site atoms from principal axes 93%
- TranCEP: Predicting transmembrane transport proteins using composition, evolutionary, and positional information 93%
Similar papers in this journal
- A fully open-source framework for deep learning protein real-valued distances 94%
- Benchmarking Protein Language Models for Protein Crystallization 94%
- Predicting interchain contacts for homodimeric and homomultimeric protein complexes using multiple sequence alignments of monomers and deep learning 93%
"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.