Revealing data leakage in protein interaction benchmarks

arXiv:2404.10457v1 Announce Type: new
Abstract: In recent years, there has been remarkable progress in machine learning for protein-protein interactions. However, prior work has predominantly focused on improving learning algorithms, with less attention paid to evaluation strategies and data preparation. Here, we demonstrate that further development of machine learning methods may be hindered by the quality of existing train-test splits. Specifically, we find that commonly used splitting strategies for protein complexes, based on protein sequence or metadata similarity, introduce major data …

abstract algorithms arxiv attention benchmarks cs.lg data data leakage data preparation development evaluation however improving interactions machine machine learning prior progress protein strategies type work