Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{2396577,
author = {Bushuiev, Anton and Bushuiev, Roman and Sedlar, Jiri and Pluskal, Tomas and Damborský, Jiří and Mazurenko, Stanislav and Sivic, Josef},
booktitle = {ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design},
language = {eng},
title = {Revealing data leakage in protein interaction benchmarks},
year = {2024}
}
TY - JOUR
ID - 2396577
AU - Bushuiev, Anton - Bushuiev, Roman - Sedlar, Jiri - Pluskal, Tomas - Damborský, Jiří - Mazurenko, Stanislav - Sivic, Josef
PY - 2024
TI - Revealing data leakage in protein interaction benchmarks
N2 - 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 leakage. This may result in overoptimistic evaluation of generalization, as well as unfair benchmarking of the models, biased towards assessing their overfitting capacity rather than practical utility. To overcome the data leakage, we recommend constructing data splits based on 3D structural similarity of protein-protein interfaces and suggest corresponding algorithms. We believe that addressing the data leakage problem is critical for further progress in this research area.
ER -
BUSHUIEV, Anton, Roman BUSHUIEV, Jiri SEDLAR, Tomas PLUSKAL, Jiří DAMBORSKÝ, Stanislav MAZURENKO a Josef SIVIC. Revealing data leakage in protein interaction benchmarks. In \textit{ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design}. 2024, 13 s.
|
