AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors.

Autor:	Fernández-Díaz R; IBM Research, Dublin, Dublin D15 HN66, Ireland.; School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.; Conway Institute of Biomolecular and Biomedical Science, University College Dublin, Dublin D04 C1P, Ireland.; The SFI Centre for Research Training in Genomics Data Science, Ireland., Cossio-Pérez R; School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.; Conway Institute of Biomolecular and Biomedical Science, University College Dublin, Dublin D04 C1P, Ireland.; Department of Science and Technology, National University of Quilmes, Bernal B1876, Provincia de Buenos Aires, Argentina., Agoni C; School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.; Conway Institute of Biomolecular and Biomedical Science, University College Dublin, Dublin D04 C1P, Ireland.; Discipline of Pharmaceutical Sciences, School of Health Sciences, University of KwaZulu-Natal, Durban 4000, South Africa., Lam HT; IBM Research, Dublin, Dublin D15 HN66, Ireland., Lopez V; IBM Research, Dublin, Dublin D15 HN66, Ireland., Shields DC; School of Medicine, University College Dublin, Dublin D04 C1P1, Ireland.; Conway Institute of Biomolecular and Biomedical Science, University College Dublin, Dublin D04 C1P, Ireland.
Jazyk:	angličtina
Zdroj:	Bioinformatics (Oxford, England) [Bioinformatics] 2024 Sep 02; Vol. 40 (9).
DOI:	10.1093/bioinformatics/btae555
Abstrakt:	Motivation: Automated machine learning (AutoML) solutions can bridge the gap between new computational advances and their real-world applications by enabling experimental scientists to build their own custom models. We examine different steps in the development life-cycle of peptide bioactivity binary predictors and identify key steps where automation cannot only result in a more accessible method, but also more robust and interpretable evaluation leading to more trustworthy models. Results: We present a new automated method for drawing negative peptides that achieves better balance between specificity and generalization than current alternatives. We study the effect of homology-based partitioning for generating the training and testing data subsets and demonstrate that model performance is overestimated when no such homology correction is used, which indicates that prior studies may have overestimated their performance when applied to new peptide sequences. We also conduct a systematic analysis of different protein language models as peptide representation methods and find that they can serve as better descriptors than a naive alternative, but that there is no significant difference across models with different sizes or algorithms. Finally, we demonstrate that an ensemble of optimized traditional machine learning algorithms can compete with more complex neural network models, while being more computationally efficient. We integrate these findings into AutoPeptideML, an easy-to-use AutoML tool to allow researchers without a computational background to build new predictive models for peptide bioactivity in a matter of minutes. Availability and Implementation: Source code, documentation, and data are available at https://github.com/IBM/AutoPeptideML and a dedicated web-server at http://peptide.ucd.ie/AutoPeptideML. A static version of the software to ensure the reproduction of the results is available at https://zenodo.org/records/13363975. (© The Author(s) 2024. Published by Oxford University Press.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu