Machine Learning Strategies to Tackle Data Challenges in Mass Spectrometry-Based Proteomics
Journal of the American Society for Mass Spectrometry · 2024-09-04 · 35 (9) · 2143-2155
DOI: 10.1021/jasms.4c00180 ↗At a glance
Journal article in Journal of the American Society for Mass Spectrometry, published online on 2024-07-29. Written by Ceder Dens and 3 co-authors. Institution: Adrem Data Lab, Department of Computer Science, University of Antwerp, Middelheimlaan 1, 2020 Antwerpen, Belgium. Major MEDLINE topics: Machine Learning, Mass Spectrometry, Proteomics. Cited 21 times so far (Crossref); 77 references. Funded by: Universiteit Antwerpen, Vlaamse regering.
Abstract (original language)
In computational proteomics, machine learning (ML) has emerged as a vital tool for enhancing data analysis. Despite significant advancements, the diversity of ML model architectures and the complexity of proteomics data present substantial challenges in the effective development and evaluation of these tools. Here, we highlight the necessity for high-quality, comprehensive data sets to train ML models and advocate for the standardization of data to support robust model development. We emphasize the instrumental role of key data sets like ProteomeTools and MassIVE-KB in advancing ML applications in proteomics and discuss the implications of data set size on model performance, highlighting that larger data sets typically yield more accurate models. To address data scarcity, we explore algorithmic strategies such as self-supervised pretraining and multitask learning. Ultimately, we hope that this discussion can serve as a call to action for the proteomics community to collaborate on data standardization and collection efforts, which are crucial for the sustainable advancement and refinement of ML methodologies in the field.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Adrem Data Lab, Department of Computer Science, University of Antwerp, Middelheimlaan 1, 2020 Antwerpen, Belgium.
ORCID profiles: Ceder Dens, Charlotte Adams, Kris Laukens, Wout Bittremieux
Funding
- Universiteit Antwerpen
- Vlaamse regering
Cite
APA
Dens, C., Adams, C., Laukens, K., & Bittremieux, W. (2024). Machine Learning Strategies to Tackle Data Challenges in Mass Spectrometry-Based Proteomics. Journal of the American Society for Mass Spectrometry, 35(9), 2143-2155. https://doi.org/10.1021/jasms.4c00180
Vancouver
Dens C, Adams C, Laukens K, Bittremieux W. Machine Learning Strategies to Tackle Data Challenges in Mass Spectrometry-Based Proteomics. Journal of the American Society for Mass Spectrometry. 2024;35(9):2143-2155. doi:10.1021/jasms.4c00180
BibTeX
@article{Dens2024,
author = {Dens, Ceder and Adams, Charlotte and Laukens, Kris and Bittremieux, Wout},
title = {Machine Learning Strategies to Tackle Data Challenges in Mass Spectrometry-Based Proteomics},
journal = {Journal of the American Society for Mass Spectrometry},
year = {2024},
volume = {35},
number = {9},
pages = {2143--2155},
doi = {10.1021/jasms.4c00180}
}
EUVIMED