Deep learning in proteomics.

Proteomics, the study of all the proteins in biological systems, is becoming a data-rich science. Protein sequences and structures have been comprehensively catalogued in online databases. With the recent advancements of the tandem mass spectrometry (MS) technology, protein expression and post-translational modifications (PTMs) can be studied in a variety of biological systems at the global scale. Sophisticated computational algorithms are needed to translate the vast amount of data into novel biological insights. Deep learning automatically extracts data representations at high levels of abstraction from data, and it thrives in data-rich research scientific domains. Here, we provide a comprehensive overview of deep learning applications in proteomics including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility complex-peptide binding affinity prediction, and protein structure prediction. We also discuss limitations and the future directions of deep learning in proteomics. We hope this review will provide readers an overview of deep learning and how it can be used to analyze proteomics data. This article is protected by copyright. All rights reserved.