DeepMS: super-fast peptide identification using end-to-end deep learning method

Abstract

Mass spectrometry (MS) has emerged as a powerful omics analysis technique, particularly in proteomics, where the initial step involves identifying MS spectra as peptide sequences. However, this process often requires substantial computational resources and expertise, taking hours or even days to complete, thereby limiting the widespread adoption of MS-based omics technologies. To overcome this challenge, we have developed DeepMS, a deep learning-based spectra identification algorithm that overcomes the speed limitations of traditional spectra identification methods. We conducted comprehensive benchmark tests, comparing six deep learning algorithms. Based on the results, we selected the VGG16 algorithm as the core model for DeepMS. This algorithm enables super-fast, end-to-end identification of peptide sequences from MS spectra with high accuracy. DeepMS is adaptable to post-translational modifications, enhancing its versatility. In fact, its identification speed surpasses the generation rate of MS spectra, enabling super-fast identification. Furthermore, we demonstrate the practical application of DeepMS in microorganism detection, highlighting its utility in clinical testing. Through the implementation of DeepMS, our aim is to revolutionize the field of MS-based proteomics and facilitate the broader application of omics technologies, opening new avenues for rapid and efficient analysis in various research and clinical domains.