pDeep3: Toward More Accurate Spectrum Prediction with Fast Few-Shot Learning
- 2 April 2021
- journal article
- research article
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 93 (14) , 5815-5822
Abstract
Spectrum prediction using deep learning has attracted a lot of attention in recent years. Although existing deep learning methods have dramatically increased the prediction accuracy, there is still considerable space for improvement, which is presently limited by the difference of fragmentation types or instrument settings. In this work, we use the few-shot learning method to fit the data online to make up for the shortcoming. The method is evaluated using ten data sets, where the instruments includes Velos, QE, Lumos, and Sciex, with collision energies being differently set. Experimental results show that few-shot learning can achieve higher prediction accuracy with almost negligible computing resources. For example, on the data set from a untrained instrument Sciex-6600, within about 10 s, the prediction accuracy is increased from 69.7% to 86.4%; on the CID (collision-induced dissociation) data set, the prediction accuracy of the model trained by HCD (higher energy collision dissociation) spectra is increased from 48.0% to 83.9%. It is also shown that, the method is not critical to data quality and is sufficiently efficient to fill the accuracy gap. The source code of pDeep3 is available at http://pfind.ict.ac.cn/software/pdeep3.Keywords
All Related Versions
Funding Information
- Ministry of Science and Technology of the People's Republic of China (2016YFA0501301)
This publication has 26 references indexed in Scilit:
- pNovo 3: precise de novo peptide sequencing using a learning-to-rank frameworkBioinformatics, 2019
- pDeep: Predicting MS/MS Spectra of Peptides with Deep LearningAnalytical Chemistry, 2017
- De novo peptide sequencing by deep learningProceedings of the National Academy of Sciences, 2017
- An Optimized Shotgun Strategy for the Rapid Generation of Comprehensive Human ProteomesCell Systems, 2017
- Building ProteomeTools based on a complete synthetic human proteomeNature Methods, 2017
- A multicenter study benchmarks software tools for label-free proteome quantificationNature Biotechnology, 2016
- A draft map of the human proteomeNature, 2014
- Mass-spectrometry-based draft of the human proteomeNature, 2014
- MS-Simulator: Predicting Y-Ion Intensities for Peptides with Two Charges Based on the Intensity Ratio of Neighboring IonsJournal of Proteome Research, 2012
- Semi-supervised learning for peptide identification from shotgun proteomics datasetsNature Methods, 2007