CFM-ID: A Web Server for Annotation, Spectrum Prediction and Metabolite Identification from MS/MS
- Felicity Allen
- Allison Pon
- Michael Wilson
- Russ Greiner, Dept of Computing Science; PI of AICML
- David S. Wishart, Departments of Computing Science and Biology, University of Alberta
We present CFM-ID, a web server supporting three tasks associated with the interpretation of tandem mass spectra (MS/MS) for the purpose of automated metabolite identification.The three tasks are peak annotation for a known chemical structure; spectrum prediction for a given chemical structure; and putative metabolite identification -- a predicted ranking of possible candidate structures for a target spectrum. The methods used are based on Competitive Fragmentation Modeling (CFM), a recently introduced probabilistic generative model for the MS/MS fragmentation process that uses machine learning techniques to learn its parameters from data. We present results of extensive testing of these algorithms on multiple datasets, showing that they out-perform existing methods such as MetFrag and FingerId. CFM-ID is made freely available at http://cfmid.wishartlab.com
Citation
F. Allen, A. Pon, M. Wilson, R. Greiner, D. Wishart. "CFM-ID: A Web Server for Annotation, Spectrum Prediction and Metabolite Identification from MS/MS". MetaboMeeting, London, England, September 2014.Keywords: | tandem mass spectrometry, cfm, MS/MS, spectrum prediction, machine learning |
Category: | In Conference |
BibTeX
@incollection{Allen+al:14, author = {Felicity Allen and Allison Pon and Michael Wilson and Russ Greiner and David S. Wishart}, title = {CFM-ID: A Web Server for Annotation, Spectrum Prediction and Metabolite Identification from MS/MS}, booktitle = {MetaboMeeting}, year = 2014, }Last Updated: February 12, 2020
Submitted by Sabina P