Accurate peptide fragmentation predictions allow data driven approaches to replace and improve upon proteomics search engine scoring functions

Abstract

The use of post-processing tools to maximize the information gained from a proteomics search engine is widely accepted and used by the community, with the most notable example being Percolator -a semi-supervised machine learning model which learns a new scoring function for a given dataset. The usage of such tools is however bound to the search engine's scoring scheme, which doesn't always make full use of the intensity information present in a spectrum. We aim to show how this tool can be applied in such a way that maximizes the use of spectrum intensity information by leveraging another machine learning-based tool, MS2PIP. MS2PIP predicts fragment ion peak intensities. We show how comparing these intensities to annotated experimental spectra by calculating direct similarity metrics provides enough information for a tool such as Percolator to accurately separate two classes of PSMs. This approach allows using more information out of the data (compared to simpler intensity based metrics, like peak counting or explained intensities summing) while maintaining control of statistics such as the false discovery rate.

Updated MS2PIP web server delivers fast and accurate MS2 peak intensity prediction for multiple fragmentation methods, instruments and labeling techniques

“…biomarkers) (9,10). Moreover, we have also shown that MS²PIP predictions can be used to improve upon and even replace proteomics search engine output when rescoring peptide-tospectrum matches (11).…”

Updated MS²PIP web server delivers fast and accurate MS² peak intensity prediction for multiple fragmentation methods, instruments and labeling techniques

“…biomarkers) (9,10). Moreover, we have also shown that MS²PIP predictions can be used to improve upon and even replace proteomics search engine output when rescoring peptide-to-spectrum matches (11).…”

Speeding Up Percolator

“…Currently, the standard version of Percolator uses a small set of features that varies slightly depending on the search engine. More complex feature sets include, for example, subscores corresponding to different ion types, scores from multiple search engines, similarity scores from fragment intensity prediction, and probabilistic gradient information of PSMs . Such sets have the potential to improve Percolator’s performance but lead to a corresponding increase in running time.…”