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

Abstract

MS²PIP is a data-driven tool that accurately predicts peak intensities for a given peptide's fragmentation mass spectrum. Since the release of the MS²PIP web server in 2015, we have brought significant updates to both the tool and the web server. Next to the original models for CID and HCD fragmentation, we have added specific models for the TripleTOF 5600+ mass spectrometer, for TMT-labeled peptides, for iTRAQ-labeled peptides and for iTRAQ-labeled phosphopeptides. Because the fragmentation pattern is heavily altered in each of these cases, these additional models greatly improve the prediction accuracy for their corresponding data types. We have also substantially reduced the computational resources required to run MS²PIP, and have completely rebuilt the web server, which now allows predictions of up to 100.000 peptide sequences in a single request. The MS²PIP web server is freely available at https://iomics.ugent.be/ms2pip/.

ExpandingN-Glycopeptide Identifications by Fragmentation Prediction and Glycome Network Smoothing

“…We found no improvement in model performance attempting to use flanking amino acid features beyond the third position from the amide bond, while the gain going from the first to the second position away was modest at best. The amino acid context around a fragmentation site sets the stage for chargelocal fragmentation pathway interactions [33, 35], which rule-based approaches to model fragmentation [21, 32, 37, 38] learned explicitly to a certain distance from the fragmentation site, while bi-direction recurrent neural network based methods [22, 23] learned across the entire sequence implicitly.…”

AHLF: ad hoc learning of peptide fragmentation from mass spectra enables an interpretable detection of phosphorylated and cross-linked peptides

“…Training on simulated data or domain randomization Tobin et al (2017) is a powerful method to improve performance for models and reducing the generalization gap. The prediction of relative intensity profiles is well received in the proteomics community as it improves database search substantially Gabriels et al (2019); Zhou et al (2017); Gessulat et al (2019). This in combination with a sophisticated noise model may become very helpful for domain randomization and training models like AHLF in the near future.…”

Methods for Proteogenomics Data Analysis, Challenges, and Scalability Bottlenecks: A Survey

“…The advantage of this technique is that the PTMs and fragmentation types can be easily incorporated in the theoretical spectra. Furthermore, recently, a few machine learning based techniques [ 147 ]-[ 150 ] have been proposed that can predict intensities along with m/z’s of fragment-ions in the theoretical spectra which can substantially improve the peptide identification rate for sequence database search. A small list of peptide database search tools includes SEQUEST [ 49 ], MSGF+ [ 151 ], SpecOMS [ 152 ], MSFragger [ 52 ], Open-pFind [ 153 ], Andromeda [ 154 ], X!…”