MSBooster: Improving Peptide Identification Rates using Deep Learning-Based Features

Yang, Kevin; Yu, Fengchao; Teo, Guo Ci; Demichev, Vadim; Ralser, Markus; Nesvizhskii, Alexey I.

doi:10.1101/2022.10.19.512904

Cited by 33 publications

(56 citation statements)

References 83 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MSFragger-DIA has been fully integrated into FragPipe, allowing one-stop DIA data analysis ( Figure 1c and Supplementary Figure 1 ). In FragPipe, the output of MSFragger-DIA and MSFragger can be processed by MSBooster [54] to leverage additional scores using deep-learning prediction. The output from MSBooster is fed to Percolator for additional rescoring and posterior error probability calculation, followed by ProteinProphet [34] for protein inference, Philosopher [55] for false discovery rate (FDR) filtering, and spectral library building with EasyPQP [48].…”

Section: Resultsmentioning

confidence: 99%

“…Using MSFragger-DIA, it is not necessary to predict the entire spectral library in advance, and there is no restriction on the size of peptides, peptide ion charge states, or modifications that can be considered. However, our workflows in FragPipe (for both DDA and DIA data) do benefit from deep learning-based predictions at the subsequent, rescoring stage with the help of MSBooster and Percolator [54]. Interestingly, we observed some advantages of using predicted spectra (instead of empirical ones) at the final targeted quantification extraction step.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

One-stop analysis of DIA proteomics data using MSFragger-DIA and FragPipe computational platform

Teo

Kong

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Liquid chromatography (LC) coupled with data-independent acquisition (DIA) mass spectrometry (MS) has been increasingly used in quantitative proteomics studies. Here, we present a fast and sensitive approach for direct peptide identification from DIA data, MSFragger-DIA, which leverages the unmatched speed of the fragment ion indexing-based search engine MSFragger. MSFragger-DIA conducts a database search of the DIA tandem mass (MS/MS) spectra prior to spectral feature detection and peak tracing across the LC dimension. We have integrated MSFragger-DIA into the FragPipe computational platform for seamless support of peptide identification and spectral library building from DIA, data dependent acquisition (DDA), or both data types combined. We compared MSFragger-DIA with other DIA tools, such as DIA-Umpire based workflow in FragPipe, Spectronaut, and in silico library-based DIA-NN and MaxDIA. We demonstrated the fast and sensitive performance of MSFragger-DIA across a variety of sample types and data acquisition schemes, including single-cell proteomics, phosphoproteomics, and large-scale tumor proteome profiling studies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

One-stop analysis of DIA proteomics data using MSFragger-DIA and FragPipe computational platform

Teo

Kong

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Here we used Percolator (version 3.05.0) for PSM rescoring and q-values reported by Percolator were used. Note that FragPipe also has an option to calculate additional features for rescoring using the MS-Booster mode . However, because MS-Booster can only be used for standard searching, not for open searching, for consistency this functionality was not enabled.…”

Section: Methodsmentioning

confidence: 99%

“…This makes it possible to improve the spectrum identification results by accepting more target PSMs at a specific FDR threshold. Since the original description of Percolator, several approaches that extend upon this idea have been proposed, including tools that use different machine learning models instead of a linear SVM, − integration with various search engines, − and additional features that the classifier can use, often powered by deep learning. − …”

Section: Introductionmentioning

confidence: 99%

Semisupervised Machine Learning for Sensitive Open Modification Spectral Library Searching

et al. 2023

View full text Add to dashboard Cite

A key analysis task in mass spectrometry proteomics is matching the acquired tandem mass spectra to their originating peptides by sequence database searching or spectral library searching. Machine learning is an increasingly popular postprocessing approach to maximize the number of confident spectrum identifications that can be obtained at a given false discovery rate threshold. Here, we have integrated semisupervised machine learning in the ANN-SoLo tool, an efficient spectral library search engine that is optimized for open modification searching to identify peptides with any type of post-translational modification. We show that machine learning rescoring boosts the number of spectra that can be identified for both standard searching and open searching, and we provide insights into relevant spectrum characteristics harnessed by the machine learning model. The semisupervised machine learning functionality has now been fully integrated into ANN-

show abstract

“…Note that FragPipe also has an option to calculate additional features for rescoring using the MS-Booster mode. 18 However, because MS-Booster can only be used for standard searching, not for open searching, for consistency this functionality was not enabled.…”

Section: Methodsmentioning

confidence: 99%

Semi-supervised machine learning for sensitive open modification spectral library searching

Arab

Fondrie

Laukens

et al. 2022

Preprint

View full text Add to dashboard Cite

A key analysis task in mass spectrometry proteomics is matching the acquired tandem mass spectra to their originating peptides by sequence database searching or spectral library searching. Machine learning is an increasingly popular post-processing approach to maximize the number of confident spectrum identifications that can be obtained at a given false discovery rate threshold. Here, we have integrated semi-supervised machine learning in the ANN-SoLo tool, an eﬀicient spectral library search engine that is optimized for open modification searching to identify peptides with any type of post-translational modification. We show that machine learning rescoring boosts the number of spectra that can be identified for both standard searching and open searching, and we provide insights into relevant spectrum characteristics harnessed by the machine learning model. The semi-supervised machine learning functionality has now been fully integrated into ANN-SoLo, which is available as open source under the permissive Apache 2.0 license on GitHub at https://github.com/bittremieux/ANN-SoLo.

show abstract

MSBooster: Improving Peptide Identification Rates using Deep Learning-Based Features

Cited by 33 publications

References 83 publications

One-stop analysis of DIA proteomics data using MSFragger-DIA and FragPipe computational platform

One-stop analysis of DIA proteomics data using MSFragger-DIA and FragPipe computational platform

Semisupervised Machine Learning for Sensitive Open Modification Spectral Library Searching

Semi-supervised machine learning for sensitive open modification spectral library searching

Contact Info

Product

Resources

About