Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Deep Learning Powers Protein Identification from Precursor MS Information

ABSTRACT: We report the DeepMS1, an approach combining deep learning-based retention time, ion mobility, detectability prediction, and linear regression-based scoring for MS1 feature identification.

ORGANISM(S): Homo Sapiens Escherichia Coli

SUBMITTER: Liang Qiao

PROVIDER: PXD046171 | iProX | Mon May 13 00:00:00 BST 2024

REPOSITORIES: iProX

ACCESS DATA

Json Xml

Publications

Deep Learning Powers Protein Identification from Precursor MS Information.

Dai Yameng Y Yang Yi Y Wu Enhui E Shen Chengpin C Qiao Liang L

Journal of proteome research 20240821 9

Proteome analysis currently heavily relies on tandem mass spectrometry (MS/MS), which does not fully utilize MS1 features, as many precursors remain unselected for MS/MS fragmentation, especially in the cases of low abundance samples and wide abundance dynamic range samples. Therefore, leveraging MS1 features as a complement to MS/MS has become an attractive option to improve the coverage of feature identification. Herein, we propose MonoMS1, an approach combining deep learning-based retention t ...[more]

PMID: 39167422

Similar Datasets

Deep Learning Powers Protein Identification from MS1 Feature Information

Project description:We report the DeepMS1, an approach combining deep learning-based retention time, ion mobility, detectability prediction, and linear regression-based scoring for MS1 feature identification.

2024-02-16 | PXD049457 |

MaxQuant software for ion mobility enhanced shotgun proteomics

Project description:Ion mobility can add a dimension to LC-MS based shotgun proteomics which has the potential to boost proteome coverage, quantification accuracy and dynamic range. Required for this is suitable software that extracts the information contained in the four-dimensional (4D) data space spanned by m/z, retention time, ion mobility and signal intensity. Here we describe the ion mobility enhanced MaxQuant software, which utilizes the added data dimension. It offers an end to end computational workflow for the identification and quantification of peptides, proteins and posttranslational modification sites in LC-IMS-MS/MS shotgun proteomics data. We apply it to trapped ion mobility spectrometry (TIMS) coupled to a quadrupole time-of-flight (QTOF) analyzer. A highly parallelizable 4D feature detection algorithm extracts peaks which are assembled to isotope patterns. Masses are recalibrated with a non-linear m/z, retention time, ion mobility and signal intensity dependent model, based on peptides from the sample. A new matching between runs (MBR) algorithm that utilizes collisional cross section (CCS) values of MS1 features in the matching process significantly gains specificity from the extra dimension. Prerequisite for using CCS values in MBR is a relative alignment of the ion mobility values between the runs. The missing value problem in protein quantification over many samples is greatly reduced by CCS aware MBR.MS1 level label-free quantification is also implemented which proves to be highly precise and accurate on a benchmark dataset with known ground truth. MaxQuant for LC-IMS-MS/MS is part of the basic MaxQuant release and can be downloaded from http://maxquant.org.

2020-04-23 | PXD014777 | Pride

A Rapid and Sensitive Single-cell Proteomic Method Based on Fast LC Separation, Deep-learning RT Prediction and MS1-only Acquisition

Project description:We report an integrate strategy that combines fast liquid chromatography (LC) separation, deep learning-based retention time (RT) prediction and MS1-only acquisition for sensitive and rapid single-cell proteome analysis. Finally, SCP-MS1 was applied to sorafenib resistant HepG2 cells.

2022-08-26 | PXD036211 |

A dataset for training/testing machine learning models of peptide feature detection: Human HELA LC-MSMS

Project description:We introduce MSTracer, a tool for peptide feature detection from MS1, which incorporates a machine-learning-combined scoring function based on peptide isotopic distribution and peptide intensity shape on the LC-MS map. By using Support Vector Regression (SVR), the quality of detected peptide features is remarkably improved. By utilising Neural Networks (NN), scores that indicate the quality of features are assigned for detected features as well. We use the Human HELA LC-MSMS dataset to train and test the results and compare with MaxQuant, OpenMS, and Dinosaur.

2021-06-18 | PXD022287 | Pride

Boosting MS1-only proteomics with machine learning allows 2000 protein identifications in single-shot human proteome analyses using 5-minute HPLC gradients

Project description:Proteome-wide analyses rely on tandem mass spectrometry and extensive separation of proteolytic mixtures imposing considerable instrumental time consumption that is one of the main obstacles in a broader acceptance of proteomics in biomedical and clinical research. Recently, we presented a fast proteomic method termed DirectMS1 based on ultra-short LC gradients, as well as MS1-only mass spectra acquisition and data processing. The method allows significant squeezing of the proteome-wide analysis time to a few minutes at the depth of quantitative proteome coverage of 1000 proteins at 1% FDR. In this work, to further increase the capabilities of the DirectMS1 method, we explored the opportunities presented by the recent progress in the machine learning area and applied the LightGBM tree-based learning algorithm into the scoring of peptide-feature matches when processing MS1 spectra. Further, we integrated the peptide feature identification algorithm of DirectMS1 with the recently introduced peptide retention time prediction utility, DeepLC. Additional approaches to improve performance of the DirectMS1 method are discussed and demonstrated, such as FAIMS coupled to the Orbitrap mass analyzer. As a result of all improvements to DirectMS1, we succeeded in identifying more than 2000 proteins at 1% FDR from the HeLa cell line in a 5 minute gradient LC-FAIMS/MS1 analysis.

2021-03-18 | PXD023977 | Pride

Combining Precursor and Fragment Information for Improved Detection of Differential Abundance in Data Independent Acquisition

Project description:In data independent acquisition, consistent, comprehensive MS1 and MS2 can be recorded. This enables statistical comparison based on the two quantitative levels.

2020-01-07 | PXD016647 | Pride

Deep Learning Predicts Peptide Transmission Profiles through FAIMS Directly from Sequence

Project description:Peptide ion mobility adds an extra dimension of separation to mass spectrometry-based proteomics. The ability to accurately pre-dict peptide ion mobility would be useful to expedite assay development and to discriminate true answers in database search. There are methods to accurately predict peptide ion mobility through drift tube devices, but methods to predict mobility through high-field asymmetric waveform ion mobility (FAIMS) are underexplored. Here, we successfully model peptide ions’ FAIMS mobility using a multi-label multi-output classification scheme to account for non-normal transmission distributions. We trained two models from over 100,000 human peptide precursors: a random forest and a long-term short-term memory (LSTM) neural network. Both models had different strengths, and the ensemble average of model predictions produced higher F2 score than either model alone. Finally, we explore cases where the models make mistakes, and demonstrate predictive performance of F2=0.66 (AUROC=0.928) on a new test dataset of nearly 40,000 different E. coli peptide ions.

2025-01-16 | PXD055252 | Pride

Prediction of glycopeptide fragment mass spectra by deep learning

Project description:Deep learning has achieved a notable success in mass spectrometry-based proteomics and is now emerging in glycoproteomics. While various deep learning models can predict fragment mass spectra of peptides with good accuracy, they cannot cope with the non-linear glycan structure in an intact glycopeptide. Herein, we propose a deep learning-based approach for the prediction of fragment spectra of intact glycopeptides. Our model adopts tree-structured long-short term memory networks to process the glycan moiety and a graph neural network architecture to incorporate potential fragmentation pathways of a specific glycan structure. This feature is beneficial to model explainability and differentiation ability of glycan structural isomers. We further demonstrated that predicted spectral libraries can be used for analyzing DIA data of glycopeptides as a supplement for library completeness. We expect that this work will provide a valuable deep learning resource for glycoproteomics.

2023-12-17 | PXD045248 |

Prosit: Proteome-wide prediction of peptide tandem mass spectra by deep learning

Project description:In this study, we extended the ProteomeTools peptide library (PROPEL, see PXD004732 and PXD010595) to train a deep neural network resulting in chromatographic retention time and fragment ion intensity predictions for (tryptic) peptides that exceed the quality of the experimental data.

2019-05-30 | PXD010871 | Pride

Zebrafish plasma analyzed by CE- and LC-MS/MS

Project description:Single analyses of a Zebrafish whole plasma digest were analyzed by both CE-MS/MS and LC-MS/MS. The identified peptides and their corresponding retention or migration times were used to train a 'blind' retention/migration time model using linear regression. This trained model provided us with information on the migration/retention coefficients resulting from the individual amino acids. All acquired tandem mass spectrometry data was processed in the Trans-Proteomic Pipeline (TPP) embedded in the Taverna scientific workflow manager. The raw data was converted to mzXML using compassXport 3.0 (Bruker) and searched with X!Tandem. The X!Tandem scores were then converted to pepXML, modeled and translated to probabilities for each peptide-spectral match by PeptideProphet. The X!Tandem search was here performed allowing a random error ±0.5 Da, +1 or +2 Da isotopic error, carbamidomethylation as fixed and oxidation as variable modification and the k-score plug-in.

2012-12-18 | PXD000112 | Pride

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data