Deep-Learning-Derived Evaluation Metrics Enable Effective Benchmarking of Computational Tools for Phosphopeptide Identification

Jiang, Wen; Wen, Bo; Li, Kai; Zeng, Wen‐Feng; Leprevost, Felipe da Veiga; Moon, Jamie; Petyuk, Vladislav; Edwards, Nathan; Liu, Tao; Nesvizhskii, Alexey I.; Zhang, Bing

doi:10.1016/j.mcpro.2021.100171

Cited by 9 publications

(19 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the search space for the top-down data is substantially larger and consequently the uncertainty of the MS/MS spectra interpretation may result in different identifications for the same proteoform species. A similar phenomenon is observed in bottom-up proteomics for data that involves PTMs (e.g., known challenge in localization of the phosphorylation residues) . One of the solutions is to group the top-down proteoform identifications based on sequence similarity, mass, and retention time.…”

Section: Introductionmentioning

confidence: 60%

“…A similar phenomenon is observed in bottom-up proteomics for data that involves PTMs (e.g., known challenge in localization of the phosphorylation residues). 12 One of the solutions is to group the top-down proteoform identifications based on sequence similarity, mass, and retention time. Indeed, previous attempts in label-free quantitative top-down proteomics grouped distinct proteoform identifications based on mass and retention time within individual LC-MS data sets.…”

Section: ■ Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TopPICR: A Companion R Package for Top-Down Proteomics Data Analysis

et al. 2023

Self Cite

View full text Add to dashboard Cite

Top-down proteomics is the analysis of proteins in their intact form without proteolysis, thus preserving valuable information about post-translational modifications, isoforms, and proteolytic processing. However, it is still a developing field due to limitations in the instrumentation, difficulties with the interpretation of complex mass spectra, and a lack of well-established quantification approaches. TopPIC is one of the popular tools for proteoform identification. We extended its capabilities into label-free proteoform quantification by developing a companion R package (TopPICR). Key steps in the TopPICR pipeline include filtering identifications, inferring a minimal set of protein accessions explaining the observed sequences, aligning retention times, recalibrating measured masses, clustering features across data sets, and finally compiling feature intensities using the match-between-runs approach. The output of the pipeline is an MSnSet object which makes downstream data analysis seamlessly compatible with packages from the Bioconductor project. It also provides the capability for visualizing proteoforms within the context of the parent protein sequence. The functionality of TopPICR is demonstrated on top-down LC-MS/MS data sets of 10 human-in-mouse xenografts of luminal and basal breast tumor samples.

show abstract

Section: Introductionmentioning

confidence: 60%

Section: ■ Introductionmentioning

confidence: 99%

TopPICR: A Companion R Package for Top-Down Proteomics Data Analysis

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Figure 1 depicts the overall DeepRescore2 workflow, which processes the results of database searching in four steps to improve phosphopeptide identification and phosphosite localization ( Methods ). First, based on the confidently identified PSMs from database searching, RT and fragment ion intensity prediction models are trained using AutoRT 21 ,27 and pDeep3 28 , respectively, and then used to predict RTs and MS/MS spectra for all identified peptide sequences with all possible phosphosite localizations (i.e., peptide isoforms). Second, for each peptide isoform, a probability score is computed taking into consideration the PhosphoRS score 16 , RT difference between predicted and experimentally observed RTs, and spectrum similarity between predicted and experimentally observed spectra, and then phosphosite localization is determined based on the combined probability score.…”

Section: Resultsmentioning

confidence: 99%

“…Recent advancements in deep learning have provided new opportunities for proteomics 22 . Deep learning derived features, such as the retention time (RT) difference between experimentally observed and computationally predicted RTs and the similarity between experimentally observed and computationally predicted MS/MS spectra have been shown to effectively discriminate correct and incorrect PSMs in phosphoproteomics, and these features have been used as evaluation metrics to benchmark computational tools for phosphopeptide identification and phosphosite localization 21 . Incorporating these features into PSM rescoring has been shown to improve peptide identification in global proteomic profiling and immunopeptidomic profiling 23,24,25 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning prediction boosts phosphoproteomics-based discoveries through improved phosphopeptide identification

Wen

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Shotgun phosphoproteomics enables high-throughput analysis of phosphopeptides in biological samples, but low phosphopeptide identification rate in data analysis limits the potential of this technology. Here we present DeepRescore2, a computational workflow that leverages deep learning-based retention time and fragment ion intensity predictions to improve phosphopeptide identification and phosphosite localization. Using a state-of-the-art computational workflow as a benchmark, DeepRescore2 increases the number of correctly identified peptide-spectrum matches by 17% in a synthetic dataset and identifies 19%-46% more phosphopeptides in biological datasets. In a liver cancer dataset, 30% of the significantly altered phosphosites between tumor and normal tissues and 60% of the prognosis-associated phosphosites identified from DeepRescore2-processed data could not be identified based on the state-of-the-art workflow. Notably, DeepRescore2-processed data uniquely identifies EGFR hyperactivation as a new target in poor-prognosis liver cancer, which is validated experimentally. Integration of deep learning prediction in DeepRescore2 improves phosphopeptide identification and facilitates biological discoveries.

show abstract

Data‐independent acquisition proteomics methods for analyzing post‐translational modifications

Yang

Qiao

2022

Proteomics

View full text Add to dashboard Cite

Protein post‐translational modifications (PTMs) increase the functional diversity of the cellular proteome. Accurate and high throughput identification and quantification of protein PTMs is a key task in proteomics research. Recent advancements in data‐independent acquisition (DIA) mass spectrometry (MS) technology have achieved deep coverage and accurate quantification of proteins and PTMs. This review provides an overview of DIA data processing methods that cover three aspects of PTMs analysis, that is, detection of PTMs, site localization, and characterization of complex modification moieties, such as glycosylation. In addition, a survey of deep learning methods that boost DIA‐based PTMs analysis is presented, including in silico spectral library generation, as well as feature scoring and error rate control. The limitations and future directions of DIA methods for PTMs analysis are also discussed. Novel data analysis methods will take advantage of advanced MS instrumentation techniques to empower DIA MS for in‐depth and accurate PTMs measurements.

show abstract

Deep-Learning-Derived Evaluation Metrics Enable Effective Benchmarking of Computational Tools for Phosphopeptide Identification

Cited by 9 publications

References 59 publications

TopPICR: A Companion R Package for Top-Down Proteomics Data Analysis

TopPICR: A Companion R Package for Top-Down Proteomics Data Analysis

Deep learning prediction boosts phosphoproteomics-based discoveries through improved phosphopeptide identification

Data‐independent acquisition proteomics methods for analyzing post‐translational modifications

Contact Info

Product

Resources

About