EnvCNN: A Convolutional Neural Network Model for Evaluating Isotopic Envelopes in Top-Down Mass-Spectral Deconvolution

Basharat, Abdul Rehman; Ning, Xia; Liu, Xiaowen

doi:10.1021/acs.analchem.0c00903

Cited by 12 publications

(19 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specific algorithms have been explicitly tailored to handle highly charged and congested spectra of isotopically resolved protein fragments, including MS-Deconv, YADA, THRASH, and its commercial implementation Xtract available in the BioPharma Finder software suite (Thermo Scientific). More recently, the Liu group released EnvCNN, a statistical artificial-intelligence-based model for scoring identified isotopic envelopes, whereby they demonstrated superior performance compared with existing scoring functions . While these tools are primarily used in conventional top-down MS analysis, most of them can also be applied to the deconvolution of native top-down mass spectra. , …”

Section: Spectral Deconvolution In High-resolution Native Msmentioning

confidence: 99%

“…More recently, the Liu group released EnvCNN, a statistical artificial-intelligence-based model for scoring identified isotopic envelopes, whereby they demonstrated superior performance compared with existing scoring functions. 176 While these tools are primarily used in conventional top-down MS analysis, most of them can also be applied to the deconvolution of native top-down mass spectra. 28,171 Overall, there are many tools available for spectral deconvolution of high-resolution native mass spectra, which have substantially helped the field make the advances described in this review.…”

Section: Spectral Deconvolution For Isotopically Resolved Mass Spectramentioning

confidence: 99%

See 1 more Smart Citation

High-Resolution Native Mass Spectrometry

2021

View full text Add to dashboard Cite

Native mass spectrometry (MS) involves the analysis and characterization of macromolecules, predominantly intact proteins and protein complexes, whereby as much as possible the native structural features of the analytes are retained. As such, native MS enables the study of secondary, tertiary, and even quaternary structure of proteins and other biomolecules. Native MS represents a relatively recent addition to the analytical toolbox of mass spectrometry and has over the past decade experienced immense growth, especially in enhancing sensitivity and resolving power but also in ease of use. With the advent of dedicated mass analyzers, sample preparation and separation approaches, targeted fragmentation techniques, and software solutions, the number of practitioners and novel applications has risen in both academia and industry. This review focuses on recent developments, particularly in high-resolution native MS, describing applications in the structural analysis of protein assemblies, proteoform profiling ofamong othersbiopharmaceuticals and plasma proteins, and quantitative and qualitative analysis of protein–ligand interactions, with the latter covering lipid, drug, and carbohydrate molecules, to name a few.

show abstract

Section: Spectral Deconvolution In High-resolution Native Msmentioning

confidence: 99%

Section: Spectral Deconvolution For Isotopically Resolved Mass Spectramentioning

confidence: 99%

High-Resolution Native Mass Spectrometry

2021

View full text Add to dashboard Cite

show abstract

“…Comparison of ECScore and EnvCNN. We compared the accuracy of ECScore and the EnvCNN score 32 on two topdown MS data sets: one from SW620 cells with three replicates and the other from ovarian cancer (OC) samples with 10 replicates (Supporting Methods S1). Using the methods in the previous section, we labeled the envelope collections reported from the first replicates of the SW620 and OC data.…”

Section: ■ Resultsmentioning

confidence: 99%

TopFD: A Proteoform Feature Detection Tool for Top–Down Proteomics

et al. 2023

Self Cite

View full text Add to dashboard Cite

Top-down liquid chromatography-mass spectrometry (LC-MS) analyzes intact proteoforms and generates mass spectra containing peaks of proteoforms with various isotopic compositions, charge states, and retention times. An essential step in top-down MS data analysis is proteoform feature detection, which aims to group these peaks into peak sets (features), each containing all peaks of a proteoform. Accurate protein feature detection enhances the accuracy in MS-based proteoform identification and quantification. Here, we present TopFD, a software tool for top-down MS feature detection that integrates algorithms for proteoform feature detection, feature boundary refinement, and machine learning models for proteoform feature evaluation. We performed extensive benchmarking of TopFD, ProMex, FlashDeconv, and Xtract using seven top-down MS data sets and demonstrated that TopFD outperforms other tools in feature accuracy, reproducibility, and feature abundance reproducibility.

show abstract

“…We compared the accuracy of ECScore and the EnvCNN score [32] on two top-down MS data sets: one from SW620 cells with three replicates and the other from ovarian cancer (OC) samples with ten replicates (Methods). Similar to the training data, we labeled the envelope collections reported from the first replicates of the SW620 and OC data.…”

Section: Resultsmentioning

confidence: 99%

TopFD - A Proteoform Feature Detection Tool for Top-Down Proteomics

Basharat

Zang

Sun

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Top-down liquid chromatography-mass spectrometry (LC-MS) analyzes intact proteoforms and generates mass spectra containing peaks of proteoforms with various isotopic compositions, charge states, and retention times. An essential step in top-down MS data analysis is proteoform feature detection, which aims to group these peaks into peak sets (features), each containing all peaks of a proteoform. Accurate protein feature detection enhances the accuracy in MS-based proteoform identification and quantification. Here we present TopFD, a software tool for top-down MS feature detection that integrates algorithms for proteoform feature detection, feature boundary refinement, and machine learning models for proteoform feature evaluation. We performed extensive benchmarking of TopFD, Promex, FlashDeconv, and Xtract using five top-down MS data sets and demonstrated that TopFD outperforms other tools in feature accuracy, reproducibility, and feature abundance reproducibility.

show abstract

EnvCNN: A Convolutional Neural Network Model for Evaluating Isotopic Envelopes in Top-Down Mass-Spectral Deconvolution

Cited by 12 publications

References 53 publications

High-Resolution Native Mass Spectrometry

High-Resolution Native Mass Spectrometry

TopFD: A Proteoform Feature Detection Tool for Top–Down Proteomics

TopFD - A Proteoform Feature Detection Tool for Top-Down Proteomics

Contact Info

Product

Resources

About