Enhancing Top-Down Proteomics Data Analysis by Combining Deconvolution Results through a Machine Learning Strategy
Open accessAbstract
Top-down mass spectrometry (MS) is a powerful tool for the identification and comprehensive characterization of proteoforms arising from alternative splicing, sequence variation, and post-translational modifications. However, the complex data set generated from top-down MS experiments requires multiple sequential data processing steps to successfully interpret the data for identifying and characterizing proteoforms. One critical step is the deconvolution of the complex isotopic distribution that arises from naturally occurring isotopes. Multiple algorithms are currently available to deconvolute top-down mass spectra, resulting in different deconvoluted peak lists with varied accuracy compared to true positive annotations. In this study, we have designed a machine learning strategy that can process and combine the peak lists from different deconvolution results. By optimizing clustering results, deconvolution results from THRASH, TopFD, MS-Deconv, and SNAP algorithms were combined into consensus peak lists at various thresholds using either a simple voting ensemble method or a random forest machine learning algorithm. For the random forest algorithm, which had better predictive performance, the consensus peak lists on average could achieve a recall value (true positive rate) of 0.60 and a precision value (positive predictive value) of 0.78. It outperforms the single best algorithm, which achieved a recall value of only 0.47 and a precision value of 0.58. This machine learning strategy enhanced the accuracy and confidence in protein identification during database searches by accelerating the detection of true positive peaks while filtering out false positive peaks. Thus, this method shows promise in enhancing proteoform identification and characterization for high-throughput data analysis in top-down proteomics.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Combining deconvolution results from a single dataset using a simple voting ensemble or random forest machine learning improved fragment identification and confidence compared to a single algorithm.
“Recently, combining deconvolution results from a single data set using a simple voting ensemble method or random forest machine learning-enabled improved fragment identification and confidence compared to a single algorithm [131].”
From Top-down proteomics: challenges, innovations, and applications in basic and clinical research (2020) · cites this paper as [131]
A machine learning tool used hierarchical clustering to merge deconvoluted peak lists from different algorithms, which effectively detects true positive peaks while filtering false positives, leading to improved accuracy and confidence in protein identification.
“This machine learning tool used hierarchical clustering to combine deconvoluted peak lists from different algorithms, which can effectively detect true positive peaks while filtering out false positive peaks, resulting in enhanced accuracy and confidence in protein identification during database search.”
From MASH Explorer: A Universal Software Environment for Top-Down Proteomics (2020) · cites this paper as [23]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430 · see citing works
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · see citing works
Pérez-Riverol, Y., Csordas, A., Bai, J.-W., Bernal-Llinares, M., Hewapathirana, S., Kundu, D. J., Inuganti, A., Griss, J., Mayer, G., Eisenacher, M., et al. (2018) · Nucleic Acids Res. · doi:10.1093/nar/gky1106 · Cited by 6,216 · see citing works
Proteoform: a single term describing protein complexity
The Consortium for Top Down Proteomics, Smith, L. M., & Kelleher, N. L. (2013) · Nature Methods · doi:10.1038/nmeth.2369 · Cited by 1,528 · see citing works
Marty, M. T., Baldwin, A. J., Marklund, E. G., Hochberg, G. K. A., Benesch, J. L. P., & Robinson, C. V. (2015) · Analytical Chemistry · doi:10.1021/acs.analchem.5b00140 · Cited by 1,000 · see citing works
How many human proteoforms are there?
Aebersold, R., Agar, J. N., Amster, I. J., Baker, M. S., Bertozzi, C. R., Boja, E. S., Costello, C. E., Cravatt, B. F., Fenselau, C., Garcia, B. A., et al. (2018) · Nature Chemical Biology · doi:10.1038/nchembio.2576 · Cited by 907 · see citing works
Self-citationDe novo peptide sequencing by deep learning
Tran, N. H., Zhang, X., Xin, L., Shan, B., & Li, M. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1705691114 · Cited by 436 · see citing works
Complete Protein Characterization Using Top-Down Mass Spectrometry and Ultraviolet Photodissociation
Shaw, J. B., Li, W., Holden, D. D., Zhang, Y., Griep-Raming, J., Fellers, R. T., Early, B. P., Thomas, P. M., Kelleher, N. L., & Brodbelt, J. S. (2013) · Journal of the American Chemical Society · doi:10.1021/ja4029654 · Cited by 371 · see citing works
Ge, Y., Lawhorn, B. G., ElNaggar, M., Strauss, E., Park, J.-H., Begley, T. P., & McLafferty, F. W. (2002) · Journal of the American Chemical Society · doi:10.1021/ja011335z · Cited by 356 · see citing works
Self-citationKou, Q., Xun, L., & Liu, X. (2016) · Bioinformatics · doi:10.1093/bioinformatics/btw398 · Cited by 276 · see citing works
Top-Down Proteomics: Ready for Prime Time?
Chen, B., Brown, K. A., Lin, Z., & Ge, Y. (2018) · Analytical Chemistry · doi:10.1021/acs.analchem.7b04747 · Cited by 210 · see citing works
Self-citationIdentification and Quantification of Proteoforms by Mass Spectrometry
Schaffer, L. V., Millikin, R. J., Miller, R. M., Anderson, L. C., Fellers, R. T., Ge, Y., Kelleher, N. L., LeDuc, R. D., Liu, X., Payne, S. H., et al. (2019) · PROTEOMICS · doi:10.1002/pmic.201800361 · Cited by 209 · see citing works
Self-citationSample classification from protein mass spectrometry, by ‘peak probability contrasts’
Tibshirani, R. J., Hastie, T. J., Narasimhan, B., Soltys, S. G., Shi, G., Koong, A. C., & Le, Q. (2004) · Bioinformatics · doi:10.1093/bioinformatics/bth357 · Cited by 197 · see citing works
Deconvolution and Database Search of Complex Tandem Mass Spectra of Intact Proteins
Liu, X., Inbar, Y., Dorrestein, P. C., Wynne, C., Edwards, N., Souda, P., Whitelegge, J. P., Bafna, V., & Pevzner, P. A. (2010) · Molecular & Cellular Proteomics · doi:10.1074/mcp.m110.002766 · Cited by 170 · see citing works
Comprehensive Analysis of Protein Modifications by Top-Down Mass Spectrometry
Zhang, H., & Ge, Y. (2011) · Circulation Cardiovascular Genetics · doi:10.1161/circgenetics.110.957829 · Cited by 148 · see citing works
Self-citationMASH Suite Pro: A Comprehensive Software Tool for Top-Down Proteomics
Cai, W., Guner, H., Gregorich, Z. R., Chen, A. J., Ayaz-Guner, S., Peng, Y., Valeja, S. G., Liu, X., & Ge, Y. (2016) · Molecular & Cellular Proteomics · doi:10.1074/mcp.o115.054387 · Cited by 132 · see citing works
Self-citationProteomic mass spectra classification using decision tree based ensemble methods
Geurts, P., Fillet, M., de Seny, D., Meuwis, M., Malaise, M., Merville, M.-P., & Wehenkel, L. A. (2005) · Computer applications in the biosciences · doi:10.1093/bioinformatics/bti494 · Cited by 131 · see citing works
Top-down Proteomics: Technology Advancements and Applications to Heart Diseases
Cai, W., Tucholski, T. M., Gregorich, Z. R., & Ge, Y. (2016) · Expert Review of Proteomics · doi:10.1080/14789450.2016.1209414 · Cited by 99 · see citing works
Self-citationIncorporating Distance-Based Top-n-gram and Random Forest To Identify Electron Transport Proteins
Ru, X., Li, L., & Zou, Q. (2019) · Journal of Proteome Research · doi:10.1021/acs.jproteome.9b00250 · Cited by 98 · see citing works
pTop 1.0: A High-Accuracy and High-Efficiency Search Engine for Intact Protein Identification
Sun, R.-X., Luo, L., Wu, L., Wang, R.-M., Zeng, W.-F., Chi, H., Liu, C., & He, S.-M. (2016) · Analytical Chemistry · doi:10.1021/acs.analchem.5b03963 · Cited by 71 · see citing works
Zhang, Y., Xin, Y., Li, Q., et al. (2017) · BioMedical Engineering OnLine · doi:10.1186/s12938-017-0416-x · Cited by 63 · see citing works
Identification of Ultramodified Proteins Using Top-Down Tandem Mass Spectra
Liu, X., Hengel, S. M., Wu, S., Tolić, N., Paša‐Tolić, L., & Pevzner, P. A. (2013) · Journal of Proteome Research · doi:10.1021/pr400849y · Cited by 54 · see citing works
Jin, Y., Diffee, G., Colman, R., Anderson, R. M., & Ge, Y. (2019) · Journal of the American Society for Mass Spectrometry · doi:10.1007/s13361-019-02139-0 · Cited by 27 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 7
- [9]Horn DM; Zubarev RA; McLafferty FW, Automated reduction and interpretation of high resolution electrospray mass spectra of large molecules. J Am Soc Mass Spectr 2000, 11 (4), 320– 332. 10757168
- [16]Kuncheva LI; Whitaker CJ, Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Mach Learn 2003, 51 (2), 181– 207.
- [17]Sollich P; Krogh A, Learning with ensembles: How over-fitting can be useful. Adv Neur In 1996, 8, 190– 196.
- [21]McIlwain SJ; Wu Z; Wenger K; Wetzel M; Tucholski T; Liu X; Sun L; Ong IM; Ge Y In MASH Explorer, a Universal, Comprehensive, and User-friendly Software Environment for Top-down Proteomics, 299322, Tuesday, Proceedings of 67th ASMS Conference on Mass Spectrometry and Allied Topics, Atlanta, GA, June 2nd - 6th, 2019.
- [26]Liaw A; Wiener M, Classification and Regression by randomForest. R News 2002, 2 (3), 18– 22.
- [28]Saxena A; Prasad M; Gupta A; Bharill N; Patel OP; Tiwari A; Er MJ; Ding WP; Lin CT, A review of clustering techniques and developments. Neurocomputing 2017, 267, 664– 681.
- [30]Cortes C; Vapnik V, Support-Vector Networks. Mach Learn 1995, 20 (3), 273– 297.
Cited by
Sorted by citations
Top-down proteomics: challenges, innovations, and applications in basic and clinical research
Brown, K. A., Melby, J. A., Roberts, D. S., & Ge, Y. (2020) · Expert Review of Proteomics · doi:10.1080/14789450.2020.1855982 · Cited by 152 · see citing works
Self-citationMASH Explorer: A Universal Software Environment for Top-Down Proteomics
Wu, Z., Roberts, D. S., Melby, J. A., Wenger, K., Wetzel, M., Gu, Y., Ramanathan, S. G., Bayne, E. F., Liu, X., Sun, R., et al. (2020) · Journal of Proteome Research · doi:10.1021/acs.jproteome.0c00469 · Cited by 76 · see citing works
Self-citation
- Authors
- McIlwain, S. J., Wu, Z., Wetzel, M., Belongia, D., Jin, Y., Wenger, K., Ong, I. M., & Ge, Y.
- Affiliations
- University of Wisconsin–Madison (US)
- Corresponding author
- McIlwain, Sean J.
- Venue
- Journal of the American Society for Mass Spectrometry
- Publisher
- American Chemical Society (ACS)
- Published
- 2020-03-30
- Volume
- 31
- Issue
- 5
- Pages
- 1104-1113
- ISSN
- 1044-0305 (ISSN-L)
- 1879-1123
- PMC
- PMC7909725
- OpenAlex
- W3014006366
- Cited by
- 27
- References
- 23
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 1 · 2023: 5 · 2022: 3 · 2021: 5 · 2020: 3
- FWCI
- 1.53
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Journal of the American Society for Mass Spectrometry (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- NIH Office of the Director (S10 OD018475)
- National Institute of General Medical Sciences (R01 GM117058, R01 GM125085)
- Topics
- Physical Sciences › Chemistry › Spectroscopy › Advanced Proteomics Techniques and Applications
- Physical Sciences › Chemistry › Spectroscopy › Mass Spectrometry Techniques and Applications
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Keywords
- top-down mass spectrometry, proteoform identification, random forest, ensemble voting, SNAP, alternative splicing, post-translational modification
- MeSH terms
- Machine Learning, Data Analysis, Algorithms, Humans, Muscle Proteins, Protein Processing, Post-Translational, Sarcomeres, Sensitivity and Specificity, Alternative Splicing, Proteomics, Tandem Mass Spectrometry
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
