Differential protein expression and peak selection in mass spectrometry data by binary discriminant analysis

MOTIVATION Proteomic mass spectrometry analysis is becoming routine in clinical diagnostics, for example to monitor cancer biomarkers using blood samples. However, differential proteomics and identification of peaks relevant for class separation remains challenging. RESULTS Here, we introduce a simple yet effective approach for identifying differentially expressed proteins using binary discriminant analysis. This approach works by data-adaptive thresholding of protein expression values and subsequent ranking of the dichotomized features using a relative entropy measure. Our framework may be viewed as a generalization of the 'peak probability contrast' approach of Tibshirani et al. (2004) and can be applied both in the two-group and the multi-group setting. Our approach is computationally inexpensive and shows in the analysis of a large-scale drug discovery test dataset equivalent prediction accuracy as a random forest. Furthermore, we were able to identify in the analysis of mass spectrometry data from a pancreas cancer study biological relevant and statistically predictive marker peaks unrecognized in the original study. AVAILABILITY AND IMPLEMENTATION The methodology for binary discriminant analysis is implemented in the R package binda, which is freely available under the GNU General Public License (version 3 or later) from CRAN at URL http://cran.r-project.org/web/packages/binda/. R scripts reproducing all described analyzes are available from the web page http://strimmerlab.org/software/binda/. CONTACT k.strimmer@imperial.ac.uk.

• Publication year

  2015

• Venue

  Bioinform.

• Publication date

  2015-02-27

• Fields of study

  Biology, Chemistry, Computer Science, Mathematics, Medicine

• Identifiers
  DOI 10.1093/bioinformatics/btv334arXiv 1502.07959PMID 26026136
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Sparse Proteomics Analysis – a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data

  2015cited by this paper
• Do we need hundreds of classifiers to solve real world classification problems?

  2014cited by this paper
• UniProt: a hub for protein information

  2014influential reference
• Potentials and pitfalls of clinical peptidomics and metabolomics.

  2013cited by this paper
• Understanding predictive information criteria for Bayesian models

  2013cited by this paper
• Testing the Statistical Significance of an Ultra-High-Dimensional Naive Bayes Classifier

  2013cited by this paper
• A hybrid approach to protein differential expression in mass spectrometry-based proteomics

  2012influential reference
• MALDIquant: a versatile R package for the analysis of mass spectrometry data

  2012cited by this paper
• Multivariate Bernoulli distribution

  2012influential reference
• Statistical Applications in Genetics and Molecular Biology High-Dimensional Regression and Variable Selection Using CAR Scores

  2011cited by this paper
• Searching for early breast cancer biomarkers by serum protein profiling of pre-diagnostic serum; a nested case-control study

  2011cited by this paper
• Independent rule in classification of multivariate binary data

  2009cited by this paper
• Serum Peptidome Profiling Revealed Platelet Factor 4 as a Potential Discriminating Peptide Associated with Pancreatic Cancer

  2009influential reference
• Feature selection in omics prediction problems using cat scores and false nondiscovery rate control

  2009cited by this paper
• Entropy Inference and the James-Stein Estimator, with Application to Nonlinear Gene Association Networks

  2008cited by this paper
• Microbiology in the post-genomic era

  2008cited by this paper
• Feature selection and machine learning with mass spectrometry data for distinguishing cancer and non-cancer samples

  2006influential reference
• Selecting the right objective measure for association analysis

  2004cited by this paper
• Sample classification from protein mass spectrometry, by 'peak probability contrasts'

  2004cited by this paper
• Molecular Similarity Searching Using Atom Environments, Information-Based Feature Selection, and a Naïve Bayesian Classifier

  2004influential reference
• Result Analysis of the NIPS 2003 Feature Selection Challenge

  2004cited by this paper
• Class Prediction by Nearest Shrunken Centroids, with Applications to DNA Microarrays

  2003cited by this paper
• Variable Selection in High‐Dimensional Multivariate Binary Data with Application to the Analysis of Microbial Community DNA Fingerprints

  2002influential reference
• Idiot's Bayes—Not So Stupid After All?

  2001cited by this paper
• Random Forests

  2001influential reference
• Protein identification and analysis tools in the ExPASy server.

  1999influential reference
• The Analysis of Multivariate Binary Data

  1972influential reference

• An Extension of the Kullback–Leibler Divergence for the Application of Machine Learning Classification Algorithms to Hierarchical Cluster Analysis

  2026cites this paper
• Haemophilus influenzae and Staphylococcus aureus population shifts during social distancing as monitored by MALDI-TOF MS

  2025cites this paper
• Discrimination of Klebsiella pneumoniae and Klebsiella quasipneumoniae by MALDI‐TOF Mass Spectrometry Coupled With Machine Learning

  2025influential citation
• Age-at-death estimation based on algorithms for multi-class discriminant analysis using binary and ordinal predictors.

  2025cites this paper
• Identification of allergens from Aspergillus fumigatus—Potential association with lung damage in asthma

  2024cites this paper
• A biological reading of a palimpsest

  2023cites this paper
• Discrimination of the chemotherapy resistance status of human leukemia and glioblastoma cell lines by MALDI-TOF-MS profiling

  2023cites this paper
• Discrimination of Escherichia coli, Shigella flexneri, and Shigella sonnei using lipid profiling by MALDI‐TOF mass spectrometry paired with machine learning

  2022influential citation
• Extended-Spectrum Beta-Lactamase and Carbapenemase-Producing prediction in Klebsiella pneumoniae based on MALDI-TOF mass spectra

  2022cites this paper
• Synergy between machine learning and natural products cheminformatics: Application to the lead discovery of anthraquinone derivatives

  2022cites this paper
• Clasificadores de Aprendizaje Automático aplicados a Datos RKI MALDI-TOF de Espectrometría de Masa de Bacterias

  2021cites this paper
• Automatic antibiotic resistance prediction in Klebsiella pneumoniae based on MALDI-TOF mass spectra

  2021cites this paper
• Using MALDI-TOF spectra in epidemiological surveillance for the detection of bacterial subgroups with a possible epidemic potential

  2021cites this paper
• Sputum proteomic analysis for distinguishing between pulmonary tuberculosis and non-tuberculosis using matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS): preliminary results.

  2021cites this paper
• Rapid diagnosis of periodontitis, a feasibility study using MALDI-TOF mass spectrometry

  2020cites this paper
• Gingival Crevicular Fluid Peptidome Profiling in Healthy and in Periodontal Diseases

  2020cites this paper
• Establishing Objective Measures of Clinical Competence in Undergraduate Medical Education Through Immersive Virtual Reality

  2020cites this paper
• Deep Learning for Proteomics Data for Feature Selection and Classification

  2019cites this paper
• MALDI-TOF mass spectrometry on intact bacteria combined with a refined analysis framework allows accurate classification of MSSA and MRSA

  2019cites this paper
• Spatio-temporal flowering patterns in Mediterranean Poaceae. A community study in SW Spain

  2018cites this paper
• Recent Advances in Mass Spectrometry‐Based Proteomic Methods for Discovery of Protein Biomarkers for Complex Human Diseases

  2018cites this paper
• Nucleosome positioning based on generalized relative entropy

  2018cites this paper
• Decision Making in Industry 4.0 Scenarios Supported by Imbalanced Data Classification

  2018cites this paper
• The Potential of the Quick Detection of Selectins Using Raman Spectroscopy to Discriminate Lung Cancer Patients from Healthy Subjects

  2018cites this paper
• Using MALDI-TOF MS typing method to decipher outbreak: the case of Staphylococcus saprophyticus causing urinary tract infections (UTIs) in Marseille, France

  2017cites this paper
• Comparison of different statistical approaches for urinary peptide biomarker detection in the context of coronary artery disease

  2016influential citation
• A Bayesian algorithm for detecting differentially expressed proteins and its application in breast cancer research

  2016cites this paper
• Design principles for clinical network-based proteomics.

  2016cites this paper
• Spectra-first feature analysis in clinical proteomics - A case study in renal cancer

  2016cites this paper
• Mass Spectrometry Analysis Using MALDIquant

  2016cites this paper
• Boolean modeling techniques for protein co-expression networks in systems medicine

  2016cites this paper
• Sparse Proteomics Analysis – a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data

  2015influential citation
• Title Comparison of different statistical approaches for urinary peptide biomarker detection in the context of coronary artery disease

  year unknowninfluential citation