biosigner: A New Method for the Discovery of Significant Molecular Signatures from Omics Data

• Published in: Frontiers in molecular biosciences Vol. 3; p. 26
• Main Authors: Rinaudo, Philippe, Boudah, Samia, Junot, Christophe, Thévenot, Etienne A
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media 21.06.2016; Frontiers Media S.A
• Subjects: Biochemistry, Molecular Biology; Computer Science; Data Analysis, Statistics and Probability; Genomics; Information Retrieval; Life Sciences; Molecular Biosciences; Physics; Quantitative Methods; omics data; support vector machine; molecular signature; random forest; biomarker; partial least squares; feature selection; proteomics; data mining; diabetic patients; Support Vector Machine; wrapper approach; bile; Random Forest; biosigner algorithm; reference binary classifier; Workflow4metabolomics; taurochenodeoxycholic acid; metabolomics; Partial Least Squares; transcriptomics; discovery of biomarkers
• ISSN: 2296-889X; 2296-889X
• DOI: 10.3389/fmolb.2016.00026

High-throughput technologies such as transcriptomics, proteomics, and metabolomics show great promise for the discovery of biomarkers for diagnosis and prognosis. Selection of the most promising candidates between the initial untargeted step and the subsequent validation phases is critical within the pipeline leading to clinical tests. Several statistical and data mining methods have been described for feature selection: in particular, wrapper approaches iteratively assess the performance of the classifier on distinct subsets of variables. Current wrappers, however, do not estimate the significance of the selected features. We therefore developed a new methodology to find the smallest feature subset which significantly contributes to the model performance, by using a combination of resampling, ranking of variable importance, significance assessment by permutation of the feature values in the test subsets, and half-interval search. We wrapped our biosigner algorithm around three reference binary classifiers (Partial Least Squares-Discriminant Analysis, Random Forest, and Support Vector Machines) which have been shown to achieve specific performances depending on the structure of the dataset. By using three real biological and clinical metabolomics and transcriptomics datasets (containing up to 7000 features), complementary signatures were obtained in a few minutes, generally providing higher prediction accuracies than the initial full model. Comparison with alternative feature selection approaches further indicated that our method provides signatures of restricted size and high stability. Finally, by using our methodology to seek metabolites discriminating type 1 from type 2 diabetic patients, several features were selected, including a fragment from the taurochenodeoxycholic bile acid. Our methodology, implemented in the biosigner R/Bioconductor package and Galaxy/Workflow4metabolomics module, should be of interest for both experimenters and statisticians to identify robust molecular signatures from large omics datasets in the process of developing new diagnostics.