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

Abstract

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.

A Data Mining Metabolomics Exploration of Glaucoma

“…A classifier with a perfect discrimination has a ROC curve that passes through the upper left corner (100% sensitivity, 100% specificity); conversely, a ROC curve close to the 1:1 diagonal represents a very poor classifier. These analyses were performed using SIMCA-P v.14.0 (Umetrics, Umea, Sweden); (4) Biosigner signature was obtained using the new wrapper algorithm 'Biosigner' [26]. The algorithm is wrapped around three machine learning approaches ran in parallel, i.e., PLS DA, Random Forest (RF), and Support Vector Machines (SVM).…”

A Plasma Metabolomic Signature Involving Purine Metabolism in Human Optic Atrophy 1 (OPA1)-Related Disorders

“…To improve the strength of our analysis, Biosigner, a machine learning algorithm implemented as a module in Galaxy/Workflow4metabolomics, was used 23 with the following criteria: 50 bootstraps, feature selections by S and A tiers (S tier ¼ final signature, metabolites passed all the selection iterations; A tier ¼ metabolites discarded during the last iteration), and a P value threshold of 0.05. This algorithm is based on three approaches: PLS-DA, random forest (RF), and support vector machines (SVM).…”

Combining mass spectrometric platforms for lipidome investigation - Application to the characterisation of disruptions in the lipid profile of pig serum upon β-agonist treatment

“…Many tools have been reported in the recent literature such as LOBSTAHS [46] or LipidMatch [47] and their evaluation/implementation would ensure higher confidence in results and facilitated link with other platforms. The selection of relevant variables could also be improved, through the use of sparse methods [48, 49] or the recent biosigner algorithm [50], precisely aiming at building reduced models. Moreover, the TG platform could be extended in order to include more lipid species, thus requiring further developments in order to increase its suitability to a wider range of lipidomics applications.…”