{"doi":"10.1371/journal.pone.0028210","title":"The Influence of Feature Selection Methods on Accuracy, Stability and Interpretability of Molecular Signatures","abstract":null,"journal":"PLoS ONE","year":2011,"id":590855,"datarank":14.221953042308305,"base_score":5.958424693029782,"endowment":5.958424693029782,"self_citation_contribution":0.8937637039544675,"citation_network_contribution":13.328189338353837,"self_endowment_contribution":0.8937637039544675,"citer_contribution":13.328189338353837,"corpus_percentile":null,"corpus_rank":null,"citation_count":386,"citer_count":200,"citers_with_citation_signal":200,"citers_with_endowment":200,"datacite_reuse_total":5,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":12328,"name":"Pierre Gestraud","orcid":"0000-0002-3893-9879","position":1,"is_corresponding":false},{"id":89926,"name":"Jean-Philippe Vert","orcid":null,"position":2,"is_corresponding":false},{"id":1511665,"name":"Anne-Claire Haury","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"The Influence of Feature Selection Methods on Accuracy, Stability and Interpretability of Molecular Signatures","abstract":"Biomarker discovery from high-dimensional data is a crucial problem with enormous applications in biology and medicine. It is also extremely challenging from a statistical viewpoint, but surprisingly few studies have investigated the relative strengths and weaknesses of the plethora of existing feature selection methods. In this study we compare 32 feature selection methods on 4 public gene expression datasets for breast cancer prognosis, in terms of predictive performance, stability and functional interpretability of the signatures they produce. We observe that the feature selection method has a significant influence on the accuracy, stability and interpretability of signatures. Surprisingly, complex wrapper and embedded methods generally do not outperform simple univariate feature selection methods, and ensemble feature selection has generally no positive effect. Overall a simple Student's t-test seems to provide the best results.","is_dataset_classified":null,"base_score":5.958424693029782,"endowment":5.958424693029782,"datacite_reuse_total":5,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"22205940","pmcid":"PMC3244389","openalex_id":"https://openalex.org/W2146739527","authors":[],"funders":[{"funder_name":"European Commission FP7","grant_id":"FP7_246513","title":null},{"funder_name":"European Commission","grant_id":"246513","title":"Nanosystems for the early Diagnosis of Neurodegenerative diseases"},{"funder_name":"French National Research Agency (ANR)","grant_id":"ANR-09-BLAN-0051","title":null}],"total_grants":3,"fwci":8.3938,"citation_percentile":0.98589883,"influential_citations":0,"citation_trend":[{"year":2012,"count":23},{"year":2013,"count":22},{"year":2014,"count":22},{"year":2015,"count":39},{"year":2016,"count":24},{"year":2017,"count":24},{"year":2018,"count":31},{"year":2019,"count":32},{"year":2020,"count":35},{"year":2021,"count":28},{"year":2022,"count":26},{"year":2023,"count":30},{"year":2024,"count":14},{"year":2025,"count":19},{"year":2026,"count":15}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0028210&type=printable","host_type":"journal"},{"url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0028210&type=printable","host_type":"publisher"},{"url":"http://dx.plos.org/10.1371/journal.pone.0028210","host_type":"publisher"},{"url":"https://doi.org/10.1371/journal.pone.0028210","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/22205940","host_type":"repository"},{"url":"http://arxiv.org/abs/1101.5008","host_type":"repository"},{"url":"https://hal.science/hal-00559580","host_type":"repository"},{"url":"https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0028210","host_type":"repository"},{"url":"https://doaj.org/article/b802b59e59bc483890bc7f6f5136830f","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3244389","host_type":"repository"},{"url":"https://arxiv.org/pdf/1101.5008","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC3244389","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC3244389?pdf=render","host_type":"Europe_PMC"},{"url":"https://dx.doi.org/10.48550/arxiv.1101.5008","host_type":""},{"url":"http://dx.doi.org/10.1371/journal.pone.0028210","host_type":""},{"url":"https://dx.doi.org/10.1371/journal.pone.0028210","host_type":""},{"url":"https://doi.org/https://doi.org/10.1371/journal.pone.0028210","host_type":""}],"fields_of_study":["Gene expression and cancer classification","Molecular Biology Techniques and Applications","Bioinformatics and Genomic Networks","0301 basic medicine","03 medical and health sciences","0303 health sciences","Area Under Curve","Biomarkers","Computational Biology","Data Interpretation, Statistical","ROC Curve"],"mesh_terms":["Data Interpretation, Statistical","ROC Curve","Biomarkers","Computational Biology","Area Under Curve"],"keywords":["Interpretability","Feature selection","Feature (linguistics)","Computer science","Stability (learning theory)","Artificial intelligence","Machine learning","Selection (genetic algorithm)","Data mining","Simple (philosophy)","Filter (signal processing)","Pattern recognition (psychology)","Bioinformatics","Biology","FOS: Computer and information sciences","Science","610","Machine Learning (stat.ML)","Quantitative Biology - Quantitative Methods","Statistics - Applications","breast cancer","[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]","Statistics - Machine Learning","biomarker discovery","Applications (stat.AP)","microarrays","Quantitative Methods (q-bio.QM)","[STAT.AP]Statistics [stat]/Applications [stat.AP]","Q","R","Computational Biology","[SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]","ROC Curve","Area Under Curve","Data Interpretation, Statistical","FOS: Biological sciences","gene expression","Medicine","[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]","signature","Biomarkers","Research Article"],"sdg_mappings":[{"sdg_number":3,"sdg_label":"3. Good health"},{"sdg_number":0,"sdg_label":"Good health and well-being"}],"linked_datasets":[{"doi":"10.6084/m9.figshare.21285809.v1","title":"Additional file 1 of Benchmark study of feature selection strategies for multi-omics data","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.21285809","title":"Additional file 1 of Benchmark study of feature selection strategies for multi-omics data","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26679413.v1","title":"Additional file 1 of Performance and clinical utility of a new supervised machine-learning pipeline in detecting rare ciliopathy patients based on deep phenotyping from electronic health records and semantic similarity","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26679413","title":"Additional file 1 of Performance and clinical utility of a new supervised machine-learning pipeline in detecting rare ciliopathy patients based on deep phenotyping from electronic health records and semantic similarity","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.48550/arxiv.1101.5008","title":"The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures","publisher":"arXiv","resource_type":"Text"}],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"geo"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-07-25T12:44:11.034279Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}