{"id":"W2973185263","doi":"10.1002/sim.8809","title":"SuRF: A new method for sparse variable selection, with application in microbiome data analysis","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Lasso (programming language); Ranking (information retrieval); Variable (mathematics); Selection (genetic algorithm); Microbiome; A priori and a posteriori; Interpretability","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00780257,0.001906489,0.002227992,0.002867377,0.000929431,0.001220294,0.00205365,0.001567295,0.004929761],"category_scores_gemma":[0.01878998,0.0009166477,0.002783979,0.003045251,0.0011565,0.00157303,0.002309308,0.003131726,0.002095488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004488336,"about_ca_system_score_gemma":0.001848979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003338952,"about_ca_topic_score_gemma":0.004198634,"domain_scores_codex":[0.9952095,0.002723138,0.0002355127,0.0006692319,0.001007676,0.0001549308],"domain_scores_gemma":[0.9922926,0.00550131,0.0004266564,0.0007275718,0.0008877923,0.0001640451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004637889,0.0001612064,0.005191082,0.0007772541,0.001122742,0.0003602059,0.0002773696,0.1734377,0.01196718,0.02804827,0.02626898,0.7519242],"study_design_scores_gemma":[0.0001139356,0.0001603393,0.001439848,0.0000803477,0.000109068,0.0002954048,0.00004623759,0.9417927,0.004037027,0.03357841,0.01826554,0.00008124351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00088845,0.0001984141,0.9976166,0.00008297637,0.00004393191,0.0000342981,0.0001545404,0.0008688861,0.0001118798],"genre_scores_gemma":[0.02557253,0.0004984821,0.9691863,0.000297123,0.0002523428,0.0005170557,0.001517362,0.0008279234,0.001330975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00780257,"threshold_uncertainty_score":0.04126447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02851641297363126,"score_gpt":0.3642394012441812,"score_spread":0.3357229882705499,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}