{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004608149,0.0001041734,0.0002583607,0.0001006721,0.0000266129,0.000005626657,0.0001914729,0.00007310724,0.00002779367],"category_scores_gemma":[0.000222247,0.00009038166,0.000009180078,0.0007822374,0.00003517154,0.000002638055,0.00004770179,0.00008941273,0.000001447413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002140492,"about_ca_system_score_gemma":0.0002180931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001564532,"about_ca_topic_score_gemma":0.005331622,"domain_scores_codex":[0.9989831,0.00005057207,0.0002758764,0.0004393273,0.00006313877,0.0001879265],"domain_scores_gemma":[0.9994023,0.00005255331,0.0000875351,0.0002910847,0.00007267306,0.00009388864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004994031,0.00008503606,0.0218453,0.0002297204,0.0002708725,0.000003726298,0.0003946728,0.00168148,0.8623433,0.00323532,0.1056582,0.003753021],"study_design_scores_gemma":[0.01681003,0.004038027,0.05126698,0.0001658606,0.0020324,0.00004500972,0.0006804361,0.2295544,0.01319166,0.004921834,0.6760165,0.001276905],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001519266,0.0001691337,0.9960485,0.001377954,0.00002218492,0.00034294,0.0004623387,0.000005232356,0.00005249546],"genre_scores_gemma":[0.03203561,0.00009036176,0.9586017,0.001395488,0.0002615957,0.00002015913,0.007362927,0.00001940619,0.0002127682],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8491516,"threshold_uncertainty_score":0.3685657,"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."}}