{"id":"W2896982788","doi":"10.1002/cjs.11617","title":"Principal component‐guided sparse regression","year":2021,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; National Science Foundation","keywords":"Principal component analysis; Feature selection; Feature (linguistics); Lasso (programming language); Component (thermodynamics); Pattern recognition (psychology); Artificial intelligence; Sparse PCA; Regression; Matrix (chemical analysis); Group (periodic table); Computer science; Quadratic equation; Principal component regression; Process (computing); Mathematics; Feature vector; Algorithm; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002033876,0.0008753876,0.001485611,0.0009371744,0.0004704845,0.00102081,0.001459839,0.001156234,0.00226667],"category_scores_gemma":[0.005541494,0.0004999314,0.0007985324,0.001286282,0.001217531,0.0008833152,0.00141442,0.002018011,0.001151099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005738004,"about_ca_system_score_gemma":0.001430044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003676168,"about_ca_topic_score_gemma":0.003513765,"domain_scores_codex":[0.998399,0.0007290986,0.00004198674,0.0002830231,0.0004361667,0.0001107045],"domain_scores_gemma":[0.9980077,0.0009173122,0.0001839344,0.000321462,0.0004844254,0.00008508548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002239586,0.0001049834,0.002030593,0.0001700834,0.0001658838,0.00009834121,0.0001006899,0.6458799,0.006988633,0.05484637,0.0257859,0.2636047],"study_design_scores_gemma":[0.0000117737,0.00001097997,0.0001160334,0.00000455626,0.000004515185,0.00001114838,0.000004174048,0.9892899,0.0006287714,0.008366946,0.001545446,0.000005590316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003677042,0.0001740289,0.9947488,0.0002354319,0.00004592822,0.00001920245,0.00006863369,0.000394421,0.0006365195],"genre_scores_gemma":[0.3109274,0.0005231554,0.6766875,0.0006156654,0.0004587952,0.0003134436,0.001521738,0.0004730003,0.008479229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003676168,"threshold_uncertainty_score":0.01075631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04266142698729843,"score_gpt":0.2852832761793879,"score_spread":0.2426218491920894,"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."}}