{"id":"W3179038740","doi":"10.1093/bioadv/vbac033","title":"Sufficient principal component regression for pattern discovery in transcriptomic data","year":2022,"lang":"en","type":"preprint","venue":"Bioinformatics Advances","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Subspace topology; Principal component analysis; Context (archaeology); Computer science; Data mining; Regression; Principal component regression; Machine learning; Artificial intelligence; Pattern recognition (psychology); Mathematics; Biology; Statistics","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":[0.0003581852,0.0002756298,0.0002731467,0.0001263199,0.0001053564,0.00008387674,0.001052962,0.0001729241,0.00001715308],"category_scores_gemma":[0.00003652987,0.0002399758,0.0001103031,0.00007290462,0.00005167871,0.00002812216,0.001360654,0.0002531765,0.000001575479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008252482,"about_ca_system_score_gemma":0.0002515874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001233345,"about_ca_topic_score_gemma":0.00007969551,"domain_scores_codex":[0.9982271,0.00004952718,0.0006267112,0.0005351699,0.0002872216,0.0002743379],"domain_scores_gemma":[0.9981394,0.00001620756,0.0004198437,0.001322605,0.00004029101,0.0000616183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004028453,0.003596269,0.02536051,0.01474551,0.0005447923,0.00001494536,0.008230117,0.1162713,0.2759228,0.0008149496,0.06009611,0.4903743],"study_design_scores_gemma":[0.001668443,0.0002494382,0.002645312,0.0003746084,0.0000420181,0.000003910487,0.002056064,0.06894666,0.01527482,0.0001099159,0.9078351,0.0007937102],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7839659,0.01300894,0.189294,0.0006073043,0.004395256,0.002939725,0.004637828,0.00005365793,0.001097361],"genre_scores_gemma":[0.9640079,0.005645981,0.007153627,0.0003282825,0.0002790047,0.0006651041,0.02127806,0.00005041745,0.0005916886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.847739,"threshold_uncertainty_score":0.9785931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0465884028724005,"score_gpt":0.3316644022699577,"score_spread":0.2850759993975572,"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."}}