{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008718671,0.001880043,0.002252013,0.002437606,0.0009148821,0.0017616,0.00222493,0.001746604,0.005370094],"category_scores_gemma":[0.04545553,0.001216218,0.001852423,0.003723794,0.002101484,0.00265639,0.002283106,0.003901729,0.005740239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009102399,"about_ca_system_score_gemma":0.003636909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002852281,"about_ca_topic_score_gemma":0.002921645,"domain_scores_codex":[0.9938893,0.003004523,0.0002844089,0.001128426,0.001472963,0.0002203652],"domain_scores_gemma":[0.9763633,0.01739244,0.0009977279,0.002834034,0.001961994,0.0004505242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007180704,0.0003456404,0.006097469,0.001342041,0.0003692704,0.0004518683,0.0002425151,0.5557345,0.009929781,0.09546218,0.04454916,0.2847575],"study_design_scores_gemma":[0.00003061867,0.00002990505,0.0004702323,0.00003801074,0.00001425996,0.00005854672,0.00001534359,0.9254922,0.001417507,0.06980308,0.002614396,0.00001584821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002278398,0.0003332165,0.994165,0.0004564152,0.00003326121,0.00005562184,0.0007279288,0.001541439,0.0004086592],"genre_scores_gemma":[0.1439285,0.001414377,0.8376148,0.0005840682,0.0003856523,0.0009412754,0.01104013,0.001330521,0.002760679],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008718671,"threshold_uncertainty_score":0.04610926,"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."}}