{"id":"W3212461952","doi":"10.1038/s42256-021-00408-w","title":"Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction","year":2021,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Generalization; Computer science; Consistency (knowledge bases); Transfer of learning; Pharmacogenomics; Labeled data; Drug response; Artificial intelligence; Machine learning; Distribution (mathematics); Domain (mathematical analysis); Data mining; Drug; Mathematics; Bioinformatics; Medicine; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003717931,0.0001310045,0.0001358662,0.00001689105,0.00009769569,0.00001344907,0.0002553852,0.0003307681,0.00001374907],"category_scores_gemma":[0.000598656,0.0001225816,0.00004195522,0.00009261278,0.00005836934,0.000005829967,0.0003056797,0.0001463964,6.396477e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001493535,"about_ca_system_score_gemma":0.00009740632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001786174,"about_ca_topic_score_gemma":0.00004432826,"domain_scores_codex":[0.9988549,0.0001324593,0.0002494728,0.0005380063,0.0001081933,0.0001169465],"domain_scores_gemma":[0.998738,0.00005611282,0.0001179499,0.0007485987,0.0002938991,0.0000454326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000380734,0.00005960526,0.0003929778,0.00001048053,0.0000282905,9.039778e-7,0.00002239709,0.00003666216,0.9913379,0.0002570351,0.005489493,0.001983536],"study_design_scores_gemma":[0.0001985427,0.0000668809,0.0002580422,0.00001866812,0.00003157592,0.000004477154,0.0000122696,0.003456931,0.9274473,0.0007123689,0.06768441,0.0001085635],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2306085,0.006869497,0.7576273,0.0004640457,0.0002015178,0.0003330189,0.003848817,0.00002556018,0.00002175895],"genre_scores_gemma":[0.9234778,0.001575582,0.04055278,0.0002317388,0.0001951342,0.00005948864,0.0335957,0.00002009932,0.0002917126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7170745,"threshold_uncertainty_score":0.4998731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01293324647000713,"score_gpt":0.3115565514539093,"score_spread":0.2986233049839022,"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."}}