{"id":"W4206292848","doi":"10.17975/sfj-2021-013","title":"Deep learning transcriptomic model for prediction of pan-drug chemotherapeutic sensitivity","year":2021,"lang":"en","type":"article","venue":"STEM Fellowship Journal","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Machine learning; Biomarker; Artificial intelligence; Drug response; Precision medicine; Personalized medicine; Feature selection; Sensitivity (control systems); Cancer; Cluster analysis; Drug; Computational biology; Transcriptome; Oncology; Computer science; Bioinformatics; Biology; Medicine; Gene expression; Internal medicine; Gene; Pharmacology; Genetics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.00173414,0.0001466887,0.000261867,0.0001103847,0.000207698,0.0001495776,0.0002527034,0.00005659114,0.000004532585],"category_scores_gemma":[0.00006121843,0.0001495221,0.0002641788,0.0002734349,0.00003627386,0.0005507412,0.00005239055,0.0003510484,0.000002038836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001022898,"about_ca_system_score_gemma":0.0004449747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001730334,"about_ca_topic_score_gemma":0.00001619839,"domain_scores_codex":[0.9980412,0.0005729093,0.00042366,0.0002938216,0.0003995217,0.0002689016],"domain_scores_gemma":[0.9985701,0.0005215087,0.0002271921,0.0002097559,0.0003740891,0.00009739242],"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":[0.00005038513,0.0001115046,0.0006821675,0.000087149,0.0001101507,0.00001843416,0.005221094,0.8705719,0.04179658,0.005574882,0.00005850141,0.07571726],"study_design_scores_gemma":[0.0006578076,0.00003626298,0.001895661,0.00005375041,0.00002964739,0.0002886387,0.0001857753,0.9729059,0.0142275,0.009481926,0.0001192635,0.0001179165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1495767,0.0004877445,0.8487095,0.0004326118,0.0004711124,0.0001058957,0.000007923684,0.00004395969,0.0001645721],"genre_scores_gemma":[0.9104109,0.00003674092,0.0887805,0.0001155035,0.0001252566,0.00000361302,0.000004199141,0.00001718942,0.0005060504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7608343,"threshold_uncertainty_score":0.6097333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04406998071208,"score_gpt":0.2846461031684375,"score_spread":0.2405761224563575,"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."}}