{"id":"W4394762701","doi":"10.1093/bioadv/vbae047","title":"Text-mining-based feature selection for anticancer drug response prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Stem Cell Network","keywords":"Feature selection; Pharmacogenomics; Machine learning; Computer science; Artificial intelligence; Feature (linguistics); Drug response; Selection (genetic algorithm); Support vector machine; Data mining; Bioinformatics; Drug; Biology","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":[0.0009291839,0.0001523469,0.0001334989,0.0002542428,0.000163547,0.000413,0.0003192271,0.00004938877,0.000004282332],"category_scores_gemma":[0.0002463937,0.0001330383,0.0000929462,0.0007104487,0.00004079276,0.001999787,0.00005360636,0.0001066874,0.00001594181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252192,"about_ca_system_score_gemma":0.0003601241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.27258e-7,"about_ca_topic_score_gemma":0.000003831843,"domain_scores_codex":[0.998836,0.00007398161,0.0002845422,0.0002367538,0.0003386568,0.0002300055],"domain_scores_gemma":[0.9982146,0.001309301,0.00009175432,0.0001968954,0.0001263591,0.00006107614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000452731,0.00006970414,0.0003640595,0.0009971439,0.00006911274,0.000003110095,0.002966373,0.4079367,0.0004071592,0.03168831,0.02560291,0.5294427],"study_design_scores_gemma":[0.0001884933,0.000105778,0.0005963061,0.0001073123,0.000009525088,0.000008770433,0.00005339311,0.8823998,0.001358201,0.002781477,0.1122542,0.0001367602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006694532,0.0008820697,0.9877992,0.002032951,0.001388433,0.0003403604,0.0000567466,0.0004649964,0.0003407518],"genre_scores_gemma":[0.1048974,0.00003625961,0.893894,0.0003864164,0.0001965915,0.0001060305,0.00002806898,0.00001697135,0.000438276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.529306,"threshold_uncertainty_score":0.5425144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01249792745781209,"score_gpt":0.3089335441867941,"score_spread":0.296435616728982,"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."}}