{"id":"W2330399655","doi":"10.1101/026534","title":"Using cell line and patient samples to improve predictions of patient drug response","year":2015,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; SickKids Foundation; University of Toronto","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; Sick Kids Foundation; Canadian Cancer Society Research Institute; Cancer Research Society","keywords":"Predictive modelling; Patient data; Clinical trial; Profiling (computer programming); Drug response; Personalized medicine; Precision medicine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004736393,0.000388452,0.0004262061,0.0002488877,0.00007211397,0.00006206755,0.0002657276,0.0003385684,0.000004697204],"category_scores_gemma":[0.0003349768,0.0004195359,0.000139244,0.0002271587,0.0001057372,0.000007732863,0.001132595,0.000253689,0.000001900966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113747,"about_ca_system_score_gemma":0.0004910843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001322695,"about_ca_topic_score_gemma":0.000005770973,"domain_scores_codex":[0.9977872,0.0002058239,0.0005660714,0.0008733448,0.0002645665,0.0003029976],"domain_scores_gemma":[0.9971122,0.00002434844,0.0004342741,0.001293047,0.0008541938,0.000281954],"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":[0.0002170855,0.0001583116,0.0005430987,0.00009404346,0.0000924418,0.000005912649,0.00003069261,0.0004075591,0.9972912,0.000001774786,0.001150669,0.000007210338],"study_design_scores_gemma":[0.0001959544,0.00036006,0.0008380497,0.0001028914,0.0001444893,1.864689e-8,0.00001556298,0.0003141374,0.9903582,0.000001173985,0.007265525,0.000403985],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926021,0.001516408,0.004604918,0.00004613053,0.0001375397,0.0006755345,0.0003453894,0.00006702891,0.000004975129],"genre_scores_gemma":[0.9776688,0.0001632094,0.02172887,0.0001304321,0.0001211376,0.0001004756,0.000001794015,0.00008010968,0.0000051927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01712395,"threshold_uncertainty_score":0.9998257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01233243657610324,"score_gpt":0.2410880184323593,"score_spread":0.2287555818562561,"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."}}