{"id":"W4383823251","doi":"10.1038/s42256-023-00688-4","title":"Reusability report: Evaluating reproducibility and reusability of a fine-tuned model to predict drug response in cancer patient samples","year":2023,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Public Health Ontario; Vector Institute; Princess Margaret Cancer Centre; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"","keywords":"Reusability; Reproducibility; Context (archaeology); Computer science; Machine learning; Artificial intelligence; Drug; Medicine; Mathematics; Statistics; Pharmacology; Software","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02064473,0.001794323,0.001276297,0.002972372,0.0006893927,0.001846088,0.002572243,0.002095163,0.001084672],"category_scores_gemma":[0.07550289,0.0006815773,0.00315467,0.001324188,0.001273708,0.001836248,0.001792353,0.001680875,0.0006638324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009699843,"about_ca_system_score_gemma":0.001739681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006628708,"about_ca_topic_score_gemma":0.005173201,"domain_scores_codex":[0.9895845,0.003040651,0.001335567,0.003056165,0.002671479,0.0003117159],"domain_scores_gemma":[0.9309258,0.03613032,0.003814717,0.02195575,0.006450329,0.0007230485],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.006115609,0.002454709,0.252704,0.00137283,0.01006388,0.001396421,0.0008137067,0.4850356,0.06261159,0.0014915,0.009427908,0.1665123],"study_design_scores_gemma":[0.000472404,0.002888205,0.04811937,0.00008048238,0.001955628,0.001056083,0.0001903308,0.8758388,0.06311149,0.00286564,0.003226329,0.0001952551],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.857964,0.001487256,0.1177796,0.0004127291,0.0003713377,0.00052565,0.007150271,0.01289847,0.001410598],"genre_scores_gemma":[0.9442902,0.0001503147,0.04442869,0.0002023969,0.00005784022,0.0002502727,0.009049195,0.0009062231,0.0006649618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9793553,"threshold_uncertainty_score":0.109181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06137390241407797,"score_gpt":0.4167704008217654,"score_spread":0.3553964984076874,"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."}}