{"id":"W1986483795","doi":"10.1007/s40290-015-0090-x","title":"Big Data in Pharmaceutical R&D: Creating a Sustainable R&D Engine","year":2015,"lang":"en","type":"article","venue":"Pharmaceutical Medicine","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nordic Life Science Pipeline (Canada)","funders":"","keywords":"Big data; Medicine; Business; Pharmacology; Computer science; Data mining","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005778656,0.0003573422,0.0005465184,0.0004627808,0.0001027863,0.0001097238,0.002397119,0.00009562711,0.0001224315],"category_scores_gemma":[0.006706547,0.0003072523,0.00004543598,0.001895892,0.0002856248,0.0009415135,0.002334047,0.0008124532,0.0001748514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003087772,"about_ca_system_score_gemma":0.0004859758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002102192,"about_ca_topic_score_gemma":0.00002121828,"domain_scores_codex":[0.9951909,0.0007077545,0.0007583891,0.001036287,0.001258657,0.001048012],"domain_scores_gemma":[0.9949229,0.002242297,0.0001053965,0.001403566,0.0003039659,0.001021834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006818715,0.001766291,0.006792485,0.0007206322,0.0002322098,0.001381843,0.008023041,0.01657741,0.002610354,0.21894,0.03918627,0.7030876],"study_design_scores_gemma":[0.003978004,0.00007864792,0.0005366987,0.0001102907,0.00005217404,0.0001445332,0.0002106124,0.4840361,0.0002663472,0.01517131,0.495015,0.000400284],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02085888,0.003151053,0.9362898,0.02484585,0.001676467,0.0006164818,0.00001064437,0.0003494408,0.01220133],"genre_scores_gemma":[0.8213534,0.000174066,0.1676159,0.00618181,0.002714432,0.00007154123,0.0001766914,0.00006723391,0.001644994],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8004945,"threshold_uncertainty_score":0.999938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3911000808631966,"score_gpt":0.4883167418636923,"score_spread":0.09721666100049575,"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."}}