{"id":"W4220753843","doi":"10.1002/minf.202100240","title":"A Descriptor Set for Quantitative Structure‐property Relationship Prediction in Biologics","year":2022,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Quantitative structure–activity relationship; In silico; Computer science; Stability (learning theory); Drug development; Artificial intelligence; Machine learning; Drug discovery; Set (abstract data type); Process (computing); Biochemical engineering; Data mining; Biological system; Computational biology; Drug; Chemistry; Bioinformatics; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0003106398,0.0001023528,0.0001710988,0.0001819167,0.0001842892,0.00001606632,0.0000994714,0.0000540511,0.0001272901],"category_scores_gemma":[0.0003177493,0.0000702498,0.00007504346,0.0002919831,0.00005243915,0.00008132739,0.00009941314,0.0003398008,0.00001013413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001279071,"about_ca_system_score_gemma":0.0001164658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003365313,"about_ca_topic_score_gemma":0.000007393693,"domain_scores_codex":[0.9989302,0.00006444004,0.0003747457,0.00008723947,0.000316606,0.0002267801],"domain_scores_gemma":[0.9995208,0.0001025209,0.00007703144,0.0001421691,0.00009065749,0.00006680885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01121695,0.001109371,0.5493319,0.004219989,0.0008339863,0.000331972,0.0495617,0.03314192,0.09466515,0.1649799,0.07301317,0.01759394],"study_design_scores_gemma":[0.008103685,0.008115471,0.0965722,0.0001722232,0.0001760066,0.0005243369,0.0165949,0.435315,0.009090535,0.01850537,0.4059686,0.0008616752],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893162,0.0001429701,0.006214928,0.0007825803,0.0001316368,0.0009301435,0.0006336771,0.00003255648,0.001815297],"genre_scores_gemma":[0.9757973,0.000008294314,0.02089969,0.001006918,0.00002055897,0.0001389363,0.0009622611,0.00001260137,0.001153445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4527597,"threshold_uncertainty_score":0.2864704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08329791264474877,"score_gpt":0.3406507462846687,"score_spread":0.2573528336399199,"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."}}