{"id":"W2745961286","doi":"10.1186/s13321-017-0234-y","title":"Comparative analysis of chemical similarity methods for modular natural products with a hypothetical structure enumeration algorithm","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"MacEwan University; McMaster University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Cheminformatics; Chemical space; Chemical similarity; Computer science; Natural product; Similarity (geometry); Enumeration; Modular design; Data mining; Drug discovery; Biochemical engineering; Algorithm; Structural similarity; Artificial intelligence; Bioinformatics; Chemistry; Mathematics; Biology; Engineering","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":[0.0004949116,0.0001595274,0.0009075613,0.0001505449,0.00008152588,0.00005354501,0.0002095751,0.0001154061,0.00001410651],"category_scores_gemma":[0.001007414,0.00009303703,0.0002243914,0.0001868788,0.0001805593,0.0003204473,0.00003468938,0.0003413813,1.260414e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098624,"about_ca_system_score_gemma":0.0001271412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001341003,"about_ca_topic_score_gemma":4.43442e-7,"domain_scores_codex":[0.9987836,0.00001227961,0.0006609708,0.00009986486,0.0002891623,0.0001541167],"domain_scores_gemma":[0.996932,0.0001118856,0.001188483,0.0003511381,0.001333911,0.00008262714],"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":[0.0007239667,0.0001253655,0.00005480687,0.0003623079,0.002509079,0.00000283319,0.001204493,0.00002076026,0.9525944,0.00004128785,0.0005758635,0.04178486],"study_design_scores_gemma":[0.0008964211,0.0002114867,0.000572041,0.00008879452,0.002976505,0.0001294215,0.00009803187,0.02635158,0.967682,0.00007613672,0.0008047406,0.0001128184],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859273,0.0002734721,0.01064689,0.002202087,0.0001793443,0.0005033786,0.00007777465,0.000007161859,0.0001825283],"genre_scores_gemma":[0.6284381,0.000007495432,0.3713139,0.00005470517,0.0001355296,2.233396e-7,0.00001934185,0.000004057822,0.00002668531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.360667,"threshold_uncertainty_score":0.379394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0263425672799847,"score_gpt":0.3490112789775224,"score_spread":0.3226687116975377,"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."}}