{"id":"W2947950688","doi":"10.1039/c9sc04503a","title":"Scaffold-based molecular design with a graph generative model","year":2019,"lang":"en","type":"article","venue":"Chemical Science","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Generative model; Generative grammar; Graph; Scaffold; Extension (predicate logic); Simple (philosophy); Process (computing)","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":[0.0006455199,0.0001437766,0.000135408,0.0001170648,0.0000867291,0.0002115461,0.001515645,0.00003149396,0.000006743418],"category_scores_gemma":[0.000071335,0.0001113575,0.00004558213,0.001587951,0.0003625381,0.0006465568,0.00024854,0.0000942194,0.00003557734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009894037,"about_ca_system_score_gemma":0.0007803032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002681802,"about_ca_topic_score_gemma":8.919988e-8,"domain_scores_codex":[0.9979046,0.00005615004,0.0001299266,0.0007121924,0.0008291125,0.0003679969],"domain_scores_gemma":[0.9988845,0.0001814621,0.00005761467,0.0005201278,0.0001754619,0.0001808296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005688277,0.00002430564,0.00002089658,0.00000240366,0.000001630869,0.000003281242,0.00005836632,0.5413296,0.4282912,0.02953676,0.0000163079,0.0007095506],"study_design_scores_gemma":[0.0001324276,0.00002625124,0.00002891159,0.000008830908,0.000001201893,0.000003139642,0.000001330997,0.5504443,0.4351703,0.01407344,0.000002936073,0.0001069594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3007217,0.00001324838,0.6978506,0.0003159543,0.00003921872,0.0001546332,5.772114e-7,0.00006139853,0.0008426877],"genre_scores_gemma":[0.5297579,1.289084e-7,0.4697458,0.0004656492,0.000004656785,0.00001034024,3.993383e-7,0.000003635739,0.00001149234],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2290362,"threshold_uncertainty_score":0.4541029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02065093017960657,"score_gpt":0.2719345199321079,"score_spread":0.2512835897525014,"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."}}