{"id":"W4231424705","doi":"10.26434/chemrxiv.8299544.v2","title":"A De Novo Molecular Generation Method Using Latent Vector Based Generative Adversarial Network","year":2019,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Autoencoder; Adversarial system; Generative grammar; Artificial intelligence; Chemical space; Set (abstract data type); Computer science; Generative adversarial network; Deep learning; Artificial neural network; Machine learning; Training set; Fraction (chemistry); Deep neural networks; Pattern recognition (psychology); Drug discovery; Chemistry; Biology; Bioinformatics","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":[],"consensus_categories":[],"category_scores_codex":[0.0009746876,0.0006813123,0.0006544829,0.0004267567,0.000289755,0.0004101007,0.000946405,0.0009158053,0.002870409],"category_scores_gemma":[0.001286571,0.0004611197,0.000752261,0.0003424008,0.0007997219,0.0008552057,0.001113861,0.001660635,0.0005285164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006241745,"about_ca_system_score_gemma":0.0006406762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009407176,"about_ca_topic_score_gemma":0.001332394,"domain_scores_codex":[0.9996783,0.00009804875,0.0000109507,0.00007650725,0.0001079148,0.00002825654],"domain_scores_gemma":[0.9994118,0.0003179846,0.000059891,0.0001050727,0.0000703086,0.00003492119],"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":[0.00009112999,0.00007991086,0.0006765245,0.000105529,0.00007702914,0.0001511002,0.00005259357,0.8418549,0.0145678,0.04754659,0.002551334,0.09224548],"study_design_scores_gemma":[0.000008661822,0.00002305977,0.00003641981,0.000004431978,0.000006788266,0.00003708136,0.000001821774,0.9914001,0.002649484,0.004496211,0.001330092,0.000005843926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005532618,0.0001708262,0.9920399,0.0001251462,0.00003826821,0.00004190669,0.00004320464,0.0004011427,0.001607007],"genre_scores_gemma":[0.374867,0.0003910334,0.6143486,0.0003933157,0.00005879656,0.0002585767,0.0003076088,0.0002879539,0.009087118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002870409,"threshold_uncertainty_score":0.009602487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06229740319530794,"score_gpt":0.3399937720826846,"score_spread":0.2776963688873766,"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."}}