{"id":"W4233151585","doi":"10.26434/chemrxiv.8299544","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":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Autoencoder; Chemical space; Generative grammar; Artificial intelligence; Generative adversarial network; Deep learning; Set (abstract data type); Artificial neural network; Adversarial system; Computer science; Machine learning; Fraction (chemistry); Generative model; Drug discovery; Pattern recognition (psychology); Chemistry; Biochemistry; Chromatography","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":[0.001478151,0.0004452767,0.0005061014,0.0001488635,0.0001298727,0.0004984459,0.001072488,0.0003612452,0.0000274719],"category_scores_gemma":[0.0001546511,0.000486577,0.0003413432,0.0003972558,0.00003517789,0.0002140729,0.00123566,0.000594517,0.00001815082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006055336,"about_ca_system_score_gemma":0.001770398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004891573,"about_ca_topic_score_gemma":0.000002478307,"domain_scores_codex":[0.9963235,0.001019154,0.0004572246,0.001156837,0.0005399943,0.0005032838],"domain_scores_gemma":[0.9978154,0.0003416255,0.0003671391,0.001057262,0.0002690809,0.0001494408],"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":[0.00001311002,0.00004182754,0.00007440412,0.00004556226,0.00009820338,0.00003483017,0.0001771502,0.9559557,0.0338638,0.008183017,0.0001768293,0.001335551],"study_design_scores_gemma":[0.0004188227,0.0000220458,0.0002180132,0.00007249966,0.00005903579,0.00001153274,0.000001261054,0.9301324,0.06083856,0.007605048,0.0001494431,0.0004713596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08125648,0.0002654386,0.9141632,0.0004414893,0.003019092,0.0005520167,0.000005015566,0.0001285642,0.0001686865],"genre_scores_gemma":[0.1554223,0.000002894168,0.8422766,0.0007827337,0.001314702,0.00004952849,0.00008055893,0.00004123954,0.00002936738],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07416584,"threshold_uncertainty_score":0.9997586,"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."}}