{"id":"W3169283615","doi":"10.48550/arxiv.2106.04011","title":"JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Janus; Inverse; Artificial neural network; Computer science; Genetic algorithm; Algorithm; Artificial intelligence; Machine learning; Mathematics","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":[0.0006202955,0.0006624531,0.0008290072,0.0004562359,0.0003825944,0.0006263338,0.001184766,0.001138033,0.001924039],"category_scores_gemma":[0.001830121,0.0004319882,0.0005557542,0.000494931,0.0007558604,0.0007310539,0.0009425666,0.00130389,0.0004551285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008369631,"about_ca_system_score_gemma":0.001079057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002897249,"about_ca_topic_score_gemma":0.004617538,"domain_scores_codex":[0.9997815,0.0000725073,0.000009088509,0.00003620347,0.0000774306,0.00002319969],"domain_scores_gemma":[0.9996088,0.0002187539,0.00004237048,0.0000483851,0.00005355563,0.00002814577],"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":[0.00005852671,0.00004215678,0.0003636943,0.00004067388,0.00004036466,0.00004213041,0.00003359522,0.9336556,0.002506228,0.01140521,0.001462663,0.05034915],"study_design_scores_gemma":[0.000007316255,0.000008893277,0.00001160763,0.000002107839,0.000002382284,0.000004465518,0.000001498084,0.9970156,0.0002975318,0.002322162,0.0003249087,0.000001603905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0296995,0.000583179,0.9627715,0.0002996081,0.00009881373,0.00006454095,0.00005447513,0.001699439,0.004728933],"genre_scores_gemma":[0.4632643,0.0003452413,0.5304298,0.0004340826,0.00005208464,0.0003104246,0.000186551,0.0003696513,0.004607838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002897249,"threshold_uncertainty_score":0.006436527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08270867139708495,"score_gpt":0.2282515621401229,"score_spread":0.1455428907430379,"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."}}