{"id":"W4243270491","doi":"10.26434/chemrxiv.13383266","title":"Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund; Compute Canada; École de technologie supérieure; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Chemical space; Computer science; Virtual screening; Generative grammar; Deep learning; Machine learning; Benchmark (surveying); Generative model; Artificial intelligence; Tree traversal; Interpolation (computer graphics); Algorithm; Drug discovery; Theoretical computer science; Bioinformatics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005602678,0.0004887758,0.0005827209,0.0001098315,0.0003870386,0.001276526,0.0005240807,0.000267725,0.00009510281],"category_scores_gemma":[0.0002336463,0.0004795004,0.00009781215,0.0001491369,0.000331589,0.001373864,0.0008025994,0.0002482375,0.000009869727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001082625,"about_ca_system_score_gemma":0.000269887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008756913,"about_ca_topic_score_gemma":0.000004782393,"domain_scores_codex":[0.9972739,0.0001494223,0.0005404167,0.001226143,0.0004164964,0.0003936827],"domain_scores_gemma":[0.9986407,0.0001295191,0.0003958063,0.0004272576,0.0002645618,0.0001421677],"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":[0.00001868018,0.00002498352,0.000003585966,0.0001528988,0.0000129706,0.000002152646,0.001575403,0.689541,0.3077183,0.0006559818,0.0001171197,0.0001769026],"study_design_scores_gemma":[0.0002695982,0.00004450653,0.000002476537,0.00007068249,0.00005947814,0.000004356191,0.0002477176,0.7831379,0.20518,0.01054034,0.00002092938,0.0004220209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08860795,0.0002600538,0.9082322,0.000730978,0.0009880536,0.0007553322,0.0001856553,0.0001589639,0.00008088447],"genre_scores_gemma":[0.06878605,0.0002121356,0.929315,0.0002697323,0.0006122045,0.0001892001,0.0004448543,0.00009221793,0.00007862414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1025383,"threshold_uncertainty_score":0.9997657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0541934749013716,"score_gpt":0.2852647401232292,"score_spread":0.2310712652218576,"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."}}