{"id":"W4399165032","doi":"10.1021/acs.jcim.3c02070","title":"Application of Transformers in Cheminformatics","year":2024,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Materials Research; Johns Hopkins University; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Computer science; Chemical space; Automatic summarization; Cheminformatics; Artificial intelligence; Machine learning; Transformer; Data science; Drug discovery; Chemistry; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008551881,0.00005400788,0.0001336875,0.0001397995,0.00001053073,0.00006957078,0.0001016529,0.00004325363,0.0000224031],"category_scores_gemma":[0.00008091442,0.00004184512,0.00002945887,0.0001186489,0.00003451968,0.001378262,0.00001585868,0.0001138729,0.000005969001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002654656,"about_ca_system_score_gemma":0.00004886659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009993012,"about_ca_topic_score_gemma":1.180027e-7,"domain_scores_codex":[0.9989182,0.000006060848,0.000738755,0.00003383181,0.0002182963,0.00008486197],"domain_scores_gemma":[0.9996386,0.0000343572,0.0001643159,0.00003842503,0.0000834117,0.00004092671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003312822,0.000008819017,0.00001512881,0.0004486826,0.000002206619,3.494762e-7,0.004268348,0.07117829,0.905866,0.0007186161,0.00002634014,0.01743414],"study_design_scores_gemma":[0.000122331,0.00001320384,0.000002074532,0.0001038064,0.000004321563,0.00002809706,0.0002080881,0.840219,0.1585749,0.0004122595,0.0002719829,0.00003997053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7362176,0.00006961995,0.2630437,0.0001469802,0.00008471638,0.00003877128,0.000001758479,0.000008736964,0.0003880931],"genre_scores_gemma":[0.9914559,0.00003965046,0.008413674,0.00006100791,0.00002367712,0.000001262777,0.000001808061,0.00000212324,9.574011e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7690407,"threshold_uncertainty_score":0.1706395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01087750625260464,"score_gpt":0.2736177912065863,"score_spread":0.2627402849539817,"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."}}