{"id":"W4413934912","doi":"10.3390/a18090547","title":"Learning SMILES Semantics: Word2Vec and Transformer Embeddings for Molecular Property Prediction","year":2025,"lang":"en","type":"article","venue":"Algorithms","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Word2vec; Property (philosophy); Computer science; Semantics (computer science); Natural language processing; Transformer; Artificial intelligence; Theoretical computer science; Programming language; Embedding; Epistemology; Engineering; Philosophy; Electrical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0004015851,0.0001165695,0.0001397301,0.0001216843,0.000161933,0.0001541456,0.0002260083,0.00004925519,0.000001978],"category_scores_gemma":[0.00008704068,0.00009195451,0.00005952644,0.0002821598,0.00004007608,0.000370988,0.00006562495,0.000116457,0.000001823179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002941489,"about_ca_system_score_gemma":0.00007605163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001506334,"about_ca_topic_score_gemma":9.823341e-7,"domain_scores_codex":[0.999046,0.00006905211,0.0001800255,0.0003542978,0.000158735,0.0001919127],"domain_scores_gemma":[0.9994805,0.0002034669,0.0000362044,0.0001396314,0.00009780783,0.00004234865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001435514,0.00005000552,0.0003655027,0.0001223491,0.00008446282,0.000006953688,0.001315308,0.01872277,0.002451989,0.02698679,0.000352991,0.9495265],"study_design_scores_gemma":[0.0004081205,0.00009399241,0.00112748,0.00006193875,0.00001924727,0.00001053634,0.00006490234,0.9655545,0.004541838,0.01751712,0.01047791,0.0001224114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01811398,0.0002229156,0.9785894,0.001509864,0.0002819003,0.0003799442,0.00000415681,0.0001323235,0.0007655493],"genre_scores_gemma":[0.2763015,0.00006808544,0.7210413,0.0004974563,0.00008090359,0.0001705332,0.00001501924,0.00001915244,0.001806054],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9494041,"threshold_uncertainty_score":0.3749796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009134015020651417,"score_gpt":0.282069606960737,"score_spread":0.2729355919400855,"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."}}