{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006870319,0.001595952,0.000647273,0.001104697,0.0002636264,0.0006562371,0.0008623933,0.0006191428,0.001874781],"category_scores_gemma":[0.002243325,0.0002584764,0.000616747,0.001241729,0.0003733551,0.001712648,0.000851132,0.001228972,0.001956215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005765123,"about_ca_system_score_gemma":0.0008332526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004361602,"about_ca_topic_score_gemma":0.01047586,"domain_scores_codex":[0.9994612,0.0001878721,0.00003799732,0.0001316783,0.000120447,0.00006073159],"domain_scores_gemma":[0.9992288,0.0003123431,0.00007702414,0.000162889,0.000174798,0.00004415475],"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":[0.0009019608,0.0007348087,0.01034135,0.0004769964,0.0002887972,0.0002800908,0.0002031673,0.2685496,0.01661576,0.01024423,0.04921355,0.6421497],"study_design_scores_gemma":[0.00002570337,0.0001184335,0.0007126862,0.00001435861,0.00001815737,0.00004561973,0.00003929614,0.986541,0.004687879,0.004965429,0.002816696,0.00001486264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3957406,0.003642521,0.558745,0.001365068,0.0005732203,0.0002431117,0.01318722,0.01975419,0.006749084],"genre_scores_gemma":[0.7596805,0.0008907915,0.1931216,0.0004509733,0.0001555469,0.0002995439,0.03889731,0.0005572273,0.005946533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004361602,"threshold_uncertainty_score":0.008672416,"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."}}