{"id":"W4413807406","doi":"10.1186/s13321-025-01073-6","title":"FusionCLM: enhanced molecular property prediction via knowledge fusion of chemical language models","year":2025,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children’s Health Research Institute; Western University; Lawson Health Research Institute; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Property (philosophy); Artificial intelligence; Ensemble learning; Inference; Machine learning; Representation (politics); Feature (linguistics); Feature learning; Deep learning; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0006200328,0.0001189306,0.0002758824,0.0002069362,0.00002684755,0.00003793825,0.0006403869,0.0000796187,0.000004971604],"category_scores_gemma":[0.0001809544,0.00008283663,0.0001450479,0.0004674325,0.00003829422,0.0008877436,0.0003202023,0.0002128971,0.000001991616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009932482,"about_ca_system_score_gemma":0.0003779311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001049926,"about_ca_topic_score_gemma":7.460952e-8,"domain_scores_codex":[0.9984515,0.00002654486,0.0008713493,0.00008244756,0.0004331051,0.0001350842],"domain_scores_gemma":[0.9984957,0.0001560565,0.0005071478,0.0002621867,0.0005085022,0.00007042393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005956923,0.0002687706,0.000004415237,0.000456526,0.00008462689,0.000006249261,0.00931282,0.02470787,0.7235529,0.005646149,0.001579843,0.2343202],"study_design_scores_gemma":[0.0003161971,0.00003275232,0.000008271265,0.0001652397,0.00001509261,0.00002325026,0.00007259229,0.4585054,0.5348874,0.005825244,0.00009654317,0.00005201657],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.165051,0.0001842724,0.8198065,0.0001354183,0.0002487816,0.00009171663,0.000001903629,0.00001751657,0.01446282],"genre_scores_gemma":[0.8475435,0.00001993267,0.1521616,0.000100149,0.00003965473,0.000002197278,0.000002727241,0.000004718666,0.0001255717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6824924,"threshold_uncertainty_score":0.337798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009688278155474715,"score_gpt":0.2810880372370465,"score_spread":0.2713997590815717,"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."}}