{"id":"W4406324461","doi":"10.1101/2025.01.08.632039","title":"Learning a CoNCISE language for small-molecule binding","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"National Science Foundation","keywords":"Chemistry; Computer science","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":[0.0009690698,0.0008192042,0.0007191292,0.0009434485,0.0002902751,0.001061366,0.001946735,0.0008140823,0.006682961],"category_scores_gemma":[0.005561836,0.0004294903,0.0006869026,0.001067669,0.0009306073,0.002956704,0.001534442,0.001550331,0.002743072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139544,"about_ca_system_score_gemma":0.001433451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003662824,"about_ca_topic_score_gemma":0.00512257,"domain_scores_codex":[0.9992169,0.0001765519,0.00007376135,0.0001924128,0.0002690239,0.00007124469],"domain_scores_gemma":[0.9982943,0.0007462946,0.0001818623,0.0004122574,0.0002706382,0.00009467942],"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":[0.0005565521,0.0002761208,0.002434193,0.0007815345,0.00005832324,0.0002448262,0.0002803344,0.2815681,0.03261859,0.2008502,0.05029068,0.4300405],"study_design_scores_gemma":[0.00002443565,0.00008636365,0.0001408188,0.00002739405,0.000009403871,0.00005242347,0.00002516529,0.9397889,0.00875079,0.04213268,0.008944585,0.00001711874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02339921,0.000476933,0.9616717,0.0006986161,0.0001681926,0.0001021551,0.00285858,0.007803109,0.002821672],"genre_scores_gemma":[0.5005962,0.0007799144,0.4793425,0.0006532746,0.0001889541,0.0004081382,0.008593561,0.0007936799,0.008643801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006682961,"threshold_uncertainty_score":0.02235675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01954981939050686,"score_gpt":0.2725172008137865,"score_spread":0.2529673814232796,"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."}}