{"id":"W4413159620","doi":"10.1101/2025.08.12.670002","title":"FragDockRL: A Reinforcement Learning Method for Fragment-Based Ligand Design via Building Block Assembly and Tethered Docking","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"National Research Foundation of Korea","keywords":"Docking (animal); Fragment (logic); Block (permutation group theory); Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Engineering; Mathematics; Algorithm; Structural engineering; Combinatorics","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":[0.0008806725,0.0009182981,0.0009154537,0.0004600938,0.0002719992,0.0004621613,0.001815372,0.00111647,0.004557089],"category_scores_gemma":[0.001697348,0.0005492909,0.0005949827,0.0003265805,0.0005274292,0.0005379948,0.0008820969,0.001214438,0.0008103437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008924634,"about_ca_system_score_gemma":0.001268067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004837065,"about_ca_topic_score_gemma":0.005555578,"domain_scores_codex":[0.9997526,0.00007729791,0.00001128246,0.00004905592,0.0000742593,0.00003551602],"domain_scores_gemma":[0.9994895,0.000291277,0.00005748546,0.00004621665,0.00007020344,0.00004537554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009843947,0.00005439041,0.0003915579,0.00008489817,0.00003506047,0.00008094052,0.00002155076,0.9248117,0.003458366,0.004096115,0.001443886,0.06542303],"study_design_scores_gemma":[0.00001517442,0.00001919622,0.00001458889,0.000002376779,0.000002450015,0.000006037226,0.000001138546,0.9987229,0.0003981151,0.0005255754,0.0002905203,0.000002037328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02004442,0.000349994,0.9731413,0.0001345632,0.00003775741,0.00009443887,0.0001110605,0.003746517,0.002340145],"genre_scores_gemma":[0.5047122,0.000207083,0.4896095,0.0003329071,0.00003307301,0.00048532,0.0003152628,0.0005346469,0.00377006],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004837065,"threshold_uncertainty_score":0.01524502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334834923007593,"score_gpt":0.2893935850629594,"score_spread":0.2660452358328835,"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."}}