{"id":"W4391685687","doi":"10.1038/s41597-023-02872-y","title":"PLAS-20k: Extended Dataset of Protein-Ligand Affinities from MD Simulations for Machine Learning Applications","year":2024,"lang":"en","type":"article","venue":"Scientific Data","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Engineering Research Board; International Institute of Information Technology, Hyderabad; Indian Institute of Technology Delhi; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Binding affinities; Affinities; Drug discovery; Computer science; Docking (animal); Pipeline (software); Artificial intelligence; Machine learning; Computational biology; Chemistry; Stereochemistry; Biology; Biochemistry","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":[0.00127266,0.002207999,0.001568543,0.001445773,0.0008650874,0.001215027,0.00390818,0.002775804,0.007827664],"category_scores_gemma":[0.003913065,0.0007388199,0.001837317,0.002144942,0.0005871271,0.001399407,0.001343551,0.002739111,0.003892191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001138761,"about_ca_system_score_gemma":0.002238484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008546884,"about_ca_topic_score_gemma":0.01383938,"domain_scores_codex":[0.9992501,0.0001908162,0.00008732086,0.0001699089,0.0002191456,0.00008261225],"domain_scores_gemma":[0.9987948,0.0004467223,0.0001160329,0.0002587199,0.0002444893,0.0001391573],"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":[0.001976291,0.001436265,0.0181091,0.00601357,0.0011207,0.000799556,0.0001698156,0.4531794,0.01305133,0.008473172,0.4485694,0.04710127],"study_design_scores_gemma":[0.001278758,0.0007200654,0.01627412,0.0002937553,0.00023412,0.0005367235,0.0001616529,0.7690586,0.01633301,0.01245108,0.1824054,0.0002527053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1875742,0.004014333,0.02720374,0.001474838,0.0006977604,0.0004092458,0.7395621,0.02564108,0.01342278],"genre_scores_gemma":[0.1403556,0.0009277819,0.02729029,0.0004694068,0.00007195094,0.0007708464,0.8271172,0.001524575,0.001472324],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.008546884,"threshold_uncertainty_score":0.02618617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0871256239288214,"score_gpt":0.3650666403697066,"score_spread":0.2779410164408852,"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."}}