{"id":"W4412597606","doi":"10.1038/s41570-025-00737-z","title":"Protein–ligand data at scale to support machine learning","year":2025,"lang":"en","type":"review","venue":"Nature Reviews Chemistry","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Structural Genomics Consortium","funders":"","keywords":"Scale (ratio); Computer science; Artificial intelligence; Machine learning; Physics","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":[0.001715412,0.0008040181,0.00130563,0.001661128,0.0001518535,0.001115459,0.001684389,0.0008870985,0.0037477],"category_scores_gemma":[0.004869011,0.0003889415,0.0005219305,0.001783351,0.0008974843,0.002011812,0.00100844,0.002135173,0.003173043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005458518,"about_ca_system_score_gemma":0.001049596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00109311,"about_ca_topic_score_gemma":0.0009887306,"domain_scores_codex":[0.999527,0.000113179,0.00002682839,0.00007602795,0.0002356075,0.00002145711],"domain_scores_gemma":[0.9972039,0.002087628,0.00008907611,0.0001851917,0.0003809395,0.000053212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005325903,0.00003731508,0.0002256219,0.003278485,0.0001153675,0.00004202446,0.00001186393,0.002107994,0.001334809,0.02267194,0.045422,0.9246994],"study_design_scores_gemma":[0.00004761746,0.00006278159,0.0007031262,0.002452909,0.0001689318,0.0004281872,0.000022109,0.008744666,0.003835203,0.06779194,0.9157016,0.00004080199],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001067187,0.9163506,0.061315,0.004760125,0.002385542,0.00007292932,0.001178213,0.0006583889,0.01221201],"genre_scores_gemma":[0.01371394,0.9199283,0.05535806,0.002375138,0.002377019,0.0001622292,0.001891225,0.0001654112,0.004028692],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.0037477,"threshold_uncertainty_score":0.0125373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05662245175390041,"score_gpt":0.4051873602277247,"score_spread":0.3485649084738243,"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."}}