{"id":"W3192540610","doi":"10.1002/wcms.1567","title":"Featurization strategies for protein–ligand interactions and their applications in scoring function development","year":2021,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Computational Molecular Science","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"SKiN Health","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Context (archaeology); Machine learning; Workflow; Function (biology); Representation (politics); Protein ligand; Similarity (geometry); Protein function prediction; Protein function; Chemistry; Biology; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009407419,0.0002321455,0.0002735527,0.0003627812,0.000569072,0.0005706915,0.0005420945,0.00003300085,0.000002273135],"category_scores_gemma":[0.0001086783,0.000212876,0.00008655562,0.001642064,0.0001650336,0.001668327,0.000952123,0.000153994,0.00000621041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001977958,"about_ca_system_score_gemma":0.0009562808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000125667,"about_ca_topic_score_gemma":0.0000135855,"domain_scores_codex":[0.9978238,0.0001580598,0.0005686373,0.0008512848,0.0003148882,0.0002833792],"domain_scores_gemma":[0.9987102,0.0002143385,0.0002028326,0.0003351246,0.0004277934,0.0001097045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001879225,0.0003087105,0.0001374629,0.000304734,0.00003144717,0.00001026545,0.003919417,0.1600871,0.0546441,0.5359498,0.00003960494,0.2445486],"study_design_scores_gemma":[0.0004570716,0.00009140825,0.007422647,0.000818198,0.0000106345,0.00008400463,0.0007110563,0.4850848,0.01008765,0.4917198,0.002980654,0.0005320915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0810844,0.001788626,0.9150517,0.0005363347,0.0002121068,0.001036906,0.000004115725,0.00005185916,0.0002339743],"genre_scores_gemma":[0.6950578,0.0000131628,0.3040542,0.0001235807,0.00002615241,0.0006387209,0.00005355017,0.00001009724,0.00002274802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6139734,"threshold_uncertainty_score":0.8680833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02956596307353733,"score_gpt":0.3389647901228054,"score_spread":0.3093988270492681,"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."}}