{"id":"W4415270618","doi":"10.17615/d4ft-pp53","title":"Discovery of a First-in-Class Small-Molecule Ligand for WDR91 Using DNA-Encoded Chemical Library Selection Followed by Machine Learning","year":2025,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Office of Science; Genentech; Ontario Genomics; National Institutes of Health; Ontario Genomics Institute; European Federation of Pharmaceutical Industries and Associations; Merck KGaA; Office of Research Infrastructure Programs, National Institutes of Health; Genome Canada; Argonne National Laboratory; U.S. Department of Energy; McGill University; Bayer; Pfizer; Bristol-Myers Squibb","keywords":"Endosome; Covalent bond; Drug discovery; Linker; Selection (genetic algorithm); Ligand (biochemistry); Adduct; Domain (mathematical analysis); Chemical space","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006357207,0.0001609532,0.0002739397,0.00006679402,0.00007391541,0.00008801148,0.0001586583,0.0001753824,0.000009795443],"category_scores_gemma":[0.0002002884,0.0001492036,0.0001921156,0.0002760495,0.0000763515,0.00003352424,0.0001432702,0.00009241356,1.823776e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001194509,"about_ca_system_score_gemma":0.00008539523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004484225,"about_ca_topic_score_gemma":0.0000246556,"domain_scores_codex":[0.9990601,0.00003057943,0.0003024194,0.0003307715,0.00006779173,0.0002083188],"domain_scores_gemma":[0.9996307,0.00007996777,0.0001009517,0.0001357527,0.00001914424,0.00003344267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002315452,0.00008844867,0.02803904,0.00008233673,0.0001186706,3.786608e-7,0.00001830844,0.00003912546,0.9692378,0.0006045991,0.001434054,0.0001057005],"study_design_scores_gemma":[0.0005267494,0.00004744779,0.00004109822,0.00006247784,0.00006862607,5.592204e-7,0.00003314075,0.004201475,0.9891074,0.0007329525,0.005022517,0.0001555237],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911759,0.001424955,0.006292462,0.0003658757,0.00003165639,0.0001298881,0.00003820341,0.00001973244,0.0005213259],"genre_scores_gemma":[0.9933363,0.00007046117,0.003638966,0.0001080731,0.00006647208,0.00002156479,0.0003565439,0.00002538911,0.002376248],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02799794,"threshold_uncertainty_score":0.6084348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006938538064976426,"score_gpt":0.2076651212201104,"score_spread":0.2007265831551339,"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."}}