{"id":"W4403553112","doi":"10.26434/chemrxiv-2024-xd385","title":"Enabling Open Machine Learning of DNA Encoded Library Selections to Accelerate the Discovery of Small Molecule Protein Binders","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Innovative Medicines Initiative; National Institute of Health Sciences","keywords":"Computer science; DNA; Computational biology; Small molecule; Nanotechnology; Chemistry; Biology; Biochemistry; Materials science","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":[0.0003613578,0.0002768197,0.0005827813,0.0002595586,0.0001089715,0.0001787407,0.0007368251,0.0001738751,0.0002118598],"category_scores_gemma":[0.0001614904,0.0001815158,0.0002625966,0.0006005786,0.0001339786,0.00008442502,0.003673146,0.001538599,0.00002576991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728333,"about_ca_system_score_gemma":0.0007043014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009879199,"about_ca_topic_score_gemma":0.00002873535,"domain_scores_codex":[0.998233,0.0001126162,0.0004801774,0.000500723,0.0003519871,0.0003214553],"domain_scores_gemma":[0.9990122,0.0001141417,0.0001664795,0.0004558281,0.0001138946,0.0001374161],"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":[0.001051426,0.000252162,0.002448004,0.004771247,0.000769399,0.00005954095,0.00111994,0.0006140723,0.984793,0.001098697,0.001574319,0.001448197],"study_design_scores_gemma":[0.0002737952,0.0002432786,0.0005218914,0.001950178,0.0001160898,0.00001249566,0.0001684059,0.002531779,0.9891348,0.001206563,0.003627233,0.0002135006],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760615,0.001597989,0.0001523567,0.007623036,0.0001072549,0.001761045,0.00003581584,0.00005104657,0.01260991],"genre_scores_gemma":[0.9459004,0.0003365032,0.001001955,0.0002231033,0.0001948046,0.0002311807,0.0001724094,0.00007291285,0.05186667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03925675,"threshold_uncertainty_score":0.7402001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06029499609277507,"score_gpt":0.3208519509255113,"score_spread":0.2605569548327363,"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."}}