{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00188428,0.001022283,0.0009898867,0.0007781145,0.0003241443,0.001746133,0.001380662,0.001026797,0.002271123],"category_scores_gemma":[0.004709742,0.000512028,0.001072879,0.0006723566,0.0006757337,0.001539786,0.001838204,0.001521144,0.001484661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009969752,"about_ca_system_score_gemma":0.001178836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001593142,"about_ca_topic_score_gemma":0.001773531,"domain_scores_codex":[0.9989034,0.0002842757,0.00006102843,0.0002664097,0.0003828941,0.0001020234],"domain_scores_gemma":[0.9983152,0.0008853501,0.0001595186,0.0003308755,0.0002226689,0.00008644641],"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":[0.0009964023,0.0007842208,0.01048112,0.0004896281,0.0002747335,0.0003880268,0.000148019,0.6450949,0.1102779,0.01316721,0.006332199,0.2115657],"study_design_scores_gemma":[0.00003507573,0.0001125975,0.0003665426,0.000009811684,0.00001557688,0.00003380097,0.00001189542,0.9467126,0.04444238,0.005921262,0.002319434,0.00001905658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1697523,0.0007027552,0.7861024,0.0006224594,0.00008063989,0.0001954326,0.002226657,0.03534375,0.004973721],"genre_scores_gemma":[0.6257131,0.0007576607,0.3607329,0.000678355,0.00006240122,0.0004461824,0.006759792,0.001016521,0.00383307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9986193,"threshold_uncertainty_score":0.009965181,"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."}}