{"id":"W3194384536","doi":"10.1101/2021.08.13.456323","title":"Machine-learning-guided library design cycle for directed evolution of enzymes: the effects of training data composition on sequence space exploration","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biochemical and Structural Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bio-oriented Technology Research Advancement Institution; Japan Society for the Promotion of Science; Institute of Genetics; National Agriculture and Food Research Organization; Ministry of Economy, Trade and Industry; National Institute of Advanced Industrial Science and Technology","keywords":"Directed evolution; Sequence space; Sequence (biology); Directed Molecular Evolution; Composition (language); Series (stratigraphy); Protein engineering; Function (biology); Protein sequencing; Chemical space; Computer science; Enzyme; Training (meteorology); Computational biology; Artificial intelligence; Biology; Bioinformatics; Genetics; Mathematics; Peptide sequence; Biochemistry; Gene; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001594321,0.0007391527,0.0008986258,0.0004158603,0.0003391036,0.0007904819,0.0007679632,0.0005699527,0.0007616621],"category_scores_gemma":[0.004329343,0.0003391752,0.0003891456,0.0004828824,0.0005071592,0.0007884575,0.0007044493,0.00119392,0.0002424789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004899479,"about_ca_system_score_gemma":0.0005422384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007576304,"about_ca_topic_score_gemma":0.001098961,"domain_scores_codex":[0.9992629,0.0002387993,0.00006839823,0.0001587811,0.0001874561,0.00008361933],"domain_scores_gemma":[0.998539,0.000800255,0.0002034282,0.0001669764,0.0001972457,0.00009314402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001053965,0.001514462,0.006804483,0.000440945,0.0001337726,0.0001769452,0.0001748352,0.2154559,0.682995,0.001426798,0.0003458391,0.08947694],"study_design_scores_gemma":[0.00005963963,0.00104285,0.001674073,0.00002852963,0.00005926118,0.00009974222,0.00003671286,0.4866141,0.5088708,0.0004205266,0.001047128,0.00004652182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9443985,0.000622543,0.05330696,0.0001243666,0.00002537207,0.0001028826,0.00006925349,0.0004453188,0.0009048572],"genre_scores_gemma":[0.9585935,0.000231143,0.0405587,0.00007306767,0.000006766583,0.00007973574,0.0001291559,0.00007029075,0.0002575288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001594321,"threshold_uncertainty_score":0.008431673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03215822108169192,"score_gpt":0.2377377466687156,"score_spread":0.2055795255870236,"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."}}