{"id":"W4206681893","doi":"10.26434/chemrxiv.11749854.v2","title":"Enhancing a De Novo Enzyme Activity by Computationally-Focused, Ultra-Low-Throughput Sequence Screening","year":2020,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Enzyme Catalysis and Immobilization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Knut och Alice Wallenbergs Stiftelse; Ministerio de Ciencia, Innovación y Universidades","keywords":"Directed evolution; Active site; Protein engineering; Folding (DSP implementation); Computational biology; Sequence space; Stability (learning theory); Directed Molecular Evolution; Protein stability; Ranking (information retrieval); Protein folding; Chemistry; Computer science; Protein design; Sequence (biology); Enzyme; Protein structure; Biology; Mathematics; Machine learning; Biochemistry; Gene; Mutant; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002464226,0.0003719385,0.0003600035,0.00003749551,0.0001148221,0.00009774447,0.0004062733,0.0004929,0.00002944408],"category_scores_gemma":[0.0002550691,0.0004194479,0.0002352352,0.0001429433,0.0001003789,0.00001037152,0.0003420778,0.000416239,0.0000138128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007526347,"about_ca_system_score_gemma":0.0003172921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004079662,"about_ca_topic_score_gemma":0.00001901467,"domain_scores_codex":[0.9980434,0.00008728149,0.0003391337,0.000949364,0.0002359032,0.0003449776],"domain_scores_gemma":[0.9988257,0.00003458083,0.0002949531,0.0005085571,0.0001741234,0.0001620556],"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":[0.00003962779,0.00006170136,0.000238936,0.0001837393,0.0001257459,0.000005031311,0.0001146443,0.002155838,0.994268,0.00001353998,0.002067042,0.0007261775],"study_design_scores_gemma":[0.0003401249,0.00004260176,0.0001706837,0.0001179057,0.00005374097,0.00001046027,0.00002437488,0.00161128,0.9940887,0.000088286,0.003009515,0.0004423358],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6658414,0.0007102786,0.3323691,0.0003500744,0.0001135633,0.0002340507,0.00005232291,0.00004756344,0.0002816256],"genre_scores_gemma":[0.9893396,0.0002211566,0.00589288,0.0006545952,0.000450647,0.00007136479,0.003075853,0.0000641584,0.0002296676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3264762,"threshold_uncertainty_score":0.9998257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02469511157357157,"score_gpt":0.2761219547140096,"score_spread":0.2514268431404381,"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."}}