{"id":"W4385373960","doi":"10.1093/bib/bbad289","title":"Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models","year":2023,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Bristol-Myers Squibb Canada; Michigan State University Foundation; Nuclear Safety and Security Commission; Bristol-Myers Squibb; National Aeronautics and Space Administration; National Institutes of Health; National Science Foundation; Michigan Economic Development Corporation; National Institute of Allergy and Infectious Diseases; Pfizer","keywords":"Computer science; Artificial intelligence; Topological data analysis; Protein engineering; Natural language processing; Computational biology; Biology; Algorithm","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":[0.0007436334,0.0009120913,0.001144087,0.00187125,0.00016079,0.001256672,0.0009992155,0.0008413158,0.001950429],"category_scores_gemma":[0.001368099,0.0003902685,0.000728522,0.002294444,0.0005658344,0.001872399,0.0008027251,0.001763023,0.001424729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005652983,"about_ca_system_score_gemma":0.0009136552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009474665,"about_ca_topic_score_gemma":0.001092422,"domain_scores_codex":[0.9997858,0.00005140922,0.00002309306,0.00004527356,0.00007882487,0.00001557184],"domain_scores_gemma":[0.9995577,0.0003068497,0.00003340074,0.00001682485,0.00007016646,0.00001502811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002317143,0.00005023435,0.0002132126,0.01003546,0.0001261274,0.0001097203,0.00006267573,0.003287839,0.001844703,0.02525062,0.0146375,0.9443587],"study_design_scores_gemma":[0.00002073632,0.0001335717,0.0007429011,0.005124612,0.0002118743,0.001015108,0.00008395471,0.009004879,0.003863022,0.04139035,0.9383099,0.00009906935],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004735503,0.9789027,0.01643542,0.0008988417,0.0002969351,0.00001949605,0.00009054628,0.0001132566,0.002769202],"genre_scores_gemma":[0.003221398,0.9865887,0.008710716,0.0002507852,0.0002103065,0.00002648275,0.0001405272,0.0000162224,0.0008349867],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.001950429,"threshold_uncertainty_score":0.006524861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08793799256485617,"score_gpt":0.3524052727944185,"score_spread":0.2644672802295623,"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."}}