{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009526258,0.000746408,0.001639092,0.0007406719,0.00008151499,0.0002254931,0.002148617,0.0009091995,0.00004377614],"category_scores_gemma":[0.001615425,0.0006641797,0.0004223166,0.001753305,0.00008070757,0.00004021627,0.002077955,0.0007920215,0.0002487048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009004574,"about_ca_system_score_gemma":0.0002142516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003676045,"about_ca_topic_score_gemma":0.0002973193,"domain_scores_codex":[0.9957688,0.00010477,0.002229529,0.000690665,0.0004946404,0.0007115305],"domain_scores_gemma":[0.9967106,0.00009972414,0.0006926263,0.002203423,0.00006822196,0.0002253884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005133208,0.0001736085,0.000003363954,0.01080147,0.002423106,0.00004831041,0.001787795,0.02152747,0.0000740876,0.002504821,0.0007155444,0.9598891],"study_design_scores_gemma":[0.0001324859,0.0002351787,0.000002907473,0.004113905,0.001344774,0.00001723632,0.0003927659,0.6442308,0.000241463,0.0006495393,0.3466512,0.001987748],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.001115596,0.4356805,0.5528654,0.0002650018,0.0002716141,0.006450762,0.002124841,0.0004419897,0.0007843237],"genre_scores_gemma":[0.0002772762,0.498168,0.47043,0.0006328632,0.0007419036,0.0009189324,0.02792231,0.0003110139,0.0005976589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9579014,"threshold_uncertainty_score":0.9995809,"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."}}