{"id":"W4288077714","doi":"10.1101/2022.07.25.501437","title":"TM-Vec: template modeling vectors for fast homology detection and alignment","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Division of Chemical, Bioengineering, Environmental, and Transport Systems; National Institute of Child Health and Human Development; Flatiron Health; University of California, San Diego; National Institutes of Health; National Science Foundation","keywords":"Structural alignment; Sequence alignment; Homology modeling; Sequence (biology); Similarity (geometry); Computer science; Sequence homology; Homology (biology); Alignment-free sequence analysis; Computational biology; Protein structure database; Loop modeling; Structural similarity; Structural Classification of Proteins database; Protein superfamily; Multiple sequence alignment; Protein structure; Artificial intelligence; Smith–Waterman algorithm; Pattern recognition (psychology); Peptide sequence; Protein structure prediction; Biology; Sequence database; Genetics; Image (mathematics); Amino acid; Gene","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":[],"consensus_categories":[],"category_scores_codex":[0.001203302,0.00153978,0.000765133,0.001150852,0.0003824375,0.001505529,0.002065858,0.001357582,0.01494648],"category_scores_gemma":[0.005153676,0.0007139981,0.0008889921,0.001476212,0.0005301805,0.002193577,0.001495998,0.002010332,0.007480269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008032037,"about_ca_system_score_gemma":0.001085225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003347043,"about_ca_topic_score_gemma":0.003277332,"domain_scores_codex":[0.9991401,0.0002213138,0.00007276505,0.0002018389,0.0002941841,0.0000697443],"domain_scores_gemma":[0.9989005,0.000404033,0.0001014815,0.000223874,0.0002976721,0.00007237946],"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":[0.0009101557,0.0001961237,0.001726877,0.0004775314,0.0002200211,0.0002378573,0.0001609283,0.1708633,0.02483221,0.04129916,0.1285719,0.630504],"study_design_scores_gemma":[0.00003637743,0.00003725576,0.0001479387,0.00001627992,0.000006716767,0.00006151206,0.00001561624,0.9735665,0.007845245,0.009729685,0.00852289,0.00001402285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004765233,0.0001868965,0.963191,0.0001277197,0.00008678714,0.00005516568,0.001753555,0.02906247,0.0007711735],"genre_scores_gemma":[0.09834325,0.0002934184,0.8800188,0.0001792976,0.00006765701,0.000418214,0.01306179,0.003978265,0.003639308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01494648,"threshold_uncertainty_score":0.05000097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01410022736592547,"score_gpt":0.2194795343695585,"score_spread":0.205379307003633,"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."}}