{"id":"W2049268173","doi":"10.1186/1471-2105-8-444","title":"Insertions and the emergence of novel protein structure: a structure-based phylogenetic study of insertions","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic","keywords":"Phylogenetic tree; Biology; Protein domain; Domain (mathematical analysis); Computational biology; Inference; Similarity (geometry); Variable (mathematics); Protein structure; Genetics; Evolutionary biology; Phylogenetics; Structural similarity; Insert (composites); Sequence alignment; Structural alignment; Computer science; Artificial intelligence; Gene; Peptide sequence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00113524,0.000255964,0.0003496485,0.002334918,0.0006791652,0.0005711621,0.0004765833,0.0006221333,0.0005181452],"category_scores_gemma":[0.002859573,0.0002387085,0.0005825934,0.002067561,0.0006532018,0.0007564844,0.0006475319,0.0005798949,0.0001643259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005755731,"about_ca_system_score_gemma":0.0003801249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001087162,"about_ca_topic_score_gemma":0.0009615963,"domain_scores_codex":[0.9996069,0.0001319394,0.00003102889,0.000109517,0.00007999195,0.00004069183],"domain_scores_gemma":[0.9988371,0.0005447318,0.0002853043,0.0001023569,0.0001318628,0.0000987621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009307542,0.0004333996,0.4674718,0.0006490472,0.0004267198,0.001939607,0.002975847,0.1611308,0.1984479,0.01781102,0.000667901,0.1471151],"study_design_scores_gemma":[0.00004072907,0.0005297359,0.2277865,0.0001370244,0.0002529431,0.002544316,0.000870693,0.730592,0.01788233,0.01438779,0.00488453,0.00009129585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9433041,0.0007547241,0.05485872,0.0001221861,0.000006180532,0.00003784948,0.00021138,0.00006735062,0.0006375021],"genre_scores_gemma":[0.9463252,0.000403782,0.05236628,0.0000336275,0.00001033331,0.00003010153,0.0006662433,0.00002917007,0.0001351278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002334918,"threshold_uncertainty_score":0.006003797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01072581265033013,"score_gpt":0.2445396766541216,"score_spread":0.2338138640037915,"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."}}