{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002209934,0.0001714194,0.0002148459,0.00008109184,0.0001043758,0.00001113096,0.0002526189,0.0001357914,0.000007416581],"category_scores_gemma":[0.0001472783,0.0001171906,0.00006454951,0.0002416419,0.0002925412,0.000006859972,0.0001112556,0.0001050518,1.36938e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004724438,"about_ca_system_score_gemma":0.0001108797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005201104,"about_ca_topic_score_gemma":0.001051875,"domain_scores_codex":[0.9988205,0.00003426376,0.0006090766,0.0001361841,0.0002133945,0.0001865305],"domain_scores_gemma":[0.9989179,0.00002806364,0.0003439169,0.0004946606,0.000160631,0.00005487989],"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":[0.00118853,0.0004488259,0.02193962,0.0005643413,0.0002195262,4.548723e-7,0.002454818,0.01065501,0.9570301,0.002544685,0.00005604201,0.002898085],"study_design_scores_gemma":[0.02035202,0.003091444,0.1201211,0.0001248227,0.000403634,0.00005247721,0.007113643,0.1332707,0.7119277,0.00209031,0.0003960655,0.001056175],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8765431,0.0001269356,0.1221396,0.00001405026,0.00005419632,0.0009306642,0.0001114012,0.000005928412,0.00007410658],"genre_scores_gemma":[0.9509578,0.000005823087,0.04885769,0.00007113273,0.00003030125,0.00001259924,0.0000437965,0.00001107213,0.000009797126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2451024,"threshold_uncertainty_score":0.4778894,"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."}}