{"id":"W3015317241","doi":"10.1101/2020.04.09.034785","title":"Choosing representative proteins based on splicing structure similarity improves the accuracy of gene tree reconstruction","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Gene; Computational biology; Homology (biology); Gene prediction; Tree (set theory); RNA splicing; Biology; Alignment-free sequence analysis; Similarity (geometry); Genetics; Alternative splicing; Gene family; Sequence alignment; Computer science; Genome; Artificial intelligence; Peptide sequence; Mathematics; Exon; Combinatorics; RNA","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":[0.001200071,0.0006502477,0.0007982022,0.001505245,0.0005275317,0.0009550159,0.0007563921,0.0008575664,0.0009172728],"category_scores_gemma":[0.003585845,0.0003557485,0.0006747664,0.001030418,0.0004547611,0.001269576,0.0006205181,0.0005681338,0.0006337418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003788932,"about_ca_system_score_gemma":0.0007474376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001124114,"about_ca_topic_score_gemma":0.001215099,"domain_scores_codex":[0.9991965,0.0001379647,0.00004961829,0.0002914508,0.000264344,0.00006017686],"domain_scores_gemma":[0.998605,0.0004310196,0.0002788368,0.0002042071,0.000401021,0.00007993585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005175426,0.0001828932,0.03360753,0.0003317093,0.0001988758,0.0004725731,0.0003088011,0.1539907,0.4461095,0.006532007,0.002058964,0.3556888],"study_design_scores_gemma":[0.00001569093,0.00006100854,0.003736412,0.00001294912,0.00003867188,0.0002419846,0.00007050318,0.9218459,0.07038417,0.002351703,0.001218939,0.00002209703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2191461,0.0003132166,0.7782509,0.000101723,0.00003232203,0.00004419752,0.00011931,0.001351781,0.0006404385],"genre_scores_gemma":[0.4806423,0.0002278952,0.5176314,0.00004510866,0.00002147568,0.00004292402,0.0005053841,0.0002201822,0.0006633672],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001505245,"threshold_uncertainty_score":0.006346643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01510460498128112,"score_gpt":0.2333245763671744,"score_spread":0.2182199713858932,"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."}}