{"id":"W4401666005","doi":"10.1093/bioinformatics/btae517","title":"Spaln3: improvement in speed and accuracy of genome mapping and spliced alignment of protein query sequences","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; National Institute of Advanced Industrial Science and Technology","keywords":"Vectorization (mathematics); Computer science; SIMD; Genome; Multiple sequence alignment; Sequence (biology); Smith–Waterman algorithm; Dynamic programming; Sequence alignment; Alignment-free sequence analysis; Speedup; Computational biology; Reference genome; Parallel computing; Gene; Algorithm; Genetics; Biology; Peptide sequence","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":[],"consensus_categories":[],"category_scores_codex":[0.0001588877,0.00009048709,0.0001353079,0.00005447275,0.00001510005,0.00001417063,0.00005570843,0.00004697355,0.000001440026],"category_scores_gemma":[0.00002054476,0.00007679163,0.00002368492,0.0000533401,0.0000741941,0.000002164203,0.000132053,0.00002750754,3.435404e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007440864,"about_ca_system_score_gemma":0.00004005071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005279938,"about_ca_topic_score_gemma":0.00001255185,"domain_scores_codex":[0.9993977,0.000006621842,0.0003230531,0.00009839983,0.0000669751,0.0001072596],"domain_scores_gemma":[0.9997408,0.00001124085,0.00008998499,0.0001096744,0.00002263686,0.00002571321],"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":[0.00000913116,0.00001056397,0.0007471936,0.0006238727,0.00005100394,6.333719e-7,0.0008066496,0.00002080132,0.9907558,0.0001669312,0.000007721191,0.00679973],"study_design_scores_gemma":[0.001111682,0.001153573,0.03035698,0.0004766369,0.00004906324,0.00001725997,0.004933753,0.007076642,0.944015,0.0008656986,0.009425496,0.0005182809],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995193,0.003857106,0.0002118952,0.00006492886,0.00003001028,0.0003059359,0.00003332153,0.000001443752,0.0003023382],"genre_scores_gemma":[0.9941909,0.001366598,0.004338505,0.00003059123,0.00001998712,0.000007884224,0.000008663282,0.000005049605,0.00003185163],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04674083,"threshold_uncertainty_score":0.3131472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141013168155046,"score_gpt":0.2362441668756906,"score_spread":0.222142850060186,"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."}}