{"id":"W17603131","doi":"10.1123/jab.23.2.119","title":"Long spaced seeds for finding similarities between biological sequences.","year":2007,"lang":"en","type":"article","venue":"BIOCOMP","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Sensitivity (control systems); Homology (biology); Measure (data warehouse); Mathematics; Algorithm; Fraction (chemistry); Computer science; Biology; Data mining; Genetics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005767397,0.0001340033,0.0001838818,0.00009569863,0.0002312031,0.0001369106,0.0007410677,0.0001156756,0.000009906887],"category_scores_gemma":[0.0000339257,0.0001027264,0.00007217424,0.0002083274,0.00006882157,0.000292148,0.0003415341,0.00009892401,0.00001608438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003465638,"about_ca_system_score_gemma":0.00002944771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002606151,"about_ca_topic_score_gemma":0.00000465733,"domain_scores_codex":[0.9988577,0.00002318469,0.0002115244,0.0003496317,0.0001662818,0.0003916397],"domain_scores_gemma":[0.9991377,0.0003017671,0.00007494559,0.0003260147,0.00004945074,0.0001101097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007787458,0.0002572478,0.2775196,0.0001625709,0.0001428693,0.0001625106,0.001544228,0.0000752312,0.01628596,0.1109009,0.01755378,0.5753173],"study_design_scores_gemma":[0.002250246,0.0009239923,0.7047239,0.0002551006,0.000028101,0.0000512883,0.0003018246,0.02652706,0.07494798,0.01966398,0.1686016,0.001724936],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07064436,0.0001759093,0.9276822,0.0003603594,0.0003138555,0.00023051,0.00002795204,0.0001783544,0.0003864919],"genre_scores_gemma":[0.8191267,0.000009467739,0.1800397,0.0001921311,0.0004331554,0.00001084209,0.00004484503,0.000006903826,0.0001362918],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7484823,"threshold_uncertainty_score":0.4189061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07917843696535799,"score_gpt":0.3195760883791828,"score_spread":0.2403976514138249,"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."}}