{"id":"W2572737325","doi":"10.1109/bibm.2016.7822641","title":"Mining sequential patterns from uncertain big DNA in the spark framework","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Scalability; Data mining; SPARK (programming language); DNA sequencing; Biomedicine; Data science; Bioinformatics; DNA; Database; Biology","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":[0.0002364706,0.00008476647,0.00007782441,0.00003778833,0.00007277964,0.0001711586,0.001239589,0.00004636791,0.00007278343],"category_scores_gemma":[0.0000409832,0.00004361556,0.00002771181,0.0002078445,0.00002706723,0.0001840522,0.0001973311,0.00007511653,0.0001037232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001856839,"about_ca_system_score_gemma":0.0000310646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006894109,"about_ca_topic_score_gemma":0.0001621296,"domain_scores_codex":[0.9990936,0.00005472877,0.0001536768,0.0003159918,0.0001796092,0.000202431],"domain_scores_gemma":[0.998714,0.000455066,0.00004055153,0.0007385777,0.00001408113,0.00003776902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001205137,0.00005867513,0.005317895,0.000001310987,0.000009467341,0.00001618139,0.001775982,0.000002780962,0.0006544523,0.0656383,0.003330997,0.9231927],"study_design_scores_gemma":[0.003126716,0.0003425963,0.2576998,0.001339147,0.00005158964,0.00006161488,0.003626303,0.1404879,0.01512963,0.3087883,0.2666977,0.002648656],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1328941,0.0000104051,0.8594515,0.006560422,0.0001908091,0.00006651799,0.00003147703,0.00006086467,0.0007339161],"genre_scores_gemma":[0.8308824,0.00000950418,0.1674288,0.001194184,0.000252138,0.00004296741,0.000008297518,0.000005249541,0.0001764549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9205441,"threshold_uncertainty_score":0.2303486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0452226995074654,"score_gpt":0.2825070435540311,"score_spread":0.2372843440465657,"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."}}