{"id":"W2889202450","doi":"10.1016/j.procs.2018.07.294","title":"Spark-based data analytics of sequence motifs in large omics data","year":2018,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Tertiary Education Trust Fund","keywords":"Computer science; SPARK (programming language); Analytics; DNA sequencing; Genomics; Sequence motif; Data mining; Sequence (biology); Computational biology; Bioinformatics; Data science; Genome; DNA; Biology; Genetics; Gene","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002200961,0.0001542314,0.0002075186,0.0002922923,0.0001908273,0.0003229391,0.01609488,0.00004011249,0.000003035937],"category_scores_gemma":[0.0002264674,0.0001471466,0.00001399143,0.003091618,0.0006851757,0.002630357,0.007270487,0.0001438094,0.00003261877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004455222,"about_ca_system_score_gemma":0.001051975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005570951,"about_ca_topic_score_gemma":0.00006634786,"domain_scores_codex":[0.9970412,0.00002254176,0.0004051226,0.001407739,0.0006078723,0.0005155496],"domain_scores_gemma":[0.9938845,0.0001149683,0.0001949194,0.005336906,0.0003159971,0.0001527128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001761375,0.00194307,0.04762023,0.0002607377,0.00003481569,0.00004868372,0.003045149,0.002193237,0.005389464,0.09481479,0.01229849,0.8323337],"study_design_scores_gemma":[0.0002031307,0.00005596128,0.004354504,0.00003879208,0.000003639791,0.000007621317,0.000005038491,0.9913809,0.001249435,0.000493005,0.002038783,0.0001691378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007360032,0.0000247891,0.9909424,0.0006159956,0.0003496968,0.0001657728,0.0003600975,0.00008467522,0.00009655973],"genre_scores_gemma":[0.358826,0.000006482926,0.6405846,0.0003383543,0.000129221,0.000003692664,0.000101868,0.000005409907,0.00000439842],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9891877,"threshold_uncertainty_score":0.9892285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1264789377452514,"score_gpt":0.3419665985896255,"score_spread":0.2154876608443741,"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."}}