{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001728971,0.0009932583,0.001425105,0.001726702,0.001270986,0.001252377,0.002098536,0.0005994085,0.0007026051],"category_scores_gemma":[0.004100866,0.0004073913,0.001242589,0.003029061,0.0006299456,0.001518851,0.001542081,0.0009489002,0.0004942361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005790344,"about_ca_system_score_gemma":0.00216636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004517562,"about_ca_topic_score_gemma":0.005636499,"domain_scores_codex":[0.9987199,0.0001867531,0.0001080255,0.0003376897,0.0005127692,0.0001349229],"domain_scores_gemma":[0.9982863,0.0005550269,0.0001377267,0.0003154289,0.0004630468,0.0002424932],"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":[0.002679537,0.001353539,0.02194173,0.00100115,0.0007076684,0.001311412,0.0011945,0.2856515,0.07329198,0.02090021,0.02839156,0.5615751],"study_design_scores_gemma":[0.00010416,0.0001700277,0.001648393,0.000009707515,0.00003894113,0.0002868382,0.0002117559,0.9600706,0.01400997,0.0187232,0.004703118,0.00002329934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1265039,0.0008453299,0.8583182,0.0006611087,0.000184608,0.0003874992,0.001579771,0.009433025,0.00208645],"genre_scores_gemma":[0.3914608,0.0004153922,0.6011057,0.0001537314,0.00009474735,0.0002781216,0.004686172,0.0002968141,0.001508403],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004517562,"threshold_uncertainty_score":0.00914377,"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."}}