{"id":"W4384924247","doi":"10.1371/journal.pcbi.1011272","title":"Ten quick tips for bioinformatics analyses using an Apache Spark distributed computing environment","year":2023,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"SPARK (programming language); Computer science; Laptop; Context (archaeology); Software; Supercomputer; Data science; Distributed Computing Environment; Distributed computing; Software engineering; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02133972,0.0043664,0.001826718,0.004500984,0.002121332,0.006361888,0.004141596,0.004231963,0.03872798],"category_scores_gemma":[0.1192676,0.002254229,0.002239012,0.004623699,0.002595693,0.00938681,0.004906015,0.009931321,0.0451433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001694309,"about_ca_system_score_gemma":0.004217288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001419917,"about_ca_topic_score_gemma":0.003309589,"domain_scores_codex":[0.9786186,0.008859527,0.00271372,0.001164303,0.007491505,0.001152332],"domain_scores_gemma":[0.8795897,0.06492087,0.005256541,0.007298029,0.03385007,0.009084841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003928921,0.0002066673,0.001168682,0.001805391,0.00006669117,0.0006552315,0.0009099947,0.0008242753,0.002991241,0.004272638,0.7743931,0.2123131],"study_design_scores_gemma":[0.0002319133,0.0003516827,0.002255093,0.002193295,0.00008397182,0.001283157,0.001086501,0.002923506,0.003705134,0.02670599,0.958876,0.0003038697],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006537121,0.01374299,0.681134,0.110462,0.02149053,0.00350427,0.006273048,0.1252573,0.03159872],"genre_scores_gemma":[0.01111907,0.006773371,0.8980849,0.02513248,0.004312203,0.002124486,0.004643245,0.01842403,0.02938626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03872798,"threshold_uncertainty_score":0.129558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.45084184428698,"score_gpt":0.4608809416873802,"score_spread":0.01003909740040021,"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."}}