{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002819127,0.0001774722,0.0003278511,0.0005231174,0.0005034696,0.0002869147,0.0008044225,0.00007199947,0.00007097928],"category_scores_gemma":[0.001254431,0.0001390164,0.0001171888,0.001053378,0.0001794907,0.0002113925,0.0005551248,0.00008400169,0.0004356848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007078231,"about_ca_system_score_gemma":0.00005935211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001599611,"about_ca_topic_score_gemma":0.000002394271,"domain_scores_codex":[0.9971166,0.0002171266,0.0008702131,0.0006836304,0.0006868955,0.0004255658],"domain_scores_gemma":[0.9961075,0.002628108,0.0003826894,0.0005420686,0.0002057699,0.0001339036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001802639,0.000130527,0.004331561,0.0000118301,0.00008769822,0.000002042082,0.0003082517,0.9620305,0.0003192427,0.001899093,0.008217838,0.02264341],"study_design_scores_gemma":[0.0002952038,0.00008409952,0.00696663,0.00000815547,0.00002786761,0.000004326765,0.0006073665,0.9640468,0.00004076566,0.02266313,0.005085684,0.0001699451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2885472,0.00001355945,0.7097154,0.0003940167,0.0003579055,0.0002592308,0.0005086547,0.0001339932,0.00007010073],"genre_scores_gemma":[0.8851895,0.000001444853,0.1104113,0.0002393699,0.0001754643,0.000007887428,0.003890623,0.00001235161,0.0000720695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5993041,"threshold_uncertainty_score":0.5668923,"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."}}