{"id":"W2180318265","doi":"10.1093/bioinformatics/btv487","title":"EPGA2: memory-efficient <i>de novo</i> assembler","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Program for New Century Excellent Talents in University; National Natural Science Foundation of China","keywords":"Computer science; Sequence assembly; Pipeline (software); Contig; De Bruijn sequence; De Bruijn graph; Construct (python library); Parallels; Genome; Reference genome; Graph; Theoretical computer science; Parallel computing; Programming language; Biology; Genetics; Gene","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":[0.0002779989,0.0001329511,0.0001157558,0.00002688156,0.00005973325,0.00002976612,0.0001730516,0.00009314036,0.000004236164],"category_scores_gemma":[0.00008283214,0.0001178229,0.000060161,0.00006229376,0.00004814633,7.176154e-7,0.0001549957,0.00004926132,0.00007173882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002260318,"about_ca_system_score_gemma":0.0001356741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000627086,"about_ca_topic_score_gemma":0.000004920037,"domain_scores_codex":[0.9992434,0.00001548981,0.0002245431,0.0001111286,0.0001361893,0.0002692673],"domain_scores_gemma":[0.9993677,0.00000695491,0.00007420308,0.0002937403,0.0001086261,0.0001488131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004203032,0.0008012185,0.01599801,0.0003295481,0.0007619038,0.00002519633,0.01153797,0.03563156,0.6369534,0.002193562,0.2454389,0.04990852],"study_design_scores_gemma":[0.003960087,0.001122832,0.007374978,0.00003404777,0.0001116875,0.0002470422,0.006837869,0.03278482,0.206872,0.0003435634,0.7389013,0.001409842],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9558766,0.0006309239,0.004079744,0.0001396747,0.0003480131,0.000157907,0.00002370698,0.000009450143,0.03873393],"genre_scores_gemma":[0.9871924,0.00008697563,0.01110994,0.0007231058,0.0002113286,0.00001278381,0.00002668887,0.00001609903,0.000620674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4934624,"threshold_uncertainty_score":0.4804677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02265554522203696,"score_gpt":0.2465160893019883,"score_spread":0.2238605440799513,"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."}}