{"id":"W2130062792","doi":"10.1093/bioinformatics/btu687","title":"E-MEM: efficient computation of maximal exact matches for very large genomes","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Compressed suffix array; Computer science; Computation; Genome; Suffix; Suffix array; Source code; Code (set theory); Algorithm; Parallel computing; Theoretical computer science; Data structure; Suffix tree; Set (abstract data type); Programming language; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002867302,0.0001117662,0.0001410192,0.00005185331,0.00004888216,0.00001657135,0.0001204263,0.0000809865,0.000005084784],"category_scores_gemma":[0.00003898563,0.0001037275,0.00008741608,0.00005223588,0.00003278258,0.000003735654,0.00006908927,0.00002598557,0.00001592331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001115761,"about_ca_system_score_gemma":0.00002806261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000113042,"about_ca_topic_score_gemma":0.000001174851,"domain_scores_codex":[0.999266,0.00001241327,0.0002925768,0.00009686781,0.0001240638,0.0002080289],"domain_scores_gemma":[0.9995113,0.00001487823,0.0001565746,0.0001803082,0.00009342678,0.00004348979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001017486,0.002164073,0.01510547,0.01070293,0.001481938,0.00000179991,0.008419343,0.05280419,0.550809,0.005400803,0.02603935,0.3260536],"study_design_scores_gemma":[0.005407262,0.00197402,0.00744104,0.00009356676,0.0001457108,0.00001491265,0.001652943,0.6722965,0.1848203,0.0003656027,0.124856,0.0009321305],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.571646,0.0002654088,0.4261553,0.00003209816,0.0001735888,0.0003928044,0.00007299923,0.00001598248,0.001245816],"genre_scores_gemma":[0.9492652,0.00004145309,0.05004843,0.00007688302,0.0001122063,0.00001696289,0.0003206077,0.00001633644,0.0001019523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6194923,"threshold_uncertainty_score":0.4229886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0106954516510049,"score_gpt":0.23836099971157,"score_spread":0.2276655480605651,"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."}}