{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000967714,0.001246288,0.0009506467,0.001503265,0.0008022017,0.001194437,0.002388109,0.00119194,0.009440734],"category_scores_gemma":[0.00564361,0.0006253169,0.000903337,0.001931337,0.0007248738,0.00249229,0.001872571,0.001033653,0.002630786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006938914,"about_ca_system_score_gemma":0.001225269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001657189,"about_ca_topic_score_gemma":0.002673846,"domain_scores_codex":[0.9994982,0.0001120471,0.00004083594,0.0001455141,0.0001413732,0.00006184306],"domain_scores_gemma":[0.9987261,0.0007467474,0.0000958306,0.0002039212,0.0001572465,0.00007012153],"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":[0.002055188,0.000440359,0.007594255,0.001791934,0.0003958213,0.0007242105,0.0005608489,0.2197939,0.04734785,0.04067432,0.08116866,0.5974527],"study_design_scores_gemma":[0.0003848872,0.0002389904,0.001940986,0.0001161824,0.00007519032,0.000531343,0.0002497513,0.8682296,0.04391227,0.06008029,0.0241784,0.00006201454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1059552,0.001420303,0.8530574,0.0008718728,0.0002390693,0.0002519768,0.003748932,0.02411519,0.01033999],"genre_scores_gemma":[0.1323057,0.0002978556,0.8590088,0.0002227961,0.00008053609,0.0003236496,0.004065426,0.001008613,0.002686661],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009440734,"threshold_uncertainty_score":0.03158236,"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."}}