{"id":"W2169569956","doi":"10.1155/2015/196591","title":"Spaced Seed Data Structures for<i>De Novo</i>Assembly","year":2015,"lang":"en","type":"article","venue":"International Journal of Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Sequence assembly; Bloom filter; Data structure; k-mer; Genome; Computer science; De Bruijn graph; De Bruijn sequence; Hybrid genome assembly; Scalability; Sequence (biology); Metagenomics; De novo transcriptome assembly; Reference genome; Algorithm; Computational biology; Biology; Theoretical computer science; Graph; Genetics; Transcriptome; Mathematics; Gene; Database; Programming language; Combinatorics","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":[0.002556717,0.0008351822,0.0008938552,0.001699695,0.001202079,0.002136976,0.0026634,0.001199883,0.003774174],"category_scores_gemma":[0.01317795,0.0008652894,0.0009198678,0.003601592,0.001090608,0.003494804,0.001961538,0.00211392,0.002991887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001568033,"about_ca_system_score_gemma":0.002442587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002030036,"about_ca_topic_score_gemma":0.004216888,"domain_scores_codex":[0.9983274,0.0002956832,0.0003927714,0.0003380976,0.0005484109,0.00009766753],"domain_scores_gemma":[0.9866326,0.003898637,0.001362345,0.005378479,0.002380543,0.0003474291],"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":[0.002144303,0.0004884003,0.01255852,0.001410452,0.0001647312,0.0004948233,0.001305679,0.07391046,0.07970951,0.15698,0.03965528,0.6311778],"study_design_scores_gemma":[0.000370134,0.0008772898,0.002693814,0.0003777411,0.0001159423,0.0005918663,0.0004059912,0.437924,0.1917278,0.2115984,0.153038,0.0002790549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01619628,0.0003419146,0.9661703,0.0003381135,0.000142916,0.000203494,0.003958121,0.01070323,0.001945688],"genre_scores_gemma":[0.07578368,0.0001970846,0.9123793,0.0002496744,0.00005714616,0.0005906801,0.00788311,0.001238808,0.001620473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003774174,"threshold_uncertainty_score":0.01352137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04572948246611166,"score_gpt":0.3164276191650766,"score_spread":0.270698136698965,"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."}}