{"id":"W2171475724","doi":"10.1093/bioinformatics/btl629","title":"Assembling millions of short DNA sequences using SSAKE","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":506,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency","funders":"BC Cancer Agency; Michael Smith Health Research BC","keywords":"DNA sequencing; Sanger sequencing; Computational biology; Hybrid genome assembly; Biology; Sequence assembly; Genome; Software; Sequence (biology); k-mer; Leverage (statistics); Deep sequencing; Genetics; DNA; Computer science; Reference genome; Gene; Transcriptome; Artificial intelligence","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":[0.0001005301,0.0001006262,0.0001217744,0.0000402725,0.00007333628,0.00001323162,0.0001133102,0.00007242782,0.000002355182],"category_scores_gemma":[0.00001593426,0.00009059,0.00006902486,0.00007644943,0.00006885668,0.000001283711,0.00007509184,0.00002713724,0.000001730198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006999951,"about_ca_system_score_gemma":0.0000508835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004135825,"about_ca_topic_score_gemma":0.00002954219,"domain_scores_codex":[0.9993551,0.000007792549,0.0003064719,0.0000808422,0.00009277602,0.000156985],"domain_scores_gemma":[0.9996264,0.000007511152,0.000084646,0.0001788985,0.00007691856,0.00002562914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005686232,0.00002600503,0.01272015,0.00004412118,0.0000466449,4.152976e-7,0.00007475852,0.00203306,0.9836224,0.0002590793,0.0004212978,0.0007464046],"study_design_scores_gemma":[0.0004580031,0.0002824099,0.02372783,0.0000530063,0.0001036277,0.00004095449,0.001013701,0.01566724,0.9341495,0.0005226017,0.02338027,0.0006008669],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923909,0.0006176092,0.0030399,0.00001352993,0.000109821,0.00008617996,0.00003461989,0.000002819885,0.003704592],"genre_scores_gemma":[0.9762148,0.0001228263,0.02342182,0.00003479234,0.0001098428,0.000002310184,0.00003214134,0.000007798129,0.00005366907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0494729,"threshold_uncertainty_score":0.3694153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02626783783145639,"score_gpt":0.2625682878332075,"score_spread":0.2363004500017511,"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."}}