{"id":"W4361298788","doi":"10.1101/gr.277637.122","title":"Proving sequence aligners can guarantee accuracy in almost <i>O</i> ( <i>m</i> log <i>n</i> ) time through an average-case analysis of the seed-chain-extend heuristic","year":2023,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Combinatorics; Substring; Chaining; Sequence (biology); Chain (unit); Upper and lower bounds; Mathematics; Algorithm; Discrete mathematics; Physics; Biology; Computer science; Data structure; Mathematical analysis; Genetics","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":[0.01384844,0.003731003,0.003345947,0.001794161,0.002417053,0.006673399,0.005309573,0.004182651,0.008088384],"category_scores_gemma":[0.0881094,0.002187129,0.004970575,0.002613716,0.005793791,0.01520368,0.00563886,0.007354775,0.004698528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003800813,"about_ca_system_score_gemma":0.006786328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002033555,"about_ca_topic_score_gemma":0.003617728,"domain_scores_codex":[0.9751318,0.005532091,0.001715998,0.00575481,0.007930765,0.003934571],"domain_scores_gemma":[0.879858,0.08178984,0.007234304,0.02354557,0.005383446,0.002188922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003239351,0.001259391,0.02251656,0.001991661,0.0008992763,0.001132136,0.001047439,0.4244725,0.0700895,0.1489144,0.03355309,0.2908847],"study_design_scores_gemma":[0.0002360415,0.0005458674,0.002233238,0.0001370872,0.0002912775,0.0009355056,0.0002187572,0.7833779,0.04821081,0.1579572,0.005749281,0.0001069312],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06799464,0.001402105,0.9049249,0.004259635,0.0002458455,0.0002056197,0.0006620625,0.009279628,0.01102551],"genre_scores_gemma":[0.5142602,0.001021504,0.4724357,0.002659537,0.0008547682,0.0003659567,0.001666501,0.003018043,0.00371772],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01384844,"threshold_uncertainty_score":0.07323843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05970532850008532,"score_gpt":0.3478031844878454,"score_spread":0.2880978559877601,"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."}}