{"id":"W1540226096","doi":"10.1007/978-3-540-71233-6_36","title":"Efficient and Scalable Indexing Techniques for Biological Sequence Data","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Search engine indexing; Scalability; Computer science; Suffix tree; Suffix; Sequence (biology); Data mining; Data structure; Search algorithm; Representation (politics); Variety (cybernetics); Theoretical computer science; Information retrieval; Algorithm; Artificial intelligence; Database; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002044138,0.000433181,0.0004506625,0.000536067,0.000373703,0.0005394053,0.004913021,0.0003896397,0.000004822728],"category_scores_gemma":[0.0001617438,0.0003381685,0.00004945486,0.0003816622,0.0008287043,0.0004410655,0.006247173,0.0005703273,0.000003543873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372771,"about_ca_system_score_gemma":0.0002832452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002332119,"about_ca_topic_score_gemma":0.00001153831,"domain_scores_codex":[0.996077,0.00002072259,0.0004580215,0.002143616,0.0006282792,0.0006723371],"domain_scores_gemma":[0.9965355,0.0006997858,0.0002308879,0.002161664,0.0001910042,0.0001810912],"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":[0.000006415799,0.00002055535,0.00002750903,0.00002867443,0.00000402211,0.00003275927,0.00007730899,0.001401663,0.0002989066,0.0123375,0.0000334021,0.9857313],"study_design_scores_gemma":[0.0001371666,0.0001727422,0.00003187108,0.0003771271,0.000003755817,0.0000795932,8.854744e-8,0.9536148,0.001073609,0.03583563,0.008181765,0.0004918186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004759465,0.000728264,0.9969233,0.0002322787,0.00062455,0.0005894475,0.00006147719,0.0002173377,0.0005758043],"genre_scores_gemma":[0.007700515,0.00007991669,0.9909307,0.0007963446,0.0003618659,0.000009683497,0.00004250156,0.00001976859,0.00005868584],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9852394,"threshold_uncertainty_score":0.999907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08733877345549901,"score_gpt":0.321815245158356,"score_spread":0.234476471702857,"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."}}