{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001301868,0.001382156,0.001797009,0.004764658,0.001311132,0.002759985,0.003041578,0.001174386,0.004473958],"category_scores_gemma":[0.005682851,0.0008124622,0.001307773,0.0118155,0.0009480524,0.005518457,0.002882372,0.001776997,0.00379276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000963613,"about_ca_system_score_gemma":0.001909695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001686538,"about_ca_topic_score_gemma":0.002805516,"domain_scores_codex":[0.9984829,0.0001676919,0.0002280461,0.000223096,0.0007660792,0.0001321811],"domain_scores_gemma":[0.9962029,0.001270875,0.0002958843,0.001502922,0.0005995666,0.0001277709],"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":[0.0003357248,0.0001728808,0.0005816498,0.0008768181,0.00008688069,0.0002232959,0.0002961799,0.01087065,0.07502332,0.02251852,0.04115164,0.8478625],"study_design_scores_gemma":[0.0003950494,0.0005671501,0.002095909,0.000269903,0.0002539044,0.001927117,0.0005356073,0.5048211,0.1858973,0.2032437,0.09979426,0.000199015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01715009,0.005956038,0.9534476,0.000768153,0.0006478954,0.0003128542,0.004230736,0.0145629,0.002923653],"genre_scores_gemma":[0.04672226,0.003435566,0.9319419,0.0002096119,0.000437422,0.0004891116,0.01221223,0.0007992432,0.003752512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004764658,"threshold_uncertainty_score":0.01496685,"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."}}