{"id":"W1802390868","doi":"10.1186/1471-2105-3-20","title":"Kangaroo – A pattern-matching program for biological sequences","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Cancer Institute","keywords":"Matching (statistics); DNA microarray; Computational biology; Computer science; Biology; Genetics; Mathematics; Statistics; Gene","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":[],"consensus_categories":[],"category_scores_codex":[0.0001150127,0.0001313507,0.0001152885,0.0000262691,0.0001323929,0.00006466855,0.0001736651,0.000128204,0.00005606227],"category_scores_gemma":[0.00004264742,0.0001033669,0.0001067812,0.00004513364,0.00005514736,0.000009106134,0.00006616407,0.00004512063,0.00003720892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001012083,"about_ca_system_score_gemma":0.00002074663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007316018,"about_ca_topic_score_gemma":0.00001851728,"domain_scores_codex":[0.9992555,0.00001679358,0.0002833922,0.0001228298,0.00007112573,0.000250304],"domain_scores_gemma":[0.9995775,0.00002017345,0.0001018265,0.0001928621,0.000051281,0.00005639885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002763209,0.002498071,0.1136395,0.003209985,0.0009591787,0.000009574565,0.01566163,0.006179302,0.03144567,0.01246013,0.06291928,0.7507414],"study_design_scores_gemma":[0.005312063,0.006394804,0.009202184,0.000165268,0.0001646028,0.0003789825,0.01185538,0.3294318,0.0322671,0.003630358,0.598192,0.0030054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7581373,0.0004752595,0.2331855,0.0001962419,0.0003232558,0.001151377,0.0002182503,0.0001226764,0.006190031],"genre_scores_gemma":[0.8513029,0.00009251688,0.1470446,0.0003310813,0.0002290166,0.0001849546,0.0002474252,0.00001216119,0.0005553496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.747736,"threshold_uncertainty_score":0.4215179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03534831055626175,"score_gpt":0.2560530521769923,"score_spread":0.2207047416207306,"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."}}