{"id":"W2133903964","doi":"10.1142/s0219720004000326","title":"OPTIMAL SPACED SEEDS FOR HOMOLOGOUS CODING REGIONS","year":2004,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Coding (social sciences); Coding region; Homology (biology); Computational biology; Homologous chromosome; Computer science; Homologous recombination; Smith–Waterman algorithm; Gene; Biology; Genetics; Algorithm; Mathematics; Sequence alignment; Statistics","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":[0.000167755,0.00009203564,0.0001623,0.0000652588,0.0001040281,0.0000158463,0.00008685487,0.00008122175,7.64809e-7],"category_scores_gemma":[0.00006242585,0.00007502225,0.00008701363,0.00003531339,0.00009927523,0.000001920914,0.00005210492,0.00005163086,5.753518e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000102006,"about_ca_system_score_gemma":0.0001040605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001489654,"about_ca_topic_score_gemma":0.000001475382,"domain_scores_codex":[0.9994162,0.000009810251,0.0003292037,0.00006850761,0.00004610749,0.0001301923],"domain_scores_gemma":[0.9993196,0.00003975432,0.0002521831,0.00005276962,0.0002796094,0.00005613794],"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":[0.001489693,0.0005181515,0.005342582,0.0003329444,0.002641482,0.00001644571,0.003825354,0.5137068,0.2433277,0.1908875,0.007325429,0.03058587],"study_design_scores_gemma":[0.04963429,0.04756755,0.0539315,0.0004268811,0.001052059,0.0121509,0.01139934,0.068804,0.06763922,0.4638076,0.2193066,0.004280028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7205101,0.0007757199,0.2773775,0.0008897817,0.0001807733,0.0001010267,0.00003455039,0.000001240082,0.0001294269],"genre_scores_gemma":[0.8799034,0.0003234087,0.1191946,0.000377112,0.0001502625,0.000002878518,0.0000285483,0.000005422943,0.00001434757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4449028,"threshold_uncertainty_score":0.3059319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01300303195621904,"score_gpt":0.2543864281263891,"score_spread":0.24138339617017,"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."}}