{"id":"W2054453573","doi":"10.1089/cmb.2007.0208","title":"New, Improved, and Practical k-Stem Sequence Similarity Measures for Probe Design","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of British Columbia","keywords":"Nearest neighbor search; Similarity (geometry); k-nearest neighbors algorithm; Sequence (biology); Computer science; Oligomer restriction; Data mining; Bit array; Algorithm; Pattern recognition (psychology); Oligonucleotide; Mathematics; Artificial intelligence; Biology; Genetics; Gene","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002839734,0.00008607565,0.0001431386,0.00003200021,0.00007424465,0.00001001979,0.00007219416,0.000115847,0.000001684426],"category_scores_gemma":[0.0001270266,0.00007259184,0.00006372322,0.00002347541,0.00007799244,0.000005196515,0.00003309511,0.00008384629,3.675227e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001383367,"about_ca_system_score_gemma":0.0004970952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000187319,"about_ca_topic_score_gemma":0.000001551693,"domain_scores_codex":[0.9993621,0.00006443002,0.0002708274,0.0001261259,0.00006061528,0.0001158796],"domain_scores_gemma":[0.9992116,0.0001083661,0.0002387972,0.00005572143,0.0003030441,0.00008249081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001441834,0.0001893618,0.005844004,0.00004422288,0.0004427228,0.00003154599,0.0001836045,0.01832289,0.9434464,0.006432971,0.008050302,0.01557014],"study_design_scores_gemma":[0.01983106,0.02646184,0.03762312,0.0001037856,0.0004249135,0.04381247,0.000328936,0.2253646,0.1383889,0.4019968,0.1032758,0.002387765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2556533,0.0002939827,0.7431688,0.0006529198,0.00009447204,0.0001114351,0.00001147734,0.000001737125,0.00001190294],"genre_scores_gemma":[0.6745288,0.0001027716,0.3249025,0.00021663,0.0001900767,0.000002198428,0.00001694841,0.000006673529,0.00003341752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8050575,"threshold_uncertainty_score":0.296021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04864507257986041,"score_gpt":0.3051138640791153,"score_spread":0.2564687914992549,"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."}}