{"id":"W3191495377","doi":"10.1101/2021.08.05.455342","title":"A graph-theoretical approach to DNA similarity analysis","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cartesian product; Computer science; Sequence (biology); Tuple; Computational biology; Theoretical computer science; Combinatorics; Algorithm; Mathematics; Biology; Discrete mathematics; Genetics","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":[0.0005621923,0.0006255513,0.0008635958,0.0004419283,0.0001651444,0.0003744607,0.0007910869,0.0008924148,0.0000836912],"category_scores_gemma":[0.0003419181,0.0006504391,0.0009268448,0.001752032,0.0002828776,0.0000124186,0.001072244,0.0005646941,0.00002182046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007666861,"about_ca_system_score_gemma":0.0004075084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006922596,"about_ca_topic_score_gemma":0.000009686216,"domain_scores_codex":[0.9963103,0.0002243139,0.0005398459,0.001826169,0.0004570164,0.0006423668],"domain_scores_gemma":[0.9964859,0.00001732425,0.000221365,0.002143176,0.0005976383,0.0005346058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004855202,0.0003955856,0.007080848,0.0001314423,0.002732258,0.00004065584,0.000007745451,0.001231796,0.9869419,0.001041126,0.0003468331,0.000001282247],"study_design_scores_gemma":[0.0003944353,0.0001361948,0.04737612,0.00008605416,0.003601117,3.733858e-8,0.00002572778,0.001357991,0.9425774,0.00001478752,0.002426521,0.002003617],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9607607,0.0008379658,0.03721111,0.0002636217,0.0002093529,0.0003498149,0.0001760756,0.00008812574,0.0001032957],"genre_scores_gemma":[0.9870726,0.0002356599,0.01113012,0.0008969401,0.0003812302,0.0001789272,0.00001556518,0.00007973262,0.000009268684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04436448,"threshold_uncertainty_score":0.9995947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009210483011695952,"score_gpt":0.2189694616206579,"score_spread":0.2097589786089619,"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."}}