{"id":"W3155072660","doi":"10.1101/2021.04.14.439840","title":"Pattern Detection in Multiple Genome Sequences with Applications: The Case of All SARS-CoV-2 Complete Variants","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Genome; Sequence (biology); String searching algorithm; Computer science; Palindrome; String (physics); Computational biology; Pattern matching; Time complexity; Computational complexity theory; Tandem repeat; DNA sequencing; Biology; Theoretical computer science; Algorithm; Genetics; Artificial intelligence; Gene; Mathematics","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":[0.001194564,0.0006381189,0.0007511474,0.002148704,0.0006188514,0.001322149,0.0009911002,0.001721334,0.001903994],"category_scores_gemma":[0.00568608,0.0003071194,0.0008325228,0.002710018,0.0006532005,0.001015126,0.001016768,0.00106748,0.0005458991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004545347,"about_ca_system_score_gemma":0.000531556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003579146,"about_ca_topic_score_gemma":0.002984389,"domain_scores_codex":[0.9990445,0.0002335504,0.00005841941,0.0002598641,0.000316035,0.00008754776],"domain_scores_gemma":[0.9971824,0.001680875,0.0002226756,0.0002774027,0.0004576996,0.0001790741],"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":[0.001963171,0.0007450173,0.07781392,0.0008527829,0.0003241534,0.02433285,0.0009601821,0.2902065,0.04027643,0.02906948,0.01720829,0.5162473],"study_design_scores_gemma":[0.00005317222,0.0001456051,0.009289244,0.00003633584,0.0000433881,0.003162247,0.0003808559,0.9408098,0.008365564,0.03137033,0.006311507,0.00003212718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6711408,0.004417156,0.310739,0.004170747,0.0003255807,0.0001476323,0.001698342,0.001809161,0.005551671],"genre_scores_gemma":[0.742205,0.000877901,0.2523888,0.0002638383,0.000227859,0.00006525556,0.001045585,0.000107628,0.002818222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003579146,"threshold_uncertainty_score":0.007116616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02579046504047828,"score_gpt":0.2330883733082204,"score_spread":0.2072979082677421,"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."}}