{"id":"W4210828936","doi":"10.1101/2022.02.07.479343","title":"Machine learning-based approach KEVOLVE efficiently identifies SARS-CoV-2 variant-specific genomic signatures","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Discriminative model; Genome; Computational biology; Context (archaeology); Genomics; Phylogenetic tree; Biology; Identification (biology); Artificial intelligence; Computer science; Genetics; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008050584,0.000748002,0.0009978699,0.00215067,0.0004040437,0.001097539,0.001035282,0.0009805365,0.002250476],"category_scores_gemma":[0.002342835,0.0002998352,0.001024263,0.0008137879,0.0003163129,0.0009740091,0.001012063,0.0008343955,0.001076991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004955076,"about_ca_system_score_gemma":0.0006657296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001748202,"about_ca_topic_score_gemma":0.003167158,"domain_scores_codex":[0.9995492,0.0000845107,0.00002996031,0.0001737523,0.00009757559,0.0000650347],"domain_scores_gemma":[0.9993361,0.0003129166,0.00006243213,0.0000913622,0.000164207,0.00003302469],"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":[0.001168661,0.0004447772,0.02442503,0.0003499824,0.0004199235,0.0003268787,0.0001859787,0.1946076,0.07280529,0.005555539,0.01049952,0.6892108],"study_design_scores_gemma":[0.00001766565,0.0000753829,0.001940078,0.000009983711,0.00002058685,0.000120639,0.00003898971,0.9801584,0.0132808,0.002387792,0.001925708,0.00002400154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3311772,0.000691618,0.6462543,0.0003594253,0.0001108463,0.0001570064,0.001954748,0.01664281,0.002652125],"genre_scores_gemma":[0.6333936,0.000183061,0.3570326,0.0002266267,0.00003418632,0.0001664038,0.004665069,0.0006475572,0.003650905],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002250476,"threshold_uncertainty_score":0.007528543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03159070815822219,"score_gpt":0.2751469800378746,"score_spread":0.2435562718796525,"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."}}