{"id":"W2314403353","doi":"10.1142/9789814667944_0018","title":"A METHOD FOR CLUSTERING HEMAGGLUTININ INFLUENZA PROTEIN SEQUENCES","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Hemagglutinin (influenza); Cluster analysis; Computer science; Computational biology; Artificial intelligence; Virology; Biology; Virus","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":[],"consensus_categories":[],"category_scores_codex":[0.0005916246,0.0001109115,0.0001044288,0.00002575257,0.00004198858,0.00003143357,0.0001687176,0.00009956516,0.0000109423],"category_scores_gemma":[0.0003875639,0.00009231792,0.00005085714,0.00004705626,0.0000270093,0.000004187094,0.0001225037,0.00006026894,0.00001358215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001055586,"about_ca_system_score_gemma":0.00008769755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003469816,"about_ca_topic_score_gemma":0.00003320261,"domain_scores_codex":[0.9992973,0.00004240974,0.0002046654,0.0001605743,0.00009986464,0.0001952535],"domain_scores_gemma":[0.9995011,0.00001250861,0.00008302416,0.000209323,0.0001013574,0.00009265973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007332308,0.0001140277,0.004362313,0.0004996927,0.0002143114,0.000003045865,0.001566028,0.01550488,0.8852243,0.005400622,0.02629491,0.06008263],"study_design_scores_gemma":[0.001524195,0.0009070227,0.00005422689,0.00002753703,0.00001556907,0.00004371128,0.0005297988,0.09162881,0.2993794,0.0007560633,0.6047111,0.0004226074],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09462664,0.000105659,0.8851871,0.0003179597,0.0000781589,0.000596807,0.000007856223,0.00005257217,0.01902724],"genre_scores_gemma":[0.09111327,0.00000110922,0.9036978,0.001156866,0.0001811102,0.0001128056,0.00003802261,0.00002044226,0.003678601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5858449,"threshold_uncertainty_score":0.3764616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03912513262033836,"score_gpt":0.3557031499078894,"score_spread":0.316578017287551,"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."}}