{"id":"W4315754521","doi":"10.1016/j.xpro.2022.102014","title":"HSDecipher: A pipeline for comparative genomic analysis of highly similar duplicate genes in eukaryotic genomes","year":2023,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation","keywords":"Pipeline (software); Genome; Gene; Computational biology; Similarity (geometry); Visualization; Phylogenetic tree; Biology; Computer science; Genetics; Data mining; Artificial intelligence; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107011,0.0001916031,0.0004927603,0.0002231224,0.0000591924,0.00001243522,0.0002517077,0.00008665748,0.00001007105],"category_scores_gemma":[0.00002204781,0.0001804099,0.0002212267,0.0005922909,0.00008142095,8.871392e-7,0.0001590477,0.00004127685,0.000006763908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001825099,"about_ca_system_score_gemma":0.00007122933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002656977,"about_ca_topic_score_gemma":0.0002230317,"domain_scores_codex":[0.9986835,0.00005210811,0.0004371955,0.0004237441,0.00009421625,0.000309245],"domain_scores_gemma":[0.9992247,0.00004335722,0.0001575754,0.000394952,0.0001287788,0.00005062476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003870914,0.0001169523,0.03894821,0.0001056854,0.00106757,0.000001914721,0.0004832539,0.01293253,0.9427094,0.0001099909,0.001271737,0.00186564],"study_design_scores_gemma":[0.004882077,0.001512231,0.415601,0.0000520087,0.0007212109,0.000001427351,0.0008624477,0.02657557,0.3866014,0.001536808,0.1605789,0.001074983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9721079,0.0006684241,0.0004773286,0.0001370834,0.000023567,0.02603552,0.000405962,0.000008357184,0.0001357806],"genre_scores_gemma":[0.950552,0.0001916448,0.001866593,0.00008871091,0.00009350762,0.04656959,0.0002513789,0.00002776161,0.0003587928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5561081,"threshold_uncertainty_score":0.7356902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05394718479387992,"score_gpt":0.3445223837232337,"score_spread":0.2905751989293538,"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."}}