{"id":"W4408952378","doi":"10.1101/2025.03.25.645269","title":"STRkit: precise, read-level genotyping of short tandem repeats using long reads and single-nucleotide variation","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Genotyping; Nanopore sequencing; Mendelian inheritance; Microsatellite; Genetics; Biology; Tandem repeat; Haplotype; Computational biology; Genome; DNA sequencing; Allele; Genotype; DNA; Gene","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":[0.003592747,0.001599118,0.001199179,0.002187127,0.0006236311,0.001999361,0.002436205,0.001388491,0.01231579],"category_scores_gemma":[0.01243985,0.001195202,0.00134812,0.001465857,0.0006369462,0.00159787,0.00263143,0.001717295,0.01630079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003790691,"about_ca_system_score_gemma":0.001287411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00118347,"about_ca_topic_score_gemma":0.002487429,"domain_scores_codex":[0.9962785,0.0007759756,0.0004064538,0.0008651809,0.001445966,0.0002279277],"domain_scores_gemma":[0.9959373,0.001492225,0.0008246265,0.0009314419,0.0005324331,0.0002818112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00287195,0.0003370583,0.04347412,0.00332571,0.002341939,0.001015793,0.001017903,0.0144221,0.2334175,0.009863349,0.32588,0.3620327],"study_design_scores_gemma":[0.0008165466,0.001177362,0.06067631,0.0005215278,0.0007158982,0.004893002,0.0002981318,0.157647,0.4053926,0.03227633,0.3343317,0.001253609],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06237969,0.0008053074,0.4771705,0.0004991312,0.0004864071,0.0003459558,0.09872916,0.3516356,0.007948304],"genre_scores_gemma":[0.1465096,0.0004832952,0.5780695,0.0008869028,0.000243107,0.001420707,0.211424,0.04152525,0.01943774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01231579,"threshold_uncertainty_score":0.0412004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02986438280123685,"score_gpt":0.241480289968703,"score_spread":0.2116159071674661,"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."}}