{"id":"W6977016039","doi":"10.6084/m9.figshare.15178728","title":"Additional file 1 of Straglr: discovering and genotyping tandem repeat expansions using whole genome long-read sequences","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Genome; Genotyping; Table (database); Whole genome sequencing; Benchmarking; Microsatellite; DNA sequencing","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002222986,0.002060717,0.001811065,0.002970021,0.001112993,0.002380977,0.003421062,0.001494486,0.7109051],"category_scores_gemma":[0.01787154,0.0009074779,0.001356334,0.005260965,0.000467879,0.002467137,0.001905657,0.001508057,0.2612649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001229059,"about_ca_system_score_gemma":0.001743741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005213365,"about_ca_topic_score_gemma":0.01018735,"domain_scores_codex":[0.9986618,0.0001936765,0.0001305057,0.0004653418,0.0003842826,0.0001644267],"domain_scores_gemma":[0.9894221,0.007183359,0.0005344772,0.001121216,0.001267789,0.0004710065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003156503,0.00005776249,0.001574016,0.002035796,0.00006980928,0.0000544628,0.00004455815,0.0009036185,0.0007672049,0.000807516,0.9862421,0.007127626],"study_design_scores_gemma":[0.002036875,0.0002748347,0.02018971,0.001072079,0.0002686001,0.0004824447,0.0002078554,0.004933369,0.006045844,0.01273811,0.9514898,0.0002604469],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001651331,0.00002711813,0.0008142363,0.00004663922,0.00002504234,0.00003315862,0.9949293,0.00306614,0.0008932392],"genre_scores_gemma":[0.003227315,0.00006628867,0.004110477,0.0002090839,0.00003412547,0.0003284471,0.9844878,0.004683287,0.002853283],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7109051,"threshold_uncertainty_score":0.4123587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03115013707645565,"score_gpt":0.2459065668569727,"score_spread":0.2147564297805171,"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."}}