2026-10-12T23:21:03Z https://www.scidb.cn/oai

10.57760/sciencedb.cjb.00007 2026-08-28T10:28:47Z

2026-08-28 A benchmark dataset for evaluating antibody V(D)J genes reconstruction algorithms doi:10.57760/sciencedb.cjb.00007 en This dataset includes gold standard clone sequencing data, GenAIRR simulation data, and immuneSIM simulation data, with a total of over 110000 sequences. The gold standard data is derived from experimentally validated B cell clones, providing authentic annotation information; The immuneSIM data has a large scale and provides complete D segment alignment sequences; GenAIRR data is generated based on two mutation models, including complete alleles, mutation rates, and functional labels. This dataset can provide a standardized evaluation benchmark for the selection, parameter optimization, and new algorithm development of antibody V (D) J backtracking algorithm.   Antibody; V(D)J recombination; Immune repertoire sequencing; Allele assignment; Benchmark dataset mu xin yue PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank