Alignment-free graph models of TCR and BCR repertoires built from Lempel-Ziv and FlashBack string decompositions. Compute sequence generation probability (Pgen) and repertoire diversity, and generate new sequences. Python with a C core.
Fast simulator of BCR and TCR sequences with full ground-truth annotations: V(D)J recombination, somatic hypermutation and sequencing artifacts across 23 species. Rust core with a Python API, for training and benchmarking AIRR-seq tools.
Deep-learning V(D)J aligner for BCR and TCR sequences. A single model predicts V/D/J allele calls, segment boundaries and the junction, with AIRR-format output. Published in Nucleic Acids Research (2025).
