@article{10927,
  abstract     = {Motivation
High plasticity of bacterial genomes is provided by numerous mechanisms including horizontal gene transfer and recombination via numerous flanking repeats. Genome rearrangements such as inversions, deletions, insertions and duplications may independently occur in different strains, providing parallel adaptation or phenotypic diversity. Specifically, such rearrangements might be responsible for virulence, antibiotic resistance and antigenic variation. However, identification of such events requires laborious manual inspection and verification of phyletic pattern consistency.
Results
Here, we define the term ‘parallel rearrangements’ as events that occur independently in phylogenetically distant bacterial strains and present a formalization of the problem of parallel rearrangements calling. We implement an algorithmic solution for the identification of parallel rearrangements in bacterial populations as a tool PaReBrick. The tool takes a collection of strains represented as a sequence of oriented synteny blocks and a phylogenetic tree as input data. It identifies rearrangements, tests them for consistency with a tree, and sorts the events by their parallelism score. The tool provides diagrams of the neighbors for each block of interest, allowing the detection of horizontally transferred blocks or their extra copies and the inversions in which copied blocks are involved. We demonstrated PaReBrick’s efficiency and accuracy and showed its potential to detect genome rearrangements responsible for pathogenicity and adaptation in bacterial genomes.},
  author       = {Zabelkin, Alexey and Yakovleva, Yulia and Bochkareva, Olga and Alexeev, Nikita},
  issn         = {1460-2059},
  journal      = {Bioinformatics},
  number       = {2},
  pages        = {357--363},
  publisher    = {Oxford Academic},
  title        = {{PaReBrick: PArallel REarrangements and BReaks identification toolkit}},
  doi          = {10.1093/bioinformatics/btab691},
  volume       = {38},
  year         = {2022},
}

@article{8645,
  abstract     = {Epistasis, the context-dependence of the contribution of an amino acid substitution to fitness, is common in evolution. To detect epistasis, fitness must be measured for at least four genotypes: the reference genotype, two different single mutants and a double mutant with both of the single mutations. For higher-order epistasis of the order n, fitness has to be measured for all 2n genotypes of an n-dimensional hypercube in genotype space forming a ‘combinatorially complete dataset’. So far, only a handful of such datasets have been produced by manual curation. Concurrently, random mutagenesis experiments have produced measurements of fitness and other phenotypes in a high-throughput manner, potentially containing a number of combinatorially complete datasets. We present an effective recursive algorithm for finding all hypercube structures in random mutagenesis experimental data. To test the algorithm, we applied it to the data from a recent HIS3 protein dataset and found all 199 847 053 unique combinatorially complete genotype combinations of dimensionality ranging from 2 to 12. The algorithm may be useful for researchers looking for higher-order epistasis in their high-throughput experimental data.},
  author       = {Esteban, Laura A and Lonishin, Lyubov R and Bobrovskiy, Daniil M and Leleytner, Gregory and Bogatyreva, Natalya S and Kondrashov, Fyodor and Ivankov, Dmitry N },
  issn         = {1460-2059},
  journal      = {Bioinformatics},
  number       = {6},
  pages        = {1960--1962},
  publisher    = {Oxford Academic},
  title        = {{HypercubeME: Two hundred million combinatorially complete datasets from a single experiment}},
  doi          = {10.1093/bioinformatics/btz841},
  volume       = {36},
  year         = {2020},
}