@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},
}

@article{279,
  abstract     = {Background: Natural selection shapes cancer genomes. Previous studies used signatures of positive selection to identify genes driving malignant transformation. However, the contribution of negative selection against somatic mutations that affect essential tumor functions or specific domains remains a controversial topic. Results: Here, we analyze 7546 individual exomes from 26 tumor types from TCGA data to explore the portion of the cancer exome under negative selection. Although we find most of the genes neutrally evolving in a pan-cancer framework, we identify essential cancer genes and immune-exposed protein regions under significant negative selection. Moreover, our simulations suggest that the amount of negative selection is underestimated. We therefore choose an empirical approach to identify genes, functions, and protein regions under negative selection. We find that expression and mutation status of negatively selected genes is indicative of patient survival. Processes that are most strongly conserved are those that play fundamental cellular roles such as protein synthesis, glucose metabolism, and molecular transport. Intriguingly, we observe strong signals of selection in the immunopeptidome and proteins controlling peptide exposition, highlighting the importance of immune surveillance evasion. Additionally, tumor type-specific immune activity correlates with the strength of negative selection on human epitopes. Conclusions: In summary, our results show that negative selection is a hallmark of cell essentiality and immune response in cancer. The functional domains identified could be exploited therapeutically, ultimately allowing for the development of novel cancer treatments.},
  author       = {Zapata, Luis and Pich, Oriol and Serrano, Luis and Kondrashov, Fyodor and Ossowski, Stephan and Schaefer, Martin},
  journal      = {Genome Biology},
  publisher    = {BioMed Central},
  title        = {{Negative selection in tumor genome evolution acts on essential cellular functions and the immunopeptidome}},
  doi          = {10.1186/s13059-018-1434-0},
  volume       = {19},
  year         = {2018},
}

@article{5995,
  abstract     = {Motivation
Computational prediction of the effect of mutations on protein stability is used by researchers in many fields. The utility of the prediction methods is affected by their accuracy and bias. Bias, a systematic shift of the predicted change of stability, has been noted as an issue for several methods, but has not been investigated systematically. Presence of the bias may lead to misleading results especially when exploring the effects of combination of different mutations.

Results
Here we use a protocol to measure the bias as a function of the number of introduced mutations. It is based on a self-consistency test of the reciprocity the effect of a mutation. An advantage of the used approach is that it relies solely on crystal structures without experimentally measured stability values. We applied the protocol to four popular algorithms predicting change of protein stability upon mutation, FoldX, Eris, Rosetta and I-Mutant, and found an inherent bias. For one program, FoldX, we manage to substantially reduce the bias using additional relaxation by Modeller. Authors using algorithms for predicting effects of mutations should be aware of the bias described here.},
  author       = {Usmanova, Dinara R and Bogatyreva, Natalya S and Ariño Bernad, Joan and Eremina, Aleksandra A and Gorshkova, Anastasiya A and Kanevskiy, German M and Lonishin, Lyubov R and Meister, Alexander V and Yakupova, Alisa G and Kondrashov, Fyodor and Ivankov, Dmitry},
  issn         = {1367-4803},
  journal      = {Bioinformatics},
  number       = {21},
  pages        = {3653--3658},
  publisher    = {Oxford University Press },
  title        = {{Self-consistency test reveals systematic bias in programs for prediction change of stability upon mutation}},
  doi          = {10.1093/bioinformatics/bty340},
  volume       = {34},
  year         = {2018},
}