@article {Alioto012997, author = {Tyler S. Alioto and Sophia Derdak and Timothy A. Beck and Paul C. Boutros and Lawrence Bower and Ivo Buchhalter and Matthew D. Eldridge and Nicholas J Harding and Lawrence E. Heisler and Eivind Hovig and David T. W. Jones and Andrew G. Lynch and Sigve Nakken and Paolo Ribeca and Anne-Sophie Sertier and Jared T. Simpson and Paul Spellman and Patrick Tarpey and Laurie Tonon and Daniel Vod{\'a}k and Takafumi N. Yamaguchi and Sergi Beltran Agullo and Marc Dabad and Robert E. Denroche and Philip Ginsbach and Simon C. Heath and Emanuele Raineri and Charlotte L. Anderson and Benedikt Brors and Ruben Drews and Roland Eils and Akihiro Fujimoto and Francesc Castro Giner and Minghui He and Pablo Hennings-Yeomans and Barbara Hutter and Natalie J{\"a}ger and Rolf Kabbe and Cyriac Kandoth and Semin Lee and Louis L{\'e}tourneau and Singer Ma and Hidewaki Nakagawa and Nagarajan Paramasivam and Anne-Marie Patch and Myron Peto and Matthias Schlesner and Sahil Seth and David Torrents and David A. Wheeler and Liu Xi and John Zhang and Daniela S. Gerhard and V{\'\i}ctor Quesada and Rafael Vald{\'e}s-Mas and Marta Gut and Thomas J. Hudson and John D. McPherson and Xose S. Puente and Ivo G. Gut}, title = {A Comprehensive Assessment of Somatic Mutation Calling in Cancer Genomes}, elocation-id = {012997}, year = {2014}, doi = {10.1101/012997}, publisher = {Cold Spring Harbor Laboratory}, abstract = {The emergence of next generation DNA sequencing technology is enabling high-resolution cancer genome analysis. Large-scale projects like the International Cancer Genome Consortium (ICGC) are systematically scanning cancer genomes to identify recurrent somatic mutations. Second generation DNA sequencing, however, is still an evolving technology and procedures, both experimental and analytical, are constantly changing. Thus the research community is still defining a set of best practices for cancer genome data analysis, with no single protocol emerging to fulfil this role. Here we describe an extensive benchmark exercise to identify and resolve issues of somatic mutation calling. Whole genome sequence datasets comprising tumor-normal pairs from two different types of cancer, chronic lymphocytic leukaemia and medulloblastoma, were shared within the ICGC and submissions of somatic mutation calls were compared to verified mutations and to each other. Varying strategies to call mutations, incomplete awareness of sources of artefacts, and even lack of agreement on what constitutes an artefact or real mutation manifested in widely varying mutation call rates and somewhat low concordance among submissions. We conclude that somatic mutation calling remains an unsolved problem. However, we have identified many issues that are easy to remedy that are presented here. Our study highlights critical issues that need to be addressed before this valuable technology can be routinely used to inform clinical decision-making.SSMSomatic Single-base Mutations or Simple Somatic Mutations, refers to a somatic single base changeSIMSomatic Insertion/deletion MutationCNVCopy Number VariantSVStructural VariantSNPSingle Nucleotide Polymorphisms, refers to a single base variable position in the germline with a frequency of \> 1\% in the general populationCLLChronic Lymphocytic LeukaemiaMBMedulloblastomaICGCInternational Cancer Genome ConsortiumBMBenchmarkAbbreviations and Definitionsaligner = mapper, these terms are used interchangeably}, URL = {https://www.biorxiv.org/content/early/2014/12/24/012997}, eprint = {https://www.biorxiv.org/content/early/2014/12/24/012997.full.pdf}, journal = {bioRxiv} }