@article{ETD,
      recid = {2707},
      author = {Whelan, Christopher},
      title = {Detecting and analyzing genomic structural variation using  distributed computing},
      school = {Ph.D.},
      address = {2014},
      number = {ETD},
      abstract = {Genomic structural variations are an important class of  genetic variants with a wide va- riety of functional  impacts. The detection of structural variations using  high-throughput short-read sequencing data is a difficult  problem, and published algorithms do not pro- vide the  sensitivity and specificity required in research and  clinical settings. Meanwhile, high-throughput sequencing is  rapidly generating ever-larger data sets, necessitating the  development of algorithms that can provide results rapidly  and scale to use cloud and cluster infrastructures.  MapReduce and Hadoop are becoming a standard for managing  the distributed processing of large data sets, but existing  structural variation detection approaches are difficult to  translate into the MapReduce framework. We have formulated  a general framework for structural variation detection in  MapReduce, and implemented a software package called  Cloudbreak, which detects genomic deletions and insertions  with very high accuracy compared to existing popular  tools.},
      url = {http://digitalcollections.ohsu.edu/record/2707},
      doi = {https://doi.org/10.6083/M4DJ5CZ2},
}