@article {6, title = {HPG pore: an efficient and scalable framework for nanopore sequencing data.}, journal = {BMC Bioinformatics}, volume = {17}, year = {2016}, month = {2016}, pages = {107}, abstract = {

BACKGROUND: The use of nanopore technologies is expected to spread in the future because they are portable and can sequence long fragments of DNA molecules without prior amplification. The first nanopore sequencer available, the MinION{\texttrademark} from Oxford Nanopore Technologies, is a USB-connected, portable device that allows real-time DNA analysis. In addition, other new instruments are expected to be released soon, which promise to outperform the current short-read technologies in terms of throughput. Despite the flood of data expected from this technology, the data analysis solutions currently available are only designed to manage small projects and are not scalable.

RESULTS: Here we present HPG Pore, a toolkit for exploring and analysing nanopore sequencing data. HPG Pore can run on both individual computers and in the Hadoop distributed computing framework, which allows easy scale-up to manage the large amounts of data expected to result from extensive use of nanopore technologies in the future.

CONCLUSIONS: HPG Pore allows for virtually unlimited sequencing data scalability, thus guaranteeing its continued management in near future scenarios. HPG Pore is available in GitHub at http://github.com/opencb/hpg-pore .

}, issn = {1471-2105}, doi = {10.1186/s12859-016-0966-0}, author = {Tarraga, Joaquin and Gallego, Asunci{\'o}n and Arnau, Vicente and Medina, Ignacio and Dopazo, Joaqu{\'\i}n} } @article {8, title = {Acceleration of short and long DNA read mapping without loss of accuracy using suffix array.}, journal = {Bioinformatics}, volume = {30}, year = {2014}, month = {2014 Dec 1}, pages = {3396-8}, abstract = {

UNLABELLED: HPG Aligner applies suffix arrays for DNA read mapping. This implementation produces a highly sensitive and extremely fast mapping of DNA reads that scales up almost linearly with read length. The approach presented here is faster (over 20{\texttimes} for long reads) and more sensitive (over 98\% in a wide range of read lengths) than the current state-of-the-art mappers. HPG Aligner is not only an optimal alternative for current sequencers but also the only solution available to cope with longer reads and growing throughputs produced by forthcoming sequencing technologies.

AVAILABILITY AND IMPLEMENTATION: https://github.com/opencb/hpg-aligner.

}, keywords = {Algorithms, Animals, DNA, Drosophila, High-Throughput Nucleotide Sequencing, Humans, Sequence Alignment, Sequence Analysis, Software}, issn = {1367-4811}, doi = {10.1093/bioinformatics/btu553}, author = {Tarraga, Joaquin and Arnau, Vicente and Mart{\'\i}nez, H{\'e}ctor and Moreno, Raul and Cazorla, Diego and Salavert-Torres, Jos{\'e} and Blanquer-Espert, Ignacio and Dopazo, Joaqu{\'\i}n and Medina, Ignacio} }