references.bib

@article{10.1093/bioinformatics/btw152,
    author = {Li, Heng},
    title = "{Minimap and miniasm: fast mapping and de novo assembly for noisy long sequences}",
    journal = {Bioinformatics},
    volume = {32},
    number = {14},
    pages = {2103-2110},
    year = {2016},
    month = {03},
    abstract = "{Motivation: Single Molecule Real-Time (SMRT) sequencing technology and Oxford Nanopore technologies (ONT) produce reads over 10 kb in length, which have enabled high-quality genome assembly at an affordable cost. However, at present, long reads have an error rate as high as 10–15\\%. Complex and computationally intensive pipelines are required to assemble such reads.Results: We present a new mapper, minimap and a de novo assembler, miniasm, for efficiently mapping and assembling SMRT and ONT reads without an error correction stage. They can often assemble a sequencing run of bacterial data into a single contig in a few minutes, and assemble 45-fold Caenorhabditis elegans data in 9 min, orders of magnitude faster than the existing pipelines, though the consensus sequence error rate is as high as raw reads. We also introduce a pairwise read mapping format and a graphical fragment assembly format, and demonstrate the interoperability between ours and current tools.Availability and implementation:https://github.com/lh3/minimap and https://github.com/lh3/miniasmContact:hengli@broadinstitute.orgSupplementary information:Supplementary data are available at Bioinformatics online.}",
    issn = {1367-4803},
    doi = {10.1093/bioinformatics/btw152},
    url = {https://doi.org/10.1093/bioinformatics/btw152},
    eprint = {https://academic.oup.com/bioinformatics/article-pdf/32/14/2103/19567911/btw152.pdf},
}

@article{10.1093/bioinformatics/bth408,
    author = {Roberts, Michael and Hayes, Wayne and Hunt, Brian R. and Mount, Stephen M. and Yorke, James A.},
    title = "{Reducing storage requirements for biological sequence comparison}",
    journal = {Bioinformatics},
    volume = {20},
    number = {18},
    pages = {3363-3369},
    year = {2004},
    month = {07},
    abstract = "{Motivation: Comparison of nucleic acid and protein sequences is a fundamental tool of modern bioinformatics. A dominant method of such string matching is the ‘seed-and-extend’ approach, in which occurrences of short subsequences called ‘seeds’ are used to search for potentially longer matches in a large database of sequences. Each such potential match is then checked to see if it extends beyond the seed. To be effective, the seed-and-extend approach needs to catalogue seeds from virtually every substring in the database of search strings. Projects such as mammalian genome assemblies and large-scale protein matching, however, have such large sequence databases that the resulting list of seeds cannot be stored in RAM on a single computer. This significantly slows the matching process.Results: We present a simple and elegant method in which only a small fraction of seeds, called ‘minimizers’, needs to be stored. Using minimizers can speed up string-matching computations by a large factor while missing only a small fraction of the matches found using all seeds.}",
    issn = {1367-4803},
    doi = {10.1093/bioinformatics/bth408},
    url = {https://doi.org/10.1093/bioinformatics/bth408},
    eprint = {https://academic.oup.com/bioinformatics/article-pdf/20/18/3363/520444/bth408.pdf},
}