@article{cock2010sanger,
  title={The Sanger FASTQ file format for sequences with quality scores, and the Solexa/Illumina FASTQ variants},
  author={Cock, Peter JA and Fields, Christopher J and Goto, Naohisa and Heuer, Michael L and Rice, Peter M},
  journal={Nucleic acids research},
  volume={38},
  number={6},
  pages={1767--1771},
  year={2010},
  publisher={Oxford University Press}
}

@ARTICLE{Boyer2016-gq,
  title     = "{obitools: a unix-inspired software package for DNA metabarcoding}",
  author    = "Boyer, Fr{\'e}d{\'e}ric and Mercier, C{\'e}line and Bonin,
               Aur{\'e}lie and Le Bras, Yvan and Taberlet, Pierre and Coissac,
               Eric",
  abstract  = "DNA metabarcoding offers new perspectives in biodiversity
               research. This recently developed approach to ecosystem study
               relies heavily on the use of next-generation sequencing (NGS)
               and thus calls upon the ability to deal with huge sequence data
               sets. The obitools package satisfies this requirement thanks to
               a set of programs specifically designed for analysing NGS data
               in a DNA metabarcoding context. Their capacity to filter and
               edit sequences while taking into account taxonomic annotation
               helps to set up tailor-made analysis pipelines for a broad range
               of DNA metabarcoding applications, including biodiversity
               surveys or diet analyses. The obitools package is distributed as
               an open source software available on the following website:
               http://metabarcoding.org/obitools. A Galaxy wrapper is available
               on the GenOuest core facility toolshed:
               http://toolshed.genouest.org.",
  journal   = "Molecular ecology resources",
  publisher = "Wiley Online Library",
  volume    =  16,
  number    =  1,
  pages     = "176--182",
  month     =  jan,
  year      =  2016,
  url       = "http://dx.doi.org/10.1111/1755-0998.12428",
  keywords  = "PCR errors; biodiversity; next-generation sequencing; sequence
               analysis; taxonomic annotation",
  language  = "en",
  issn      = "1755-098X, 1755-0998",
  pmid      = "25959493",
  doi       = "10.1111/1755-0998.12428"
}


@article{Lipman1985-hw,
	abstract = {An algorithm was developed which facilitates the search for
              similarities between newly determined amino acid sequences and
              sequences already available in databases. Because of the
              algorithm's efficiency on many microcomputers, sensitive protein
              database searches may now become a routine procedure for
              molecular biologists. The method efficiently identifies regions
              of similar sequence and then scores the aligned identical and
              differing residues in those regions by means of an amino acid
              replacability matrix. This matrix increases sensitivity by giving
              high scores to those amino acid replacements which occur
              frequently in evolution. The algorithm has been implemented in a
              computer program designed to search protein databases very
              rapidly. For example, comparison of a 200-amino-acid sequence to
              the 500,000 residues in the National Biomedical Research
              Foundation library would take less than 2 minutes on a
              minicomputer, and less than 10 minutes on a microcomputer (IBM
              PC).},
	author = {Lipman, D J and Pearson, W R},
	date-added = {2023-01-26 15:17:10 +0100},
	date-modified = {2023-01-26 15:17:10 +0100},
	issn = {0036-8075},
	journal = {Science},
	month = mar,
	number = 4693,
	pages = {1435--1441},
	pmid = {2983426},
	title = {{Rapid and sensitive protein similarity searches}},
	url = {http://www.ncbi.nlm.nih.gov/pubmed/2983426},
	volume = 227,
	year = 1985,
	bdsk-url-1 = {http://www.ncbi.nlm.nih.gov/pubmed/2983426}}