@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}} @ARTICLE{Shehzad2012-pn, title = "{Carnivore diet analysis based on next-generation sequencing: Application to the leopard cat (Prionailurus bengalensis) in Pakistan}", author = "Shehzad, Wasim and Riaz, Tiayyba and Nawaz, Muhammad A and Miquel, Christian and Poillot, Carole and Shah, Safdar A and Pompanon, Francois and Coissac, Eric and Taberlet, Pierre", journal = "Molecular ecology", publisher = "Wiley Online Library", volume = 21, number = 8, pages = "1951--1965", year = 2012, url = "https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1365-294X.2011.05424.x", issn = "0962-1083" } @ARTICLE{Riaz2011-gn, title = "{ecoPrimers: inference of new DNA barcode markers from whole genome sequence analysis}", author = "Riaz, Tiayyba and Shehzad, Wasim and Viari, Alain and Pompanon, Fran{\c c}ois and Taberlet, Pierre and Coissac, Eric", abstract = "Using non-conventional markers, DNA metabarcoding allows biodiversity assessment from complex substrates. In this article, we present ecoPrimers, a software for identifying new barcode markers and their associated PCR primers. ecoPrimers scans whole genomes to find such markers without a priori knowledge. ecoPrimers optimizes two quality indices measuring taxonomical range and discrimination to select the most efficient markers from a set of reference sequences, according to specific experimental constraints such as marker length or specifically targeted taxa. The key step of the algorithm is the identification of conserved regions among reference sequences for anchoring primers. We propose an efficient algorithm based on data mining, that allows the analysis of huge sets of sequences. We evaluate the efficiency of ecoPrimers by running it on three different sequence sets: mitochondrial, chloroplast and bacterial genomes. Identified barcode markers correspond either to barcode regions already in use for plants or animals, or to new potential barcodes. Results from empirical experiments carried out on a promising new barcode for analyzing vertebrate diversity fully agree with expectations based on bioinformatics analysis. These tests demonstrate the efficiency of ecoPrimers for inferring new barcodes fitting with diverse experimental contexts. ecoPrimers is available as an open source project at: http://www.grenoble.prabi.fr/trac/ecoPrimers.", journal = "Nucleic acids research", volume = 39, number = 21, pages = "e145", month = nov, year = 2011, url = "http://dx.doi.org/10.1093/nar/gkr732", language = "en", issn = "0305-1048, 1362-4962", pmid = "21930509", doi = "10.1093/nar/gkr732", pmc = "PMC3241669" } @ARTICLE{Seguritan2001-tg, title = "{FastGroup: a program to dereplicate libraries of 16S rDNA sequences}", author = "Seguritan, V and Rohwer, F", abstract = "BACKGROUND: Ribosomal 16S DNA sequences are an essential tool for identifying and classifying microbes. High-throughput DNA sequencing now makes it economically possible to produce very large datasets of 16S rDNA sequences in short time periods, necessitating new computer tools for analyses. Here we describe FastGroup, a Java program designed to dereplicate libraries of 16S rDNA sequences. By dereplication we mean to: 1) compare all the sequences in a data set to each other, 2) group similar sequences together, and 3) output a representative sequence from each group. In this way, duplicate sequences are removed from a library. RESULTS: FastGroup was tested using a library of single-pass, bacterial 16S rDNA sequences cloned from coral-associated bacteria. We found that the optimal strategy for dereplicating these sequences was to: 1) trim ambiguous bases from the 5' end of the sequences and all sequence 3' of the conserved Bact517 site, 2) match the sequences from the 3' end, and 3) group sequences > or =97\% identical to each other. CONCLUSIONS: The FastGroup program simplifies the dereplication of 16S rDNA sequence libraries and prepares the raw sequences for subsequent analyses.", journal = "BMC bioinformatics", volume = 2, pages = "9", month = oct, year = 2001, url = "http://dx.doi.org/10.1186/1471-2105-2-9", language = "en", issn = "1471-2105", pmid = "11707150", doi = "10.1186/1471-2105-2-9", pmc = "PMC59723" }