Reorganization of the documentation book directory

Former-commit-id: 095acaf9c8649b0e527c6253dc79330feedac865

doc/lib/book.bib

@@ -0,0 +1,709 @@
+@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"
+}
+
+
+@ARTICLE{Taberlet2012-pf,
+  title    = "{Environmental DNA}",
+  author   = "Taberlet, Pierre and Coissac, Eric and Hajibabaei, Mehrdad and
+              Rieseberg, Loren H",
+  journal  = "Molecular ecology",
+  volume   =  21,
+  number   =  8,
+  pages    = "1789--1793",
+  month    =  apr,
+  year     =  2012,
+  url      = "http://dx.doi.org/10.1111/j.1365-294X.2012.05542.x",
+  language = "en",
+  issn     = "0962-1083, 1365-294X",
+  pmid     = "22486819",
+  doi      = "10.1111/j.1365-294X.2012.05542.x"
+}
+
+
+@ARTICLE{Sogin2006-ab,
+  title    = "{Microbial diversity in the deep sea and the underexplored "rare
+              biosphere"}",
+  author   = "Sogin, Mitchell L and Morrison, Hilary G and Huber, Julie A and
+              Mark Welch, David and Huse, Susan M and Neal, Phillip R and
+              Arrieta, Jesus M and Herndl, Gerhard J",
+  abstract = "The evolution of marine microbes over billions of years predicts
+              that the composition of microbial communities should be much
+              greater than the published estimates of a few thousand distinct
+              kinds of microbes per liter of seawater. By adopting a massively
+              parallel tag sequencing strategy, we show that bacterial
+              communities of deep water masses of the North Atlantic and
+              diffuse flow hydrothermal vents are one to two orders of
+              magnitude more complex than previously reported for any microbial
+              environment. A relatively small number of different populations
+              dominate all samples, but thousands of low-abundance populations
+              account for most of the observed phylogenetic diversity. This
+              ``rare biosphere'' is very ancient and may represent a nearly
+              inexhaustible source of genomic innovation. Members of the rare
+              biosphere are highly divergent from each other and, at different
+              times in earth's history, may have had a profound impact on
+              shaping planetary processes.",
+  journal  = "Proceedings of the National Academy of Sciences of the United
+              States of America",
+  volume   =  103,
+  number   =  32,
+  pages    = "12115--12120",
+  month    =  aug,
+  year     =  2006,
+  url      = "http://dx.doi.org/10.1073/pnas.0605127103",
+  issn     = "0027-8424",
+  pmid     = "16880384",
+  doi      = "10.1073/pnas.0605127103",
+  pmc      = "PMC1524930"
+}
+
+
+@ARTICLE{Sonstebo2010-vv,
+  title    = "{Using next-generation sequencing for molecular reconstruction of
+              past Arctic vegetation and climate}",
+  author   = "S{\o}nsteb{\o}, J H and Gielly, L and Brysting, A K and Elven, R
+              and Edwards, M and Haile, J and Willerslev, E and Coissac, E and
+              Rioux, D and Sannier, J and Taberlet, P and Brochmann, C",
+  abstract = "Palaeoenvironments and former climates are typically inferred
+              from pollen and macrofossil records. This approach is
+              time-consuming and suffers from low taxonomic resolution and
+              biased taxon sampling. Here, we test an alternative DNA-based
+              approach utilizing the P6 loop in the chloroplast trnL (UAA)
+              intron; a short (13-158 bp) and variable region with highly
+              conserved flanking sequences. For taxonomic reference, a whole
+              trnL intron sequence database was constructed from recently
+              collected material of 842 species, representing all widespread
+              and/or ecologically important taxa of the species-poor arctic
+              flora. The P6 loop alone allowed identification of all families,
+              most genera (>75\%) and one-third of the species, thus providing
+              much higher taxonomic resolution than pollen records. The
+              suitability of the P6 loop for analysis of samples containing
+              degraded ancient DNA from a mixture of species is demonstrated by
+              high-throughput parallel pyrosequencing of permafrost-preserved
+              DNA and reconstruction of two plant communities from the last
+              glacial period. Our approach opens new possibilities for
+              DNA-based assessment of ancient as well as modern biodiversity of
+              many groups of organisms using environmental samples.",
+  journal  = "Molecular ecology resources",
+  volume   =  10,
+  number   =  6,
+  pages    = "1009--1018",
+  month    =  nov,
+  year     =  2010,
+  url      = "http://dx.doi.org/10.1111/j.1755-0998.2010.02855.x",
+  language = "en",
+  issn     = "1755-098X, 1755-0998",
+  pmid     = "21565110",
+  doi      = "10.1111/j.1755-0998.2010.02855.x"
+}
+
+@ARTICLE{Yoccoz2012-ix,
+  title    = "{DNA from soil mirrors plant taxonomic and growth form diversity}",
+  author   = "Yoccoz, N G and Br{\aa}then, K A and Gielly, L and Haile, J and
+              Edwards, M E and Goslar, T and Von Stedingk, H and Brysting, A K
+              and Coissac, E and Pompanon, F and S{\o}nsteb{\o}, J H and
+              Miquel, C and Valentini, A and De Bello, F and Chave, J and
+              Thuiller, W and Wincker, P and Cruaud, C and Gavory, F and
+              Rasmussen, M and Gilbert, M T P and Orlando, L and Brochmann, C
+              and Willerslev, E and Taberlet, P",
+  abstract = "Ecosystems across the globe are threatened by climate change and
+              human activities. New rapid survey approaches for monitoring
+              biodiversity would greatly advance assessment and understanding
+              of these threats. Taking advantage of next-generation DNA
+              sequencing, we tested an approach we call metabarcoding:
+              high-throughput and simultaneous taxa identification based on a
+              very short (usually <100 base pairs) but informative DNA
+              fragment. Short DNA fragments allow the use of degraded DNA from
+              environmental samples. All analyses included amplification using
+              plant-specific versatile primers, sequencing and estimation of
+              taxonomic diversity. We tested in three steps whether degraded
+              DNA from dead material in soil has the potential of efficiently
+              assessing biodiversity in different biomes. First, soil DNA from
+              eight boreal plant communities located in two different
+              vegetation types (meadow and heath) was amplified. Plant
+              diversity detected from boreal soil was highly consistent with
+              plant taxonomic and growth form diversity estimated from
+              conventional above-ground surveys. Second, we assessed DNA
+              persistence using samples from formerly cultivated soils in
+              temperate environments. We found that the number of crop DNA
+              sequences retrieved strongly varied with years since last
+              cultivation, and crop sequences were absent from nearby,
+              uncultivated plots. Third, we assessed the universal
+              applicability of DNA metabarcoding using soil samples from
+              tropical environments: a large proportion of species and families
+              from the study site were efficiently recovered. The results open
+              unprecedented opportunities for large-scale DNA-based
+              biodiversity studies across a range of taxonomic groups using
+              standardized metabarcoding approaches.",
+  journal  = "Molecular ecology",
+  volume   =  21,
+  number   =  15,
+  pages    = "3647--3655",
+  month    =  aug,
+  year     =  2012,
+  url      = "http://dx.doi.org/10.1111/j.1365-294X.2012.05545.x",
+  language = "en",
+  issn     = "0962-1083, 1365-294X",
+  pmid     = "22507540",
+  doi      = "10.1111/j.1365-294X.2012.05545.x"
+}
+
+
+@ARTICLE{Parducci2012-rn,
+  title    = "{Glacial survival of boreal trees in northern Scandinavia}",
+  author   = "Parducci, Laura and J{\o}rgensen, Tina and Tollefsrud, Mari Mette
+              and Elverland, Ellen and Alm, Torbj{\o}rn and Fontana, Sonia L
+              and Bennett, K D and Haile, James and Matetovici, Irina and
+              Suyama, Yoshihisa and Edwards, Mary E and Andersen, Kenneth and
+              Rasmussen, Morten and Boessenkool, Sanne and Coissac, Eric and
+              Brochmann, Christian and Taberlet, Pierre and Houmark-Nielsen,
+              Michael and Larsen, Nicolaj Krog and Orlando, Ludovic and
+              Gilbert, M Thomas P and Kj{\ae}r, Kurt H and Alsos, Inger Greve
+              and Willerslev, Eske",
+  abstract = "It is commonly believed that trees were absent in Scandinavia
+              during the last glaciation and first recolonized the Scandinavian
+              Peninsula with the retreat of its ice sheet some 9000 years ago.
+              Here, we show the presence of a rare mitochondrial DNA haplotype
+              of spruce that appears unique to Scandinavia and with its highest
+              frequency to the west-an area believed to sustain ice-free
+              refugia during most of the last ice age. We further show the
+              survival of DNA from this haplotype in lake sediments and pollen
+              of Tr{\o}ndelag in central Norway dating back ~10,300 years and
+              chloroplast DNA of pine and spruce in lake sediments adjacent to
+              the ice-free And{\o}ya refugium in northwestern Norway as early
+              as ~22,000 and 17,700 years ago, respectively. Our findings imply
+              that conifer trees survived in ice-free refugia of Scandinavia
+              during the last glaciation, challenging current views on survival
+              and spread of trees as a response to climate changes.",
+  journal  = "Science",
+  volume   =  335,
+  number   =  6072,
+  pages    = "1083--1086",
+  month    =  mar,
+  year     =  2012,
+  url      = "http://dx.doi.org/10.1126/science.1216043",
+  language = "en",
+  issn     = "0036-8075, 1095-9203",
+  pmid     = "22383845",
+  doi      = "10.1126/science.1216043"
+}
+
+
+@MISC{Chariton2010-cz,
+  title   = "{Influence of the choice of physical and chemistry variables on
+             interpreting patterns of sediment contaminants and their
+             relationships with estuarine macrobenthic communities}",
+  author  = "Chariton, Anthony A and Roach, Anthony C and Simpson, Stuart L and
+             Batley, Graeme E",
+  journal = "Marine and Freshwater Research",
+  volume  =  61,
+  number  =  10,
+  pages   = "1109",
+  year    =  2010,
+  url     = "http://dx.doi.org/10.1071/mf09263",
+  doi     = "10.1071/mf09263"
+}
+
+
+@ARTICLE{Baldwin2013-yc,
+  title     = "{Impacts of inundation and drought on eukaryote biodiversity in
+               semi-arid floodplain soils}",
+  author    = "Baldwin, Darren S and Colloff, Matthew J and Rees, Gavin N and
+               Chariton, Anthony A and Watson, Garth O and Court, Leon N and
+               Hartley, Diana M and Morgan, Matthew J and King, Andrew J and
+               Wilson, Jessica S and Hodda, Michael and Hardy, Christopher M",
+  abstract  = "Floodplain ecosystems are characterized by alternating wet and
+               dry phases and periodic inundation defines their ecological
+               character. Climate change, river regulation and the construction
+               of levees have substantially altered natural flooding and drying
+               regimes worldwide with uncertain effects on key biotic groups.
+               In southern Australia, we hypothesized that soil eukaryotic
+               communities in climate change affected areas of a semi-arid
+               floodplain would transition towards comprising mainly dry-soil
+               specialist species with increasing drought severity. Here, we
+               used 18S rRNA amplicon pyrosequencing to measure the eukaryote
+               community composition in soils that had been depleted of water
+               to varying degrees to confirm that reproducible transitional
+               changes occur in eukaryotic biodiversity on this floodplain.
+               Interflood community structures (3 years post-flood) were
+               dominated by persistent rather than either aquatic or
+               dry-specialist organisms. Only 2\% of taxa were unique to dry
+               locations by 8 years post-flood, and 10\% were restricted to wet
+               locations (inundated a year to 2 weeks post-flood). Almost half
+               (48\%) of the total soil biota were detected in both these
+               environments. The discovery of a large suite of organisms able
+               to survive nearly a decade of drought, and up to a year
+               submerged supports the concept of inherent resilience of
+               Australian semi-arid floodplain soil communities under
+               increasing pressure from climatic induced changes in water
+               availability.",
+  journal   = "Molecular ecology",
+  publisher = "Wiley Online Library",
+  volume    =  22,
+  number    =  6,
+  pages     = "1746--1758",
+  month     =  mar,
+  year      =  2013,
+  url       = "http://dx.doi.org/10.1111/mec.12190",
+  issn      = "0962-1083, 1365-294X",
+  pmid      = "23379967",
+  doi       = "10.1111/mec.12190"
+}
+
+
+@ARTICLE{Andersen2012-gj,
+  title     = "{Meta-barcoding of {\"e}dirt{\'\i}DNA from soil reflects
+               vertebrate biodiversity}",
+  author    = "Andersen, Kenneth and Bird, Karen Lise and Rasmussen, Morten and
+               Haile, James and Breuning-Madsen, Henrik and Kjaer, Kurt H and
+               Orlando, Ludovic and Gilbert, M Thomas P and Willerslev, Eske",
+  journal   = "Molecular ecology",
+  publisher = "Wiley Online Library",
+  volume    =  21,
+  number    =  8,
+  pages     = "1966--1979",
+  year      =  2012,
+  issn      = "0962-1083"
+}
+
+
+@ARTICLE{Thomsen2012-au,
+  title    = "{Monitoring endangered freshwater biodiversity using environmental
+              DNA}",
+  author   = "Thomsen, Philip Francis and Kielgast, Jos and Iversen, Lars L and
+              Wiuf, Carsten and Rasmussen, Morten and Gilbert, M Thomas P and
+              Orlando, Ludovic and Willerslev, Eske",
+  abstract = "Freshwater ecosystems are among the most endangered habitats on
+              Earth, with thousands of animal species known to be threatened or
+              already extinct. Reliable monitoring of threatened organisms is
+              crucial for data-driven conservation actions but remains a
+              challenge owing to nonstandardized methods that depend on
+              practical and taxonomic expertise, which is rapidly declining.
+              Here, we show that a diversity of rare and threatened freshwater
+              animals--representing amphibians, fish, mammals, insects and
+              crustaceans--can be detected and quantified based on DNA obtained
+              directly from small water samples of lakes, ponds and streams. We
+              successfully validate our findings in a controlled mesocosm
+              experiment and show that DNA becomes undetectable within 2 weeks
+              after removal of animals, indicating that DNA traces are near
+              contemporary with presence of the species. We further demonstrate
+              that entire faunas of amphibians and fish can be detected by
+              high-throughput sequencing of DNA extracted from pond water. Our
+              findings underpin the ubiquitous nature of DNA traces in the
+              environment and establish environmental DNA as a tool for
+              monitoring rare and threatened species across a wide range of
+              taxonomic groups.",
+  journal  = "Molecular ecology",
+  volume   =  21,
+  number   =  11,
+  pages    = "2565--2573",
+  month    =  jun,
+  year     =  2012,
+  url      = "http://dx.doi.org/10.1111/j.1365-294X.2011.05418.x",
+  issn     = "0962-1083, 1365-294X",
+  pmid     = "22151771",
+  doi      = "10.1111/j.1365-294X.2011.05418.x"
+}
+
+
+@ARTICLE{Valentini2009-ay,
+  title     = "{New perspectives in diet analysis based on DNA barcoding and
+               parallel pyrosequencing: the trnL approach}",
+  author    = "Valentini, Alice and Miquel, Christian and Nawaz, Muhammad Ali
+               and Bellemain, Eva and Coissac, Eric and Pompanon, Fran{\c c}ois
+               and Gielly, Ludovic and Cruaud, Corinne and Nascetti, Giuseppe
+               and Wincker, Patrick and Swenson, Jon E and Taberlet, Pierre",
+  abstract  = "The development of DNA barcoding (species identification using a
+               standardized DNA sequence), and the availability of recent DNA
+               sequencing techniques offer new possibilities in diet analysis.
+               DNA fragments shorter than 100-150 bp remain in a much higher
+               proportion in degraded DNA samples and can be recovered from
+               faeces. As a consequence, by using universal primers that
+               amplify a very short but informative DNA fragment, it is
+               possible to reliably identify the plant taxon that has been
+               eaten. According to our experience and using this identification
+               system, about 50\% of the taxa can be identified to species
+               using the trnL approach, that is, using the P6 loop of the
+               chloroplast trnL (UAA) intron. We demonstrated that this new
+               method is fast, simple to implement, and very robust. It can be
+               applied for diet analyses of a wide range of phytophagous
+               species at large scales. We also demonstrated that our approach
+               is efficient for mammals, birds, insects and molluscs. This
+               method opens new perspectives in ecology, not only by allowing
+               large-scale studies on diet, but also by enhancing studies on
+               resource partitioning among competing species, and describing
+               food webs in ecosystems.",
+  journal   = "Molecular ecology resources",
+  publisher = "WILEY-BLACKWELL PUBLISHING, INC",
+  volume    =  9,
+  number    =  1,
+  pages     = "51--60",
+  month     =  jan,
+  year      =  2009,
+  url       = "http://dx.doi.org/10.1111/j.1755-0998.2008.02352.x",
+  address   = "COMMERCE PLACE, 350 MAIN ST, MALDEN 02148, MA USA",
+  keywords  = "chloroplast DNA; diet analysis; DNA barcoding; faeces;
+               pyrosequencing; trnL (UAA) intron; universal primers",
+  language  = "en",
+  issn      = "1755-098X",
+  pmid      = "21564566",
+  doi       = "10.1111/j.1755-0998.2008.02352.x"
+}
+
+
+@ARTICLE{Kowalczyk2011-kg,
+  title     = "{Influence of management practices on large herbivore diet---Case
+               of European bison in Bia{\l}owie{\.z}a Primeval Forest (Poland)}",
+  author    = "Kowalczyk, Rafa{\l} and Taberlet, Pierre and Coissac, Eric and
+               Valentini, Alice and Miquel, Christian and Kami{\'n}ski, Tomasz
+               and W{\'o}jcik, Jan M",
+  abstract  = "Large herbivores are keystone species in many forest areas, as
+               they shape the structure, species diversity and functioning of
+               those ecosystems. The European bison Bison bonasus has been
+               successfully restored after extinction in the wild at the
+               beginning of 20th century. As free-ranging populations of the
+               species were re-established mainly in forest habitats, knowledge
+               of the impact by the largest European terrestrial mammal on tree
+               stands is essential. This helps to make management and
+               conservation decisions for viable population maintenance of the
+               species in the wild. Using a novel DNA-based method of herbivore
+               diet analysis, the trnL approach (DNA-barcoding), we
+               investigated the influence of different foraging conditions
+               (access to supplementary fodder) on bison diet in winter and its
+               potential impact on woody species. Faecal samples were collected
+               from different bison treatment groups: (1) intensively fed; (2)
+               less intensively fed; (3) non-fed utilising forest habitats; and
+               (4) non-fed utilising agricultural areas surrounding the Forest.
+               These were analysed to estimate the proportion of different
+               plant groups consumed by bison. Bison groups differed
+               significantly in their diet. The amount of woody materials
+               (trees and shrubs) consumed by bison increased with decreasing
+               access to supplementary fodder, ranging from 16\% in intensively
+               fed bison to 65\% in non-fed bison utilising forest habitats.
+               Inversely, the amount of herbs, grasses and sedges decreased
+               from 82\% in intensively fed bison to 32\% in non fed bison
+               utilising forest habitats. The species of trees mainly browsed
+               by bison, Carpinus/Corylus, Betula sp. and Salix sp., were of
+               lower economic importance for forest management. The impact of
+               bison on tree species needs further investigation, however, we
+               can predict that browsing by bison, mainly on Carpinus/Corylus,
+               makes an insignificant impact on forestry due to the high and
+               increasing representation of this species in the forest
+               understory. Supplementary feeding has several negative effects
+               on bison ecology and health, therefore reduced and distributed
+               supplementary feeding should be applied as the management
+               practice in the Bia{\l}owie{\.z}a Forest.",
+  journal   = "Forest ecology and management",
+  publisher = "ELSEVIER SCIENCE BV",
+  volume    =  261,
+  number    =  4,
+  pages     = "821--828",
+  month     =  feb,
+  year      =  2011,
+  url       = "http://www.sciencedirect.com/science/article/pii/S0378112710006961",
+  annote    = "di",
+  address   = "PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS",
+  keywords  = "Bison bonasus; trnL approach; DNA barcoding; Diet analysis;
+               Large ungulates; Wildlife management; L approach",
+  language  = "English",
+  issn      = "0378-1127",
+  doi       = "10.1016/j.foreco.2010.11.026"
+}
+
+
+@ARTICLE{Deagle2009-yh,
+  title    = "{Analysis of Australian fur seal diet by pyrosequencing prey DNA
+              in faeces}",
+  author   = "Deagle, Bruce E and Kirkwood, Roger and Jarman, Simon N",
+  abstract = "DNA-based techniques have proven useful for defining trophic
+              links in a variety of ecosystems and recently developed
+              sequencing technologies provide new opportunities for dietary
+              studies. We investigated the diet of Australian fur seals
+              (Arctocephalus pusillus doriferus) by pyrosequencing prey DNA
+              from faeces collected at three breeding colonies across the
+              seals' range. DNA from 270 faecal samples was amplified with four
+              polymerase chain reaction primer sets and a blocking primer was
+              used to limit amplification of fur seal DNA. Pooled amplicons
+              from each colony were sequenced using the Roche GS-FLX platform,
+              generating > 20,000 sequences. Software was developed to sort and
+              group similar sequences. A total of 54 bony fish, 4 cartilaginous
+              fish and 4 cephalopods were identified based on the most
+              taxonomically informative amplicons sequenced (mitochondrial
+              16S). The prevalence of sequences from redbait (Emmelichthys
+              nitidus) and jack mackerel (Trachurus declivis) confirm the
+              importance of these species in the seals' diet. A third fish
+              species, blue mackerel (Scomber australasicus), may be a more
+              important prey species than previously recognised. There were
+              major differences in the proportions of prey DNA recovered in
+              faeces from different colonies, probably reflecting differences
+              in prey availability. Parallel hard-part analysis identified
+              largely the same main prey species as did the DNA-based
+              technique, but with lower species diversity and no remains from
+              cartilaginous prey. The pyrosequencing approach presented
+              significantly expands the capabilities of DNA-based methods of
+              dietary analysis and is suitable for large-scale diet
+              investigations on a broad range of animals.",
+  journal  = "Molecular ecology",
+  volume   =  18,
+  number   =  9,
+  pages    = "2022--2038",
+  month    =  may,
+  year     =  2009,
+  url      = "http://dx.doi.org/10.1111/j.1365-294X.2009.04158.x",
+  issn     = "0962-1083, 1365-294X",
+  pmid     = "19317847",
+  doi      = "10.1111/j.1365-294X.2009.04158.x"
+}
+
+
+@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{Schloss2009-qy,
+  title    = "{Introducing mothur: open-source, platform-independent,
+              community-supported software for describing and comparing
+              microbial communities}",
+  author   = "Schloss, Patrick D and Westcott, Sarah L and Ryabin, Thomas and
+              Hall, Justine R and Hartmann, Martin and Hollister, Emily B and
+              Lesniewski, Ryan A and Oakley, Brian B and Parks, Donovan H and
+              Robinson, Courtney J and Sahl, Jason W and Stres, Blaz and
+              Thallinger, Gerhard G and Van Horn, David J and Weber, Carolyn F",
+  abstract = "mothur aims to be a comprehensive software package that allows
+              users to use a single piece of software to analyze community
+              sequence data. It builds upon previous tools to provide a
+              flexible and powerful software package for analyzing sequencing
+              data. As a case study, we used mothur to trim, screen, and align
+              sequences; calculate distances; assign sequences to operational
+              taxonomic units; and describe the alpha and beta diversity of
+              eight marine samples previously characterized by pyrosequencing
+              of 16S rRNA gene fragments. This analysis of more than 222,000
+              sequences was completed in less than 2 h with a laptop computer.",
+  journal  = "Applied and environmental microbiology",
+  volume   =  75,
+  number   =  23,
+  pages    = "7537--7541",
+  month    =  dec,
+  year     =  2009,
+  url      = "http://dx.doi.org/10.1128/AEM.01541-09",
+  issn     = "0099-2240, 1098-5336",
+  pmid     = "19801464",
+  doi      = "10.1128/AEM.01541-09",
+  pmc      = "PMC2786419"
+}
+
+
+@ARTICLE{Caporaso2010-ii,
+  title   = "{QIIME allows analysis of high-throughput community sequencing data}",
+  author  = "Caporaso, J Gregory and Kuczynski, Justin and Stombaugh, Jesse and
+             Bittinger, Kyle and Bushman, Frederic D and Costello, Elizabeth K
+             and Fierer, Noah and Pe{\~n}a, Antonio Gonzalez and Goodrich,
+             Julia K and Gordon, Jeffrey I and Huttley, Gavin A and Kelley,
+             Scott T and Knights, Dan and Koenig, Jeremy E and Ley, Ruth E and
+             Lozupone, Catherine A and McDonald, Daniel and Muegge, Brian D and
+             Pirrung, Meg and Reeder, Jens and Sevinsky, Joel R and Turnbaugh,
+             Peter J and Walters, William A and Widmann, Jeremy and Yatsunenko,
+             Tanya and Zaneveld, Jesse and Knight, Rob",
+  journal = "Nature methods",
+  volume  =  7,
+  number  =  5,
+  pages   = "335--336",
+  month   =  may,
+  year    =  2010,
+  url     = "http://dx.doi.org/10.1038/nmeth.f.303",
+  issn    = "1548-7091, 1548-7105",
+  pmid    = "20383131",
+  doi     = "10.1038/nmeth.f.303",
+  pmc     = "PMC3156573"
+}

doc/lib/descriptions/_obigrep.qmd

@@ -0,0 +1 @@
+The `obigrep` command is somewhat analogous to the standard Unix `grep` command. It selects a subset of sequence records from a sequence file. A sequence record is a complex object consisting of an identifier, a set of attributes (a key, defined by its name, associated with a value), a definition, and the sequence itself. Instead of working text line by text line like the standard Unix tool, `obigrep` selection is done sequence record by sequence record. A large number of options allow you to refine the selection on any element of the sequence. `obigrep` allows you to specify multiple conditions simultaneously (which take on the value `TRUE` or `FALSE`) and only those sequence records which meet all conditions (all conditions are `TRUE`) are selected. `obigrep` is able to work on two paired read files. The selection criteria apply to one or the other of the readings in each pair depending on the mode chosen (**\--paired-mode** option). In all cases the selection is applied in the same way to both files, thus maintaining their consistency.

doc/lib/options/_input.qmd

@@ -0,0 +1,22 @@
+{{< include ../lib/options/input/_embl.qmd >}}
+
+{{< include ../lib/options/input/_genbank.qmd >}}
+
+{{< include ../lib/options/input/_ecopcr.qmd >}}
+
+
+**\--input-OBI-header**
+
+: OBITools V4 introduced a new format based on [JSON](https://en.wikipedia.org/wiki/JSON) for storing annotations in the FASTA and FASTQ title lines. Nevertheless they continue to parse the old OBITools format for these annotation (`KEY=VALUE;`). Both formats for annotations are automatically recognizd. That option force the parsing of the annotations following the genuine OBITools format.
+
+**\--input-json-header**
+
+: Forces the parsing of the FASTA and FASTQ annotations usng the new OBITools JSON based format. 
+
+**\--solexa**
+
+: Sequence quality scores in FASTQ format are supposed to follow to Sanger convention for their ASCII encoding. Somme old raw data files produced by Solexa sequencers used another encoding schema. That options allows to correctly read these ald FASTQ files.  
+
+**\--no-order**
+
+: OBITools V4 are massively parallelized. When several input files are provided this option allows to processed them in parallel. But the order of the file indicated on the command line will no more be related to the order of the sequences in the output of the command.

doc/lib/options/_output.qmd

@@ -0,0 +1,11 @@
+**\--fasta-output** 
+
+**\--fastq-output** 
+
+**\--output-OBI-header**, **-O** 
+
+**\--output-json-header**
+
+{{< include ../lib/options/output/_out.qmd >}}
+
+{{< include ../lib/options/output/_compress.qmd >}}

doc/lib/options/_system.qmd

@@ -0,0 +1,15 @@
+**Helpful options**
+
+{{< include ../lib/options/system/_help.qmd >}}
+
+{{< include ../lib/options/system/_no-progressbar.qmd >}}
+
+**Managing parallel execution**
+
+{{< include ../lib/options/system/_max-cpu.qmd >}}
+
+{{< include ../lib/options/system/_workers.qmd >}}
+
+**OBITools debuging related options**
+
+{{< include ../lib/options/system/_debug.qmd >}}

doc/lib/options/input/_ecopcr.qmd

@@ -0,0 +1,3 @@
+**\--ecopcr**
+
+: indicates that the input data follow the ecopcr tabular format produced by [ecoPCR](https://metabarcoding.org/ecopcr).

doc/lib/options/input/_embl.qmd

@@ -0,0 +1,4 @@
+**\--embl**
+
+: indicates that the input data follow the EMBL flatfile format.
+

doc/lib/options/input/_genbank.qmd

@@ -0,0 +1,4 @@
+**\--genbank**
+
+: indicates that the input data follow the Genbank flatfile format.
+

doc/lib/options/output/_compress.qmd

@@ -0,0 +1,3 @@
+**\--compress**, **-Z**
+
+: The ouput is compressed following the [gzip](https://en.wikipedia.org/wiki/Gzip) format.

doc/lib/options/output/_out.qmd

@@ -0,0 +1,3 @@
+**\--out** _FILENAME_, **-o**
+
+: OBITools, as all standard UNIX tools, print their results to the standard output (`stdout`). To save them, stdout must be redirected to a file. That option allows to specify explicitely an output file to the command. This is especially useful when OBITools are processing paired files. In that later case, the indicated output file names is modified by adding to it the *\_R1* (forward file) and *\_R2* (reverse file) suffix just before the extensions (*e.g.* sequence.fasta becomes sequence_R1.fasta and sequence_R2.fasta). If that option is not specified and paired files are processed only the forward data are ouputed to the _stdout_.

doc/lib/options/selection/_max-count.qmd

@@ -0,0 +1,3 @@
+**\--max-count** | **-C** _COUNT_
+
+: only sequences reprensenting no more than _COUNT_ reads will be selected. That option rely on the `count` attribute. If the `count` attribute is not defined for a sequence record, it is assumed equal to $1$. 

doc/lib/options/selection/_min-count.qmd

@@ -0,0 +1,3 @@
+**\--min-count** | **-c** _COUNT_
+
+: only sequences reprensenting at least _COUNT_ reads will be selected. That option rely on the `count` attribute. If the `count` attribute is not defined for a sequence record, it is assumed equal to $1$. 

doc/lib/options/system/_debug.qmd

@@ -0,0 +1,2 @@
+**\--debug**
+

doc/lib/options/system/_help.qmd

@@ -0,0 +1,3 @@
+**\--help**, **-h**
+
+: Display a friendly help message.

doc/lib/options/system/_max-cpu.qmd

@@ -0,0 +1,3 @@
+**\--max-cpu**
+
+: OBITools V4 are able to run in parallel on all the CPU cores available on the computer. It is sometime required to limit the computation to a smaller number of cores. That option specify the maximum number of cores that the OBITools command can use. This behaviour can also be set up using the `OBIMAXCPU` environment variable.

doc/lib/options/system/_no-progressbar.qmd

@@ -0,0 +1,2 @@
+**\--no-progressbar**
+

doc/lib/options/system/_workers.qmd

@@ -0,0 +1,2 @@
+**\--workers**, **-w**
+