Mercurial > repos > cmonjeau > stacks
view STACKS_refmap.xml @ 1:ccfa8e539bdf
add archive toolbox to manage zip outputs
| author | cmonjeau |
|---|---|
| date | Mon, 24 Aug 2015 10:09:14 +0000 |
| parents | d6ba40f6c824 |
| children |
line wrap: on
line source
<tool id="STACKSrefmap" name="STACKS : Reference map" force_history_refresh="True"> <description>Run the STACKS ref_map.pl wrapper</description> <configfiles> <configfile name="parent_sequences"> #if str( $options_usage.options_usage_selector ) == "genetic" #for $input in $options_usage.parent_sequence: ${input.display_name}::${input} #end for #end if </configfile> <configfile name="progeny_sequences"> #if str( $options_usage.options_usage_selector ) == "genetic" and str( $options_usage.options_progeny.options_progeny_selector ) == "yes" #for $input in $options_usage.options_progeny.progeny_sequence: ${input.display_name}::${input} #end for #end if </configfile> <configfile name="individual_samples"> #if str( $options_usage.options_usage_selector ) == "population" #for $input in $options_usage.individual_sample: ${input.display_name}::${input} #end for #end if </configfile> </configfiles> <requirements> <requirement type="package" version="1.18">stacks</requirement> </requirements> <command interpreter="python"> STACKS_refmap.py #if str( $options_usage.options_usage_selector ) == "genetic" -p $parent_sequences #if str( $options_usage.options_progeny.options_progeny_selector ) == "yes" -r $progeny_sequences #end if #else -s $individual_samples #if str( $options_usage.options_popmap.popmap_selector) == "yes" -O $options_usage.options_popmap.popmap #end if #end if -n $mismatchbetlocibuild -m $mincov --bound_low $snp_options.boundlow --bound_high $snp_options.boundhigh --alpha $snp_options.alpha --catalogsnps $catalogsnps --catalogalleles $catalogalleles --catalogtags $catalogtags --logfile $output --compress_output $output_compress ##additionnal outputs --total_output $total_output --tags_output $tags_output --snps_output $snps_output --alleles_output $alleles_output --matches_output $matches_output </command> <inputs> <conditional name="options_usage"> <param name="options_usage_selector" type="select" label="Select your usage"> <option value="genetic" selected="true">Genetic map</option> <option value="population">Population</option> </param> <when value="genetic"> <param name="parent_sequence" format="sam,zip,tar.gz" type="data" multiple="true" label="Files containing parent sequences" help="SAM/ZIP/TAR.GZ files" /> <conditional name="options_progeny"> <param name="options_progeny_selector" type="select" label="Use progeny files"> <option value="yes" selected="true">Yes</option> <option value="no">No</option> </param> <when value="yes"> <param name="progeny_sequence" format="sam,zip,tar.gz" type="data" multiple="true" label="Files containing progeny sequences" help="SAM/ZIP/TAR.GZ files containing progeny sequences from a mapping cross" /> </when> <when value="no"> </when> </conditional> </when> <when value="population"> <param name="individual_sample" format="sam,zip,tar.gz" type="data" multiple="true" label="Files containing an individual sample from a population" help="SAM/ZIP/TAR.GZ files." /> <conditional name="options_popmap"> <param name="popmap_selector" type="select" label="Analyzing one or more populations?" > <option value="no" selected="true">No</option> <option value="yes">Yes</option> </param> <when value="no"></when> <when value="yes"> <param name="popmap" type="data" format="tabular,txt" label="Specify a population map" help="If analyzing one or more populations, specify a population map" /> </when> </conditional> </when> </conditional> <param name="mismatchbetlocibuild" type="integer" value="0" label="specify the number of mismatches allowed between loci when building the catalog" /> <param name="mincov" type="integer" value="1" label="Minimum depth of coverage" help="specify the minimum depth of coverage to report a stack in pstacks" /> <!-- SNP Model options --> <section name="snp_options" title="SNP_Model_Options" expanded="False"> <param name="boundlow" type="float" value="0.0" min="0.0" max="1.0" label="lower bound for epsilon, the error rate" help="between 0 and 1.0"/> <param name="boundhigh" type="float" value="1.0" min="0.0" max="1.0" label="upper bound for epsilon, the error rate" help="between 0 and 1.0" /> <param name="alpha" type="float" value="0.05" min="0.001" max="0.1" label="chi square significance level required to call a heterozygote or homozygote" help="either 0.1, 0.05 (default), 0.01, or 0.001" /> </section> <!-- Output options --> <param name="output_compress" type="select" label="Output type" help="please see below for details"> <option value="default" selected="true">No compression</option> <option value="categories">Compressed by categories</option> <option value="total">Compressed all outputs</option> </param> </inputs> <outputs> <data format="txt" name="output" label="result.log with ${tool.name} on ${on_string}" /> <data format="txt" name="additional" label="additional file with ${tool.name}" hidden="true"> <discover_datasets pattern="__designation_and_ext__" directory="galaxy_outputs" visible="true" /> </data> <data format="tabular" name="catalogsnps" label="catalog.snps with ${tool.name} on ${on_string}" /> <data format="tabular" name="catalogalleles" label="catalog.alleles with ${tool.name} on ${on_string}" /> <data format="tabular" name="catalogtags" label="catalog.tags with ${tool.name} on ${on_string}" /> <!-- additionnal output archives --> <data format="zip" name="total_output" label="total_output.zip with ${tool.name} on ${on_string}" > <filter>output_compress == "total"</filter> </data> <data format="zip" name="tags_output" label="tags_output.zip with ${tool.name} on ${on_string}" > <filter>output_compress == "categories"</filter> </data> <data format="zip" name="snps_output" label="snps_output.zip with ${tool.name} on ${on_string}" > <filter>output_compress == "categories"</filter> </data> <data format="zip" name="alleles_output" label="alleles_output.zip with ${tool.name} on ${on_string}" > <filter>output_compress == "categories"</filter> </data> <data format="zip" name="matches_output" label="matches_output.zip with ${tool.name} on ${on_string}" > <filter>output_compress == "categories"</filter> </data> </outputs> <help> .. class:: infomark **What it does** This program expects data that have been aligned to a reference genome, and can accept data directly from Bowtie, or from any aligner that can produce SAM format. To avoid datasets names problems, we recommand the use of the *Map with BWA for STACKS tool*. This program will execute each of the Stacks components: first, running pstacks on each of the samples specified, building loci (based on the reference alignment) and calling SNPs in each. Second, cstacks will be run to create a catalog of all loci specified as 'parents' or 'samples' on the command line, again using alignment to match loci in the catalog. Finally, sstacks will be executed to match each sample against the catalog. The ref_map.pl program will also load the results of each stage of the analysis: individual loci, the catalog, and matches against the catalog into the database (although this can be disabled). After matching the program will build a database index to speed up access (index_radtags.pl) and enable web-based filtering. -------- **Created by:** Stacks was developed by Julian Catchen with contributions from Angel Amores, Paul Hohenlohe, and Bill Cresko -------- **Example:** Input files: - SAM, zip, tar.gz - Population map:: indv_01 1 indv_02 1 indv_03 1 indv_04 2 indv_05 2 indv_06 2 Output files: - XXX.tags.tsv file:: Column Name Description 1 Sql ID This field will always be "0", however the MySQL database will assign an ID when it is loaded. 2 Sample ID Each sample passed through Stacks gets a unique id for that sample. 3 Stack ID Each stack formed gets an ID. 4 Chromosome If aligned to a reference genome using pstacks, otherwise it is blank. 5 Basepair If aligned to ref genome using pstacks. 6 Strand If aligned to ref genome using pstacks. 7 Sequence Type Either 'consensus', 'primary' or 'secondary', see the Stacks paper for definitions of these terms. 8 Sequence ID The individual sequence read that was merged into this stack. 9 Sequence The raw sequencing read. 10 Deleveraged Flag If "1", this stack was processed by the deleveraging algorithm and was broken down from a larger stack. 11 Blacklisted Flag If "1", this stack was still confounded depsite processing by the deleveraging algorithm. 12 Lumberja ckstack Flag If "1", this stack was set aside due to having an extreme depth of coverage. Notes: For the tags file, each stack will start in the file with a consensus sequence for the entire stack followed by the flags for that stack. Then, each individual read that was merged into that stack will follow. The next stack will start with another consensus sequence. - XXX.snps.tsv file:: Column Name Description 1 Sql ID This field will always be "0", however the MySQL database will assign an ID when it is loaded. 2 Sample ID 3 Stack ID 4 SNP Column 5 Likelihood ratio From the SNP-calling model. 6 Rank_1 Majority nucleotide. 7 Rank_2 Alternative nucleotide. Notes: If a stack has two SNPs called within it, then there will be two lines in this file listing each one. - XXX.alleles.tsv file:: Column Name Description 1 Sql ID This field will always be "0", however the MySQL database will assign an ID when it is loaded. 2 Sample ID 3 Stack ID 4 Haplotype The haplotype, as constructed from the called SNPs at each locus. 5 Percent Percentage of reads that have this haplotype 6 Count Raw number of reads that have this haplotype - XXX.matches.tsv file:: Column Name Description 1 Sql ID This field will always be "0", however the MySQL database will assign an ID when it is loaded. 2 Batch ID 3 Catalog ID 4 Sample ID 5 Stack ID 6 Haplotype 7 Stack Depth Notes: Each line in this file records a match between a catalog locus and a locus in an individual, for a particular haplotype. The Batch ID plus the Catalog ID together represent a unique locus in the entire population, while the Sample ID and the Stack ID together represent a unique locus in an individual sample. - batch_X.sumstats.tsv Summary Statistics Output:: Batch ID The batch identifier for this data set. Locus ID Catalog locus identifier. Chromosome If aligned to a reference genome. Basepair If aligned to a reference genome. This is the alignment of the whole catalog locus. The exact basepair reported is aligned to the location of the RAD site (depending on whether alignment is to the positive or negative strand). Column The nucleotide site within the catalog locus. Population ID The ID supplied to the populations program, as written in the population map file. P Nucleotide The most frequent allele at this position in this population. Q Nucleotide The alternative allele. Number of Individuals Number of individuals sampled in this population at this site. P Frequency of most frequent allele. Observed Heterozygosity The proportion of individuals that are heterozygotes in this population. Observed Homozygosity The proportion of individuals that are homozygotes in this population. Expected Heterozygosity Heterozygosity expected under Hardy-Weinberg equilibrium. Expected Homozygosity Homozygosity expected under Hardy-Weinberg equilibrium. pi An estimate of nucleotide diversity. Smoothed pi A weighted average of p depending on the surrounding 3s of sequence in both directions. Smoothed pi P-value If bootstrap resampling is enabled, a p-value ranking the significance of p within this population. FIS The inbreeding coefficient of an individual (I) relative to the subpopulation (S). Smoothed FIS A weighted average of FIS depending on the surrounding 3s of sequence in both directions. Smoothed FIS P-value If bootstrap resampling is enabled, a p-value ranking the significance of FIS within this population. Private allele True (1) or false (0), depending on if this allele is only occurs in this population. - batch_X.fst_Y-Z.tsv Pairwise FST Output:: Batch ID The batch identifier for this data set. Locus ID Catalog locus identifier. Population ID 1 The ID supplied to the populations program, as written in the population map file. Population ID 2 The ID supplied to the populations program, as written in the population map file. Chromosome If aligned to a reference genome. Basepair If aligned to a reference genome. This is the alignment of the whole catalog locus. The exact basepair reported is aligned to the location of the RAD site (depending on whether alignment is to the positive or negative strand). Column The nucleotide site within the catalog locus. Overall pi An estimate of nucleotide diversity across the two populations. FST A measure of population differentiation. FET p-value P-value describing if the FST measure is statistically significant according to Fisher's Exact Test. Odds Ratio Fisher's Exact Test odds ratio CI High Fisher's Exact Test confidence interval. CI Low Fisher's Exact Test confidence interval. LOD Score Logarithm of odds score. Expected Heterozygosity Heterozygosity expected under Hardy-Weinberg equilibrium. Expected Homozygosity Homozygosity expected under Hardy-Weinberg equilibrium. Corrected FST FST with either the FET p-value, or a window-size or genome size Bonferroni correction. Smoothed FST A weighted average of FST depending on the surrounding 3s of sequence in both directions. Smoothed FST P-value If bootstrap resampling is enabled, a p-value ranking the significance of FST within this pair of populations. Instructions to add the functionality of archives management in Galaxy on the `eBiogenouest HUB wiki <https://www.e-biogenouest.org/wiki/ManArchiveGalaxy>`_ . -------- **Project links:** `STACKS website <http://creskolab.uoregon.edu/stacks/>`_ . `STACKS manual <http://creskolab.uoregon.edu/stacks/stacks_manual.pdf>`_ . `STACKS google group <https://groups.google.com/forum/#!forum/stacks-users>`_ . -------- **References:** -J. Catchen, P. Hohenlohe, S. Bassham, A. Amores, and W. Cresko. Stacks: an analysis tool set for population genomics. Molecular Ecology. 2013. -J. Catchen, S. Bassham, T. Wilson, M. Currey, C. O'Brien, Q. Yeates, and W. Cresko. The population structure and recent colonization history of Oregon threespine stickleback determined using restriction-site associated DNA-sequencing. Molecular Ecology. 2013. -J. Catchen, A. Amores, P. Hohenlohe, W. Cresko, and J. Postlethwait. Stacks: building and genotyping loci de novo from short-read sequences. G3: Genes, Genomes, Genetics, 1:171-182, 2011. -A. Amores, J. Catchen, A. Ferrara, Q. Fontenot and J. Postlethwait. Genome evolution and meiotic maps by massively parallel DNA sequencing: Spotted gar, an outgroup for the teleost genome duplication. Genetics, 188:799'808, 2011. -P. Hohenlohe, S. Amish, J. Catchen, F. Allendorf, G. Luikart. RAD sequencing identifies thousands of SNPs for assessing hybridization between rainbow trout and westslope cutthroat trout. Molecular Ecology Resources, 11(s1):117-122, 2011. -K. Emerson, C. Merz, J. Catchen, P. Hohenlohe, W. Cresko, W. Bradshaw, C. Holzapfel. Resolving postglacial phylogeography using high-throughput sequencing. Proceedings of the National Academy of Science, 107(37):16196-200, 2010. -------- **Integrated by:** Yvan Le Bras and Cyril Monjeaud GenOuest Bio-informatics Core Facility UMR 6074 IRISA INRIA-CNRS-UR1 Rennes (France) support@genouest.org If you use this tool in Galaxy, please cite : `Y. Le Bras, A. Roult, C. Monjeaud, M. Bahin, O. Quenez, C. Heriveau, A. Bretaudeau, O. Sallou, O. Collin, Towards a Life Sciences Virtual Research Environment : an e-Science initiative in Western France. JOBIM 2013. <https://www.e-biogenouest.org/resources/128>`_ </help> <citations> <citation type="doi">10.1111/mec.12354</citation> <citation type="doi">10.1111/mec.12330</citation> <citation type="doi">10.1534/g3.111.000240</citation> <citation type="doi">10.1534/genetics.111.127324</citation> <citation type="doi">10.1111/j.1755-0998.2010.02967.x</citation> <citation type="doi">10.1073/pnas.1006538107</citation> <citation type="bibtex">@INPROCEEDINGS{JOBIM2013, author = {Le Bras, Y. and ROULT, A. and Monjeaud, C. and Bahin, M. and Quenez, O. and Heriveau, C. and Bretaudeau, A. and Sallou, O. and Collin, O.}, title = {Towards a Life Sciences Virtual Research Environment: An e-Science initiative in Western France}, booktitle = {JOBIM 2013 Proceedings}, year = {2013}, url = {https://www.e-biogenouest.org/resources/128}, pages = {97-106} }</citation> </citations> </tool>