Mercurial > repos > cmonjeau > lordec

changeset 0:46caddb8b8eb

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author cmonjeau
date Fri, 05 Jun 2015 11:41:13 -0400
parents
children 7e727cb0fdb1
files lordec_correct.xml lordec_graph.xml lordec_stat.xml lordec_trim.xml tool_dependencies.xml
diffstat 5 files changed, 327 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/lordec_correct.xml	Fri Jun 05 11:41:13 2015 -0400
@@ -0,0 +1,90 @@
+<tool id="lordeccorrect" name="lordeccorrect" version="0.5.3">
+  <description>is an efficient tool for correcting sequencing errors in PacBio reads</description>
+  <requirements>
+    <requirement type="package" version="0.5.3">lordec</requirement>
+  </requirements>
+  <command>
+lordec-correct
+-2 $short_reads
+-i $long_reads
+-k $kmer_len
+-o $corrected_read_file
+-s $solid_threshold
+-S $stat_file
+#if str( $advanced_options.advanced_options_selector) == "advanced"
+-t $advanced_options.trials
+-b $advanced_options.branch
+-e $advanced_options.errorrate
+-T $advanced_options.threads
+#end if 
+2&gt;1
+  </command>
+
+  <inputs>
+<!-- Input data files -->
+<param name="short_reads" type="data" format="fasta,fastq.gz,fastq" label="short read FASTA/Q file" />
+<param name="long_reads" type="data" format="fasta,fastq.gz,fastq" label="long read FASTA/Q file" help="PacBio reads files" />
+<param name="kmer_len" type="integer" label="Size of kmers" value="31" help="Only uneven number"/>
+<param name="solid_threshold" type="integer" label="solidity abundance threshold for k-mers" value="4" />
+<conditional name="advanced_options">
+<param name="advanced_options_selector" type="select" label="lordec correct advanced options">
+<option value="default" selected="true">Default</option>
+<option value="advanced">Advanced</option>
+</param>
+<when value="default"></when>
+<when value="advanced">
+<param name="trials" type="integer" label="number of target k-mers" value="5" />
+<param name="branch" type="integer" label="maximum number of branches to explore" value="200" />
+<param name="errorrate" type="float" label="maximum error rate" value="0.4" />
+<param name="threads" type="integer" label="number of threads" value="1" />
+</when>
+</conditional>
+
+  </inputs>
+
+  <outputs>
+      <data format="fasta"  name="corrected_read_file" label="${tool.name} on ${on_string}: corrected_read_file.fa" />
+      <data format="txt"  name="stat_file" label="${tool.name} on ${on_string}: stat_file" />
+  </outputs>
+  <help>
+
+**Description**
+Program for correcting sequencing errors in PacBio reads using highly accurate short reads (e.g. Illumina).
+
+LoRDEC outputs the corrected reads to the given file in FASTA format. The regions that remain weak after the correction are outputted in lower case characters and the solid regions are outputted in upper case characters.
+
+-------
+
+**Web site**
+
+http://www.atgc-montpellier.fr/lordec/
+
+-------
+
+**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. &lt;https://www.e-biogenouest.org/resources/128&gt;`_
+
+  </help>
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btu538</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>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/lordec_graph.xml	Fri Jun 05 11:41:13 2015 -0400
@@ -0,0 +1,82 @@
+<tool id="lordecgraph" name="lordec_graph" version="0.5.3">
+  <description>is an efficient tool to generate de Bruijn graph from PacBio corrected reads</description>
+  <requirements>
+    <requirement type="package" version="0.5.3">lordec</requirement>
+  </requirements>
+  <command>
+lordec-build-SR-graph
+-2 $short_reads
+-k $kmer_len
+-s $solid_threshold
+-g $outgraph
+#if str( $advanced_options.advanced_options_selector) == "advanced"
+-T $advanced_options.threads
+#end if 
+2&gt;1
+  </command>
+
+  <inputs>
+<!-- Input data files -->
+<param name="short_reads" type="data" format="fasta,fastq.gz,fastq" label="short read FASTA/Q file" />
+<param name="kmer_len" type="integer" label="Size of kmers" value="31" help="Only uneven number"/>
+<param name="solid_threshold" type="integer" label="solidity abundance threshold for k-mers" value="4" />
+
+<conditional name="advanced_options">
+<param name="advanced_options_selector" type="select" label="lordec graph advanced options">
+<option value="default" selected="true">Default</option>
+<option value="advanced">Advanced</option>
+</param>
+<when value="default"></when>
+<when value="advanced">
+<param name="threads" type="integer" label="number of threads" value="1" />
+</when>
+</conditional>
+
+  </inputs>
+
+  <outputs>
+      <data format="HDF5"  name="outgraph" label="${tool.name} on ${on_string}: de_Bruijn_graph" />
+  </outputs>
+  <help>
+
+**Description**
+To correct long reads or to generate k-mer statistics, LoRDEC builds a de Bruijn Graph from the short reads file. This program allows to build and save the graph in a file before doing such analyses, and then to load the graph file instead of computing it from the short read file. This saves time if you reuse the graph several times. The graph is saved in [[http://fr.wikipedia.org/wiki/Hierarchical_Data_Format][Hierarchical Data Format]] (HDF5: version 5).
+
+
+LoRDEC outputs the corrected reads to the given file in FASTA format. The regions that remain weak after the correction are outputted in lower case characters and the solid regions are outputted in upper case characters.
+
+-------
+
+**Web site**
+
+http://www.atgc-montpellier.fr/lordec/
+
+-------
+
+**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. &lt;https://www.e-biogenouest.org/resources/128&gt;`_
+
+  </help>
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btu538</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>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/lordec_stat.xml	Fri Jun 05 11:41:13 2015 -0400
@@ -0,0 +1,83 @@
+<tool id="lordecstat" name="lordecstat" version="0.5.3">
+  <description>is an efficient tool to generate statistics on solid and weak k-mers in PacBio corrected reads</description>
+  <requirements>
+    <requirement type="package" version="0.5.3">lordec</requirement>
+  </requirements>
+  <command>
+lordec-stat
+-2 $short_reads
+-i $long_reads
+-k $kmer_len
+-s $solid_threshold
+-S $stat_file
+#if str( $advanced_options.advanced_options_selector) == "advanced"
+-T $advanced_options.threads
+#end if 
+2&gt;1
+  </command>
+
+  <inputs>
+<!-- Input data files -->
+<param name="short_reads" type="data" format="fasta,fastq.gz,fastq" label="short read FASTA/Q file" />
+<param name="long_reads" type="data" format="fasta,fastq.gz,fastq" label="long read FASTA/Q file" help="PacBio reads files" />
+<param name="kmer_len" type="integer" label="Size of kmers" value="31" help="Only uneven number"/>
+<param name="solid_threshold" type="integer" label="solidity abundance threshold for k-mers" value="4" />
+
+<conditional name="advanced_options">
+<param name="advanced_options_selector" type="select" label="lordec stat advanced options">
+<option value="default" selected="true">Default</option>
+<option value="advanced">Advanced</option>
+</param>
+<when value="default"></when>
+<when value="advanced">
+<param name="threads" type="integer" label="number of threads" value="1" />
+</when>
+</conditional>
+
+  </inputs>
+
+  <outputs>
+      <data format="txt"  name="stat_file" label="${tool.name} on ${on_string}: stat_file" />
+  </outputs>
+  <help>
+
+**Description**
+Program to generate statistics on solid and weak k-mers after correcting sequencing errors in PacBio reads using highly accurate short reads (e.g. Illumina).
+
+LoRDEC outputs the corrected reads to the given file in FASTA format. The regions that remain weak after the correction are outputted in lower case characters and the solid regions are outputted in upper case characters.
+
+-------
+
+**Web site**
+
+http://www.atgc-montpellier.fr/lordec/
+
+-------
+
+**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. &lt;https://www.e-biogenouest.org/resources/128&gt;`_
+
+  </help>
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btu538</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>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/lordec_trim.xml	Fri Jun 05 11:41:13 2015 -0400
@@ -0,0 +1,66 @@
+<tool id="lordectrim" name="lordectrim" version="0.5.3">
+  <description>is an efficient tool to trim weak regions of PacBio corrected reads</description>
+  <requirements>
+    <requirement type="package" version="0.5.3">lordec</requirement>
+  </requirements>
+  <command>
+#if $split
+lordec-trim-split
+#else
+lordec-trim
+#end if
+-i $long_reads
+-o $corrected_read_file
+</command>
+
+  <inputs>
+<!-- Input data files -->
+<param name="long_reads" type="data" format="fasta,fastq.gz,fastq" label="long read FASTA/Q file" help="PacBio reads files" />
+<param name="split" type="boolean" label="use the split option" help="trim all weak regions and split the reads on inner weak regions" />
+  </inputs>
+
+  <outputs>
+      <data format="fasta"  name="corrected_read_file" label="${tool.name} on ${on_string}: corrected_read_file.fa" />
+  </outputs>
+  <help>
+
+**Description**
+Program for correcting sequencing errors in PacBio reads using highly accurate short reads (e.g. Illumina).
+
+LoRDEC outputs the corrected reads to the given file in FASTA format. The regions that remain weak after the correction are outputted in lower case characters and the solid regions are outputted in upper case characters.
+
+-------
+
+**Web site**
+
+http://www.atgc-montpellier.fr/lordec/
+
+-------
+
+**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. &lt;https://www.e-biogenouest.org/resources/128&gt;`_
+
+  </help>
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btu538</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>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Fri Jun 05 11:41:13 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="lordec" version="0.5.3">
+      <repository changeset_revision="d528c1c6a909" name="package_lordec" owner="cmonjeau" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>