Mercurial > repos > bcclaywell > microbiome_pplacer_suite

changeset 6:3c50a937d7c1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bcclaywell
date Wed, 15 Apr 2015 19:14:23 -0400
parents 2d023c621bd0
children b6ece07bec6a
files alignment.xml bootstrap.xml classification.xml decorate.xml filter.xml macros.xml pplacer.xml preclassification.xml preprocessing.xml refpkgzip_to_refpkg.xml render_datatable.xml usearch.xml
diffstat 12 files changed, 133 insertions(+), 73 deletions(-) [+]
line wrap: on
line diff
--- a/alignment.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/alignment.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_alignment" name="Align query sequences" version="1.0.0">
   <description>with sequences in a reference package</description>
-  <requirements>
-    <requirement type="package">yapp_env</requirement>
-  </requirements>
   <macros>
     <import>macros.xml</import>
   </macros>
-  <version_command>echo "guppy $(guppy --version)"</version_command>
+  <requirements>
+    <requirement type="package">yapp_env</requirement>
+  </requirements>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
+  <version_command>echo "$(taxit -V); $(cmalign -h | grep INFERNAL); $(esl-alimerge -h | grep Easel)"</version_command>
   <command interpreter="bash">
     alignment-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="refpkg" type="data" format="refpkg" label="Reference package"/>
     <param name="input_seqs" type="data" format="fasta" label="Input sequences"/>
@@ -44,4 +44,8 @@
 reference sequences.
 
   </help>
+  <citations>
+    <expand macro="cite_taxtastic"/>
+    <expand macro="cite_infernal"/>
+  </citations>
 </tool>
--- a/bootstrap.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/bootstrap.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_bootstrap" name="Prepare data" version="1.1.0">
   <description>for analysis</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
   <requirements>
     <requirement type="package">yapp_env</requirement>
   </requirements>
-  <macros>
-    <import>macros.xml</import>
-  </macros>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
   <version_command>echo "bootstrap script 1.1.0"</version_command>
   <command interpreter="bash">
     bootstrap-wrapper.sh $config
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="plate_id" type="integer" value="1" label="Plate number"/>
     <conditional name="run_type">
--- a/classification.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/classification.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_classification" name="Output classifications" version="2.1.0">
   <description>in tabular format</description>
-  <requirements>
-    <requirement type="package">yapp_env</requirement>
-  </requirements>
   <macros>
     <import>macros.xml</import>
   </macros>
-  <version_command>echo "guppy $(guppy --version)"</version_command>
+  <requirements>
+    <requirement type="package">yapp_env</requirement>
+  </requirements>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
+  <version_command>echo "pplacer $(pplacer --version)"</version_command>
   <command interpreter="bash">
     classification-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="split_map" type="data" format="csv" label="Read-to-specimen map"/>
     <param name="label_map" type="data" format="csv" label="Specimen-to-label map"/>
@@ -101,4 +101,7 @@
     GLKT0ZE01CQ2BU             below_species       species  341694   0.073214
 
   </help>
+  <citations>
+    <expand macro="cite_pplacer"/>
+  </citations>
 </tool>
--- a/decorate.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/decorate.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_decorate" name="Decorate" version="1.0.0">
   <description>classification results with sample metadata</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
   <requirements>
     <requirement type="package">yapp_env</requirement>
   </requirements>
-  <macros>
-    <import>macros.xml</import>
-  </macros>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
   <version_command>echo "decorate script 1.0.0"</version_command>
   <command interpreter="bash">
     decorate-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="group_by_specimen" type="data" format="csv" label="Grouped-by-specimen classification"/>
     <param name="metadata" type="data" format="csv" label="Sample metadata"/>
--- a/filter.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/filter.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_filter" name="Filter and trim" version="1.2.0">
   <description>sequences</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
   <requirements>
     <requirement type="package">yapp_env</requirement>
   </requirements>
-  <macros>
-    <import>macros.xml</import>
-  </macros>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
   <version_command>seqmagick --version</version_command>
   <command interpreter="bash">
     filter-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <!-- TODO: can take either fasta+qual or fastq -->
     <param name="plate_id" type="integer" value="1" label="Plate number"/>
@@ -100,4 +100,8 @@
 .. _quality filter documentation: http://fhcrc.github.io/seqmagick/quality_filter.html
 
   </help>
+  <citations>
+    <expand macro="cite_seqmagick"/>
+    <expand macro="cite_biopython"/>
+  </citations>
 </tool>
--- a/macros.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/macros.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -5,4 +5,49 @@
     <regex match="traceback" level="fatal"/>
     <regex match="warning" level="warning"/>
   </macro>
+  <macro name="cite_seqmagick">
+    <citation type="bibtex">@MISC{fhcrc_seqmagick,
+  title       = {seqmagick: An imagemagick-like frontend to Biopython SeqIO},
+  author      = {McCoy, C. O. and Hodges, B. and Rosenthal, C. and Gallagher, A. and Matsen, IV, F. A.},
+  publisher   = {GitHub},
+  url         = "http://github.com/fhcrc/seqmagick",
+  note        = "version 0.5.0"
+}
+    </citation>
+  </macro>
+  <!-- Biopython 1.63 -->
+  <macro name="cite_biopython">
+    <citation type="doi">10.1093/bioinformatics/btp163</citation>
+  </macro>
+  <macro name="cite_taxtastic">
+    <citation type="bibtex">@MISC{fhcrc_taxtastic,
+  title       = {taxtastic: Create and maintain phylogenetic "reference packages" of biological sequences},
+  author      = {McCoy, C. O. and Hoffman, N. G. and Gallagher, A. and Hodges, B. and Ross, F. and Matsen, IV, F. A.},
+  publisher   = {GitHub},
+  url         = "http://github.com/fhcrc/taxtastic",
+  note        = "version 0.5.2"
+}
+    </citation>
+  </macro>
+  <!-- INFERNAL 1.1 -->
+  <macro name="cite_infernal">
+    <citation type="doi">10.1093/bioinformatics/btt509</citation>
+  </macro>
+  <!-- pplacer 1.1alpha
+       (the citation is for pplacer 1.0) -->
+  <macro name="cite_pplacer">
+    <citation type="doi">10.1186/1471-2105-11-538</citation>
+    <citation type="bibtex">@MISC{fhcrc_pplacer,
+  title       = {pplacer: Phylogenetic placement and downstream analysis},
+  author      = {Gallagher, A. and McCoy, C. O. and Claywell, B. C. and Small, C. T. and Hodges, B. and Hoffman, N. G. and Matsen, IV, F. A.},
+  publisher   = {GitHub},
+  url         = "http://github.com/matsen/pplacer",
+  note        = "version v1.1.alpha16-1-gf748c91"
+}
+    </citation>
+  </macro>
+  <!-- USEARCH 6 -->
+  <macro name="cite_usearch">
+    <citation type="doi">10.1093/bioinformatics/btq461</citation>
+  </macro>
 </macros>
--- a/pplacer.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/pplacer.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_pplacer" name="Place aligned sequences" version="1.0.0">
   <description>on a reference tree</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
   <requirements>
     <requirement type="package">yapp_env</requirement>
   </requirements>
-  <macros>
-    <import>macros.xml</import>
-  </macros>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
   <version_command>echo "pplacer $(pplacer --version)"</version_command>
   <command interpreter="bash">
     pplacer-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="refpkg" type="data" format="refpkg" label="Reference package"/>
     <param name="query_seqs" type="data" format="fasta" label="Query alignment"/>
@@ -41,13 +41,8 @@
 according to a reference alignment, producing taxonomic annotations which can
 be used for classification and visualization.
 
------
-
-**Citation**
-
-Matsen F, Kodner R, Armbrust E V: **pplacer: linear time maximum-likelihood and
-Bayesian phylogenetic placement of sequences onto a fixed reference tree**. BMC
-Bioinformatics 2010, **11**:1.
-
   </help>
+  <citations>
+    <expand macro="cite_pplacer"/>
+  </citations>
 </tool>
--- a/preclassification.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/preclassification.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_preclassification" name="Generate database" version="1.2.0">
   <description>for classification</description>
-  <requirements>
-    <requirement type="package">yapp_env</requirement>
-  </requirements>
   <macros>
     <import>macros.xml</import>
   </macros>
-  <version_command>echo "guppy $(guppy --version)"</version_command>
+  <requirements>
+    <requirement type="package">yapp_env</requirement>
+  </requirements>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
+  <version_command>echo "pplacer $(pplacer --version)"</version_command>
   <command interpreter="bash">
     preclassification-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="dedup_info" type="data" format="csv" label="Deduplication info"/>
     <param name="refpkg" type="data" format="refpkg" label="Reference package"/>
@@ -47,4 +47,7 @@
 in taxonomic classification.
 
   </help>
+  <citations>
+    <expand macro="cite_pplacer"/>
+  </citations>
 </tool>
--- a/preprocessing.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/preprocessing.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -1,18 +1,18 @@
 <tool id="PHYLO_preprocessing" name="Deduplicate sequences" version="3.0.0">
   <description>in preparation for alignment and placement</description>
-  <requirements>
-    <requirement type="package">yapp_env</requirement>
-  </requirements>
   <macros>
     <import>macros.xml</import>
   </macros>
-  <version_command>echo "guppy $(guppy --version)"</version_command>
+  <requirements>
+    <requirement type="package">yapp_env</requirement>
+  </requirements>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
+  <version_command>echo "pplacer $(pplacer --version)"</version_command>
   <command interpreter="bash">
     preprocessing-wrapper.sh ${config}
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="input_seqs" type="data" format="fasta" label="Input sequences"/>
     <param name="split_map" type="data" format="csv" label="Read-to-specimen map"/>
@@ -42,4 +42,7 @@
 This tool deduplicates input sequences in preparation for alignment and placement.
 
   </help>
+  <citations>
+    <expand macro="cite_pplacer"/>
+  </citations>
 </tool>
--- a/refpkgzip_to_refpkg.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/refpkgzip_to_refpkg.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -7,5 +7,12 @@
     <data name="output" format="refpkg"/>
   </outputs>
   <help>
+
+.. class:: infomark
+
+**What it does**
+
+This tool unpacks a reference package from a ZIP file.
+
   </help>
 </tool>
--- a/render_datatable.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/render_datatable.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -3,12 +3,12 @@
   <macros>
     <import>macros.xml</import>
   </macros>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
   <command interpreter="bash">
     render_datatable-wrapper.sh $config
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="input" type="data" format="csv" label="CSV file"/>
   </inputs>
--- a/usearch.xml	Thu Mar 26 16:56:09 2015 -0400
+++ b/usearch.xml	Wed Apr 15 19:14:23 2015 -0400
@@ -3,13 +3,13 @@
   <macros>
     <import>macros.xml</import>
   </macros>
+  <stdio>
+    <expand macro="basic_errors"/>
+  </stdio>
   <version_command>/home/matsengrp/local/bin/usearch6_64 --version</version_command>
   <command interpreter="bash">
     usearch-wrapper.sh $config
   </command>
-  <stdio>
-    <expand macro="basic_errors"/>
-  </stdio>
   <inputs>
     <param name="input_seqs" type="data" format="fasta" label="Input sequences"/>
     <param name="class_db" type="data" format="sqlite3" label="Placement database"/>
@@ -39,12 +39,8 @@
 This tool queries large sequence databases for target sequences and assigns
 those sequences to clusters.
 
------
-
-**Citation**
-
-Edgar, R C: **Search and clustering orders of magnitude faster than
-BLAST**. Bioinformatics 2010, **26**:19.
-
   </help>
+  <citations>
+    <expand macro="cite_usearch"/>
+  </citations>
 </tool>