Mercurial > repos > mingchen0919 > aurora_htseq

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/htseq_count.Rmd	Tue Mar 06 15:16:40 2018 -0500
@@ -0,0 +1,29 @@
+---
+title: 'HTML report title'
+output:
+    html_document:
+      number_sections: true
+      toc: true
+      theme: cosmo
+      highlight: tango
+---
+
+```{r setup, include=FALSE, warning=FALSE, message=FALSE}
+knitr::opts_chunk$set(
+  echo = as.logical(),
+  error = TRUE
+)
+```
+
+
+# Code for computational analysis
+
+```{r 'step 1'}
+
+```
+
+```{r 'ste[ 2'}
+
+```
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/htseq_count.xml	Tue Mar 06 15:16:40 2018 -0500
@@ -0,0 +1,53 @@
+<tool name="Tool report" id="tool_1" version="1.0.0">
+  <description>Counting reads in features.</description>
+  <requirements>
+        <requirement type="package" version="1.15.0.6-0">pandoc</requirement><requirement type="package" version="1.20.0">r-getopt</requirement><requirement type="package" version="1.6">r-rmarkdown</requirement><requirement type="package" version="0.9.1">htseq</requirement></requirements>
+  <stdio>
+        <regex match="XXX" source="stderr" level="warning" description="Check the warnings_and_errors.txt file for more details."/></stdio>
+  <command><![CDATA[
+
+
+        Rscript '${__tool_directory__}/rmarkdown_report_render.R'
+
+			-e $echo
+			-o $report
+			-d $report.files_path
+			-s $sink_message
+			-t '${__tool_directory__}'
+
+
+
+    ]]></command>
+  <inputs>
+        <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Display analysis code in report?"/><param type="data" name="alignment_file" label="Alignment file (SAM/BAM)" optional="False" format="sam,bam"/><param type="data" name="gff" label="GFF file" optional="False" format="gff, gff3"/><param type="text" name="format" argument="-f" label="Input data format" help="Possible values are bam and sam." optional="False" value="bam"/><param type="text" name="order" argument="-r" label="Order" help="Possible values are &lt;code&gt;name&lt;/code&gt; and &lt;code&gt;pos&lt;/code&gt;. This option indicates whether the input data has been sorted by &lt;code&gt;name&lt;/code&gt; or &lt;code&gt;pos&lt;/code&gt;. " optional="False" value="name"/><param type="select" name="stranded" argument="-s" label="Stranded" optional="False" multiple="False"><option value="yes" selected="true">Yes</option><option value="no" selected="false">No</option><option value="reverse" selected="false">Reverse</option></param><param type="integer" name="minaqual" argument="-a" label="Alignment quality " help="Skip all reads with alignment quality lower than the given minimum value (default: 10)" optional="False" value="10" min="0"/><param type="text" name="feature_type" argument="-t" label="Feature type" help="Feature type (3rd column in GFF file) to be used, all features of other type are ignored (default, suitable for RNA-Seq analysis using an Ensembl GTF file: exon)" optional="False" value="exon"/><param type="text" name="idattr" argument="-i" label="ID attribute" help="GFF attribute to be used as feature ID. Several GFF lines with the same feature ID will be considered as parts of the same feature. The feature ID is used to identity the counts in the output table. The default, suitable for RNA-Seq analysis using an Ensembl GTF file, is gene_id." optional="False" value="gene_id"/><param type="text" name="additional_attr" argument="--additional-attr" label="Additional attributes" help="Additional feature attributes, which will be printed as an additional column after the primary attribute column but before the counts column(s). The default is none, a suitable value to get gene names using an Ensembl GTF file is gene_name." optional="True"/><param type="select" name="mode" argument="-m" label="Mode" help="Mode to handle reads overlapping more than one feature. Possible values for &lt;mode&gt; are union, intersection-strict and intersection-nonempty (default: union)" optional="False" multiple="False"><option value="union" selected="true">Union</option><option value="intersection-strict" selected="false">Intersection (strict)</option><option value="intersection-nonempty" selected="false">Intersection (nonempty)</option></param></inputs>
+  <outputs>
+        <data format="html" name="report" label="tool report"/><data format="txt" name="sink_message" label="Warnings and Errors" from_work_dir="warnings_and_errors.txt"/><data name="count" format="txt" label="Aurora htseq-count on ${on_string}" hidden="false"/></outputs>
+  <citations>
+        <citation type="bibtex"><![CDATA[
+            @article{allaire2016rmarkdown,
+            title={rmarkdown: Dynamic Documents for R, 2016},
+            author={Allaire, J and Cheng, Joe and Xie, Yihui and McPherson, Jonathan and Chang, Winston and Allen, Jeff
+            and Wickham, Hadley and Atkins, Aron and Hyndman, Rob},
+            journal={R package version 0.9},
+            volume={6},
+            year={2016}
+            }
+        ]]></citation><citation type="bibtex"><![CDATA[
+            @book{xie2015dynamic,
+            title={Dynamic Documents with R and knitr},
+            author={Xie, Yihui},
+            volume={29},
+            year={2015},
+            publisher={CRC Press}
+            }
+        ]]></citation><citation type="bibtex"><![CDATA[@article{anders2015htseq,
+  title={HTSeq—a Python framework to work with high-throughput sequencing data},
+  author={Anders, Simon and Pyl, Paul Theodor and Huber, Wolfgang},
+  journal={Bioinformatics},
+  volume={31},
+  number={2},
+  pages={166--169},
+  year={2015},
+  publisher={Oxford University Press}
+}]]></citation></citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/htseq_count_render.R	Tue Mar 06 15:16:40 2018 -0500
@@ -0,0 +1,52 @@
+##============ Sink warnings and errors to a file ==============
+## use the sink() function to wrap all code within it.
+##==============================================================
+zz = file('warnings_and_errors.txt')
+sink(zz)
+sink(zz, type = 'message')
+
+#------------import libraries--------------------
+options(stringsAsFactors = FALSE)
+
+library(getopt)
+library(rmarkdown)
+#------------------------------------------------
+
+
+#------------get arguments into R--------------------
+# library(dplyr)
+# getopt_specification_matrix(extract_short_flags('')) %>%
+#   write.table(file = 'spec.txt', sep = ',', row.names = FALSE, col.names = TRUE, quote = FALSE)
+
+
+spec_matrix = as.matrix()
+opt = getopt(spec_matrix)
+#----------------------------------------------------
+
+
+#-----------using passed arguments in R
+#           to define system environment variables---
+do.call(Sys.setenv, opt[-1])
+#----------------------------------------------------
+
+#---------- often used variables ----------------
+# OUTPUT_DIR: path to the output associated directory, which stores all outputs
+# TOOL_DIR: path to the tool installation directory
+OUTPUT_DIR = ''
+TOOL_DIR =   ''
+RMD_NAME = ''
+OUTPUT_REPORT = opt$X_o
+
+# create the output associated directory to store all outputs
+dir.create(OUTPUT_DIR, recursive = TRUE)
+
+#-----------------render Rmd--------------
+render(paste0(TOOL_DIR, RMD_NAME, sep = '/'), output_file = OUTPUT_REPORT)
+#------------------------------------------
+
+#==============the end==============
+
+
+##--------end of code rendering .Rmd templates----------------
+sink()
+##=========== End of sinking output=============================
\ No newline at end of file