Mercurial > repos > mingchen0919 > statonlab_fasta_splitter

changeset 2:38435c74e795 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
working version
author mingchen0919
date Mon, 09 Apr 2018 14:20:42 -0400
parents ecf34bd52987
children
files split.pl split_fasta.Rmd split_fasta.xml
diffstat 3 files changed, 13 insertions(+), 7 deletions(-) [+]
line wrap: on
line diff
--- a/split.pl	Mon Apr 09 13:32:55 2018 -0400
+++ b/split.pl	Mon Apr 09 14:20:42 2018 -0400
@@ -24,7 +24,7 @@
 
  for($i = 1; $i <= $numOfFiles; $i++){
 	print "$i\n";
-	open FILE, ">".$homfile.".".$i || die "Can't open file";
+	open FILE, ">".$homfile.".".$i.".fasta" || die "Can't open file";
 	print FILE $lineIn;
 	$seqs = 1;
         $lineIn = <IN>;
@@ -40,7 +40,7 @@
 	close FILE;
  }
  $i = $i -1;
- open FILE, ">>".$homfile.".".$i;
+ open FILE, ">>".$homfile.".".$i.".fasta";
  while ($lineIn = <IN>){
 	print FILE $lineIn;
  }
--- a/split_fasta.Rmd	Mon Apr 09 13:32:55 2018 -0400
+++ b/split_fasta.Rmd	Mon Apr 09 14:20:42 2018 -0400
@@ -16,9 +16,9 @@
 
 # single-end.sh
 cat <<EOF >${X_d}/job-script.sh
-cd ${WORKING_DIR}/fasta_files && ${X_t}/split.pl \\
-  --input_file=${X_A} \\
-  --seqs_per_file=${X_B} \\  > ${X_d}/fasta_splitter-log.txt 2>&1
+cd ${WORKING_DIR}/fasta_files && \\
+  cp ${X_A} input.fasta && \\
+  ${X_t}/split.pl input.fasta ${X_B} > ${X_d}/fasta_splitter-log.txt 2>&1
 EOF
 ```
 
@@ -28,6 +28,12 @@
 sh ${X_d}/job-script.sh
 ```
 
+```{bash}
+# remove original input fasta
+rm ${WORKING_DIR}/fasta_files/input.fasta
+mv ${WORKING_DIR}/fasta_files/out ${X_d}/split-out.txt
+```
+
 ```{r, 'display output directory contents', results='asis', echo=FALSE}
 ## after the job is done, we list all files from the output directory.
 ## full relative path to the output directory needs to be displayed.
--- a/split_fasta.xml	Mon Apr 09 13:32:55 2018 -0400
+++ b/split_fasta.xml	Mon Apr 09 14:20:42 2018 -0400
@@ -16,9 +16,9 @@
 	-B '$number'
 ]]></command>
   <inputs>
-    <param type="data" name="fasta_input" label="FASTA input" optional="False" multiple="False"/><param type="integer" name="number" label="Number" help="The number of files the FASTA file will be split into" optional="False" value="200" min="1"/></inputs>
+    <param type="data" name="fasta_input" label="FASTA input" optional="False" format="fasta,fa" multiple="False"/><param type="integer" name="number" label="Number" help="The number of files the FASTA file will be split into" optional="False" value="200" min="1"/></inputs>
   <outputs>
-        <data name="report" format="html" label="${tool.name} report on ${on_string}" hidden="false"/><data name="sink_message" format="txt" label="${tool.name} log on ${on_string}" from_work_dir="warnings_and_errors.txt" hidden="false"/><collection name="list_collection" type="list" label="${tool.name} on ${on_string}"><discover_datasets pattern="__name_and_ext__" directory="fasta_files" visible="true"/></collection></outputs>
+        <data name="report" format="html" label="${tool.name} report on ${on_string}" hidden="false"/><data name="sink_message" format="txt" label="${tool.name} log on ${on_string}" from_work_dir="warnings_and_errors.txt" hidden="false"/><collection name="list_collection" type="list" label="${tool.name} on ${on_string}"><discover_datasets pattern="__name_and_ext__" directory="fasta_files" visible="false"/></collection></outputs>
   <citations>
         <citation type="bibtex"><![CDATA[
             @article{allaire2016rmarkdown,