changeset 5:0ed708869995 draft

add flagstat

--- a/star.Rmd	Sun Mar 04 01:37:25 2018 -0500
+++ b/star.Rmd	Sun Mar 04 11:15:02 2018 -0500
@@ -11,7 +11,7 @@
 ```
 
 
-# Generating genome indexes
+## Generating genome indexes
 
 ```{bash}
 cd ${X_d}
@@ -36,12 +36,12 @@
 
 
 ```{r}
-# display skewer job script
+# display index-genome code
 index_genome_sh = paste0(opt$X_d, '/index-genome.sh')
 tags$code(tags$pre(readChar(index_genome_sh, file.info(index_genome_sh)$size )))
 ```
 
-# Running mapping jobs
+## Running mapping jobs
 
 ```{bash}
 cd ${X_d}
@@ -63,21 +63,34 @@
 
 
 ```{r}
-# display skewer job script
+# display mapping code
 mapping_sh = paste0(opt$X_d, '/mapping.sh')
 tags$code(tags$pre(readChar(mapping_sh, file.info(mapping_sh)$size )))
 ```
 
 
-# SAM to sorted BAM
+## SAM to sorted BAM
 
 ```{bash}
 cd ${X_d}
-samtools view \
-  -bS Aligned.out.sam > Aligned.out.bam
-  
-samtools sort \
-  -o Aligned.out.sorted.bam \
-  Aligned.out.bam
+
+echo "samtools sort -o Aligned.out.sorted.bam Aligned.out.sam" > sam2bam.sh
+
+sh sam2bam.sh
+
+cp Aligned.out.sorted.bam ${X_S}
 ```
 
+```{r}
+# display sam to bam code
+sam2bam_sh = paste0(opt$X_d, '/sam2bam.sh')
+tags$code(tags$pre(readChar(sam2bam_sh, file.info(sam2bam_sh)$size )))
+```
+
+## Mapping statistics
+
+```{bash}
+cd ${X_d}
+samtools flagstat Aligned.out.sorted.bam
+```
+

--- a/star.xml	Sun Mar 04 01:37:25 2018 -0500
+++ b/star.xml	Sun Mar 04 11:15:02 2018 -0500
@@ -1,4 +1,4 @@
-<tool id="aurora_star" name="Aurora Star" version="1.0.0">
+<tool id="aurora_star" name="Aurora STAR" version="1.0.0">
     <description>ultrafast universal RNA-seq aligner&#xD;
     </description>
     <requirements>
@@ -29,6 +29,8 @@
     <inputs>
         <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false"
                label="Display analysis code in report?"/>
+        <param type="data" name="first_reads" label="First reads" optional="False" format="fastq,fastqsanger"/>
+        <param type="data" name="second_reads" label="Second reads" optional="True" format="fastq,fastqsanger"/>
         <param type="data" name="genomeFastaFiles" argument="--genomeFastaFiles" label="Genome fasta files"
                optional="False" format="fasta,fa"/>
         <param type="data" name="sjdbGTFfile" argument="--sjdbGTFfile" label="Annotated transcripts"
@@ -37,8 +39,6 @@
         <param type="integer" name="sjdbOverhang" argument="--sjdbOverhang" label="sjdbOverhang"
                help="the length of the genomic sequence around the annotated junction to be used in constructing the splice junctions database. Ideally, this length should be equal to the ReadLength-1, where ReadLength is the length of the reads. For instance, for Illumina 2x100b paired-end reads, the ideal value is 100-1=99. In case of reads of varying length, the ideal value is max(ReadLength)-1. In most cases, a generic value of 100 will work as well as the ideal value."
                optional="False" value="100" min="1"/>
-        <param type="data" name="first_reads" label="First reads" optional="False" format="fastq,fastqsanger"/>
-        <param type="data" name="second_reads" label="Second reads" optional="True" format="fastq,fastqsanger"/>
     </inputs>
     <outputs>
         <data name="report" format="html" label="${tool.name} report" hidden="false"/>