Skip to main content
https://github.com/arjunrajlaboratory/RajLabSeqTools
10 December 2020, 08:13:14 UTC
Raw File Download Save again
Tip revision: c5b88eb5aa3fa9f6a657d8b078405ce82f7e0e2d authored by Eric Sanford on 09 October 2019, 20:53:45 UTC
Updated STAR version, set default reference genome to hg38, added gene_names from gtf file when there is no HGNC symbol match, made it easier to change the reference genome by defining it in the setEnvironmentVariables.sh script. Modified some snakemake files to make that alternate pipeline almost runnable on the cluster in an interactive node.
Tip revision: c5b88eb
prepareSamForHTSeq.sh 
#!
# run from within "repo" directory

EXPERIMENT=$1
SAMPLEID=$2

ALIGNMENT_TOOL_NAME=rum

if [[ ! -z "$3" ]]; then
    ALIGNMENT_TOOL_NAME="$3"
fi

commandName=prepareSamForHTSeq

if [ ! -d $EXPERIMENT/analyzed/$SAMPLEID/log ]; then
    mkdir $EXPERIMENT/analyzed/$SAMPLEID/log
fi
JOURNAL=$EXPERIMENT/analyzed/$SAMPLEID/log/$(date +%Y-%m-%d_%H-%M).$commandName.log


if [ ! -d $EXPERIMENT/analyzed/$SAMPLEID/htseq ]; then
    mkdir $EXPERIMENT/analyzed/$SAMPLEID/htseq
fi

readNameSortCmd="samtools sort -n \
    $EXPERIMENT/analyzed/$SAMPLEID/$ALIGNMENT_TOOL_NAME/$SAMPLEID.sorted.mapped.unique.bam \
    $EXPERIMENT/analyzed/$SAMPLEID/htseq/$SAMPLEID.nameSorted"

fixMateCmd="samtools fixmate \
    $EXPERIMENT/analyzed/$SAMPLEID/htseq/$SAMPLEID.nameSorted.bam \
    $EXPERIMENT/analyzed/$SAMPLEID/htseq/$SAMPLEID.nameSorted.mateFixed.bam"

toSamCmd="samtools view -h \
    $EXPERIMENT/analyzed/$SAMPLEID/htseq/$SAMPLEID.nameSorted.mateFixed.bam \
    > $EXPERIMENT/analyzed/$SAMPLEID/htseq/$SAMPLEID.nameSorted.mateFixed.sam"

echo "Starting..." >> $JOURNAL
date >> $JOURNAL
echo "$readNameSortCmd" >> $JOURNAL
eval "$readNameSortCmd"
echo "$fixMateCmd" >> $JOURNAL
eval "$fixMateCmd"
echo "$toSamCmd" >> $JOURNAL
eval "$toSamCmd"
date >> $JOURNAL
echo "Done" >> $JOURNAL