diff --git a/prepare_bcbio_config_crf.sh b/prepare_bcbio_config_crf.sh index f9e3c007b4b0d98efe88a4a3ca87078de625fdb1..65caf4201ebafc0b1415bad481c50c59db8c86f2 100755 --- a/prepare_bcbio_config_crf.sh +++ b/prepare_bcbio_config_crf.sh @@ -51,8 +51,8 @@ perl -pi -e 's/\r//' $PROJECT_ID.ped # create reads directory for project mkdir -p $READS_DIR/$PROJECT_ID -# generate the family_ids list - makes strong assumption about relative paths! -ls ../../data/$PROJECT_ID/*.gz | grep -v Undetermined | cut -d '/' -f 5 | cut -f 1,3 -d '_' | sort -u > $PROJECT_ID.family_ids.txt +# generate the family_ids list +ls $DOWNLOAD_DIR/$PROJECT_ID/*.gz | grep -v Undetermined | cut -d '/' -f 5 | cut -f 1,3 -d '_' | sort -u > $PROJECT_ID.family_ids.txt PLATE_ID=`cut -f 1 -d '_' $PROJECT_ID.family_ids.txt | sort -u` for FAMILY_ID in `cut -f 2 -d '_' $PROJECT_ID.family_ids.txt` @@ -63,9 +63,12 @@ do > ${PROJECT_ID}_${PLATE_ID}_${FAMILY_ID}.ped done +SHORT_PROJECT_ID=`echo $PROJECT_ID | cut -f 1 -d '_'` +PREFIX=${SHORT_PROJECT_ID}_${VERSION}_${FAMILY_ID} + for FAMILY_ID in `cat ${PROJECT_ID}.family_ids.txt` do - echo "samplename,description,batch,sex,phenotype,variant_regions" > ${VERSION}_${PROJECT_ID}_${FAMILY_ID}.csv + echo "samplename,description,batch,sex,phenotype,variant_regions" > $PREFIX.csv COUNT=`wc -l ${PROJECT_ID}_${FAMILY_ID}.ped | awk '{ print $1 }'` for ((i=1; i<=$COUNT; i=i+1)) @@ -76,25 +79,29 @@ do for FILE in `ls $DOWNLOAD_DIR/$PROJECT_ID/*${SAMPLE}*.gz` do - echo "$FILE,$SAMPLE,$FAMILY_ID,$SEX,$PHENOTYPE,$TARGET" >> ${VERSION}_${PROJECT_ID}_${FAMILY_ID}.csv + echo "$FILE,$SAMPLE,$FAMILY_ID,$SEX,$PHENOTYPE,$TARGET" >> $PREFIX.csv done done - bcbio_prepare_samples.py --out $READS_DIR/$PROJECT_ID --csv ${VERSION}_${PROJECT_ID}_${FAMILY_ID}.csv + bcbio_prepare_samples.py --out $READS_DIR/$PROJECT_ID --csv $PREFIX.csv - mv ${VERSION}_${PROJECT_ID}_${FAMILY_ID}-merged.csv ${VERSION}_${PROJECT_ID}_${FAMILY_ID}.csv + mv $PREFIX-merged.csv $PREFIX.csv BARE_FAMILY_ID=`echo $FAMILY_ID | cut -d '_' -f 2` - bcbio_nextgen.py -w template $BCBIO_TEMPLATE ${VERSION}_${PROJECT_ID}_${FAMILY_ID}.csv $READS_DIR/$PROJECT_ID/*_${BARE_FAMILY_ID}_R[12].fastq.gz + bcbio_nextgen.py -w template $BCBIO_TEMPLATE $PREFIX.csv $READS_DIR/$PROJECT_ID/*_${BARE_FAMILY_ID}_R[12].fastq.gz - mv ${VERSION}_${PROJECT_ID}_${FAMILY_ID}/config/${VERSION}_${PROJECT_ID}_${FAMILY_ID}.yaml $CONFIG_DIR/ + mv $PREFIX/config/$PREFIX.yaml $CONFIG_DIR/ COMPRESSED_ID=`echo "$FAMILY_ID" | perl -pe "s/\_//"` - perl -i -pe "s/${COMPRESSED_ID}/${FAMILY_ID}/" $CONFIG_DIR/${VERSION}_${PROJECT_ID}_${FAMILY_ID}.yaml + perl -i -pe "s/${COMPRESSED_ID}/${FAMILY_ID}/" $CONFIG_DIR/$PREFIX.yaml + + rm -r $PREFIX - rm -r ${VERSION}_${PROJECT_ID}_${FAMILY_ID} + mkdir -p ${OUTPUT_DIR}/${SHORT_PROJECT_ID}_${VERSION}/params/ + mv ${PREFIX}.csv ${OUTPUT_DIR}/${SHORT_PROJECT_ID}_${VERSION}/params/ + mv ${PROJECT_ID}_${FAMILY_ID}.ped ${OUTPUT_DIR}/${SHORT_PROJECT_ID}_${VERSION}/params/ done