diff --git a/1_run_discovery.sh b/1_run_discovery.sh index 5b88171..9c3bb7d 100644 --- a/1_run_discovery.sh +++ b/1_run_discovery.sh @@ -6,7 +6,9 @@ mkdir -p logs LOGE="logs/1_run_discovery.err" LOGO="logs/1_run_discovery.out" -CMD="bash src/run_discovery.sh $@ -J 10 -vvv -t $GDC_TOKEN $CASES > $LOGO 2> $LOGE" +NJOBS="5" + +CMD="bash src/run_discovery.sh $@ -J $NJOBS -vvv -t $GDC_TOKEN $CASES > $LOGO 2> $LOGE" >&2 echo Running: $CMD >&2 echo Writing logs to $LOGO and $LOGE eval $CMD diff --git a/src/make_catalog2.sh b/src/make_catalog2.sh index 8fd8ad0..c08e984 100644 --- a/src/make_catalog2.sh +++ b/src/make_catalog2.sh @@ -325,6 +325,7 @@ function get_SN { # * sample submitter id # * sample id # * sample type +# * preservation method (NEW) # * aliquot submitter id # * aliquot id # * analyte_type @@ -333,9 +334,11 @@ function get_sample_type { ALIQUOT_NAME=$1 ALIQUOTS_FN=$2 +# >&2 echo DEBUG: get_sample_type ALIQUOT_NAME = $ALIQUOT_NAME ALIQUOTS_FN = $ALIQUOTS_FN + # Matching to ALIQUOT name with grep is inexact # SAMPLE_TYPE=$(grep $ALIQUOT_NAME $ALIQUOTS_FN | cut -f 4 | sort -u) - SAMPLE_TYPE=$(awk -v AN=$ALIQUOT_NAME 'BEGIN{FS="\t";OFS="\t"}{if ($5 == AN ) print $4}' $ALIQUOTS_FN | sort -u) + SAMPLE_TYPE=$(awk -v AN=$ALIQUOT_NAME 'BEGIN{FS="\t";OFS="\t"}{if ($6 == AN ) print $4}' $ALIQUOTS_FN | sort -u) MATCH_COUNT=$(echo -n "$SAMPLE_TYPE" | grep -c '^') if [ $MATCH_COUNT == 0 ]; then >&2 echo ERROR: Sample type for aliquot $ALIQUOT_NAME not found in $ALIQUOTS_FN diff --git a/src/queryGDC.sh b/src/queryGDC.sh index 21334d7..bb58ba0 100755 --- a/src/queryGDC.sh +++ b/src/queryGDC.sh @@ -20,7 +20,8 @@ # ######### -PYTHON="/usr/bin/python3" +#PYTHON="/usr/bin/python3" +PYTHON="/diskmnt/Projects/Users/mwyczalk/miniconda3/bin/python" JQ="jq" if ! command -v $JQ &> /dev/null