| 1 | #! /bin/bash
|
| 2 |
|
| 3 | GPML_SOURCE_DIR="./wikipathways-20180210-gpml-Homo_sapiens";
|
| 4 | MAPPED_DIR="./mapped";
|
| 5 |
|
| 6 | if [ ! -d "$MAPPED_DIR" ]; then
|
| 7 | mkdir "$MAPPED_DIR";
|
| 8 | fi
|
| 9 |
|
| 10 | if [ ! -d "$GPML_SOURCE_DIR" ]; then
|
| 11 | wget "http://data.wikipathways.org/current/gpml/$GPML_SOURCE_DIR.zip";
|
| 12 | unzip "$GPML_SOURCE_DIR.zip" -d "$GPML_SOURCE_DIR";
|
| 13 | rm "$GPML_SOURCE_DIR.zip";
|
| 14 | fi
|
| 15 |
|
| 16 | for f in $(ls $GPML_SOURCE_DIR | grep "WP.*.gpml"); do
|
| 17 |
|
| 18 | gpml="$GPML_SOURCE_DIR/$f"
|
| 19 | organism=$(xpath "$gpml" "//@Organism" | awk '{gsub(/\ *[a-zA-Z][a-zA-Z0-9]*="/ , ""); gsub(/"\ */, ""); print $0}');
|
| 20 | xpath $gpml "//Xref/@*[name()='Database' or name()='ID']" |\
|
| 21 | awk '{gsub(/["\ ]*Database="/, "\n"); gsub (/"\ *[a-zA-Z][a-zA-Z0-9]*="/, "\t"); gsub(/"\ */, ""); print $0}' |\
|
| 22 | awk 'NF' |\
|
| 23 | ./bin/bridgedb xrefs -f "tsv" "$organism" 0 1 chembl.compound chebi wikidata ensembl ncbigene \
|
| 24 | > "$MAPPED_DIR/$f.gmt.tsv"
|
| 25 | done
|