Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improvements #15

Merged
merged 4 commits into from
Jun 20, 2024
Merged

Improvements #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
de0124a
Remove ChEBI duplicates
egonw Jun 19, 2024
b0ed23d
Added the additional data sources needed downstream
egonw Jun 19, 2024
3288f18
Added the new headers
egonw Jun 19, 2024
67f324e
Auto update JAR
egonw Jun 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified meta-data-action-1.1.2-jar-with-dependencies.jar
View file
Open in desktop
Binary file not shown.
Binary file modified meta-data-action-1.1.2.jar
View file
Open in desktop
Binary file not shown.
18 changes: 15 additions & 3 deletions meta.data.action/src/main/java/meta/data/action/MetaDataExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,7 +175,7 @@ private static void printPathwayInfo(String pId, String revision, List<Author> a
private static void printNodeList(String pId, PathwayModel p) throws IOException, ClassNotFoundException, IDMapperException {
File file = new File(folder, pId + "-datanodes.tsv");
BufferedWriter w = new BufferedWriter(new FileWriter(file));
w.write("Label\tType\tIdentifier\tComment\tEnsembl\tNCBI gene\tHGNC\tUniProt\tWikidata\tChEBI\tInChI\n");
w.write("Label\tType\tIdentifier\tComment\tEnsembl\tNCBI gene\tHGNC\tUniProt\tWikidata\tChEBI\tInChI\tPubChem\tChemSpider\tHMDB\tKEGG\tLipidMapd\n");
ArrayList<String> elementTypes = new ArrayList<String>(Arrays.asList("Metabolite", "GeneProduct", "Protein"));

// create idmapper stack using gdb.config file
Expand Down Expand Up @@ -213,12 +213,14 @@ private static void printNodeList(String pId, PathwayModel p) throws IOException
private static String getIDMappingsString(DataNode e, String pId, PathwayModel p, IDMapperStack idmpStack) throws ClassNotFoundException, IOException, IDMapperException {
// perform ID Mapping for Ensembl, NCBI gene, HGNC, UniProt, Wikidata, ChEBI, InChI
//DataSourceTxt.init();
ArrayList<String> dataSourceList = new ArrayList<String>(Arrays.asList("En", "L", "H", "S", "Wd", "Ce","Ik"));
ArrayList<String> dataSourceList = new ArrayList<String>(Arrays.asList("En", "L", "H", "S", "Wd", "Ce","Ik", "Cpc", "Cs", "Ch", "Ck", "Lm"));
String result = "";

// For each data source in the header, mapID and append the result to the string.
for (String sysCode : dataSourceList) {
Set<Xref> stackResult = idmpStack.mapID(e.getXref(), DataSource.getExistingBySystemCode(sysCode));
Set<Xref> stackResult = cleaner(
idmpStack.mapID(e.getXref(), DataSource.getExistingBySystemCode(sysCode))
);
// Check if more than one Xref was returned. If yes, then append them using semicolon.
String stackStr = "";
for (Xref ref : stackResult) {
Expand All @@ -242,6 +244,16 @@ private static String getIDMappingsString(DataNode e, String pId, PathwayModel p
return result;
}

private static Set<Xref> cleaner(Set<Xref> stackResult) {
Set<Xref> cleaner = new HashSet<>();
for (Xref ref : stackResult) {
String id = ref.getId();
if (id.startsWith("CHEBI:")) id = id.replace("CHEBI:", "");
cleaner.add(new Xref(id, ref.getDataSource()));
}
return cleaner;
}

private static void printRefList(String pId, PathwayModel p) throws IOException {
File file = new File(folder, pId + "-refs.tsv");
BufferedWriter w = new BufferedWriter(new FileWriter(file));
Expand Down