Skip to content

Fixing issue with an edge case CIF parsing #1055

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

Merged
josemduarte merged 2 commits into from
Jan 30, 2023
Merged

Fixing issue with an edge case CIF parsing #1055

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b0a1da5
Fix for entity_src_nat category parsing, when some items missing
josemduarte Jan 29, 2023
5b99e7a
More comprehensive fix
josemduarte Jan 30, 2023
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
38 changes: 22 additions & 16 deletions ...a-structure/src/main/java/org/biojava/nbio/structure/io/cif/CifStructureConsumerImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@
import java.util.NoSuchElementException;
import java.util.Optional;
import java.util.OptionalInt;
import java.util.stream.Collectors;
import java.util.stream.IntStream;

import javax.vecmath.Matrix4d;
Expand Down Expand Up @@ -1397,27 +1396,34 @@ private void addAncilliaryEntityData(int asymRowIndex, EntityInfo entityInfo) {
}

private void addInformationFromEntitySrcSyn(int rowIndex, EntityInfo entityInfo) {
entityInfo.setOrganismCommon(entitySrcSyn.getOrganismCommonName().get(rowIndex));
entityInfo.setOrganismScientific(entitySrcSyn.getOrganismScientific().get(rowIndex));
entityInfo.setOrganismTaxId(entitySrcSyn.getNcbiTaxonomyId().get(rowIndex));
entityInfo.setOrganismCommon(getCifFieldNullAware(entitySrcSyn.getOrganismCommonName(), rowIndex, null));
entityInfo.setOrganismScientific(getCifFieldNullAware(entitySrcSyn.getOrganismScientific(), rowIndex, null));
entityInfo.setOrganismTaxId(getCifFieldNullAware(entitySrcSyn.getNcbiTaxonomyId(), rowIndex, null));
}

private void addInformationFromEntitySrcNat(int rowIndex, EntityInfo entityInfo) {
entityInfo.setAtcc(entitySrcNat.getPdbxAtcc().get(rowIndex));
entityInfo.setCell(entitySrcNat.getPdbxCell().get(rowIndex));
entityInfo.setOrganismCommon(entitySrcNat.getCommonName().get(rowIndex));
entityInfo.setOrganismScientific(entitySrcNat.getPdbxOrganismScientific().get(rowIndex));
entityInfo.setOrganismTaxId(entitySrcNat.getPdbxNcbiTaxonomyId().get(rowIndex));
entityInfo.setAtcc(getCifFieldNullAware(entitySrcNat.getPdbxAtcc(), rowIndex, null));
entityInfo.setCell(getCifFieldNullAware(entitySrcNat.getPdbxCell(), rowIndex, null));
entityInfo.setOrganismCommon(getCifFieldNullAware(entitySrcNat.getCommonName(), rowIndex, null));
entityInfo.setOrganismScientific(getCifFieldNullAware(entitySrcNat.getPdbxOrganismScientific(), rowIndex, null));
entityInfo.setOrganismTaxId(getCifFieldNullAware(entitySrcNat.getPdbxNcbiTaxonomyId(), rowIndex, null));
}

private void addInformationFromEntitySrcGen(int rowIndex, EntityInfo entityInfo) {
entityInfo.setAtcc(entitySrcGen.getPdbxGeneSrcAtcc().get(rowIndex));
entityInfo.setCell(entitySrcGen.getPdbxGeneSrcCell().get(rowIndex));
entityInfo.setOrganismCommon(entitySrcGen.getGeneSrcCommonName().get(rowIndex));
entityInfo.setOrganismScientific(entitySrcGen.getPdbxGeneSrcScientificName().get(rowIndex));
entityInfo.setOrganismTaxId(entitySrcGen.getPdbxGeneSrcNcbiTaxonomyId().get(rowIndex));
entityInfo.setExpressionSystemTaxId(entitySrcGen.getPdbxHostOrgNcbiTaxonomyId().get(rowIndex));
entityInfo.setExpressionSystem(entitySrcGen.getPdbxHostOrgScientificName().get(rowIndex));
entityInfo.setAtcc(getCifFieldNullAware(entitySrcGen.getPdbxGeneSrcAtcc(), rowIndex, null));
entityInfo.setCell(getCifFieldNullAware(entitySrcGen.getPdbxGeneSrcCell(), rowIndex, null));
entityInfo.setOrganismCommon(getCifFieldNullAware(entitySrcGen.getGeneSrcCommonName(), rowIndex, null));
entityInfo.setOrganismScientific(getCifFieldNullAware(entitySrcGen.getPdbxGeneSrcScientificName(), rowIndex, null));
entityInfo.setOrganismTaxId(getCifFieldNullAware(entitySrcGen.getPdbxGeneSrcNcbiTaxonomyId(), rowIndex, null));
entityInfo.setExpressionSystemTaxId(getCifFieldNullAware(entitySrcGen.getPdbxHostOrgNcbiTaxonomyId(), rowIndex, null));
entityInfo.setExpressionSystem(getCifFieldNullAware(entitySrcGen.getPdbxHostOrgScientificName(), rowIndex, null));
}

private String getCifFieldNullAware(StrColumn column, int rowIndex, String defaultValue) {
if (column.isDefined())
return column.get(rowIndex);
else
return defaultValue;
}

private void setStructNcsOps() {
Expand Down