Skip to content

More on lenient PDBx/mmCIF parsing #1106

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 3 commits into from
Feb 27, 2025
Merged

More on lenient PDBx/mmCIF parsing #1106

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
93c1c8f
Handle more missing fields in struct_ref_seq
josemduarte Feb 21, 2025
65d3dcd
Lenient to missing atom_site.occupancy
josemduarte Feb 21, 2025
12dcb2c
Another safeguard, that applies to some PDB-IHM entries
josemduarte Feb 21, 2025
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
61 changes: 35 additions & 26 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 @@ -333,7 +333,7 @@ public void consumeAtomSite(AtomSite atomSite) {
atom.setY(cartnY.get(atomIndex));
atom.setZ(cartnZ.get(atomIndex));

atom.setOccupancy((float) occupancy.get(atomIndex));
atom.setOccupancy((float) (occupancy.isDefined()? occupancy.get(atomIndex) : 1.0));
atom.setTempFactor((float) bIsoOrEquiv.get(atomIndex));

if (altLocation == null || altLocation.isEmpty() || ".".equals(altLocation)) {
Expand Down Expand Up @@ -975,7 +975,7 @@ public void consumeStructRefSeq(StructRefSeq structRefSeq) {
dbRef.setIdCode(structRefSeq.getPdbxPDBIdCode().isDefined()? structRefSeq.getPdbxPDBIdCode().get(rowIndex):null);
dbRef.setDbAccession(structRefSeq.getPdbxDbAccession().isDefined()? structRefSeq.getPdbxDbAccession().get(rowIndex):null);
dbRef.setDbIdCode(structRefSeq.getPdbxDbAccession().isDefined()? structRefSeq.getPdbxDbAccession().get(rowIndex):null);
dbRef.setChainName(structRefSeq.getPdbxStrandId().get(rowIndex));
dbRef.setChainName(structRefSeq.getPdbxStrandId().isDefined()? structRefSeq.getPdbxStrandId().get(rowIndex):null);

OptionalInt structRefRowIndex = IntStream.range(0, structRef.getRowCount())
.filter(i -> structRef.getId().get(i).equals(refId))
Expand All @@ -990,34 +990,39 @@ public void consumeStructRefSeq(StructRefSeq structRefSeq) {

int seqBegin;
int seqEnd;
char beginInsCode = ' ';
char endInsCode = ' ';

try {
seqBegin = Integer.parseInt(structRefSeq.getPdbxAuthSeqAlignBeg().get(rowIndex));
seqEnd = Integer.parseInt(structRefSeq.getPdbxAuthSeqAlignEnd().get(rowIndex));
} catch (NumberFormatException e) {
// this happens in a few entries, annotation error? e.g. 6eoj
logger.warn("Couldn't parse pdbx_auth_seq_align_beg/end in _struct_ref_seq. Will not store dbref " +
"alignment info for accession {}. Error: {}", dbRef.getDbAccession(), e.getMessage());
return;
}
if (structRefSeq.getPdbxAuthSeqAlignBeg().isDefined() && structRefSeq.getPdbxAuthSeqAlignEnd().isDefined()) {
try {
seqBegin = Integer.parseInt(structRefSeq.getPdbxAuthSeqAlignBeg().get(rowIndex));
seqEnd = Integer.parseInt(structRefSeq.getPdbxAuthSeqAlignEnd().get(rowIndex));
} catch (NumberFormatException e) {
// this happens in a few entries, annotation error? e.g. 6eoj
logger.warn("Couldn't parse pdbx_auth_seq_align_beg/end in _struct_ref_seq. Will not store dbref " +
"alignment info for accession {}. Error: {}", dbRef.getDbAccession(), e.getMessage());
return;
}

char beginInsCode = ' ';
String pdbxSeqAlignBegInsCode = structRefSeq.getPdbxSeqAlignBegInsCode().get(rowIndex);
if (pdbxSeqAlignBegInsCode.length() > 0) {
beginInsCode = pdbxSeqAlignBegInsCode.charAt(0);
}
String pdbxSeqAlignBegInsCode = structRefSeq.getPdbxSeqAlignBegInsCode().get(rowIndex);
if (pdbxSeqAlignBegInsCode.length() > 0) {
beginInsCode = pdbxSeqAlignBegInsCode.charAt(0);
}

char endInsCode = ' ';
String pdbxSeqAlignEndInsCode = structRefSeq.getPdbxSeqAlignEndInsCode().get(rowIndex);
if (pdbxSeqAlignEndInsCode.length() > 0) {
endInsCode = pdbxSeqAlignEndInsCode.charAt(0);
}
String pdbxSeqAlignEndInsCode = structRefSeq.getPdbxSeqAlignEndInsCode().get(rowIndex);
if (pdbxSeqAlignEndInsCode.length() > 0) {
endInsCode = pdbxSeqAlignEndInsCode.charAt(0);
}

if (beginInsCode == '?') {
beginInsCode = ' ';
}
if (endInsCode == '?') {
endInsCode = ' ';
if (beginInsCode == '?') {
beginInsCode = ' ';
}
if (endInsCode == '?') {
endInsCode = ' ';
}
} else {
seqBegin = structRefSeq.getSeqAlignBeg().get(rowIndex);
seqEnd = structRefSeq.getSeqAlignEnd().get(rowIndex);
}

dbRef.setSeqBegin(seqBegin);
Expand Down Expand Up @@ -1814,6 +1819,10 @@ private void initMaps() {

String[] chainNames = entityPoly.getPdbxStrandId().get(rowIndex).split(",");
List<String> asymIds = entityId2asymId.get(entityPoly.getEntityId().get(rowIndex));
if (asymIds == null) {
logger.warn("No asym ids found for entity {} in _struct_asym. Can't provide a mapping from asym ids to author chain ids for this entity", entityPoly.getEntityId().get(rowIndex));
break;
}
if (chainNames.length != asymIds.size()) {
logger.warn("The list of asym ids (from _struct_asym) and the list of author ids (from _entity_poly) " +
"for entity {} have different lengths! Can't provide a mapping from asym ids to author chain " +
Expand Down