Skip to content

More lenient mmCIF parsing #1083

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
Mar 4, 2024
Merged

More lenient mmCIF parsing #1083

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
805a902
Be more lenient with some missing atom_site fields
josemduarte Mar 2, 2024
ac14da4
Better with ternary if
josemduarte Mar 2, 2024
3e26abe
Adding test case
josemduarte Mar 4, 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
12 changes: 8 additions & 4 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 @@ -217,7 +217,8 @@ public void consumeAtomSite(AtomSite atomSite) {
isHetAtmInFile = true;
}

String insCodeString = pdbxPDBInsCode.get(atomIndex);
String insCodeString = pdbxPDBInsCode.isDefined()? pdbxPDBInsCode.get(atomIndex) : null;

Character insCode = null;
if (insCodeString != null && !insCodeString.isEmpty() && !"?".equals(insCodeString)) {
insCode = insCodeString.charAt(0);
Expand Down Expand Up @@ -246,7 +247,8 @@ public void consumeAtomSite(AtomSite atomSite) {
}

String asymId = labelAsymId.get(atomIndex);
String authId = authAsymId.get(atomIndex);
String authId = authAsymId.isDefined()? authAsymId.get(atomIndex) : asymId;

if (currentChain == null) {
currentChain = new ChainImpl();
currentChain.setName(authId);
Expand Down Expand Up @@ -277,7 +279,9 @@ public void consumeAtomSite(AtomSite atomSite) {
}
}

ResidueNumber residueNumber = new ResidueNumber(authId, authSeqId.get(atomIndex), insCode);
int authSeqIdInt = authSeqId.isDefined()? authSeqId.get(atomIndex) : (int)seqId;

ResidueNumber residueNumber = new ResidueNumber(authId, authSeqIdInt, insCode);

String recordName = groupPDB.get(atomIndex);
String compId = labelCompId.get(atomIndex);
Expand All @@ -289,7 +293,7 @@ public void consumeAtomSite(AtomSite atomSite) {
}

Group altGroup = null;
String altLocation = labelAltId.get(atomIndex);
String altLocation = labelAltId.isDefined()? labelAltId.get(atomIndex) : null;

if (startOfNewChain) {
currentGroup = createGroup(recordName, oneLetterCode, compId, seqId);
Expand Down
49 changes: 48 additions & 1 deletion ...va-structure/src/test/java/org/biojava/nbio/structure/io/cif/CifFileConsumerImplTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ private static int[] countEntityTypes(List<EntityInfo> entities) {

/**
* This tests for cases where dots appear in integer fields. Unusual but it happens in some PDB entries like 1s32.
* See issue https://github.com/biojava/biojava/issues/368
* See issue <a href="https://github.com/biojava/biojava/issues/368">...</a>
*/
@Test
public void specialCases() throws IOException {
Expand Down Expand Up @@ -220,4 +220,51 @@ public void specialCases() throws IOException {
column.valueKinds().forEach(vk -> assertEquals(ValueKind.NOT_PRESENT, vk));
column.stringData().forEach(sd -> assertTrue(sd.isEmpty()));
}

/**
* Testing files with atom_site that doesn't have author fields. E.g. cif files from Meta's ESM Atlas (<a href="https://esmatlas.com">...</a>)
*/
@Test
public void testAtomSiteWithMissingAuthFields() throws IOException {
// taken from MGYP000911143359.cif
String mmcifStr =
"data_\n" +
"loop_\n" +
"_atom_site.group_PDB\n" +
"_atom_site.id\n" +
"_atom_site.type_symbol\n" +
"_atom_site.label_atom_id\n" +
"_atom_site.label_comp_id\n" +
"_atom_site.label_asym_id\n" +
"_atom_site.label_entity_id\n" +
"_atom_site.label_seq_id\n" +
"_atom_site.Cartn_x\n" +
"_atom_site.Cartn_y\n" +
"_atom_site.Cartn_z\n" +
"_atom_site.occupancy\n" +
"_atom_site.B_iso_or_equiv\n" +
"_atom_site.pdbx_PDB_model_num\n" +
"\n" +
"ATOM 1 N N MET A 1 1 -26.091 68.903 7.841 1.00 90.0 1\n" +
"ATOM 2 C CA MET A 1 1 -26.275 67.677 7.069 1.00 91.0 1\n" +
"ATOM 3 C C MET A 1 1 -24.933 67.025 6.755 1.00 90.0 1\n" +
"ATOM 4 C CB MET A 1 1 -27.033 67.967 5.773 1.00 89.0 1\n" +
"ATOM 5 O O MET A 1 1 -24.314 67.331 5.734 1.00 90.0 1\n" +
"ATOM 6 C CG MET A 1 1 -28.544 67.973 5.934 1.00 86.0 1\n" +
"ATOM 7 S SD MET A 1 1 -29.390 68.904 4.598 1.00 86.0 1\n" +
"ATOM 8 C CE MET A 1 1 -29.202 67.734 3.224 1.00 83.0 1\n" +
"ATOM 9 N N ASN A 1 2 -24.267 66.233 7.730 1.00 90.0 1\n" +
"ATOM 10 C CA ASN A 1 2 -22.897 65.827 8.029 1.00 91.0 1\n" +
"ATOM 11 C C ASN A 1 2 -22.600 64.427 7.500 1.00 90.0 1\n" +
"ATOM 12 C CB ASN A 1 2 -22.634 65.893 9.535 1.00 88.0 1\n" +
"ATOM 13 O O ASN A 1 2 -23.092 63.436 8.044 1.00 89.0 1\n" +
"ATOM 14 C CG ASN A 1 2 -22.191 67.269 9.990 1.00 86.0 1\n" +
"ATOM 15 N ND2 ASN A 1 2 -22.255 67.511 11.294 1.00 87.0 1\n" +
"ATOM 16 O OD1 ASN A 1 2 -21.795 68.108 9.177 1.00 87.0 1\n" ;
MmCifFile cifFile = CifIO.readFromInputStream(new ByteArrayInputStream(mmcifStr.getBytes())).as(StandardSchemata.MMCIF);
Structure s = CifStructureConverter.fromCifFile(cifFile);
assertNotNull(s);
assertEquals(2, s.getPolyChain("A").getAtomGroups().size());
assertEquals(2, s.getPolyChainByPDB("A").getAtomGroups().size());
}
}