Skip to content

Parsing resolution values in PDB (REMARK 2 and REMARK 3 [new format]) and mmCif #1001

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
aalhossary merged 5 commits into from
Dec 8, 2021
Merged

Parsing resolution values in PDB (REMARK 2 and REMARK 3 [new format]) and mmCif #1001

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
96def7e
Parsing REMARK 2 and REMARK 3 (new format)
aalhossary Nov 27, 2021
c16c2a8
Parsing EM resolution in mmCif parser
aalhossary Dec 2, 2021
0dea8f5
Safer condition
aalhossary Dec 6, 2021
73343ef
Resolution defaults to 99 if no value is available.
aalhossary Dec 7, 2021
f04916a
Referring to DEFAULT_RESOLUTION instead of 99
aalhossary Dec 8, 2021
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: 12 additions & 0 deletions biojava-structure/src/main/java/org/biojava/nbio/structure/PDBHeader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -580,6 +580,18 @@ public void setCrystallographicInfo(PDBCrystallographicInfo crystallographicInfo
this.crystallographicInfo = crystallographicInfo;
}

/**
* Returns the resolution (or effective resolution) of the experiment. This is
* related to <code>_refine.ls_d_res_high</code> (DIFFRACTION) or
* <code>_em_3d_reconstruction.resolution</code> (ELECTRON MICROSCOPY) for mmCif
* format, or to <code>REMARK 2</code> or <code>REMARK 3</code> for PDB legacy
* format. If more than one value is available (in rare cases), the last one is
* reported. If no value is available, it defaults to
* {@link #DEFAULT_RESOLUTION} ({@value #DEFAULT_RESOLUTION}).
*
* @return The reported experiment resolution, {@link #DEFAULT_RESOLUTION}
* ({@value #DEFAULT_RESOLUTION}) if no value is available.
*/
public float getResolution() {
return resolution;
}
Expand Down
38 changes: 25 additions & 13 deletions biojava-structure/src/main/java/org/biojava/nbio/structure/io/PDBFileParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1351,7 +1351,7 @@ private void pdb_REMARK_Handler(String line) {
if (line.startsWith("REMARK 800")) {
pdb_REMARK_800_Handler(line);

} else if ( line.startsWith("REMARK 350")){
} else if ( line.startsWith("REMARK 350")){

if ( params.isParseBioAssembly()) {

Expand All @@ -1361,6 +1361,10 @@ private void pdb_REMARK_Handler(String line) {

bioAssemblyParser.pdb_REMARK_350_Handler(line);
}
} else if (line.startsWith("REMARK 2")) {
//REMARK 2 RESOLUTION.
Pattern pR = Pattern.compile("^REMARK 2 RESOLUTION.\\s+(\\d+\\.\\d+)\\s+ANGSTROMS\\..*");
handleResolutionLine(line, pR);

// REMARK 3 (for R free)
// note: if more than 1 value present (occurring in hybrid experimental technique entries, e.g. 3ins, 4n9m)
Expand Down Expand Up @@ -1396,21 +1400,29 @@ private void pdb_REMARK_Handler(String line) {
// then last one encountered will be taken
} else if (line.startsWith("REMARK 3 RESOLUTION RANGE HIGH")){
Pattern pR = Pattern.compile("^REMARK 3 RESOLUTION RANGE HIGH \\(ANGSTROMS\\) :\\s+(\\d+\\.\\d+).*");
Matcher mR = pR.matcher(line);
if (mR.matches()) {
try {
float res = Float.parseFloat(mR.group(1));
if (pdbHeader.getResolution()!=PDBHeader.DEFAULT_RESOLUTION) {
logger.warn("More than 1 resolution value present, will use last one {} and discard previous {} "
,mR.group(1), String.format("%4.2f",pdbHeader.getResolution()));
}
pdbHeader.setResolution(res);
} catch (NumberFormatException e) {
logger.info("Could not parse resolution '{}', ignoring it",mR.group(1));
handleResolutionLine(line, pR);
} else if (line.startsWith("REMARK 3 EFFECTIVE RESOLUTION")){
Pattern pR = Pattern.compile("^REMARK 3 EFFECTIVE RESOLUTION \\(ANGSTROMS\\)\\s+:\\s+(\\d+\\.\\d+).*");
handleResolutionLine(line, pR);
}
}

public void handleResolutionLine(String line, Pattern pR) {
Matcher mR = pR.matcher(line);
if (mR.matches()) {
final String resString = mR.group(1);
try {
float res = Float.parseFloat(resString);
final float resInHeader = pdbHeader.getResolution();
if (resInHeader!=PDBHeader.DEFAULT_RESOLUTION && resInHeader != res) {
logger.warn("More than 1 resolution value present, will use last one {} and discard previous {} "
,resString, String.format("%4.2f",resInHeader));
}
pdbHeader.setResolution(res);
} catch (NumberFormatException e) {
logger.info("Could not parse resolution '{}', ignoring it",resString);
}
}

}


Expand Down
9 changes: 8 additions & 1 deletion biojava-structure/src/main/java/org/biojava/nbio/structure/io/cif/CifStructureConsumer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
import org.rcsb.cif.schema.mm.DatabasePDBRemark;
import org.rcsb.cif.schema.mm.DatabasePDBRev;
import org.rcsb.cif.schema.mm.DatabasePDBRevRecord;
import org.rcsb.cif.schema.mm.Em3dReconstruction;
import org.rcsb.cif.schema.mm.Entity;
import org.rcsb.cif.schema.mm.EntityPoly;
import org.rcsb.cif.schema.mm.EntityPolySeq;
Expand Down Expand Up @@ -107,7 +108,13 @@ public interface CifStructureConsumer extends CifFileConsumer<Structure> {
*/
void consumeDatabasePDBRevRecord(DatabasePDBRevRecord databasePDBrevRecord);

/**
/**
* Consume Electron Microscopy 3D reconstruction data
* @param em3dReconstruction
*/
void consumeEm3dReconstruction(Em3dReconstruction em3dReconstruction);

/**
* Consume a particular Cif category.
* @param entity data
*/
Expand Down
18 changes: 18 additions & 0 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 @@ -69,6 +69,7 @@
import org.rcsb.cif.schema.mm.DatabasePDBRemark;
import org.rcsb.cif.schema.mm.DatabasePDBRev;
import org.rcsb.cif.schema.mm.DatabasePDBRevRecord;
import org.rcsb.cif.schema.mm.Em3dReconstruction;
import org.rcsb.cif.schema.mm.Entity;
import org.rcsb.cif.schema.mm.EntityPoly;
import org.rcsb.cif.schema.mm.EntityPolySeq;
Expand Down Expand Up @@ -128,6 +129,7 @@ public class CifStructureConsumerImpl implements CifStructureConsumer {
private List<Chain> currentModel;
private PDBHeader pdbHeader;
private String currentNmrModelNumber;
private Em3dReconstruction em3dReconstruction;
private List<Chain> entityChains;

private Entity entity;
Expand Down Expand Up @@ -644,6 +646,18 @@ public void consumeDatabasePDBRevRecord(DatabasePDBRevRecord databasePDBrevRecor
revRecords.add(new org.biojava.nbio.structure.DatabasePDBRevRecord(databasePDBrevRecord, i));
}
}

@Override
public void consumeEm3dReconstruction(Em3dReconstruction em3dReconstruction) {
this.em3dReconstruction = em3dReconstruction;

for (int rowIndex = 0; rowIndex < em3dReconstruction.getRowCount(); rowIndex++) { //can it have more than 1 value?
final FloatColumn resolution = em3dReconstruction.getResolution();
if (ValueKind.PRESENT.equals(resolution.getValueKind(rowIndex)))
pdbHeader.setResolution((float) resolution.get(rowIndex));
}
//TODO other fields (maybe RFree)?
}

@Override
public void consumeEntity(Entity entity) {
Expand Down Expand Up @@ -831,6 +845,10 @@ public void consumePdbxStructOperList(PdbxStructOperList pdbxStructOperList) {
public void consumeRefine(Refine refine) {
for (int rowIndex = 0; rowIndex < refine.getRowCount(); rowIndex++) {
// RESOLUTION
ValueKind valueKind = refine.getLsDResHigh().getValueKind(rowIndex);
if (! ValueKind.PRESENT.equals(valueKind)) {
continue;
}
// in very rare cases (for instance hybrid methods x-ray + neutron diffraction, e.g. 3ins, 4n9m)
// there are 2 resolution values, one for each method
// we take the last one found so that behaviour is like in PDB file parsing
Expand Down
1 change: 1 addition & 0 deletions biojava-structure/src/main/java/org/biojava/nbio/structure/io/cif/CifStructureConverter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,7 @@ public static Structure fromCifFile(CifFile cifFile, FileParsingParameters param
consumer.consumeDatabasePDBRemark(cifBlock.getDatabasePDBRemark());
consumer.consumeDatabasePDBRev(cifBlock.getDatabasePDBRev());
consumer.consumeDatabasePDBRevRecord(cifBlock.getDatabasePDBRevRecord());
consumer.consumeEm3dReconstruction(cifBlock.getEm3dReconstruction());
consumer.consumeEntity(cifBlock.getEntity());
consumer.consumeEntityPoly(cifBlock.getEntityPoly());
consumer.consumeEntitySrcGen(cifBlock.getEntitySrcGen());
Expand Down