/**
* Loads the biological assembly for a given PDB ID and bioAssemblyId. If a bioAssemblyId > 0 is
* specified, the corresponding biological assembly file will be loaded. Note, the number of
* available biological unit files varies. Many entries don't have a biological assembly specified
* (i.e. NMR structures), many entries have only one biological assembly (bioAssemblyId=1), and a
* few structures have multiple biological assemblies. Set bioAssemblyFallback to true, to
* download the original PDB file in cases that a biological assembly file is not available.
*
* @param pdbId the PDB ID
* @param bioAssemblyId the 1-based index of the biological assembly (0 gets the asymmetric unit)
* @param bioAssemblyFallback if true, try reading original PDB file in case the biological
* assembly file is not available
* @return a structure object
* @throws IOException
* @throws StructureException
* @author Peter Rose
* @since 3.2
*/
public Structure getBiologicalAssembly(
String pdbId, int bioAssemblyId, boolean bioAssemblyFallback)
throws StructureException, IOException {
if (bioAssemblyId < 0) {
throw new StructureException(
"bioAssemblyID must be nonnegative: " + pdbId + " bioAssemblyId " + bioAssemblyId);
}
Structure s = StructureIO.getBiologicalAssembly(pdbId, bioAssemblyId, this);
if (s == null && bioAssemblyFallback) return StructureIO.getBiologicalAssembly(pdbId, 0, this);
return s;
}
public static void toSequenceFile(String fileName, Collection<String> pdbIds, boolean verbose)
throws IOException {
int failure = 0;
int success = 0;
int chains = 0;
try (SequenceFile.Writer writer =
SequenceFile.createWriter(
new Configuration(),
SequenceFile.Writer.file(new Path(fileName)),
SequenceFile.Writer.keyClass(Text.class),
SequenceFile.Writer.valueClass(IntArrayWritable.class),
SequenceFile.Writer.compression(
SequenceFile.CompressionType.BLOCK, new BZip2Codec())); ) {
for (String pdbId : pdbIds) {
if (verbose) {
System.out.println(pdbId);
}
Structure s = null;
try {
s = StructureIO.getStructure(pdbId);
success++;
} catch (Exception e) {
// some files can't be read. Let's just skip those!
e.printStackTrace();
failure++;
continue;
}
if (s == null) {
System.err.println("structure null: " + pdbId);
continue;
}
if (s.getChains().size() == 0) {
continue;
}
chains += append(writer, pdbId, s);
}
IOUtils.closeStream(writer);
}
if (verbose) {
System.out.println("Total structures: " + pdbIds.size());
System.out.println("Success: " + success);
System.out.println("Failure: " + failure);
System.out.println("Chains: " + chains);
}
}
public static void main(String[] args) throws IOException {
String timeStamp =
new SimpleDateFormat("yyyyMMdd_HHmmss").format(Calendar.getInstance().getTime());
String uri = args[0] + "_" + timeStamp + ".seq";
Set<String> pdbIds = getAll();
StructureIO.setAtomCache(cache);
cache.setPath("/Users/Chris/Documents/RCSB/Data/Protein_chains/cache/");
long start = System.nanoTime();
toSequenceFile(uri, pdbIds, true);
long end = System.nanoTime();
System.out.println("Time: " + (end - start) / 1E9 + " sec.");
}
