private void dnaCommand(HttpServletRequest req, DazzleResponse resp, DazzleDataSource dds)
throws IOException, DataSourceException, ServletException, DazzleException {
DazzleReferenceSource drs = (DazzleReferenceSource) dds;
List segments = DazzleTools.getSegments(dds, req, resp);
if (segments.size() == 0) {
throw new DazzleException(
DASStatus.STATUS_BAD_COMMAND_ARGUMENTS, "No segments specified for dna command");
}
// Fetch and validate the requests.
Map segmentResults = new HashMap();
for (Iterator i = segments.iterator(); i.hasNext(); ) {
Segment seg = (Segment) i.next();
try {
Sequence seq = drs.getSequence(seg.getReference());
if (seq.getAlphabet() != DNATools.getDNA()) {
throw new DazzleException(
DASStatus.STATUS_SERVER_ERROR,
"Sequence " + seg.toString() + " is not in the DNA alphabet");
}
if (seg.isBounded()) {
if (seg.getMin() < 1 || seg.getMax() > seq.length()) {
throw new DazzleException(
DASStatus.STATUS_BAD_COORDS,
"Segment " + seg.toString() + " doesn't fit sequence of length " + seq.length());
}
}
segmentResults.put(seg, seq);
} catch (NoSuchElementException ex) {
throw new DazzleException(DASStatus.STATUS_BAD_REFERENCE, ex);
} catch (DataSourceException ex) {
throw new DazzleException(DASStatus.STATUS_SERVER_ERROR, ex);
}
}
//
// Looks okay -- generate the response document
//
XMLWriter xw = resp.startDasXML("DASDNA", "dasdna.dtd");
try {
xw.openTag("DASDNA");
for (Iterator i = segmentResults.entrySet().iterator(); i.hasNext(); ) {
Map.Entry me = (Map.Entry) i.next();
Segment seg = (Segment) me.getKey();
Sequence seq = (Sequence) me.getValue();
xw.openTag("SEQUENCE");
xw.attribute("id", seg.getReference());
xw.attribute("version", drs.getLandmarkVersion(seg.getReference()));
if (seg.isBounded()) {
xw.attribute("start", "" + seg.getStart());
xw.attribute("stop", "" + seg.getStop());
} else {
xw.attribute("start", "" + 1);
xw.attribute("stop", "" + seq.length());
}
SymbolList syms = seq;
if (seg.isBounded()) {
syms = syms.subList(seg.getMin(), seg.getMax());
}
if (seg.isInverted()) {
syms = DNATools.reverseComplement(syms);
}
xw.openTag("DNA");
xw.attribute("length", "" + syms.length());
for (int pos = 1; pos <= syms.length(); pos += 60) {
int maxPos = Math.min(syms.length(), pos + 59);
xw.println(syms.subStr(pos, maxPos));
}
xw.closeTag("DNA");
xw.closeTag("SEQUENCE");
}
xw.closeTag("DASDNA");
xw.close();
} catch (Exception ex) {
throw new DazzleException(ex, "Error writing DNA document");
}
}
/**
* Returns the input subsequence matched by the previous match.
*
* <p>For a matcher m with input sequence s, the expressions m.group() and s.substring(m.start(),
* m.end()) are equivalent. Note that some patterns, for example a*, match the empty SymbolList.
* This method will return the empty string when the pattern successfully matches the empty string
* in the input.
*
* @return The (possibly empty) subsequence matched by the previous match, in SymbolList form.
*/
public SymbolList group() {
return sl.subList(start(), end() - 1);
}
/**
* Calculate the predicted properties of this polypeptide.
*
* @return a <code>PeptideProperties</code> object containing the predicted properties of this
* polypeptide.
*/
public PeptideProperties calculateStats() {
if (this.getResidues() == null) {
logger.warn("No residues for '" + this.getUniqueName() + "'");
return null;
}
String residuesString = new String(this.getResidues());
SymbolList residuesSymbolList = null;
PeptideProperties pp = new PeptideProperties();
try {
SymbolTokenization proteinTokenization = ProteinTools.getTAlphabet().getTokenization("token");
residuesSymbolList = new SimpleSymbolList(proteinTokenization, residuesString);
if (residuesSymbolList.length() == 0) {
logger.error(
String.format(
"Polypeptide feature '%s' has zero-length residues", this.getUniqueName()));
return pp;
}
try {
// if the sequence ends with a termination symbol (*), we need to remove it
if (residuesSymbolList.symbolAt(residuesSymbolList.length()) == ProteinTools.ter()) {
if (residuesSymbolList.length() == 1) {
logger.error(
String.format(
"Polypeptide feature '%s' only has termination symbol", this.getUniqueName()));
return pp;
}
residuesSymbolList = residuesSymbolList.subList(1, residuesSymbolList.length() - 1);
}
} catch (IndexOutOfBoundsException exception) {
throw new RuntimeException(exception);
}
} catch (BioException e) {
logger.error("Can't translate into a protein sequence", e);
return pp;
}
pp.setAminoAcids(residuesSymbolList.length());
try {
double isoElectricPoint = new IsoelectricPointCalc().getPI(residuesSymbolList, false, false);
pp.setIsoelectricPoint(isoElectricPoint);
} catch (Exception e) {
logger.error(
String.format("Error computing protein isoelectric point for '%s'", residuesSymbolList),
e);
}
double mass2 = calculateMass(residuesSymbolList);
if (mass2 != -1) {
// mass = mass2;
pp.setMass(mass2);
}
double charge = calculateCharge(residuesString);
pp.setCharge(charge);
return pp;
}
/**
* Returns the input subsequence captured by the given group during the previous match operation.
*
* <p>For a matcher m, input sequence s, and group index g, the expressions m.group(g) and
* s.substring(m.start(g), m.end(g)) are equivalent. Capturing groups are indexed from left to
* right, starting at one. Group zero denotes the entire pattern, so the expression m.group(0) is
* equivalent to m.group(). If the match was successful but the group specified failed to match
* any part of the input sequence, then null is returned. Note that some groups, for example (a*),
* match the empty string. This method will return the empty string when such a group successfully
* matches the emtpy string in the input.
*
* @return The (possibly empty) subsequence captured by the group during the previous match, or
* null if the group failed to match part of the input.
*/
public SymbolList group(int group) throws IndexOutOfBoundsException {
int start = matcher.start(group);
int end = matcher.end(group);
if ((start == -1) && (end == -1)) return null;
else return sl.subList(start(group), end(group) - 1);
}
