X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fws%2Fsifts%2FSiftsClient.java;h=176c511acdedb5a4f997c65adf771f56f3f9536d;hb=9b6d2ddd33ba5e479953700040e1129847e47a06;hp=bde215da2a187639c968ad1946da67e1333c5905;hpb=5f2df50328b5b4e3ca082b8bf27360aaabc69e3a;p=jalview.git diff --git a/src/jalview/ws/sifts/SiftsClient.java b/src/jalview/ws/sifts/SiftsClient.java index bde215d..176c511 100644 --- a/src/jalview/ws/sifts/SiftsClient.java +++ b/src/jalview/ws/sifts/SiftsClient.java @@ -18,7 +18,7 @@ * along with Jalview. If not, see . * The Jalview Authors are detailed in the 'AUTHORS' file. */ -package jalview.io; +package jalview.ws.sifts; import jalview.analysis.AlignSeq; import jalview.api.DBRefEntryI; @@ -34,7 +34,6 @@ import jalview.xml.binding.sifts.Entry.Entity.Segment; import jalview.xml.binding.sifts.Entry.Entity.Segment.ListMapRegion.MapRegion; import jalview.xml.binding.sifts.Entry.Entity.Segment.ListResidue.Residue; import jalview.xml.binding.sifts.Entry.Entity.Segment.ListResidue.Residue.CrossRefDb; -import jalview.xml.binding.sifts.Entry.EntryDetail; import jalview.xml.binding.sifts.Entry.ListDB.Db; import java.io.File; @@ -46,8 +45,9 @@ import java.io.InputStream; import java.io.PrintStream; import java.net.URL; import java.net.URLConnection; -import java.util.HashMap; +import java.util.ArrayList; import java.util.HashSet; +import java.util.LinkedHashMap; import java.util.List; import java.util.zip.GZIPInputStream; @@ -65,6 +65,10 @@ public class SiftsClient implements SiftsClientI private String pdbId; + private String structId; + + private String segStartEnd; + private static final int BUFFER_SIZE = 4096; private static final String SIFTS_FTP_BASE_URL = "ftp://ftp.ebi.ac.uk/pub/databases/msd/sifts/xml/"; @@ -248,7 +252,8 @@ public class SiftsClient implements SiftsClientI * @throws Exception * if no valid source DBRefEntry was found for the given sequences */ - public DBRefEntryI getValidSourceDBRef(SequenceI seq) throws Exception + public DBRefEntryI getValidSourceDBRef(SequenceI seq) + throws SiftsException { DBRefEntryI sourceDBRef = null; sourceDBRef = seq.getSourceDBRef(); @@ -269,7 +274,7 @@ public class SiftsClient implements SiftsClientI if (dbRefs == null || dbRefs.length < 1) { - throw new Exception("Could not get source DB Ref"); + throw new SiftsException("Could not get source DB Ref"); } for (DBRefEntryI dbRef : dbRefs) @@ -291,7 +296,7 @@ public class SiftsClient implements SiftsClientI { return sourceDBRef; } - throw new Exception("Could not get source DB Ref"); + throw new SiftsException("Could not get source DB Ref"); } @@ -331,44 +336,80 @@ public class SiftsClient implements SiftsClientI return accessions; } + @Override + public StructureMapping getSiftsStructureMapping(SequenceI seq, + String pdbFile, String chain) throws SiftsException + { + structId = (chain == null) ? pdbId : pdbId + "|" + chain; + System.out.println("Getting mapping for: " + pdbId + "|" + chain + + " : seq- " + seq.getName()); + + final StringBuilder mappingDetails = new StringBuilder(128); + PrintStream ps = new PrintStream(System.out) + { + @Override + public void print(String x) + { + mappingDetails.append(x); + } + + @Override + public void println() + { + mappingDetails.append(NEWLINE); + } + }; + int[][] mapping = getGreedyMapping(chain, seq, ps); + + String mappingOutput = mappingDetails.toString(); + return new StructureMapping(seq, pdbFile, pdbId, chain, mapping, + mappingOutput); + } @Override public int[][] getGreedyMapping(String entityId, SequenceI seq, java.io.PrintStream os) - throws Exception + throws SiftsException { + int matchedResStart = -1; + int matchedResEnd = -1; + int counter = 0; + int pdbStart = -1; + int pdbEnd = -1; + int sStart = -1; + int sEnd = -1; + boolean startDetected = false; + System.out.println("Generating mappings for : " + entityId); Entity entity = null; entity = getEntityById(entityId); String seqStr = AlignSeq.extractGaps(jalview.util.Comparison.GapChars, seq.getSequenceAsString()); - // StringBuilder mappedStrucSeq = new StringBuilder(seqStr.length()); - String[] mappedStrucSeq = new String[seqStr.length()]; - int mapping[][] = new int[seqStr.length()][2]; + int mapping[][] = new int[seqStr.length() + seq.getStart()][2]; DBRefEntryI sourceDBRef = seq.getSourceDBRef(); if (sourceDBRef == null) { sourceDBRef = getValidSourceDBRef(seq); - // TODO if sourceDBRef is null at this point then throw an Exception - // TODO update sequence start/end with sourceDBRef start/end // seq.setStart(sourceDBRef.getStartRes()); // seq.setEnd(sourceDBRef.getEndRes()); } String crossRefAccessionId = sourceDBRef.getAccessionId(); - int start = seq.getStart() - 1; + int count = 0; for (int residue[] : mapping) { - residue[1] = start++; + residue[1] = count++; + residue[0] = -1; } - HashMap resNumMap = new HashMap(); + LinkedHashMap resNumMap = new LinkedHashMap(); List segments = entity.getSegment(); for (Segment segment : segments) { + segStartEnd = segment.getStart() + " - " + segment.getEnd(); System.out.println("Mappging segments : " + segment.getSegId() + "\\" - + segment.getStart() + "-" + segment.getEnd()); + + segStartEnd); List residues = segment.getListResidue().getResidue(); for (Residue residue : residues) { @@ -386,42 +427,84 @@ public class SiftsClient implements SiftsClientI { continue; } + int loopCount = 0; for (int[] x : mapping) { - if (x[1] == refDbResNum) + if (loopCount > seq.getStart() && x[1] == refDbResNum) { int resNum = Integer.valueOf(residue.getDbResNum()); x[0] = resNum; - String value = "x"; - resNumMap.put(resNum, value); + char resCharCode = ResidueProperties + .getSingleCharacterCode(residue.getDbResName()); + resNumMap.put(resNum, String.valueOf(resCharCode)); } + ++loopCount; } } } - - //Generate visual mapping output - // StringBuilder strucSeq = new StringBuilder(); - // for(int[] x : mapping){ - // if(mapping[0] == 0){ - // strucSeq.append(b) - // } - // } - mappedStrucSeq[1] = "x"; + + for (int[] x : mapping) + { + if (!startDetected && x[0] > -1) + { + matchedResStart = counter; + // System.out.println(matchedResStart); + startDetected = true; + } + + if (startDetected && x[0] == -1) + { + matchedResEnd = counter; + } + ++counter; + } + + String matchedSeqStr = seqStr; + if (matchedResStart != -1) + { + matchedResEnd = (matchedResEnd == -1) ? counter : matchedResEnd; + pdbStart = mapping[matchedResStart][0]; + pdbEnd = mapping[matchedResEnd - 1][0]; + sStart = mapping[matchedResStart][1]; + sEnd = mapping[matchedResEnd - 1][1]; + int seqStart = seq.getStart(); + if (seqStart > 1) + { + matchedResStart = matchedResStart - seqStart; + matchedResEnd = matchedResEnd - seqStart; + } + else + { + --matchedResStart; + --matchedResEnd; + } + matchedSeqStr = seqStr.substring(matchedResStart, matchedResEnd); + } + + StringBuilder targetStrucSeqs = new StringBuilder(); + for (String res : resNumMap.values()) + { + targetStrucSeqs.append(res); + } + try { - System.out.println(">>>> seq: " + seqStr + "\nlength " - + seqStr.length()); - System.out.println(">>>> pdb: " + mappedStrucSeq.toString() - + "\nlength " + mappedStrucSeq.toString().length()); - - String printedMapping = getMappingOutput(mappedStrucSeq.toString(), - seqStr, "seqAccession", "strucAccession", "pep", 3) - .toString(); if (os != null) { - os.print(printedMapping); + MappingOutputPojo mop = new MappingOutputPojo(); + mop.setSeqStart(sStart); + mop.setSeqEnd(sEnd); + mop.setSeqName(seq.getName()); + mop.setSeqResidue(matchedSeqStr); + + mop.setStrStart(pdbStart); + mop.setStrEnd(pdbEnd); + mop.setStrName(structId); + mop.setStrResidue(targetStrucSeqs.toString()); + + mop.setType("pep"); + os.print(getMappingOutput(mop).toString()); } - System.out.println(); } catch (Exception ex) { ex.printStackTrace(); @@ -436,44 +519,9 @@ public class SiftsClient implements SiftsClientI && getAllMappingAccession().contains(accessionId); } - @Override - public StructureMapping getSiftsStructureMapping(SequenceI seq, - String pdbFile, String chain) - { - System.out.println("Getting mapping for: " + pdbId + "|" + chain - + " : seq- " + seq.getName()); - - final StringBuilder mappingDetails = new StringBuilder(128); - PrintStream ps = new PrintStream(System.out) - { - @Override - public void print(String x) - { - mappingDetails.append(x); - } - - @Override - public void println() - { - mappingDetails.append(NEWLINE); - } - }; - int[][] mapping = null; - try - { - mapping = getGreedyMapping(chain, seq, ps); - } catch (Exception e) - { - e.printStackTrace(); - } - // String mappingOutput = mappingDetails.toString(); - String mappingOutput = null; - return new StructureMapping(seq, pdbFile, pdbId, chain, mapping, - mappingOutput); - } @Override - public Entity getEntityById(String id) throws Exception + public Entity getEntityById(String id) throws SiftsException { List entities = siftsEntry.getEntity(); for (Entity entity : entities) @@ -484,52 +532,77 @@ public class SiftsClient implements SiftsClientI } return entity; } - throw new Exception("Entity " + id + " not found"); + throw new SiftsException("Entity " + id + " not found"); } @Override public String[] getEntryDBs() { System.out.println("\nListing DB entries..."); + List availDbs = new ArrayList(); List dbs = siftsEntry.getListDB().getDb(); for (Db db : dbs) { + availDbs.add(db.getDbSource()); System.out.println(db.getDbSource() + " | " + db.getDbCoordSys()); } - return null; - } - - @Override - public void getEntryDetails() - { - List eds = siftsEntry.getEntryDetail(); - for (EntryDetail ed : eds) - { - System.out.println("Entry Details: " + ed.getContent() + " " - + ed.getDbSource() + " " + ed.getProperty() + " " - + ed.toString()); - } + return availDbs.toArray(new String[0]); } @Override - public StringBuffer getMappingOutput(String astr1, String astr2, String s1id, - String s2id, String type, int nochunks) + public StringBuffer getMappingOutput(MappingOutputPojo mp) { - int maxid = s1id.length(); + String seqRes = mp.getSeqResidue(); + String seqName = mp.getSeqName(); + int sStart = mp.getSeqStart(); + int sEnd = mp.getSeqEnd(); + + String strRes = mp.getStrResidue(); + String strName = mp.getStrName(); + int pdbStart = mp.getStrStart(); + int pdbEnd = mp.getStrEnd(); + + String type = mp.getType(); + + int maxid = (seqName.length() >= strName.length()) ? seqName.length() + : strName.length(); int len = 72 - maxid - 1; - StringBuffer output = new StringBuffer(); + + // int nochunks = 2;// mp.getWrapHeight(); + int nochunks = ((seqRes.length()) / len) + + ((seqRes.length()) % len > 0 ? 1 : 0); // output mappings + StringBuffer output = new StringBuffer(); + output.append(NEWLINE); + output.append("Sequence ⟷ Structure mapping details:"); + output.append(NEWLINE).append(NEWLINE); + + output.append(new Format("%" + maxid + "s").form(seqName)); + output.append(" : "); + output.append(String.valueOf(sStart)); + output.append(" - "); + output.append(String.valueOf(sEnd)); + output.append(" Maps to "); + output.append(NEWLINE); + output.append(new Format("%" + maxid + "s").form(structId)); + output.append(" : "); + output.append(String.valueOf(pdbStart)); + output.append(" - "); + output.append(String.valueOf(pdbEnd)); + output.append(NEWLINE).append(NEWLINE); + float pid = 0; for (int j = 0; j < nochunks; j++) { // Print the first aligned sequence - output.append(new Format("%" + (maxid) + "s").form(s1id)).append(" "); + output.append(new Format("%" + (maxid) + "s").form(seqName)).append( + " "); for (int i = 0; i < len; i++) { - if ((i + (j * len)) < astr1.length()) + if ((i + (j * len)) < seqRes.length()) { - output.append(astr1.charAt(i + (j * len))); + output.append(seqRes.charAt(i + (j * len))); } } @@ -539,10 +612,10 @@ public class SiftsClient implements SiftsClientI // Print out the matching chars for (int i = 0; i < len; i++) { - if ((i + (j * len)) < astr1.length()) + if ((i + (j * len)) < seqRes.length()) { - if (astr1.charAt(i + (j * len)) == astr2.charAt(i + (j * len)) - && !jalview.util.Comparison.isGap(astr1.charAt(i + if (seqRes.charAt(i + (j * len)) == strRes.charAt(i + (j * len)) + && !jalview.util.Comparison.isGap(seqRes.charAt(i + (j * len)))) { pid++; @@ -550,8 +623,8 @@ public class SiftsClient implements SiftsClientI } else if (type.equals("pep")) { - if (ResidueProperties.getPAM250(astr1.charAt(i + (j * len)), - astr2.charAt(i + (j * len))) > 0) + if (ResidueProperties.getPAM250(seqRes.charAt(i + (j * len)), + strRes.charAt(i + (j * len))) > 0) { output.append("."); } @@ -568,21 +641,23 @@ public class SiftsClient implements SiftsClientI } // Now print the second aligned sequence output = output.append(NEWLINE); - output = output.append(new Format("%" + (maxid) + "s").form(s2id)) + output = output.append(new Format("%" + (maxid) + "s").form(strName)) .append(" "); for (int i = 0; i < len; i++) { - if ((i + (j * len)) < astr2.length()) + if ((i + (j * len)) < strRes.length()) { - output.append(astr2.charAt(i + (j * len))); + output.append(strRes.charAt(i + (j * len))); } } output.append(NEWLINE).append(NEWLINE); } - pid = pid / (astr1.length()) * 100; - System.out.println(output); - System.out.println(pid); - // TODO return output & pid + pid = pid / (seqRes.length()) * 100; + output.append("Length of alignment = " + seqRes.length()) + .append(NEWLINE); + output.append(new Format("Percentage ID = %2.2f").form(pid)); + output.append(NEWLINE); + output.append("Mapping method: SIFTS").append(NEWLINE); return output; }