2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 package jalview.ws.sifts;
23 import jalview.analysis.AlignSeq;
24 import jalview.analysis.scoremodels.ScoreMatrix;
25 import jalview.analysis.scoremodels.ScoreModels;
26 import jalview.api.DBRefEntryI;
27 import jalview.api.SiftsClientI;
28 import jalview.datamodel.DBRefEntry;
29 import jalview.datamodel.DBRefSource;
30 import jalview.datamodel.SequenceI;
31 import jalview.io.StructureFile;
32 import jalview.schemes.ResidueProperties;
33 import jalview.structure.StructureMapping;
34 import jalview.structures.models.MappingOutputModel;
35 import jalview.util.Comparison;
36 import jalview.util.DBRefUtils;
37 import jalview.util.Format;
38 import jalview.xml.binding.sifts.Entry;
39 import jalview.xml.binding.sifts.Entry.Entity;
40 import jalview.xml.binding.sifts.Entry.Entity.Segment;
41 import jalview.xml.binding.sifts.Entry.Entity.Segment.ListMapRegion.MapRegion;
42 import jalview.xml.binding.sifts.Entry.Entity.Segment.ListResidue.Residue;
43 import jalview.xml.binding.sifts.Entry.Entity.Segment.ListResidue.Residue.CrossRefDb;
44 import jalview.xml.binding.sifts.Entry.Entity.Segment.ListResidue.Residue.ResidueDetail;
47 import java.io.FileInputStream;
48 import java.io.FileOutputStream;
49 import java.io.IOException;
50 import java.io.InputStream;
51 import java.io.PrintStream;
53 import java.net.URLConnection;
54 import java.nio.file.Files;
55 import java.nio.file.Path;
56 import java.nio.file.attribute.BasicFileAttributes;
57 import java.util.ArrayList;
58 import java.util.Arrays;
59 import java.util.Collection;
60 import java.util.Collections;
61 import java.util.Date;
62 import java.util.HashMap;
63 import java.util.HashSet;
64 import java.util.List;
67 import java.util.TreeMap;
68 import java.util.zip.GZIPInputStream;
70 import javax.xml.bind.JAXBContext;
71 import javax.xml.bind.Unmarshaller;
72 import javax.xml.stream.XMLInputFactory;
73 import javax.xml.stream.XMLStreamReader;
76 import MCview.PDBChain;
78 public class SiftsClient implements SiftsClientI
81 * for use in mocking out file fetch for tests only
82 * - reset to null after testing!
84 private static File mockSiftsFile;
86 private static final int UNASSIGNED = StructureMapping.UNASSIGNED; // -1
88 private static final int PDB_RES_POS = StructureMapping.PDB_RES_NUM_INDEX; // 0
90 private Entry siftsEntry;
92 private StructureFile structureFile;
96 private String structId;
98 private CoordinateSys seqCoordSys = CoordinateSys.UNIPROT;
100 private static final int BUFFER_SIZE = 4096;
102 private static final int PDB_ATOM_POS = 1;
104 private static final String NOT_OBSERVED = "Not_Observed";
106 private static final String SIFTS_FTP_BASE_URL = "http://ftp.ebi.ac.uk/pub/databases/msd/sifts/xml/";
108 private final static String NEWLINE = System.lineSeparator();
110 private String curSourceDBRef;
112 private HashSet<String> curDBRefAccessionIdsString;
114 private enum CoordinateSys
116 UNIPROT("UniProt"), PDB("PDBresnum"), PDBe("PDBe");
119 private CoordinateSys(String name)
124 public String getName()
130 private enum ResidueDetailType
132 NAME_SEC_STRUCTURE("nameSecondaryStructure"), CODE_SEC_STRUCTURE(
133 "codeSecondaryStructure"), ANNOTATION("Annotation");
136 private ResidueDetailType(String code)
141 public String getCode()
148 * Fetch SIFTs file for the given PDBfile and construct an instance of
152 * @throws SiftsException
154 public SiftsClient(StructureFile structureFile) throws SiftsException
156 this.structureFile = structureFile;
157 this.pdbId = structureFile.getId();
158 File siftsFile = getSiftsFile(pdbId);
159 siftsEntry = parseSIFTs(siftsFile);
163 * Parse the given SIFTs File and return a JAXB POJO of parsed data
166 * - the GZipped SIFTs XML file to parse
169 * if a problem occurs while parsing the SIFTs XML
171 private Entry parseSIFTs(File siftFile) throws SiftsException
173 try (InputStream in = new FileInputStream(siftFile);
174 GZIPInputStream gzis = new GZIPInputStream(in);)
176 // System.out.println("File : " + siftFile.getAbsolutePath());
177 JAXBContext jc = JAXBContext.newInstance("jalview.xml.binding.sifts");
178 XMLStreamReader streamReader = XMLInputFactory.newInstance()
179 .createXMLStreamReader(gzis);
180 Unmarshaller um = jc.createUnmarshaller();
181 return (Entry) um.unmarshal(streamReader);
182 } catch (Exception e)
185 throw new SiftsException(e.getMessage());
190 * Get a SIFTs XML file for a given PDB Id from Cache or download from FTP
191 * repository if not found in cache
194 * @return SIFTs XML file
195 * @throws SiftsException
197 public static File getSiftsFile(String pdbId) throws SiftsException
200 * return mocked file if it has been set
202 if (mockSiftsFile != null)
204 return mockSiftsFile;
207 String siftsFileName = SiftsSettings.getSiftDownloadDirectory()
208 + pdbId.toLowerCase() + ".xml.gz";
209 File siftsFile = new File(siftsFileName);
210 if (siftsFile.exists())
212 // The line below is required for unit testing... don't comment it out!!!
213 System.out.println(">>> SIFTS File already downloaded for " + pdbId);
215 if (isFileOlderThanThreshold(siftsFile,
216 SiftsSettings.getCacheThresholdInDays()))
218 File oldSiftsFile = new File(siftsFileName + "_old");
219 siftsFile.renameTo(oldSiftsFile);
222 siftsFile = downloadSiftsFile(pdbId.toLowerCase());
223 oldSiftsFile.delete();
225 } catch (IOException e)
228 oldSiftsFile.renameTo(siftsFile);
229 return new File(siftsFileName);
239 siftsFile = downloadSiftsFile(pdbId.toLowerCase());
240 } catch (IOException e)
242 throw new SiftsException(e.getMessage());
248 * This method enables checking if a cached file has exceeded a certain
254 * the threshold in days
257 public static boolean isFileOlderThanThreshold(File file, int noOfDays)
259 Path filePath = file.toPath();
260 BasicFileAttributes attr;
264 attr = Files.readAttributes(filePath, BasicFileAttributes.class);
265 diffInDays = (int) ((new Date().getTime() - attr.lastModifiedTime()
266 .toMillis()) / (1000 * 60 * 60 * 24));
267 // System.out.println("Diff in days : " + diffInDays);
268 } catch (IOException e)
272 return noOfDays <= diffInDays;
276 * Download a SIFTs XML file for a given PDB Id from an FTP repository
279 * @return downloaded SIFTs XML file
280 * @throws SiftsException
281 * @throws IOException
283 public static File downloadSiftsFile(String pdbId) throws SiftsException,
286 if (pdbId.contains(".cif"))
288 pdbId = pdbId.replace(".cif", "");
290 String siftFile = pdbId + ".xml.gz";
291 String siftsFileFTPURL = SIFTS_FTP_BASE_URL + siftFile;
292 String downloadedSiftsFile = SiftsSettings.getSiftDownloadDirectory()
294 File siftsDownloadDir = new File(
295 SiftsSettings.getSiftDownloadDirectory());
296 if (!siftsDownloadDir.exists())
298 siftsDownloadDir.mkdirs();
300 // System.out.println(">> Download ftp url : " + siftsFileFTPURL);
301 // long now = System.currentTimeMillis();
302 URL url = new URL(siftsFileFTPURL);
303 URLConnection conn = url.openConnection();
304 InputStream inputStream = conn.getInputStream();
305 FileOutputStream outputStream = new FileOutputStream(
306 downloadedSiftsFile);
307 byte[] buffer = new byte[BUFFER_SIZE];
309 while ((bytesRead = inputStream.read(buffer)) != -1)
311 outputStream.write(buffer, 0, bytesRead);
313 outputStream.close();
315 // System.out.println(">>> File downloaded : " + downloadedSiftsFile
316 // + " took " + (System.currentTimeMillis() - now) + "ms");
317 return new File(downloadedSiftsFile);
321 * Delete the SIFTs file for the given PDB Id in the local SIFTs download
325 * @return true if the file was deleted or doesn't exist
327 public static boolean deleteSiftsFileByPDBId(String pdbId)
329 File siftsFile = new File(SiftsSettings.getSiftDownloadDirectory()
330 + pdbId.toLowerCase() + ".xml.gz");
331 if (siftsFile.exists())
333 return siftsFile.delete();
339 * Get a valid SIFTs DBRef for the given sequence current SIFTs entry
342 * - the target sequence for the operation
343 * @return a valid DBRefEntry that is SIFTs compatible
345 * if no valid source DBRefEntry was found for the given sequences
347 public DBRefEntryI getValidSourceDBRef(SequenceI seq)
348 throws SiftsException
350 List<DBRefEntry> dbRefs = seq.getPrimaryDBRefs();
351 if (dbRefs == null || dbRefs.size() < 1)
353 throw new SiftsException(
354 "Source DBRef could not be determined. DBRefs might not have been retrieved.");
357 for (DBRefEntry dbRef : dbRefs)
359 if (dbRef == null || dbRef.getAccessionId() == null
360 || dbRef.getSource() == null)
364 String canonicalSource = DBRefUtils.getCanonicalName(dbRef
366 if (isValidDBRefEntry(dbRef)
367 && (canonicalSource.equalsIgnoreCase(DBRefSource.UNIPROT) || canonicalSource
368 .equalsIgnoreCase(DBRefSource.PDB)))
373 throw new SiftsException("Could not get source DB Ref");
377 * Check that the DBRef Entry is properly populated and is available in this
378 * SiftClient instance
381 * - DBRefEntry to validate
382 * @return true validation is successful otherwise false is returned.
384 boolean isValidDBRefEntry(DBRefEntryI entry)
386 return entry != null && entry.getAccessionId() != null
387 && isFoundInSiftsEntry(entry.getAccessionId());
391 public HashSet<String> getAllMappingAccession()
393 HashSet<String> accessions = new HashSet<String>();
394 List<Entity> entities = siftsEntry.getEntity();
395 for (Entity entity : entities)
397 List<Segment> segments = entity.getSegment();
398 for (Segment segment : segments)
400 List<MapRegion> mapRegions = segment.getListMapRegion()
402 for (MapRegion mapRegion : mapRegions)
405 .add(mapRegion.getDb().getDbAccessionId().toLowerCase());
413 public StructureMapping getSiftsStructureMapping(SequenceI seq,
414 String pdbFile, String chain) throws SiftsException
416 structId = (chain == null) ? pdbId : pdbId + "|" + chain;
417 System.out.println("Getting SIFTS mapping for " + structId + ": seq "
420 final StringBuilder mappingDetails = new StringBuilder(128);
421 PrintStream ps = new PrintStream(System.out)
424 public void print(String x)
426 mappingDetails.append(x);
430 public void println()
432 mappingDetails.append(NEWLINE);
435 HashMap<Integer, int[]> mapping = getGreedyMapping(chain, seq, ps);
437 String mappingOutput = mappingDetails.toString();
438 StructureMapping siftsMapping = new StructureMapping(seq, pdbFile,
439 pdbId, chain, mapping, mappingOutput);
444 public HashMap<Integer, int[]> getGreedyMapping(String entityId,
445 SequenceI seq, java.io.PrintStream os) throws SiftsException
447 List<Integer> omitNonObserved = new ArrayList<Integer>();
448 int nonObservedShiftIndex = 0;
449 // System.out.println("Generating mappings for : " + entityId);
450 Entity entity = null;
451 entity = getEntityById(entityId);
452 String originalSeq = AlignSeq.extractGaps(
453 jalview.util.Comparison.GapChars, seq.getSequenceAsString());
454 HashMap<Integer, int[]> mapping = new HashMap<Integer, int[]>();
455 DBRefEntryI sourceDBRef;
456 sourceDBRef = getValidSourceDBRef(seq);
457 // TODO ensure sequence start/end is in the same coordinate system and
458 // consistent with the choosen sourceDBRef
460 // set sequence coordinate system - default value is UniProt
461 if (sourceDBRef.getSource().equalsIgnoreCase(DBRefSource.PDB))
463 seqCoordSys = CoordinateSys.PDB;
466 HashSet<String> dbRefAccessionIdsString = new HashSet<String>();
467 for (DBRefEntry dbref : seq.getDBRefs())
469 dbRefAccessionIdsString.add(dbref.getAccessionId().toLowerCase());
471 dbRefAccessionIdsString.add(sourceDBRef.getAccessionId().toLowerCase());
473 curDBRefAccessionIdsString = dbRefAccessionIdsString;
474 curSourceDBRef = sourceDBRef.getAccessionId();
476 TreeMap<Integer, String> resNumMap = new TreeMap<Integer, String>();
477 List<Segment> segments = entity.getSegment();
478 SegmentHelperPojo shp = new SegmentHelperPojo(seq, mapping, resNumMap,
479 omitNonObserved, nonObservedShiftIndex);
480 processSegments(segments, shp);
483 populateAtomPositions(entityId, mapping);
484 } catch (Exception e)
488 if (seqCoordSys == CoordinateSys.UNIPROT)
490 padWithGaps(resNumMap, omitNonObserved);
492 int seqStart = UNASSIGNED;
493 int seqEnd = UNASSIGNED;
494 int pdbStart = UNASSIGNED;
495 int pdbEnd = UNASSIGNED;
497 if (mapping.isEmpty())
499 throw new SiftsException("SIFTS mapping failed");
502 Integer[] keys = mapping.keySet().toArray(new Integer[0]);
505 seqEnd = keys[keys.length - 1];
507 String matchedSeq = originalSeq;
508 if (seqStart != UNASSIGNED)
510 pdbStart = mapping.get(seqStart)[PDB_RES_POS];
511 pdbEnd = mapping.get(seqEnd)[PDB_RES_POS];
512 int orignalSeqStart = seq.getStart();
513 if (orignalSeqStart >= 1)
515 int subSeqStart = (seqStart >= orignalSeqStart) ? seqStart
516 - orignalSeqStart : 0;
517 int subSeqEnd = seqEnd - (orignalSeqStart - 1);
518 subSeqEnd = originalSeq.length() < subSeqEnd ? originalSeq.length()
520 matchedSeq = originalSeq.substring(subSeqStart, subSeqEnd);
524 matchedSeq = originalSeq.substring(1, originalSeq.length());
528 StringBuilder targetStrucSeqs = new StringBuilder();
529 for (String res : resNumMap.values())
531 targetStrucSeqs.append(res);
536 MappingOutputModel mop = new MappingOutputModel();
537 mop.setSeqStart(seqStart);
538 mop.setSeqEnd(seqEnd);
539 mop.setSeqName(seq.getName());
540 mop.setSeqResidue(matchedSeq);
542 mop.setStrStart(pdbStart);
543 mop.setStrEnd(pdbEnd);
544 mop.setStrName(structId);
545 mop.setStrResidue(targetStrucSeqs.toString());
548 os.print(getMappingOutput(mop).toString());
554 void processSegments(List<Segment> segments, SegmentHelperPojo shp)
556 SequenceI seq = shp.getSeq();
557 HashMap<Integer, int[]> mapping = shp.getMapping();
558 TreeMap<Integer, String> resNumMap = shp.getResNumMap();
559 List<Integer> omitNonObserved = shp.getOmitNonObserved();
560 int nonObservedShiftIndex = shp.getNonObservedShiftIndex();
561 for (Segment segment : segments)
563 // System.out.println("Mapping segments : " + segment.getSegId() + "\\"s
565 List<Residue> residues = segment.getListResidue().getResidue();
566 for (Residue residue : residues)
568 int currSeqIndex = UNASSIGNED;
569 List<CrossRefDb> cRefDbs = residue.getCrossRefDb();
570 CrossRefDb pdbRefDb = null;
571 for (CrossRefDb cRefDb : cRefDbs)
573 if (cRefDb.getDbSource().equalsIgnoreCase(DBRefSource.PDB))
577 if (cRefDb.getDbCoordSys()
578 .equalsIgnoreCase(seqCoordSys.getName())
579 && isAccessionMatched(cRefDb.getDbAccessionId()))
581 currSeqIndex = getLeadingIntegerValue(
582 cRefDb.getDbResNum(), UNASSIGNED);
583 if (pdbRefDb != null)
585 break;// exit loop if pdb and uniprot are already found
589 if (currSeqIndex == UNASSIGNED)
593 if (currSeqIndex >= seq.getStart() && currSeqIndex <= seq.getEnd())
596 int resNum = (pdbRefDb == null) ? getLeadingIntegerValue(
597 residue.getDbResNum(), UNASSIGNED)
598 : getLeadingIntegerValue(pdbRefDb.getDbResNum(),
601 if (isResidueObserved(residue)
602 || seqCoordSys == CoordinateSys.UNIPROT)
604 char resCharCode = ResidueProperties
605 .getSingleCharacterCode(ResidueProperties
606 .getCanonicalAminoAcid(residue.getDbResName()));
607 resNumMap.put(currSeqIndex, String.valueOf(resCharCode));
611 omitNonObserved.add(currSeqIndex);
612 ++nonObservedShiftIndex;
614 mapping.put(currSeqIndex - nonObservedShiftIndex, new int[] {
615 Integer.valueOf(resNum), UNASSIGNED });
622 * Get the leading integer part of a string that begins with an integer.
625 * - the string input to process
627 * - value returned if unsuccessful
630 static int getLeadingIntegerValue(String input, int failValue)
636 String[] parts = input.split("(?=\\D)(?<=\\d)");
637 if (parts != null && parts.length > 0 && parts[0].matches("[0-9]+"))
639 return Integer.valueOf(parts[0]);
648 * Target chain to populate mapping of its atom positions.
650 * Two dimension array of residue index versus atom position
651 * @throws IllegalArgumentException
652 * Thrown if chainId or mapping is null
653 * @throws SiftsException
655 void populateAtomPositions(String chainId, Map<Integer, int[]> mapping)
656 throws IllegalArgumentException, SiftsException
660 PDBChain chain = structureFile.findChain(chainId);
662 if (chain == null || mapping == null)
664 throw new IllegalArgumentException(
665 "Chain id or mapping must not be null.");
667 for (int[] map : mapping.values())
669 if (map[PDB_RES_POS] != UNASSIGNED)
671 map[PDB_ATOM_POS] = getAtomIndex(map[PDB_RES_POS], chain.atoms);
674 } catch (NullPointerException e)
676 throw new SiftsException(e.getMessage());
677 } catch (Exception e)
679 throw new SiftsException(e.getMessage());
685 * @param residueIndex
686 * The residue index used for the search
688 * A collection of Atom to search
689 * @return atom position for the given residue index
691 int getAtomIndex(int residueIndex, Collection<Atom> atoms)
695 throw new IllegalArgumentException(
696 "atoms collection must not be null!");
698 for (Atom atom : atoms)
700 if (atom.resNumber == residueIndex)
702 return atom.atomIndex;
709 * Checks if the residue instance is marked 'Not_observed' or not
714 private boolean isResidueObserved(Residue residue)
716 Set<String> annotations = getResidueAnnotaitons(residue,
717 ResidueDetailType.ANNOTATION);
718 if (annotations == null || annotations.isEmpty())
722 for (String annotation : annotations)
724 if (annotation.equalsIgnoreCase(NOT_OBSERVED))
733 * Get annotation String for a given residue and annotation type
739 private Set<String> getResidueAnnotaitons(Residue residue,
740 ResidueDetailType type)
742 HashSet<String> foundAnnotations = new HashSet<String>();
743 List<ResidueDetail> resDetails = residue.getResidueDetail();
744 for (ResidueDetail resDetail : resDetails)
746 if (resDetail.getProperty().equalsIgnoreCase(type.getCode()))
748 foundAnnotations.add(resDetail.getContent());
751 return foundAnnotations;
755 public boolean isAccessionMatched(String accession)
757 boolean isStrictMatch = true;
758 return isStrictMatch ? curSourceDBRef.equalsIgnoreCase(accession)
759 : curDBRefAccessionIdsString.contains(accession.toLowerCase());
762 private boolean isFoundInSiftsEntry(String accessionId)
764 Set<String> siftsDBRefs = getAllMappingAccession();
765 return accessionId != null
766 && siftsDBRefs.contains(accessionId.toLowerCase());
770 * Pad omitted residue positions in PDB sequence with gaps
774 void padWithGaps(Map<Integer, String> resNumMap,
775 List<Integer> omitNonObserved)
777 if (resNumMap == null || resNumMap.isEmpty())
781 Integer[] keys = resNumMap.keySet().toArray(new Integer[0]);
782 // Arrays.sort(keys);
783 int firstIndex = keys[0];
784 int lastIndex = keys[keys.length - 1];
785 // System.out.println("Min value " + firstIndex);
786 // System.out.println("Max value " + lastIndex);
787 for (int x = firstIndex; x <= lastIndex; x++)
789 if (!resNumMap.containsKey(x) && !omitNonObserved.contains(x))
791 resNumMap.put(x, "-");
797 public Entity getEntityById(String id) throws SiftsException
799 // Determines an entity to process by performing a heuristic matching of all
800 // Entities with the given chainId and choosing the best matching Entity
801 Entity entity = getEntityByMostOptimalMatchedId(id);
806 throw new SiftsException("Entity " + id + " not found");
810 * This method was added because EntityId is NOT always equal to ChainId.
811 * Hence, it provides the logic to greedily detect the "true" Entity for a
812 * given chainId where discrepancies exist.
817 public Entity getEntityByMostOptimalMatchedId(String chainId)
819 // System.out.println("---> advanced greedy entityId matching block entered..");
820 List<Entity> entities = siftsEntry.getEntity();
821 SiftsEntitySortPojo[] sPojo = new SiftsEntitySortPojo[entities.size()];
823 for (Entity entity : entities)
825 sPojo[count] = new SiftsEntitySortPojo();
826 sPojo[count].entityId = entity.getEntityId();
828 List<Segment> segments = entity.getSegment();
829 for (Segment segment : segments)
831 List<Residue> residues = segment.getListResidue().getResidue();
832 for (Residue residue : residues)
834 List<CrossRefDb> cRefDbs = residue.getCrossRefDb();
835 for (CrossRefDb cRefDb : cRefDbs)
837 if (!cRefDb.getDbSource().equalsIgnoreCase("PDB"))
841 ++sPojo[count].resCount;
842 if (cRefDb.getDbChainId().equalsIgnoreCase(chainId))
844 ++sPojo[count].chainIdFreq;
849 sPojo[count].pid = (100 * sPojo[count].chainIdFreq)
850 / sPojo[count].resCount;
853 Arrays.sort(sPojo, Collections.reverseOrder());
854 // System.out.println("highest matched entity : " + sPojo[0].entityId);
855 // System.out.println("highest matched pid : " + sPojo[0].pid);
857 if (sPojo[0].entityId != null)
859 if (sPojo[0].pid < 1)
863 for (Entity entity : entities)
865 if (!entity.getEntityId().equalsIgnoreCase(sPojo[0].entityId))
875 private class SiftsEntitySortPojo implements
876 Comparable<SiftsEntitySortPojo>
878 public String entityId;
880 public int chainIdFreq;
887 public int compareTo(SiftsEntitySortPojo o)
889 return this.pid - o.pid;
893 private class SegmentHelperPojo
895 private SequenceI seq;
897 private HashMap<Integer, int[]> mapping;
899 private TreeMap<Integer, String> resNumMap;
901 private List<Integer> omitNonObserved;
903 private int nonObservedShiftIndex;
905 public SegmentHelperPojo(SequenceI seq,
906 HashMap<Integer, int[]> mapping,
907 TreeMap<Integer, String> resNumMap,
908 List<Integer> omitNonObserved, int nonObservedShiftIndex)
912 setResNumMap(resNumMap);
913 setOmitNonObserved(omitNonObserved);
914 setNonObservedShiftIndex(nonObservedShiftIndex);
917 public SequenceI getSeq()
922 public void setSeq(SequenceI seq)
927 public HashMap<Integer, int[]> getMapping()
932 public void setMapping(HashMap<Integer, int[]> mapping)
934 this.mapping = mapping;
937 public TreeMap<Integer, String> getResNumMap()
942 public void setResNumMap(TreeMap<Integer, String> resNumMap)
944 this.resNumMap = resNumMap;
947 public List<Integer> getOmitNonObserved()
949 return omitNonObserved;
952 public void setOmitNonObserved(List<Integer> omitNonObserved)
954 this.omitNonObserved = omitNonObserved;
957 public int getNonObservedShiftIndex()
959 return nonObservedShiftIndex;
962 public void setNonObservedShiftIndex(int nonObservedShiftIndex)
964 this.nonObservedShiftIndex = nonObservedShiftIndex;
969 public StringBuilder getMappingOutput(MappingOutputModel mp)
970 throws SiftsException
972 String seqRes = mp.getSeqResidue();
973 String seqName = mp.getSeqName();
974 int sStart = mp.getSeqStart();
975 int sEnd = mp.getSeqEnd();
977 String strRes = mp.getStrResidue();
978 String strName = mp.getStrName();
979 int pdbStart = mp.getStrStart();
980 int pdbEnd = mp.getStrEnd();
982 String type = mp.getType();
984 int maxid = (seqName.length() >= strName.length()) ? seqName.length()
986 int len = 72 - maxid - 1;
988 int nochunks = ((seqRes.length()) / len)
989 + ((seqRes.length()) % len > 0 ? 1 : 0);
991 StringBuilder output = new StringBuilder(512);
992 output.append(NEWLINE);
993 output.append("Sequence \u27f7 Structure mapping details").append(
995 output.append("Method: SIFTS");
996 output.append(NEWLINE).append(NEWLINE);
998 output.append(new Format("%" + maxid + "s").form(seqName));
999 output.append(" : ");
1000 output.append(String.valueOf(sStart));
1001 output.append(" - ");
1002 output.append(String.valueOf(sEnd));
1003 output.append(" Maps to ");
1004 output.append(NEWLINE);
1005 output.append(new Format("%" + maxid + "s").form(structId));
1006 output.append(" : ");
1007 output.append(String.valueOf(pdbStart));
1008 output.append(" - ");
1009 output.append(String.valueOf(pdbEnd));
1010 output.append(NEWLINE).append(NEWLINE);
1012 ScoreMatrix pam250 = ScoreModels.getInstance().getPam250();
1013 int matchedSeqCount = 0;
1014 for (int j = 0; j < nochunks; j++)
1016 // Print the first aligned sequence
1017 output.append(new Format("%" + (maxid) + "s").form(seqName)).append(
1020 for (int i = 0; i < len; i++)
1022 if ((i + (j * len)) < seqRes.length())
1024 output.append(seqRes.charAt(i + (j * len)));
1028 output.append(NEWLINE);
1029 output.append(new Format("%" + (maxid) + "s").form(" ")).append(" ");
1032 * Print out the match symbols:
1033 * | for exact match (ignoring case)
1034 * . if PAM250 score is positive
1037 for (int i = 0; i < len; i++)
1041 if ((i + (j * len)) < seqRes.length())
1043 char c1 = seqRes.charAt(i + (j * len));
1044 char c2 = strRes.charAt(i + (j * len));
1045 boolean sameChar = Comparison.isSameResidue(c1, c2, false);
1046 if (sameChar && !Comparison.isGap(c1))
1051 else if (type.equals("pep"))
1053 if (pam250.getPairwiseScore(c1, c2) > 0)
1067 } catch (IndexOutOfBoundsException e)
1072 // Now print the second aligned sequence
1073 output = output.append(NEWLINE);
1074 output = output.append(new Format("%" + (maxid) + "s").form(strName))
1076 for (int i = 0; i < len; i++)
1078 if ((i + (j * len)) < strRes.length())
1080 output.append(strRes.charAt(i + (j * len)));
1083 output.append(NEWLINE).append(NEWLINE);
1085 float pid = (float) matchedSeqCount / seqRes.length() * 100;
1086 if (pid < SiftsSettings.getFailSafePIDThreshold())
1088 throw new SiftsException(">>> Low PID detected for SIFTs mapping...");
1090 output.append("Length of alignment = " + seqRes.length()).append(
1092 output.append(new Format("Percentage ID = %2.2f").form(pid));
1097 public int getEntityCount()
1099 return siftsEntry.getEntity().size();
1103 public String getDbAccessionId()
1105 return siftsEntry.getDbAccessionId();
1109 public String getDbCoordSys()
1111 return siftsEntry.getDbCoordSys();
1115 public String getDbSource()
1117 return siftsEntry.getDbSource();
1121 public String getDbVersion()
1123 return siftsEntry.getDbVersion();
1126 public static void setMockSiftsFile(File file)
1128 mockSiftsFile = file;