-/*\r
- * Jalview - A Sequence Alignment Editor and Viewer\r
- * Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
- *\r
- * This program is free software; you can redistribute it and/or\r
- * modify it under the terms of the GNU General Public License\r
- * as published by the Free Software Foundation; either version 2\r
- * of the License, or (at your option) any later version.\r
- *\r
- * This program is distributed in the hope that it will be useful,\r
- * but WITHOUT ANY WARRANTY; without even the implied warranty of\r
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
- * GNU General Public License for more details.\r
- *\r
- * You should have received a copy of the GNU General Public License\r
- * along with this program; if not, write to the Free Software\r
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
- */\r
-package jalview.analysis;\r
-\r
-import java.util.*;\r
-\r
-import jalview.datamodel.*;\r
-\r
-/**\r
- * <p>Title: </p>\r
- *\r
- * <p>Description: </p>\r
- *\r
- * <p>Copyright: Copyright (c) 2004</p>\r
- *\r
- * <p>Company: Dundee University</p>\r
- *\r
- * @author not attributable\r
- * @version 1.0\r
- */\r
-public class SeqsetUtils\r
-{\r
-\r
- /**\r
- * Store essential properties of a sequence in a hashtable for later recovery\r
- * Keys are Name, Start, End, SeqFeatures, PdbId\r
- * @param seq SequenceI\r
- * @return Hashtable\r
- */\r
- public static Hashtable SeqCharacterHash(SequenceI seq)\r
- {\r
- Hashtable sqinfo = new Hashtable();\r
- sqinfo.put("Name", seq.getName());\r
- sqinfo.put("Start", new Integer(seq.getStart()));\r
- sqinfo.put("End", new Integer(seq.getEnd()));\r
- sqinfo.put("SeqFeatures", (seq.getSequenceFeatures() !=null) ? seq.getSequenceFeatures() : new Vector());\r
- sqinfo.put("PdbId",\r
- (seq.getPDBId() != null) ? seq.getPDBId() : new Vector());\r
- sqinfo.put("datasetSequence", (seq.getDatasetSequence() !=null) ? seq.getDatasetSequence() : new Sequence("THISISAPLACEHOLDER",""));\r
- return sqinfo;\r
- }\r
-\r
- /**\r
- * Recover essential properties of a sequence from a hashtable\r
- * TODO: replace these methods with something more elegant.\r
- * @param sq SequenceI\r
- * @param sqinfo Hashtable\r
- * @return boolean\r
- */\r
- public static boolean SeqCharacterUnhash(SequenceI sq, Hashtable sqinfo)\r
- {\r
- boolean namePresent = true;\r
- String oldname = (String) sqinfo.get("Name");\r
- Integer start = (Integer) sqinfo.get("Start");\r
- Integer end = (Integer) sqinfo.get("End");\r
- java.util.Vector sfeatures = (java.util.Vector) sqinfo.get(\r
- "SeqFeatures");\r
- Vector pdbid = (Vector) sqinfo.get("PdbId");\r
- Sequence seqds = (Sequence) sqinfo.get("datasetSequence");\r
- if (oldname == null)\r
- {\r
- namePresent = false;\r
- }\r
- else\r
- {\r
- sq.setName(oldname);\r
- }\r
-\r
- if (!pdbid.equals(""))\r
- {\r
- sq.setPDBId(pdbid);\r
- }\r
-\r
- if ( (start != null) && (end != null))\r
- {\r
- sq.setStart(start.intValue());\r
- sq.setEnd(end.intValue());\r
- }\r
-\r
- if ((sfeatures != null) && (sfeatures.size()>0))\r
- {\r
- sq.setSequenceFeatures(sfeatures);\r
- }\r
- if ((seqds!=null) && !(seqds.getName().equals("THISISAPLACEHOLDER") && seqds.getLength()==0)) {\r
- sq.setDatasetSequence(seqds);\r
- }\r
-\r
- return namePresent;\r
- }\r
-\r
- /**\r
- * Form of the unique name used in uniquify for the i'th sequence in an ordered vector of sequences.\r
- * @param i int\r
- * @return String\r
- */\r
- public static String unique_name(int i)\r
- {\r
- return new String("Sequence" + i);\r
- }\r
-\r
- /**\r
- * Generates a hash of SeqCharacterHash properties for each sequence\r
- * in a sequence set, and optionally renames the sequences to an\r
- * unambiguous 'safe' name.\r
- * @param sequences SequenceI[]\r
- * @param write_names boolean set this to rename each of the sequences to its unique_name(index) name\r
- * @return Hashtable to be passed to @see deuniquify to recover original names (and properties) for renamed sequences\r
- */\r
- public static Hashtable uniquify(SequenceI[] sequences, boolean write_names)\r
- {\r
- // Generate a safely named sequence set and a hash to recover the sequence names\r
- Hashtable map = new Hashtable();\r
- //String[] un_names = new String[sequences.length];\r
-\r
- for (int i = 0; i < sequences.length; i++)\r
- {\r
- String safename = unique_name(i);\r
- map.put(safename, SeqCharacterHash(sequences[i]));\r
-\r
- if (write_names)\r
- {\r
- sequences[i].setName(safename);\r
- }\r
- }\r
-\r
-\r
- return map;\r
- }\r
- /**\r
- * recover unsafe sequence names and original properties for a sequence\r
- * set using a map generated by @see uniquify(sequences,true)\r
- * @param map Hashtable\r
- * @param sequences SequenceI[]\r
- * @return boolean\r
- */\r
- public static boolean deuniquify(Hashtable map, SequenceI[] sequences)\r
- {\r
- jalview.analysis.SequenceIdMatcher matcher = new SequenceIdMatcher(sequences);\r
- SequenceI msq = null;\r
- Enumeration keys = map.keys();\r
- Vector unmatched = new Vector();\r
- for (int i=0, j=sequences.length; i<j; i++)\r
- unmatched.add(sequences[i]);\r
- while (keys.hasMoreElements()) {\r
- Object key = keys.nextElement();\r
- if (key instanceof String) {\r
- if ((msq = matcher.findIdMatch((String) key))!=null) {\r
- Hashtable sqinfo = (Hashtable) map.get(key);\r
- unmatched.remove(msq);\r
- SeqCharacterUnhash(msq, sqinfo);\r
- }\r
- else\r
- {\r
- System.err.println("Can't find '"+((String) key)+"' in uniquified alignment");\r
- }\r
- }\r
- }\r
- if (unmatched.size()>0) {\r
- System.err.println("Did not find matches for :");\r
- for (Enumeration i = unmatched.elements(); i.hasMoreElements(); System.out.println(((SequenceI) i.nextElement()).getName()))\r
- ;\r
- return false;\r
- }\r
-\r
- return true;\r
- }\r
- /**\r
- * returns a subset of the sequenceI seuqences,\r
- * including only those that contain at least one residue.\r
- * @param sequences SequenceI[]\r
- * @return SequenceI[]\r
- */\r
- public static SequenceI[] getNonEmptySequenceSet(SequenceI[] sequences) {\r
- // Identify first row of alignment with residues for prediction\r
- boolean ungapped[] = new boolean[sequences.length];\r
- int msflen=0;\r
- for (int i=0,j=sequences.length; i<j;i++) {\r
- String tempseq = jalview.analysis.AlignSeq.extractGaps(jalview.util.Comparison.GapChars, sequences[i].getSequence());\r
- if (tempseq.length()==0)\r
- ungapped[i]=false;\r
- else {\r
- ungapped[i]=true;\r
- msflen++;\r
- }\r
- }\r
- if (msflen==0)\r
- return null; // no minimal set\r
- // compose minimal set\r
- SequenceI[] mset = new SequenceI[msflen];\r
- for (int i=0,j=sequences.length,k=0; i<j;i++) {\r
- if (ungapped[i])\r
- mset[k++] = sequences[i];\r
- }\r
- ungapped = null;\r
- return mset;\r
- }\r
-}\r
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.analysis;
+
+import jalview.datamodel.HiddenMarkovModel;
+import jalview.datamodel.PDBEntry;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
+
+import java.util.Enumeration;
+import java.util.Hashtable;
+import java.util.List;
+import java.util.Vector;
+
+public class SeqsetUtils
+{
+
+ /**
+ * Store essential properties of a sequence in a hashtable for later recovery
+ * Keys are Name, Start, End, SeqFeatures, PdbId, HMM
+ *
+ * @param seq
+ * SequenceI
+ * @return Hashtable
+ */
+ public static Hashtable SeqCharacterHash(SequenceI seq)
+ {
+ Hashtable sqinfo = new Hashtable();
+ sqinfo.put("Name", seq.getName());
+ sqinfo.put("Start", new Integer(seq.getStart()));
+ sqinfo.put("End", new Integer(seq.getEnd()));
+ if (seq.getDescription() != null)
+ {
+ sqinfo.put("Description", seq.getDescription());
+ }
+
+ Vector<SequenceFeature> sfeat = new Vector<>();
+ List<SequenceFeature> sfs = seq.getFeatures().getAllFeatures();
+ sfeat.addAll(sfs);
+
+ if (seq.getDatasetSequence() == null)
+ {
+ sqinfo.put("SeqFeatures", sfeat);
+ sqinfo.put("PdbId",
+ (seq.getAllPDBEntries() != null) ? seq.getAllPDBEntries()
+ : new Vector<PDBEntry>());
+ }
+ else
+ {
+ sqinfo.put("datasetSequence",
+ (seq.getDatasetSequence() != null) ? seq.getDatasetSequence()
+ : new Sequence("THISISAPLACEHOLDER", ""));
+ }
+ if (seq.hasHMMProfile())
+ {
+ sqinfo.put("HMM", seq.getHMM());
+ }
+ return sqinfo;
+ }
+
+ /**
+ * Recover essential properties of a sequence from a hashtable TODO: replace
+ * these methods with something more elegant.
+ *
+ * @param sq
+ * SequenceI
+ * @param sqinfo
+ * Hashtable
+ * @return boolean true if name was not updated from sqinfo Name entry
+ */
+ public static boolean SeqCharacterUnhash(SequenceI sq, Hashtable sqinfo)
+ {
+ boolean namePresent = true;
+ if (sqinfo == null)
+ {
+ return false;
+ }
+ String oldname = (String) sqinfo.get("Name");
+ Integer start = (Integer) sqinfo.get("Start");
+ Integer end = (Integer) sqinfo.get("End");
+ Vector<SequenceFeature> sfeatures = (Vector<SequenceFeature>) sqinfo
+ .get("SeqFeatures");
+ Vector<PDBEntry> pdbid = (Vector<PDBEntry>) sqinfo.get("PdbId");
+ String description = (String) sqinfo.get("Description");
+ Sequence seqds = (Sequence) sqinfo.get("datasetSequence");
+ HiddenMarkovModel hmm = (HiddenMarkovModel) sqinfo.get("HMM");
+ if (oldname == null)
+ {
+ namePresent = false;
+ }
+ else
+ {
+ sq.setName(oldname);
+ }
+ if (pdbid != null && pdbid.size() > 0)
+ {
+ sq.setPDBId(pdbid);
+ }
+
+ if ((start != null) && (end != null))
+ {
+ sq.setStart(start.intValue());
+ sq.setEnd(end.intValue());
+ }
+
+ if (sfeatures != null && !sfeatures.isEmpty())
+ {
+ sq.setSequenceFeatures(sfeatures);
+ }
+ if (description != null)
+ {
+ sq.setDescription(description);
+ }
+ if ((seqds != null) && !(seqds.getName().equals("THISISAPLACEHOLDER")
+ && seqds.getLength() == 0))
+ {
+ if (sfeatures != null)
+ {
+ System.err.println(
+ "Implementation error: setting dataset sequence for a sequence which has sequence features.\n\tDataset sequence features will not be visible.");
+ }
+ sq.setDatasetSequence(seqds);
+ }
+
+ if (hmm != null)
+ {
+ sq.setHMM(new HiddenMarkovModel(hmm, sq));
+ }
+ return namePresent;
+ }
+
+ /**
+ * Form of the unique name used in uniquify for the i'th sequence in an
+ * ordered vector of sequences.
+ *
+ * @param i
+ * int
+ * @return String
+ */
+ public static String unique_name(int i)
+ {
+ return new String("Sequence" + i);
+ }
+
+ /**
+ * Generates a hash of SeqCharacterHash properties for each sequence in a
+ * sequence set, and optionally renames the sequences to an unambiguous 'safe'
+ * name.
+ *
+ * @param sequences
+ * SequenceI[]
+ * @param write_names
+ * boolean set this to rename each of the sequences to its
+ * unique_name(index) name
+ * @return Hashtable to be passed to
+ * @see deuniquify to recover original names (and properties) for renamed
+ * sequences
+ */
+ public static Hashtable uniquify(SequenceI[] sequences,
+ boolean write_names)
+ {
+ // Generate a safely named sequence set and a hash to recover the sequence
+ // names
+ Hashtable map = new Hashtable();
+ // String[] un_names = new String[sequences.length];
+
+ for (int i = 0; i < sequences.length; i++)
+ {
+ String safename = unique_name(i);
+ map.put(safename, SeqCharacterHash(sequences[i]));
+
+ if (write_names)
+ {
+ sequences[i].setName(safename);
+ }
+ }
+
+ return map;
+ }
+
+ /**
+ * recover unsafe sequence names and original properties for a sequence set
+ * using a map generated by
+ *
+ * @see uniquify(sequences,true)
+ * @param map
+ * Hashtable
+ * @param sequences
+ * SequenceI[]
+ * @return boolean
+ */
+ public static boolean deuniquify(Hashtable map, SequenceI[] sequences)
+ {
+ return deuniquify(map, sequences, true);
+ }
+
+ /**
+ * recover unsafe sequence names and original properties for a sequence set
+ * using a map generated by
+ *
+ * @see uniquify(sequences,true)
+ * @param map
+ * Hashtable
+ * @param sequences
+ * SequenceI[]
+ * @param quiet
+ * when false, don't complain about sequences without any data in the
+ * map.
+ * @return boolean
+ */
+ public static boolean deuniquify(Hashtable map, SequenceI[] sequences,
+ boolean quiet)
+ {
+ jalview.analysis.SequenceIdMatcher matcher = new SequenceIdMatcher(
+ sequences);
+ SequenceI msq = null;
+ Enumeration keys = map.keys();
+ Vector unmatched = new Vector();
+ for (int i = 0, j = sequences.length; i < j; i++)
+ {
+ unmatched.addElement(sequences[i]);
+ }
+ while (keys.hasMoreElements())
+ {
+ Object key = keys.nextElement();
+ if (key instanceof String)
+ {
+ if ((msq = matcher.findIdMatch((String) key)) != null)
+ {
+ Hashtable sqinfo = (Hashtable) map.get(key);
+ unmatched.removeElement(msq);
+ SeqCharacterUnhash(msq, sqinfo);
+ }
+ else
+ {
+ if (!quiet)
+ {
+ System.err.println("Can't find '" + ((String) key)
+ + "' in uniquified alignment");
+ }
+ }
+ }
+ }
+ if (unmatched.size() > 0 && !quiet)
+ {
+ System.err.println("Did not find matches for :");
+ for (Enumeration i = unmatched.elements(); i
+ .hasMoreElements(); System.out
+ .println(((SequenceI) i.nextElement()).getName()))
+ {
+ ;
+ }
+ return false;
+ }
+
+ return true;
+ }
+
+ /**
+ * returns a subset of the sequenceI seuqences, including only those that
+ * contain at least one residue.
+ *
+ * @param sequences
+ * SequenceI[]
+ * @return SequenceI[]
+ */
+ public static SequenceI[] getNonEmptySequenceSet(SequenceI[] sequences)
+ {
+ // Identify first row of alignment with residues for prediction
+ boolean ungapped[] = new boolean[sequences.length];
+ int msflen = 0;
+ for (int i = 0, j = sequences.length; i < j; i++)
+ {
+ String tempseq = jalview.analysis.AlignSeq.extractGaps(
+ jalview.util.Comparison.GapChars,
+ sequences[i].getSequenceAsString());
+
+ if (tempseq.length() == 0)
+ {
+ ungapped[i] = false;
+ }
+ else
+ {
+ ungapped[i] = true;
+ msflen++;
+ }
+ }
+ if (msflen == 0)
+ {
+ return null; // no minimal set
+ }
+ // compose minimal set
+ SequenceI[] mset = new SequenceI[msflen];
+ for (int i = 0, j = sequences.length, k = 0; i < j; i++)
+ {
+ if (ungapped[i])
+ {
+ mset[k++] = sequences[i];
+ }
+ }
+ ungapped = null;
+ return mset;
+ }
+}