-/*\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 jalview.analysis.*;\r
-\r
-import jalview.datamodel.*;\r
-\r
-import java.util.*;\r
-\r
-\r
-/**\r
- * Takes in a vector of sequences and column start and column end\r
- * and returns a vector of size (end-start+1). Each element of the\r
- * vector contains a hashtable with the keys being residues and\r
- * the values being the count of each residue in that column.\r
- * This class is used extensively in calculating alignment colourschemes\r
- * that depend on the amount of conservation in each alignment column.\r
- * @author $author$\r
- * @version $Revision$\r
- */\r
-public class AAFrequency\r
-{\r
- /** Takes in a vector of sequences and column start and column end\r
- * and returns a vector of size (end-start+1). Each element of the\r
- * vector contains a hashtable with the keys being residues and\r
- * the values being the count of each residue in that column.\r
- * This class is used extensively in calculating alignment colourschemes\r
- * that depend on the amount of conservation in each alignment column. */\r
- public static Vector calculate(Vector sequences, int start, int end)\r
- {\r
- Vector result = new Vector();\r
-\r
- for (int i = start; i <= end; i++)\r
- {\r
- Hashtable residueHash = new Hashtable();\r
- int maxCount = 0;\r
- String maxResidue = "-";\r
- int nongap = 0;\r
-\r
- for (int j = 0; j < sequences.size(); j++)\r
- {\r
- if (sequences.elementAt(j) instanceof Sequence)\r
- {\r
- Sequence s = (Sequence) sequences.elementAt(j);\r
-\r
- if (s.getSequence().length() > i)\r
- {\r
- String res = s.getSequence().charAt(i) + "";\r
-\r
- if (!jalview.util.Comparison.isGap(res.charAt(0)))\r
- {\r
- nongap++;\r
- }\r
- else\r
- {\r
- res = "-"; // we always use this for gaps in the property vectors\r
- }\r
-\r
- if (residueHash.containsKey(res))\r
- {\r
- int count = ((Integer) residueHash.get(res)).intValue();\r
- count++;\r
-\r
- if (!jalview.util.Comparison.isGap(res.charAt(0)) &&\r
- (count >= maxCount))\r
- {\r
- if (count > maxCount)\r
- {\r
- maxResidue = res;\r
- }\r
- else if (maxResidue.indexOf(res) == -1)\r
- {\r
- maxResidue += res;\r
- }\r
-\r
- maxCount = count;\r
- }\r
-\r
- residueHash.put(res, new Integer(count));\r
- }\r
- else\r
- {\r
- residueHash.put(res, new Integer(1));\r
- }\r
- }\r
- else\r
- {\r
- if (residueHash.containsKey("-"))\r
- {\r
- int count = ((Integer) residueHash.get("-")).intValue();\r
- count++;\r
- residueHash.put("-", new Integer(count));\r
- }\r
- else\r
- {\r
- residueHash.put("-", new Integer(1));\r
- }\r
- }\r
- }\r
- }\r
-\r
- residueHash.put("maxCount", new Integer(maxCount));\r
-\r
- if (maxCount < 0)\r
- {\r
- System.out.println("asasa " + maxCount);\r
- }\r
-\r
- residueHash.put("maxResidue", maxResidue);\r
- residueHash.put("size", new Integer(sequences.size()));\r
- residueHash.put("nongap", new Integer(nongap));\r
- result.addElement(residueHash);\r
- }\r
-\r
- return result;\r
- }\r
-}\r
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
+ * Copyright (C) 2011 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ *
+ * 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/>.
+ */
+package jalview.analysis;
+
+import java.util.*;
+
+import jalview.datamodel.*;
+
+/**
+ * Takes in a vector or array of sequences and column start and column end and
+ * returns a new Hashtable[] of size maxSeqLength, if Hashtable not supplied.
+ * This class is used extensively in calculating alignment colourschemes that
+ * depend on the amount of conservation in each alignment column.
+ *
+ * @author $author$
+ * @version $Revision$
+ */
+public class AAFrequency
+{
+ // No need to store 1000s of strings which are not
+ // visible to the user.
+ public static final String MAXCOUNT = "C";
+
+ public static final String MAXRESIDUE = "R";
+
+ public static final String PID_GAPS = "G";
+
+ public static final String PID_NOGAPS = "N";
+
+ public static final String PROFILE = "P";
+
+ public static final Hashtable[] calculate(Vector sequences, int start,
+ int end)
+ {
+ return calculate(sequences, start, end, false);
+ }
+
+ public static final Hashtable[] calculate(Vector sequences, int start,
+ int end, boolean profile)
+ {
+ SequenceI[] seqs = new SequenceI[sequences.size()];
+ int width = 0;
+ for (int i = 0; i < sequences.size(); i++)
+ {
+ seqs[i] = (SequenceI) sequences.elementAt(i);
+ if (seqs[i].getLength() > width)
+ {
+ width = seqs[i].getLength();
+ }
+ }
+
+ Hashtable[] reply = new Hashtable[width];
+
+ if (end >= width)
+ {
+ end = width;
+ }
+
+ calculate(seqs, start, end, reply, profile);
+
+ return reply;
+ }
+
+ public static final void calculate(SequenceI[] sequences, int start,
+ int end, Hashtable[] result)
+ {
+ calculate(sequences, start, end, result, false);
+ }
+
+ public static final void calculate(SequenceI[] sequences, int start,
+ int end, Hashtable[] result, boolean profile)
+ {
+ Hashtable residueHash;
+ int maxCount, nongap, i, j, v, jSize = sequences.length;
+ String maxResidue;
+ char c;
+ float percentage;
+
+ int[] values = new int[255];
+
+ char[] seq;
+
+ for (i = start; i < end; i++)
+ {
+ residueHash = new Hashtable();
+ maxCount = 0;
+ maxResidue = "";
+ nongap = 0;
+ values = new int[255];
+
+ for (j = 0; j < jSize; j++)
+ {
+ if (sequences[j]==null)
+ {
+ System.err.println("WARNING: Consensus skipping null sequence - possible race condition.");
+ continue;
+ }
+ seq = sequences[j].getSequence();
+ if (seq.length > i)
+ {
+ c = seq[i];
+
+ if (c == '.' || c == ' ')
+ {
+ c = '-';
+ }
+
+ if (c == '-')
+ {
+ values['-']++;
+ continue;
+ }
+ else if ('a' <= c && c <= 'z')
+ {
+ c -= 32; // ('a' - 'A');
+ }
+
+ nongap++;
+ values[c]++;
+
+ }
+ else
+ {
+ values['-']++;
+ }
+ }
+
+ for (v = 'A'; v < 'Z'; v++)
+ {
+ if (values[v] < 2 || values[v] < maxCount)
+ {
+ continue;
+ }
+
+ if (values[v] > maxCount)
+ {
+ maxResidue = String.valueOf((char) v);
+ }
+ else if (values[v] == maxCount)
+ {
+ maxResidue += String.valueOf((char) v);
+ }
+ maxCount = values[v];
+ }
+
+ if (maxResidue.length() == 0)
+ {
+ maxResidue = "-";
+ }
+ if (profile)
+ {
+ residueHash.put(PROFILE, new int[][]
+ { values, new int[]
+ { jSize, nongap } });
+ }
+ residueHash.put(MAXCOUNT, new Integer(maxCount));
+ residueHash.put(MAXRESIDUE, maxResidue);
+
+ percentage = ((float) maxCount * 100) / (float) jSize;
+ residueHash.put(PID_GAPS, new Float(percentage));
+
+ percentage = ((float) maxCount * 100) / (float) nongap;
+ residueHash.put(PID_NOGAPS, new Float(percentage));
+ result[i] = residueHash;
+ }
+ }
+
+ /**
+ * Compute all or part of the annotation row from the given consensus
+ * hashtable
+ *
+ * @param consensus
+ * - pre-allocated annotation row
+ * @param hconsensus
+ * @param iStart
+ * @param width
+ * @param ignoreGapsInConsensusCalculation
+ * @param includeAllConsSymbols
+ */
+ public static void completeConsensus(AlignmentAnnotation consensus,
+ Hashtable[] hconsensus, int iStart, int width,
+ boolean ignoreGapsInConsensusCalculation,
+ boolean includeAllConsSymbols)
+ {
+ completeConsensus(consensus, hconsensus, iStart, width,
+ ignoreGapsInConsensusCalculation, includeAllConsSymbols, null); // new
+ // char[]
+ // { 'A', 'C', 'G', 'T', 'U' });
+ }
+
+ public static void completeConsensus(AlignmentAnnotation consensus,
+ Hashtable[] hconsensus, int iStart, int width,
+ boolean ignoreGapsInConsensusCalculation,
+ boolean includeAllConsSymbols, char[] alphabet)
+ {
+ float tval, value;
+ if (consensus == null || consensus.annotations == null
+ || consensus.annotations.length < width)
+ {
+ // called with a bad alignment annotation row - wait for it to be
+ // initialised properly
+ return;
+ }
+ for (int i = iStart; i < width; i++)
+ {
+ if (i >= hconsensus.length)
+ {
+ // happens if sequences calculated over were shorter than alignment
+ // width
+ consensus.annotations[i] = null;
+ continue;
+ }
+ value = 0;
+ if (ignoreGapsInConsensusCalculation)
+ {
+ value = ((Float) hconsensus[i].get(AAFrequency.PID_NOGAPS))
+ .floatValue();
+ }
+ else
+ {
+ value = ((Float) hconsensus[i].get(AAFrequency.PID_GAPS))
+ .floatValue();
+ }
+
+ String maxRes = hconsensus[i].get(AAFrequency.MAXRESIDUE).toString();
+ String mouseOver = hconsensus[i].get(AAFrequency.MAXRESIDUE) + " ";
+ if (maxRes.length() > 1)
+ {
+ mouseOver = "[" + maxRes + "] ";
+ maxRes = "+";
+ }
+ int[][] profile = (int[][]) hconsensus[i].get(AAFrequency.PROFILE);
+ if (profile != null && includeAllConsSymbols)
+ {
+ mouseOver = "";
+ if (alphabet != null)
+ {
+ for (int c = 0; c < alphabet.length; c++)
+ {
+ tval = ((float) profile[0][alphabet[c]])
+ * 100f
+ / (float) profile[1][ignoreGapsInConsensusCalculation ? 1
+ : 0];
+ mouseOver += ((c == 0) ? "" : "; ") + alphabet[c] + " "
+ + ((int) tval) + "%";
+ }
+ }
+ else
+ {
+ Object[] ca = new Object[profile[0].length];
+ float[] vl = new float[profile[0].length];
+ for (int c = 0; c < ca.length; c++)
+ {
+ ca[c] = new char[]
+ { (char) c };
+ vl[c] = (float) profile[0][c];
+ }
+ ;
+ jalview.util.QuickSort.sort(vl, ca);
+ for (int p = 0, c = ca.length - 1; profile[0][((char[]) ca[c])[0]] > 0; c--)
+ {
+ if (((char[]) ca[c])[0] != '-')
+ {
+ tval = ((float) profile[0][((char[]) ca[c])[0]])
+ * 100f
+ / (float) profile[1][ignoreGapsInConsensusCalculation ? 1
+ : 0];
+ mouseOver += ((p == 0) ? "" : "; ") + ((char[]) ca[c])[0]
+ + " " + ((int) tval) + "%";
+ p++;
+
+ }
+ }
+
+ }
+ }
+ else
+ {
+ mouseOver += ((int) value + "%");
+ }
+ consensus.annotations[i] = new Annotation(maxRes, mouseOver, ' ',
+ value);
+ }
+ }
+
+ /**
+ * get the sorted profile for the given position of the consensus
+ *
+ * @param hconsensus
+ * @return
+ */
+ public static int[] extractProfile(Hashtable hconsensus,
+ boolean ignoreGapsInConsensusCalculation)
+ {
+ int[] rtnval = new int[64];
+ int[][] profile = (int[][]) hconsensus.get(AAFrequency.PROFILE);
+ if (profile == null)
+ return null;
+ Object[] ca = new Object[profile[0].length];
+ float[] vl = new float[profile[0].length];
+ for (int c = 0; c < ca.length; c++)
+ {
+ ca[c] = new char[]
+ { (char) c };
+ vl[c] = (float) profile[0][c];
+ }
+ ;
+ jalview.util.QuickSort.sort(vl, ca);
+ rtnval[0] = 1;
+ for (int c = ca.length - 1; profile[0][((char[]) ca[c])[0]] > 0; c--)
+ {
+ if (((char[]) ca[c])[0] != '-')
+ {
+ rtnval[rtnval[0]++] = ((char[]) ca[c])[0];
+ rtnval[rtnval[0]++] = (int) (((float) profile[0][((char[]) ca[c])[0]]) * 100f / (float) profile[1][ignoreGapsInConsensusCalculation ? 1
+ : 0]);
+ }
+ }
+ return rtnval;
+ }
+}
git://source.jalview.org / jalview.git / blobdiff