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 /* Author: Lauren Michelle Lui
22 * Methods are based on RALEE methods http://personalpages.manchester.ac.uk/staff/sam.griffiths-jones/software/ralee/
23 * Additional Author: Jan Engelhart (2011) - Structure consensus and bug fixing
24 * Additional Author: Anne Menard (2012) - Pseudoknot support and secondary structure consensus
27 package jalview.analysis;
29 import jalview.analysis.SecStrConsensus.SimpleBP;
30 import jalview.datamodel.SequenceFeature;
31 import jalview.util.MessageManager;
33 import java.util.ArrayList;
34 import java.util.Arrays;
35 import java.util.HashSet;
36 import java.util.Hashtable;
37 import java.util.Stack;
38 import java.util.Vector;
43 static Hashtable<Integer, Integer> pairHash = new Hashtable();
45 private static final Character[] openingPars =
46 { '(', '[', '{', '<', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J',
47 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',
50 private static final Character[] closingPars =
51 { ')', ']', '}', '>', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j',
52 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x',
55 private static HashSet<Character> openingParsSet = new HashSet<Character>(
56 Arrays.asList(openingPars));
58 private static HashSet<Character> closingParsSet = new HashSet<Character>(
59 Arrays.asList(closingPars));
61 private static Hashtable<Character, Character> closingToOpening = new Hashtable<Character, Character>();
65 // Initializing final data structure
66 for (int i = 0; i < openingPars.length; i++)
68 // System.out.println(closingPars[i] + "->" + openingPars[i]);
69 closingToOpening.put(closingPars[i], openingPars[i]);
73 private static boolean isOpeningParenthesis(char c)
75 return openingParsSet.contains(c);
78 private static boolean isClosingParenthesis(char c)
80 return closingParsSet.contains(c);
83 private static char matchingOpeningParenthesis(char closingParenthesis)
84 throws WUSSParseException
86 if (!isClosingParenthesis(closingParenthesis))
88 throw new WUSSParseException(MessageManager.formatMessage("exception.querying_matching_opening_parenthesis_for_non_closing_parenthesis", new String[]{new StringBuffer(closingParenthesis).toString()}), -1);
91 return closingToOpening.get(closingParenthesis);
95 * Based off of RALEE code ralee-get-base-pairs. Keeps track of open bracket
96 * positions in "stack" vector. When a close bracket is reached, pair this
97 * with the last element in the "stack" vector and store in "pairs" vector.
98 * Remove last element in the "stack" vector. Continue in this manner until
99 * the whole string is processed.
102 * Secondary structure line of an RNA Stockholm file
103 * @return Array of SequenceFeature; type = RNA helix, begin is open base
104 * pair, end is close base pair
106 public static Vector<SimpleBP> GetSimpleBPs(CharSequence line)
107 throws WUSSParseException
109 Hashtable<Character, Stack<Integer>> stacks = new Hashtable<Character, Stack<Integer>>();
110 Vector<SimpleBP> pairs = new Vector<SimpleBP>();
112 while (i < line.length())
114 char base = line.charAt(i);
116 if (isOpeningParenthesis(base))
118 if (!stacks.containsKey(base))
120 stacks.put(base, new Stack<Integer>());
122 stacks.get(base).push(i);
125 else if (isClosingParenthesis(base))
128 char opening = matchingOpeningParenthesis(base);
130 if (!stacks.containsKey(opening))
132 throw new WUSSParseException(MessageManager.formatMessage("exception.mismatched_unseen_closing_char", new String[]{new StringBuffer(base).toString()}), i);
135 Stack<Integer> stack = stacks.get(opening);
138 // error whilst parsing i'th position. pass back
139 throw new WUSSParseException(MessageManager.formatMessage("exception.mismatched_closing_char", new String[]{new StringBuffer(base).toString()}), i);
141 int temp = stack.pop();
143 pairs.add(new SimpleBP(temp, i));
147 for (char opening : stacks.keySet())
149 Stack<Integer> stack = stacks.get(opening);
152 throw new WUSSParseException(MessageManager.formatMessage("exception.mismatched_opening_char", new String[]{new StringBuffer(opening).toString(),Integer.valueOf(stack.pop()).toString()}), i);
158 public static SequenceFeature[] GetBasePairs(CharSequence line)
159 throws WUSSParseException
161 Vector<SimpleBP> bps = GetSimpleBPs(line);
162 SequenceFeature[] outPairs = new SequenceFeature[bps.size()];
163 for (int p = 0; p < bps.size(); p++)
165 SimpleBP bp = bps.elementAt(p);
166 outPairs[p] = new SequenceFeature("RNA helix", "", "", bp.getBP5(),
172 public static ArrayList<SimpleBP> GetModeleBP(CharSequence line)
173 throws WUSSParseException
175 Vector<SimpleBP> bps = GetSimpleBPs(line);
176 return new ArrayList<SimpleBP>(bps);
180 * Function to get the end position corresponding to a given start position
183 * - start position of a base pair
184 * @return - end position of a base pair
187 * makes no sense at the moment :( public int findEnd(int indice){ //TODO:
188 * Probably extend this to find the start to a given end? //could be done by
189 * putting everything twice to the hash ArrayList<Integer> pair = new
190 * ArrayList<Integer>(); return pairHash.get(indice); }
194 * Figures out which helix each position belongs to and stores the helix
195 * number in the 'featureGroup' member of a SequenceFeature Based off of RALEE
196 * code ralee-helix-map.
199 * Array of SequenceFeature (output from Rna.GetBasePairs)
201 public static void HelixMap(SequenceFeature[] pairs)
204 int helix = 0; // Number of helices/current helix
205 int lastopen = 0; // Position of last open bracket reviewed
206 int lastclose = 9999999; // Position of last close bracket reviewed
207 int i = pairs.length; // Number of pairs
209 int open; // Position of an open bracket under review
210 int close; // Position of a close bracket under review
213 Hashtable helices = new Hashtable(); // Keep track of helix number for each
216 // Go through each base pair and assign positions a helix
217 for (i = 0; i < pairs.length; i++)
220 open = pairs[i].getBegin();
221 close = pairs[i].getEnd();
223 // System.out.println("open " + open + " close " + close);
224 // System.out.println("lastclose " + lastclose + " lastopen " + lastopen);
226 // we're moving from right to left based on closing pair
228 * catch things like <<..>>..<<..>> |
230 if (open > lastclose)
236 * catch things like <<..<<..>>..<<..>>>> |
238 j = pairs.length - 1;
241 int popen = pairs[j].getBegin();
243 // System.out.println("j " + j + " popen " + popen + " lastopen "
244 // +lastopen + " open " + open);
245 if ((popen < lastopen) && (popen > open))
247 if (helices.containsValue(popen)
248 && (((Integer) helices.get(popen)) == helix))
262 // Put positions and helix information into the hashtable
263 helices.put(open, helix);
264 helices.put(close, helix);
266 // Record helix as featuregroup
267 pairs[i].setFeatureGroup(Integer.toString(helix));