X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FRna.java;h=7c077088af2c9ce76661c8e13dcf09c22069f9d9;hb=9c1dd670f293d8f33de55133397b4cd2d4baf38e;hp=ba18732a982dd8cad4e18aa9f828a83dddd55e8a;hpb=d5c5166fcfbdaec2297d68e1e47a869e3bf2049b;p=jalview.git
diff --git a/src/jalview/analysis/Rna.java b/src/jalview/analysis/Rna.java
index ba18732..7c07708 100644
--- a/src/jalview/analysis/Rna.java
+++ b/src/jalview/analysis/Rna.java
@@ -1,112 +1,233 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
- * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle
+ * 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.
- *
+ * 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 .
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
*/
-
/* Author: Lauren Michelle Lui
* Methods are based on RALEE methods http://personalpages.manchester.ac.uk/staff/sam.griffiths-jones/software/ralee/
+ * Additional Author: Jan Engelhart (2011) - Structure consensus and bug fixing
+ * Additional Author: Anne Menard (2012) - Pseudoknot support and secondary structure consensus
* */
package jalview.analysis;
+import jalview.analysis.SecStrConsensus.SimpleBP;
+import jalview.datamodel.SequenceFeature;
+import jalview.util.MessageManager;
+
import java.util.ArrayList;
import java.util.Hashtable;
+import java.util.List;
import java.util.Stack;
import java.util.Vector;
-import jalview.datamodel.SequenceFeature;
-
public class Rna
{
- static Hashtable pairHash = new Hashtable();
+
+ /**
+ * Answers true if the character is a valid open pair rna secondary structure
+ * symbol. Currently accepts A-Z, ([{<
+ *
+ * @param c
+ * @return
+ */
+ public static boolean isOpeningParenthesis(char c)
+ {
+ return ('A' <= c && c <= 'Z' || c == '(' || c == '[' || c == '{' || c == '<');
+ }
+
+ /**
+ * Answers true if the string is a valid open pair rna secondary structure
+ * symbol. Currently accepts A-Z, ([{<
+ *
+ * @param s
+ * @return
+ */
+ public static boolean isOpeningParenthesis(String s)
+ {
+ return s != null && s.length() == 1
+ && isOpeningParenthesis(s.charAt(0));
+ }
+
+ /**
+ * Answers true if the character is a valid close pair rna secondary structure
+ * symbol. Currently accepts a-z, )]}>
+ *
+ * @param c
+ * @return
+ */
+ public static boolean isClosingParenthesis(char c)
+ {
+ return ('a' <= c && c <= 'z' || c == ')' || c == ']' || c == '}' || c == '>');
+ }
+
+ /**
+ * Answers true if the string is a valid close pair rna secondary structure
+ * symbol. Currently accepts a-z, )]}>
+ *
+ * @param s
+ * @return
+ */
+ public static boolean isClosingParenthesis(String s)
+ {
+ return s != null && s.length() == 1
+ && isClosingParenthesis(s.charAt(0));
+ }
+
+ /**
+ * Returns the matching open pair symbol for the given closing symbol.
+ * Currently returns A-Z for a-z, or ([{< for )]}>, or the input symbol if it
+ * is not a valid closing symbol.
+ *
+ * @param c
+ * @return
+ */
+ public static char getMatchingOpeningParenthesis(char c)
+ {
+ if ('a' <= c && c <= 'z')
+ {
+ return (char) (c + 'A' - 'a');
+ }
+ switch (c)
+ {
+ case ')':
+ return '(';
+ case ']':
+ return '[';
+ case '}':
+ return '{';
+ case '>':
+ return '<';
+ default:
+ return c;
+ }
+ }
+
/**
* Based off of RALEE code ralee-get-base-pairs. Keeps track of open bracket
* positions in "stack" vector. When a close bracket is reached, pair this
- * with the last element in the "stack" vector and store in "pairs" vector.
- * Remove last element in the "stack" vector. Continue in this manner until
- * the whole string is processed.
+ * with the last matching element in the "stack" vector and store in "pairs"
+ * vector. Remove last element in the "stack" vector. Continue in this manner
+ * until the whole string is processed. Parse errors are thrown as exceptions
+ * wrapping the error location - position of the first unmatched closing
+ * bracket, or string length if there is an unmatched opening bracket.
*
* @param line
* Secondary structure line of an RNA Stockholm file
- * @return Array of SequenceFeature; type = RNA helix, begin is open base
- * pair, end is close base pair
+ * @return
+ * @throw {@link WUSSParseException}
*/
- public static SequenceFeature[] GetBasePairs(CharSequence line) throws WUSSParseException
+ public static Vector getSimpleBPs(CharSequence line)
+ throws WUSSParseException
{
- Stack stack = new Stack();
- Vector pairs = new Vector();
-
+ Hashtable> stacks = new Hashtable>();
+ Vector pairs = new Vector();
int i = 0;
while (i < line.length())
{
char base = line.charAt(i);
- if ((base == '<') || (base == '(') || (base == '{') || (base == '['))
+ if (isOpeningParenthesis(base))
{
- stack.push(i);
+ if (!stacks.containsKey(base))
+ {
+ stacks.put(base, new Stack());
+ }
+ stacks.get(base).push(i);
+
}
- else if ((base == '>') || (base == ')') || (base == '}')
- || (base == ']'))
+ else if (isClosingParenthesis(base))
{
+ char opening = getMatchingOpeningParenthesis(base);
+
+ if (!stacks.containsKey(opening))
+ {
+ throw new WUSSParseException(MessageManager.formatMessage(
+ "exception.mismatched_unseen_closing_char",
+ new String[] { String.valueOf(base) }), i);
+ }
+
+ Stack stack = stacks.get(opening);
if (stack.isEmpty())
{
// error whilst parsing i'th position. pass back
- throw new WUSSParseException("Mismatched closing bracket", i);
+ throw new WUSSParseException(MessageManager.formatMessage(
+ "exception.mismatched_closing_char",
+ new String[] { String.valueOf(base) }), i);
}
- Object temp = stack.pop();
- pairs.addElement(temp);
- pairs.addElement(i);
- }
+ int temp = stack.pop();
+ pairs.add(new SimpleBP(temp, i));
+ }
i++;
}
-
- int numpairs = pairs.size() / 2;
- SequenceFeature[] outPairs = new SequenceFeature[numpairs];
-
- // Convert pairs to array
- for (int p = 0; p < pairs.size(); p += 2)
+ for (char opening : stacks.keySet())
{
- int begin = Integer.parseInt(pairs.elementAt(p).toString());
- int end = Integer.parseInt(pairs.elementAt(p + 1).toString());
-
- outPairs[p / 2] = new SequenceFeature("RNA helix", "", "", begin,
- end, "");
- //pairHash.put(begin, end);
-
+ Stack stack = stacks.get(opening);
+ if (!stack.empty())
+ {
+ /*
+ * we have an unmatched opening bracket; report error as at
+ * i (length of input string)
+ */
+ throw new WUSSParseException(MessageManager.formatMessage(
+ "exception.mismatched_opening_char",
+ new String[] { String.valueOf(opening),
+ String.valueOf(stack.pop()) }), i);
+ }
}
+ return pairs;
+ }
+ public static SequenceFeature[] getBasePairs(List bps)
+ throws WUSSParseException
+ {
+ SequenceFeature[] outPairs = new SequenceFeature[bps.size()];
+ for (int p = 0; p < bps.size(); p++)
+ {
+ SimpleBP bp = bps.get(p);
+ outPairs[p] = new SequenceFeature("RNA helix", "", "", bp.getBP5(),
+ bp.getBP3(), "");
+ }
return outPairs;
}
-
-
+
+ public static List getModeleBP(CharSequence line)
+ throws WUSSParseException
+ {
+ Vector bps = getSimpleBPs(line);
+ return new ArrayList(bps);
+ }
+
/**
* Function to get the end position corresponding to a given start position
- * @param indice - start position of a base pair
+ *
+ * @param indice
+ * - start position of a base pair
* @return - end position of a base pair
*/
- /*makes no sense at the moment :(
- public int findEnd(int indice){
- //TODO: Probably extend this to find the start to a given end?
- //could be done by putting everything twice to the hash
- ArrayList pair = new ArrayList();
- return pairHash.get(indice);
- }*/
-
+ /*
+ * makes no sense at the moment :( public int findEnd(int indice){ //TODO:
+ * Probably extend this to find the start to a given end? //could be done by
+ * putting everything twice to the hash ArrayList pair = new
+ * ArrayList(); return pairHash.get(indice); }
+ */
/**
* Figures out which helix each position belongs to and stores the helix
@@ -128,8 +249,8 @@ public class Rna
int close; // Position of a close bracket under review
int j; // Counter
- Hashtable helices = new Hashtable(); // Keep track of helix number for each
- // position
+ Hashtable helices = new Hashtable();
+ // Keep track of helix number for each position
// Go through each base pair and assign positions a helix
for (i = 0; i < pairs.length; i++)
@@ -163,7 +284,7 @@ public class Rna
if ((popen < lastopen) && (popen > open))
{
if (helices.containsValue(popen)
- && (((Integer) helices.get(popen)) == helix))
+ && ((helices.get(popen)) == helix))
{
continue;
}
@@ -189,5 +310,186 @@ public class Rna
}
}
-}
+ /**
+ * Answers true if the character is a recognised symbol for RNA secondary
+ * structure. Currently accepts a-z, A-Z, ()[]{}<>.
+ *
+ * @param c
+ * @return
+ */
+ public static boolean isRnaSecondaryStructureSymbol(char c)
+ {
+ return isOpeningParenthesis(c) || isClosingParenthesis(c);
+ }
+
+ /**
+ * Answers true if the string is a recognised symbol for RNA secondary
+ * structure. Currently accepts a-z, A-Z, ()[]{}<>.
+ *
+ * @param s
+ * @return
+ */
+ public static boolean isRnaSecondaryStructureSymbol(String s)
+ {
+ return isOpeningParenthesis(s) || isClosingParenthesis(s);
+ }
+
+ /**
+ * Translates a string to RNA secondary structure representation. Returns the
+ * string with any non-SS characters changed to spaces. Accepted characters
+ * are a-z, A-Z, and (){}[]<> brackets.
+ *
+ * @param ssString
+ * @return
+ */
+ public static String getRNASecStrucState(String ssString)
+ {
+ if (ssString == null)
+ {
+ return null;
+ }
+ StringBuilder result = new StringBuilder(ssString.length());
+ for (int i = 0; i < ssString.length(); i++)
+ {
+ char c = ssString.charAt(i);
+ result.append(isRnaSecondaryStructureSymbol(c) ? c : " ");
+ }
+ return result.toString();
+ }
+
+ /**
+ * Answers true if the base-pair is either a canonical (A-T/U, C-G) or a
+ * wobble (G-T/U) pair (either way round), else false
+ *
+ * @param first
+ * @param second
+ * @return
+ */
+ public static boolean isCanonicalOrWobblePair(char first, char second)
+ {
+ if (first > 'Z')
+ {
+ first -= 32;
+ }
+ if (second > 'Z')
+ {
+ second -= 32;
+ }
+
+ switch (first)
+ {
+ case 'A':
+ switch (second)
+ {
+ case 'T':
+ case 'U':
+ return true;
+ }
+ break;
+ case 'C':
+ switch (second)
+ {
+ case 'G':
+ return true;
+ }
+ break;
+ case 'T':
+ case 'U':
+ switch (second)
+ {
+ case 'A':
+ case 'G':
+ return true;
+ }
+ break;
+ case 'G':
+ switch (second)
+ {
+ case 'C':
+ case 'T':
+ case 'U':
+ return true;
+ }
+ break;
+ }
+ return false;
+ }
+
+ public static boolean isCanonicalPair(char first, char second)
+ {
+
+ if (first > 'Z')
+ {
+ first -= 32;
+ }
+ if (second > 'Z')
+ {
+ second -= 32;
+ }
+
+ switch (first)
+ {
+ case 'A':
+ switch (second)
+ {
+ case 'T':
+ case 'U':
+ return true;
+ }
+ break;
+ case 'G':
+ switch (second)
+ {
+ case 'C':
+ return true;
+ }
+ break;
+ case 'C':
+ switch (second)
+ {
+ case 'G':
+ return true;
+ }
+ break;
+ case 'T':
+ case 'U':
+ switch (second)
+ {
+ case 'A':
+ return true;
+ }
+ break;
+ }
+ return false;
+ }
+
+ /**
+ * Returns the matching close pair symbol for the given opening symbol.
+ * Currently returns a-z for A-Z, or )]}> for ([{<, or the input symbol if it
+ * is not a valid opening symbol.
+ *
+ * @param c
+ * @return
+ */
+ public static char getMatchingClosingParenthesis(char c)
+ {
+ if ('A' <= c && c <= 'Z')
+ {
+ return (char) (c + 'a' - 'A');
+ }
+ switch (c)
+ {
+ case '(':
+ return ')';
+ case '[':
+ return ']';
+ case '{':
+ return '}';
+ case '<':
+ return '>';
+ default:
+ return c;
+ }
+ }
+}