-/* \r
- * @(#)SequenceUtil.java 1.0 September 2009\r
- * \r
- * Copyright (c) 2009 Peter Troshin\r
- * \r
- * Jalview Web Services version: 2.0 \r
- * \r
- * This library is free software; you can redistribute it and/or modify it under the terms of the\r
- * Apache License version 2 as published by the Apache Software Foundation\r
- * \r
- * This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without\r
- * even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the Apache \r
- * License for more details.\r
- * \r
- * A copy of the license is in apache_license.txt. It is also available here:\r
- * see: http://www.apache.org/licenses/LICENSE-2.0.txt\r
- * \r
- * Any republication or derived work distributed in source code form\r
- * must include this copyright and license notice.\r
+/*\r
+ * @(#)SequenceUtil.java 1.0 September 2009 Copyright (c) 2009 Peter Troshin\r
+ * Jalview Web Services version: 2.0 This library is free software; you can\r
+ * redistribute it and/or modify it under the terms of the Apache License\r
+ * version 2 as published by the Apache Software Foundation This library is\r
+ * distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;\r
+ * without even the implied warranty of MERCHANTABILITY or FITNESS FOR A\r
+ * PARTICULAR PURPOSE. See the Apache License for more details. A copy of the\r
+ * license is in apache_license.txt. It is also available here: see:\r
+ * http://www.apache.org/licenses/LICENSE-2.0.txt Any republication or derived\r
+ * work distributed in source code form must include this copyright and license\r
+ * notice.\r
*/\r
\r
package compbio.data.sequence;\r
import java.io.OutputStreamWriter;\r
import java.util.ArrayList;\r
import java.util.List;\r
+import java.util.Scanner;\r
import java.util.logging.Level;\r
import java.util.regex.Matcher;\r
import java.util.regex.Pattern;\r
*/\r
public final class SequenceUtil {\r
\r
- /**\r
- * A whitespace character: [\t\n\x0B\f\r]\r
- */\r
- public static final Pattern WHITE_SPACE = Pattern.compile("\\s");\r
-\r
- /**\r
- * A digit\r
- */\r
- public static final Pattern DIGIT = Pattern.compile("\\d");\r
-\r
- /**\r
- * Non word\r
- */\r
- public static final Pattern NONWORD = Pattern.compile("\\W");\r
-\r
- /**\r
- * Valid Amino acids\r
- */\r
- public static final Pattern AA = Pattern.compile("[ARNDCQEGHILKMFPSTWYV]+",\r
- Pattern.CASE_INSENSITIVE);\r
-\r
- /**\r
- * inversion of AA pattern\r
- */\r
- public static final Pattern NON_AA = Pattern.compile(\r
- "[^ARNDCQEGHILKMFPSTWYV]+", Pattern.CASE_INSENSITIVE);\r
-\r
- /**\r
- * Same as AA pattern but with two additional letters - XU\r
- */\r
- public static final Pattern AMBIGUOUS_AA = Pattern.compile(\r
- "[ARNDCQEGHILKMFPSTWYVXU]+", Pattern.CASE_INSENSITIVE);\r
-\r
- /**\r
- * Nucleotides a, t, g, c, u\r
- */\r
- public static final Pattern NUCLEOTIDE = Pattern.compile("[AGTCU]+",\r
- Pattern.CASE_INSENSITIVE);\r
-\r
- /**\r
- * Ambiguous nucleotide\r
- */\r
- public static final Pattern AMBIGUOUS_NUCLEOTIDE = Pattern.compile(\r
- "[AGTCRYMKSWHBVDNU]+", Pattern.CASE_INSENSITIVE); // see IUPAC\r
- /**\r
- * Non nucleotide\r
- */\r
- public static final Pattern NON_NUCLEOTIDE = Pattern.compile("[^AGTCU]+",\r
- Pattern.CASE_INSENSITIVE);\r
-\r
- private SequenceUtil() {\r
- } // utility class, no instantiation\r
-\r
- /*\r
- * public static void write_PirSeq(OutputStream os, FastaSequence seq)\r
- * throws IOException { BufferedWriter pir_out = new BufferedWriter(new\r
- * OutputStreamWriter(os)); pir_out.write(">P1;" + seq.getId() +\r
- * SysPrefs.newlinechar); pir_out.write(seq.getSequence() +\r
- * SysPrefs.newlinechar); pir_out.close(); }\r
- * \r
- * public static void write_FastaSeq(OutputStream os, FastaSequence seq)\r
- * throws IOException { BufferedWriter fasta_out = new BufferedWriter( new\r
- * OutputStreamWriter(os)); fasta_out.write(">" + seq.getId() +\r
- * SysPrefs.newlinechar); fasta_out.write(seq.getSequence() +\r
- * SysPrefs.newlinechar); fasta_out.close(); }\r
- */\r
-\r
- /**\r
- * @return true is the sequence contains only letters a,c, t, g, u\r
- */\r
- public static boolean isNucleotideSequence(final FastaSequence s) {\r
- return SequenceUtil.isNonAmbNucleotideSequence(s.getSequence());\r
- }\r
-\r
- /**\r
- * Ambiguous DNA chars : AGTCRYMKSWHBVDN // differs from protein in only one\r
- * (!) - B char\r
- */\r
- public static boolean isNonAmbNucleotideSequence(String sequence) {\r
- sequence = SequenceUtil.cleanSequence(sequence);\r
- if (SequenceUtil.DIGIT.matcher(sequence).find()) {\r
- return false;\r
+ /**\r
+ * A whitespace character: [\t\n\x0B\f\r]\r
+ */\r
+ public static final Pattern WHITE_SPACE = Pattern.compile("\\s");\r
+\r
+ /**\r
+ * A digit\r
+ */\r
+ public static final Pattern DIGIT = Pattern.compile("\\d");\r
+\r
+ /**\r
+ * Non word\r
+ */\r
+ public static final Pattern NONWORD = Pattern.compile("\\W");\r
+\r
+ /**\r
+ * Valid Amino acids\r
+ */\r
+ public static final Pattern AA = Pattern.compile("[ARNDCQEGHILKMFPSTWYV]+",\r
+ Pattern.CASE_INSENSITIVE);\r
+\r
+ /**\r
+ * inversion of AA pattern\r
+ */\r
+ public static final Pattern NON_AA = Pattern.compile(\r
+ "[^ARNDCQEGHILKMFPSTWYV]+", Pattern.CASE_INSENSITIVE);\r
+\r
+ /**\r
+ * Same as AA pattern but with two additional letters - XU\r
+ */\r
+ public static final Pattern AMBIGUOUS_AA = Pattern.compile(\r
+ "[ARNDCQEGHILKMFPSTWYVXU]+", Pattern.CASE_INSENSITIVE);\r
+\r
+ /**\r
+ * Nucleotides a, t, g, c, u\r
+ */\r
+ public static final Pattern NUCLEOTIDE = Pattern.compile("[AGTCU]+",\r
+ Pattern.CASE_INSENSITIVE);\r
+\r
+ /**\r
+ * Ambiguous nucleotide\r
+ */\r
+ public static final Pattern AMBIGUOUS_NUCLEOTIDE = Pattern.compile(\r
+ "[AGTCRYMKSWHBVDNU]+", Pattern.CASE_INSENSITIVE); // see IUPAC\r
+ /**\r
+ * Non nucleotide\r
+ */\r
+ public static final Pattern NON_NUCLEOTIDE = Pattern.compile("[^AGTCU]+",\r
+ Pattern.CASE_INSENSITIVE);\r
+\r
+ private SequenceUtil() {\r
+ } // utility class, no instantiation\r
+\r
+ /*\r
+ * public static void write_PirSeq(OutputStream os, FastaSequence seq)\r
+ * throws IOException { BufferedWriter pir_out = new BufferedWriter(new\r
+ * OutputStreamWriter(os)); pir_out.write(">P1;" + seq.getId() +\r
+ * SysPrefs.newlinechar); pir_out.write(seq.getSequence() +\r
+ * SysPrefs.newlinechar); pir_out.close(); } public static void\r
+ * write_FastaSeq(OutputStream os, FastaSequence seq) throws IOException {\r
+ * BufferedWriter fasta_out = new BufferedWriter( new\r
+ * OutputStreamWriter(os)); fasta_out.write(">" + seq.getId() +\r
+ * SysPrefs.newlinechar); fasta_out.write(seq.getSequence() +\r
+ * SysPrefs.newlinechar); fasta_out.close(); }\r
+ */\r
+\r
+ /**\r
+ * @return true is the sequence contains only letters a,c, t, g, u\r
+ */\r
+ public static boolean isNucleotideSequence(final FastaSequence s) {\r
+ return SequenceUtil.isNonAmbNucleotideSequence(s.getSequence());\r
}\r
- if (SequenceUtil.NON_NUCLEOTIDE.matcher(sequence).find()) {\r
- return false;\r
- /*\r
- * System.out.format("I found the text starting at " +\r
- * "index %d and ending at index %d.%n", nonDNAmatcher .start(),\r
- * nonDNAmatcher.end());\r
- */\r
+\r
+ /**\r
+ * Ambiguous DNA chars : AGTCRYMKSWHBVDN // differs from protein in only one\r
+ * (!) - B char\r
+ */\r
+ public static boolean isNonAmbNucleotideSequence(String sequence) {\r
+ sequence = SequenceUtil.cleanSequence(sequence);\r
+ if (SequenceUtil.DIGIT.matcher(sequence).find()) {\r
+ return false;\r
+ }\r
+ if (SequenceUtil.NON_NUCLEOTIDE.matcher(sequence).find()) {\r
+ return false;\r
+ /*\r
+ * System.out.format("I found the text starting at " +\r
+ * "index %d and ending at index %d.%n", nonDNAmatcher .start(),\r
+ * nonDNAmatcher.end());\r
+ */\r
+ }\r
+ final Matcher DNAmatcher = SequenceUtil.NUCLEOTIDE.matcher(sequence);\r
+ return DNAmatcher.find();\r
}\r
- final Matcher DNAmatcher = SequenceUtil.NUCLEOTIDE.matcher(sequence);\r
- return DNAmatcher.find();\r
- }\r
-\r
- /**\r
- * Removes all whitespace chars in the sequence string\r
- * \r
- * @param sequence\r
- * @return cleaned up sequence\r
- */\r
- public static String cleanSequence(String sequence) {\r
- assert sequence != null;\r
- final Matcher m = SequenceUtil.WHITE_SPACE.matcher(sequence);\r
- sequence = m.replaceAll("").toUpperCase();\r
- return sequence;\r
- }\r
-\r
- /**\r
- * Removes all special characters and digits as well as whitespace chars\r
- * from the sequence\r
- * \r
- * @param sequence\r
- * @return cleaned up sequence\r
- */\r
- public static String deepCleanSequence(String sequence) {\r
- sequence = SequenceUtil.cleanSequence(sequence);\r
- sequence = SequenceUtil.DIGIT.matcher(sequence).replaceAll("");\r
- sequence = SequenceUtil.NONWORD.matcher(sequence).replaceAll("");\r
- final Pattern othernonSeqChars = Pattern.compile("[_-]+");\r
- sequence = othernonSeqChars.matcher(sequence).replaceAll("");\r
- return sequence;\r
- }\r
-\r
- /**\r
- * \r
- * @param sequence\r
- * @return true is the sequence is a protein sequence, false overwise\r
- */\r
- public static boolean isProteinSequence(String sequence) {\r
- sequence = SequenceUtil.cleanSequence(sequence);\r
- if (SequenceUtil.isNonAmbNucleotideSequence(sequence)) {\r
- return false;\r
+\r
+ /**\r
+ * Removes all whitespace chars in the sequence string\r
+ * \r
+ * @param sequence\r
+ * @return cleaned up sequence\r
+ */\r
+ public static String cleanSequence(String sequence) {\r
+ assert sequence != null;\r
+ final Matcher m = SequenceUtil.WHITE_SPACE.matcher(sequence);\r
+ sequence = m.replaceAll("").toUpperCase();\r
+ return sequence;\r
}\r
- if (SequenceUtil.DIGIT.matcher(sequence).find()) {\r
- return false;\r
+\r
+ /**\r
+ * Removes all special characters and digits as well as whitespace chars\r
+ * from the sequence\r
+ * \r
+ * @param sequence\r
+ * @return cleaned up sequence\r
+ */\r
+ public static String deepCleanSequence(String sequence) {\r
+ sequence = SequenceUtil.cleanSequence(sequence);\r
+ sequence = SequenceUtil.DIGIT.matcher(sequence).replaceAll("");\r
+ sequence = SequenceUtil.NONWORD.matcher(sequence).replaceAll("");\r
+ final Pattern othernonSeqChars = Pattern.compile("[_-]+");\r
+ sequence = othernonSeqChars.matcher(sequence).replaceAll("");\r
+ return sequence;\r
}\r
- if (SequenceUtil.NON_AA.matcher(sequence).find()) {\r
- return false;\r
+\r
+ /**\r
+ * @param sequence\r
+ * @return true is the sequence is a protein sequence, false overwise\r
+ */\r
+ public static boolean isProteinSequence(String sequence) {\r
+ sequence = SequenceUtil.cleanSequence(sequence);\r
+ if (SequenceUtil.isNonAmbNucleotideSequence(sequence)) {\r
+ return false;\r
+ }\r
+ if (SequenceUtil.DIGIT.matcher(sequence).find()) {\r
+ return false;\r
+ }\r
+ if (SequenceUtil.NON_AA.matcher(sequence).find()) {\r
+ return false;\r
+ }\r
+ final Matcher protmatcher = SequenceUtil.AA.matcher(sequence);\r
+ return protmatcher.find();\r
}\r
- final Matcher protmatcher = SequenceUtil.AA.matcher(sequence);\r
- return protmatcher.find();\r
- }\r
-\r
- /**\r
- * Check whether the sequence confirms to amboguous protein sequence\r
- * \r
- * @param sequence\r
- * @return return true only if the sequence if ambiguous protein sequence\r
- * Return false otherwise. e.g. if the sequence is non-ambiguous\r
- * protein or DNA\r
- */\r
- public static boolean isAmbiguosProtein(String sequence) {\r
- sequence = SequenceUtil.cleanSequence(sequence);\r
- if (SequenceUtil.isNonAmbNucleotideSequence(sequence)) {\r
- return false;\r
+\r
+ /**\r
+ * Check whether the sequence confirms to amboguous protein sequence\r
+ * \r
+ * @param sequence\r
+ * @return return true only if the sequence if ambiguous protein sequence\r
+ * Return false otherwise. e.g. if the sequence is non-ambiguous\r
+ * protein or DNA\r
+ */\r
+ public static boolean isAmbiguosProtein(String sequence) {\r
+ sequence = SequenceUtil.cleanSequence(sequence);\r
+ if (SequenceUtil.isNonAmbNucleotideSequence(sequence)) {\r
+ return false;\r
+ }\r
+ if (SequenceUtil.DIGIT.matcher(sequence).find()) {\r
+ return false;\r
+ }\r
+ if (SequenceUtil.NON_AA.matcher(sequence).find()) {\r
+ return false;\r
+ }\r
+ if (SequenceUtil.AA.matcher(sequence).find()) {\r
+ return false;\r
+ }\r
+ final Matcher amb_prot = SequenceUtil.AMBIGUOUS_AA.matcher(sequence);\r
+ return amb_prot.find();\r
}\r
- if (SequenceUtil.DIGIT.matcher(sequence).find()) {\r
- return false;\r
+\r
+ /**\r
+ * Writes list of FastaSequeces into the outstream formatting the sequence\r
+ * so that it contains width chars on each line\r
+ * \r
+ * @param outstream\r
+ * @param sequences\r
+ * @param width\r
+ * - the maximum number of characters to write in one line\r
+ * @throws IOException\r
+ */\r
+ public static void writeFasta(final OutputStream outstream,\r
+ final List<FastaSequence> sequences, final int width)\r
+ throws IOException {\r
+ writeFastaKeepTheStream(outstream, sequences, width);\r
+ outstream.close();\r
}\r
- if (SequenceUtil.NON_AA.matcher(sequence).find()) {\r
- return false;\r
+\r
+ public static void writeFastaKeepTheStream(final OutputStream outstream,\r
+ final List<FastaSequence> sequences, final int width)\r
+ throws IOException {\r
+ final OutputStreamWriter writer = new OutputStreamWriter(outstream);\r
+ final BufferedWriter fastawriter = new BufferedWriter(writer);\r
+ for (final FastaSequence fs : sequences) {\r
+ fastawriter.write(">" + fs.getId() + "\n");\r
+ fastawriter.write(fs.getFormatedSequence(width));\r
+ fastawriter.write("\n");\r
+ }\r
+ fastawriter.flush();\r
+ writer.flush();\r
+ }\r
+\r
+ /**\r
+ * Reads fasta sequences from inStream into the list of FastaSequence\r
+ * objects\r
+ * \r
+ * @param inStream\r
+ * from\r
+ * @return list of FastaSequence objects\r
+ * @throws IOException\r
+ */\r
+ public static List<FastaSequence> readFasta(final InputStream inStream)\r
+ throws IOException {\r
+ final List<FastaSequence> seqs = new ArrayList<FastaSequence>();\r
+\r
+ final BufferedReader infasta = new BufferedReader(\r
+ new InputStreamReader(inStream, "UTF8"), 16000);\r
+ final Pattern pattern = Pattern.compile("//s+");\r
+\r
+ String line;\r
+ String sname = "", seqstr = null;\r
+ do {\r
+ line = infasta.readLine();\r
+ if ((line == null) || line.startsWith(">")) {\r
+ if (seqstr != null) {\r
+ seqs.add(new FastaSequence(sname.substring(1), seqstr));\r
+ }\r
+ sname = line; // remove >\r
+ seqstr = "";\r
+ } else {\r
+ final String subseq = pattern.matcher(line).replaceAll("");\r
+ seqstr += subseq;\r
+ }\r
+ } while (line != null);\r
+\r
+ infasta.close();\r
+ return seqs;\r
}\r
- if (SequenceUtil.AA.matcher(sequence).find()) {\r
- return false;\r
+\r
+ /**\r
+ * Writes FastaSequence in the file, each sequence will take one line only\r
+ * \r
+ * @param os\r
+ * @param sequences\r
+ * @throws IOException\r
+ */\r
+ public static void writeFasta(final OutputStream os,\r
+ final List<FastaSequence> sequences) throws IOException {\r
+ final OutputStreamWriter outWriter = new OutputStreamWriter(os);\r
+ final BufferedWriter fasta_out = new BufferedWriter(outWriter);\r
+ for (final FastaSequence fs : sequences) {\r
+ fasta_out.write(fs.getOnelineFasta());\r
+ }\r
+ fasta_out.close();\r
+ outWriter.close();\r
+ }\r
+\r
+ public static List<AnnotatedSequence> readJRonn(final File result)\r
+ throws IOException, UnknownFileFormatException {\r
+ InputStream input = new FileInputStream(result);\r
+ List<AnnotatedSequence> sequences = readJRonn(input);\r
+ input.close();\r
+ return sequences;\r
}\r
- final Matcher amb_prot = SequenceUtil.AMBIGUOUS_AA.matcher(sequence);\r
- return amb_prot.find();\r
- }\r
-\r
- /**\r
- * Writes list of FastaSequeces into the outstream formatting the sequence\r
- * so that it contains width chars on each line\r
- * \r
- * @param outstream\r
- * @param sequences\r
- * @param width\r
- * - the maximum number of characters to write in one line\r
- * @throws IOException\r
- */\r
- public static void writeFasta(final OutputStream outstream,\r
- final List<FastaSequence> sequences, final int width)\r
- throws IOException {\r
- final OutputStreamWriter writer = new OutputStreamWriter(outstream);\r
- final BufferedWriter fastawriter = new BufferedWriter(writer);\r
- for (final FastaSequence fs : sequences) {\r
- fastawriter.write(fs.getFormatedSequence(width));\r
+\r
+ /**\r
+ * Reader for JRonn horizontal file format >Foobar M G D T T A G 0.48 0.42\r
+ * 0.42 0.48 0.52 0.53 0.54 All values are tab delimited\r
+ * \r
+ * @param inStream\r
+ * @return\r
+ * @throws IOException\r
+ * @throws UnknownFileFormatException\r
+ */\r
+ public static List<AnnotatedSequence> readJRonn(final InputStream inStream)\r
+ throws IOException, UnknownFileFormatException {\r
+ final List<AnnotatedSequence> seqs = new ArrayList<AnnotatedSequence>();\r
+\r
+ final BufferedReader infasta = new BufferedReader(\r
+ new InputStreamReader(inStream, "UTF8"), 16000);\r
+\r
+ String line;\r
+ String sname = "";\r
+ do {\r
+ line = infasta.readLine();\r
+ if (line == null || line.isEmpty()) {\r
+ // skip empty lines\r
+ continue;\r
+ }\r
+ if (line.startsWith(">")) {\r
+ // read name\r
+ sname = line.trim().substring(1);\r
+ // read sequence line\r
+ line = infasta.readLine();\r
+ final String sequence = line.replace("\t", "");\r
+ // read annotation line\r
+ line = infasta.readLine();\r
+ String[] annotValues = line.split("\t");\r
+ float[] annotation = convertToNumber(annotValues);\r
+ if (annotation.length != sequence.length()) {\r
+ throw new UnknownFileFormatException(\r
+ "File does not look like Jronn horizontally formatted output file!\n"\r
+ + JRONN_WRONG_FORMAT_MESSAGE);\r
+ }\r
+ seqs.add(new AnnotatedSequence(sname, sequence, annotation));\r
+ }\r
+ } while (line != null);\r
+\r
+ infasta.close();\r
+ return seqs;\r
}\r
- outstream.flush();\r
- fastawriter.close();\r
- writer.close();\r
- }\r
-\r
- /**\r
- * Reads fasta sequences from inStream into the list of FastaSequence\r
- * objects\r
- * \r
- * @param inStream\r
- * from\r
- * @return list of FastaSequence objects\r
- * @throws IOException\r
- */\r
- public static List<FastaSequence> readFasta(final InputStream inStream)\r
- throws IOException {\r
- final List<FastaSequence> seqs = new ArrayList<FastaSequence>();\r
-\r
- final BufferedReader infasta = new BufferedReader(\r
- new InputStreamReader(inStream, "UTF8"), 16000);\r
- final Pattern pattern = Pattern.compile("//s+");\r
-\r
- String line;\r
- String sname = "", seqstr = null;\r
- do {\r
- line = infasta.readLine();\r
- if ((line == null) || line.startsWith(">")) {\r
- if (seqstr != null) {\r
- seqs.add(new FastaSequence(sname.substring(1), seqstr));\r
+\r
+ private static float[] convertToNumber(String[] annotValues)\r
+ throws UnknownFileFormatException {\r
+ float[] annotation = new float[annotValues.length];\r
+ try {\r
+ for (int i = 0; i < annotation.length; i++) {\r
+ annotation[i] = Float.parseFloat(annotValues[i]);\r
+ }\r
+ } catch (NumberFormatException e) {\r
+ throw new UnknownFileFormatException(JRONN_WRONG_FORMAT_MESSAGE,\r
+ e.getCause());\r
}\r
- sname = line; // remove >\r
- seqstr = "";\r
- } else {\r
- final String subseq = pattern.matcher(line).replaceAll("");\r
- seqstr += subseq;\r
- }\r
- } while (line != null);\r
-\r
- infasta.close();\r
- return seqs;\r
- }\r
-\r
- /**\r
- * Writes FastaSequence in the file, each sequence will take one line only\r
- * \r
- * @param os\r
- * @param sequences\r
- * @throws IOException\r
- */\r
- public static void writeFasta(final OutputStream os,\r
- final List<FastaSequence> sequences) throws IOException {\r
- final OutputStreamWriter outWriter = new OutputStreamWriter(os);\r
- final BufferedWriter fasta_out = new BufferedWriter(outWriter);\r
- for (final FastaSequence fs : sequences) {\r
- fasta_out.write(fs.getOnelineFasta());\r
+ return annotation;\r
}\r
- fasta_out.close();\r
- outWriter.close();\r
- }\r
-\r
- public static List<AnnotatedSequence> readJRonn(final File result)\r
- throws IOException, UnknownFileFormatException {\r
- InputStream input = new FileInputStream(result);\r
- List<AnnotatedSequence> sequences = readJRonn(input);\r
- input.close();\r
- return sequences;\r
- }\r
-\r
- /**\r
- * Reader for JRonn horizontal file format\r
- * \r
- * >Foobar\r
- * \r
- * M G D T T A G\r
- * \r
- * 0.48 0.42 0.42 0.48 0.52 0.53 0.54\r
- * \r
- * All values are tab delimited\r
- * \r
- * @param inStream\r
- * @return\r
- * @throws IOException\r
- * @throws UnknownFileFormatException\r
- */\r
- public static List<AnnotatedSequence> readJRonn(final InputStream inStream)\r
- throws IOException, UnknownFileFormatException {\r
- final List<AnnotatedSequence> seqs = new ArrayList<AnnotatedSequence>();\r
-\r
- final BufferedReader infasta = new BufferedReader(\r
- new InputStreamReader(inStream, "UTF8"), 16000);\r
-\r
- String line;\r
- String sname = "";\r
- do {\r
- line = infasta.readLine();\r
- if (line == null || line.isEmpty()) {\r
- // skip empty lines\r
- continue;\r
- }\r
- if (line.startsWith(">")) {\r
- // read name\r
- sname = line.trim().substring(1);\r
- // read sequence line\r
- line = infasta.readLine();\r
- final String sequence = line.replace("\t", "");\r
- // read annotation line\r
- line = infasta.readLine();\r
- String[] annotValues = line.split("\t");\r
- float[] annotation = convertToNumber(annotValues);\r
- if (annotation.length != sequence.length()) {\r
- throw new UnknownFileFormatException(\r
- "File does not look like Jronn horizontally formatted output file!\n"\r
- + JRONN_WRONG_FORMAT_MESSAGE);\r
+\r
+ private static final String JRONN_WRONG_FORMAT_MESSAGE = "Jronn file must be in the following format:\n"\r
+ + ">sequence_name\n "\r
+ + "M V S\n"\r
+ + "0.43 0.22 0.65\n"\r
+ + "Where first line is the sequence name,\n"\r
+ + "second line is the tab delimited sequence,\n"\r
+ + "third line contains tab delimited disorder prediction values.\n"\r
+ + "No lines are allowed between these three. Additionally, the number of "\r
+ + "sequence residues must be equal to the number of the disorder values.";\r
+\r
+ /**\r
+ * Closes the Closable and logs the exception if any\r
+ * \r
+ * @param log\r
+ * @param stream\r
+ */\r
+ public final static void closeSilently(java.util.logging.Logger log,\r
+ Closeable stream) {\r
+ if (stream != null) {\r
+ try {\r
+ stream.close();\r
+ } catch (IOException e) {\r
+ log.log(Level.WARNING, e.getLocalizedMessage(), e.getCause());\r
+ }\r
}\r
- seqs.add(new AnnotatedSequence(sname, sequence, annotation));\r
- }\r
- } while (line != null);\r
-\r
- infasta.close();\r
- return seqs;\r
- }\r
-\r
- private static float[] convertToNumber(String[] annotValues)\r
- throws UnknownFileFormatException {\r
- float[] annotation = new float[annotValues.length];\r
- try {\r
- for (int i = 0; i < annotation.length; i++) {\r
- annotation[i] = Float.parseFloat(annotValues[i]);\r
- }\r
- } catch (NumberFormatException e) {\r
- throw new UnknownFileFormatException(JRONN_WRONG_FORMAT_MESSAGE, e\r
- .getCause());\r
}\r
- return annotation;\r
- }\r
-\r
- private static final String JRONN_WRONG_FORMAT_MESSAGE = "Jronn file must be in the following format:\n"\r
- + ">sequence_name\n "\r
- + "M V S\n"\r
- + "0.43 0.22 0.65\n"\r
- + "Where first line is the sequence name,\n"\r
- + "second line is the tab delimited sequence,\n"\r
- + "third line contains tab delimited disorder prediction values.\n"\r
- + "No lines are allowed between these three. Additionally, the number of "\r
- + "sequence residues must be equal to the number of the disorder values.";\r
-\r
- /**\r
- * Closes the Closable and logs the exception if any\r
- * \r
- * @param log\r
- * @param stream\r
- */\r
- public final static void closeSilently(java.util.logging.Logger log,\r
- Closeable stream) {\r
- if (stream != null) {\r
- try {\r
- stream.close();\r
- } catch (IOException e) {\r
- log.log(Level.WARNING, e.getLocalizedMessage(), e.getCause());\r
- }\r
+\r
+ /**\r
+ * \r
+ * TODO complete!\r
+ * \r
+ * # RESIDUE COILS REM465 HOTLOOPS M 0.86010 0.88512 0.37094 T 0.79983\r
+ * 0.85864 0.44331 .... # RESIDUE COILS REM465 HOTLOOPS M 0.86010 0.88512\r
+ * 0.37094\r
+ * \r
+ * @param input\r
+ * @return\r
+ * @throws IOException\r
+ * @throws UnknownFileFormatException\r
+ */\r
+ public static List<MultiAnnotatedSequence<DisemblResultAnnot>> readDisembl(\r
+ final InputStream input) throws IOException,\r
+ UnknownFileFormatException {\r
+ Scanner scan = new Scanner(input);\r
+ scan.useDelimiter("# RESIDUE COILS REM465 HOTLOOPS\n");\r
+ if (!scan.hasNext()) {\r
+ throw new UnknownFileFormatException(\r
+ "In Disembl score format each seqeunce score is expected to start from the line: "\r
+ + "'# RESIDUE COILS REM465 HOTLOOPS\\n'."\r
+ + " No such line was found!");\r
+ }\r
+\r
+ List<MultiAnnotatedSequence<DisemblResultAnnot>> results = new ArrayList<MultiAnnotatedSequence<DisemblResultAnnot>>();\r
+ int seqCounter = 0;\r
+ while (scan.hasNext()) {\r
+ seqCounter++;\r
+ String singleSeq = scan.next();\r
+ Scanner scansingle = new Scanner(singleSeq);\r
+ StringBuffer seqbuffer = new StringBuffer();\r
+ List<Float> coils = new ArrayList<Float>();\r
+ List<Float> rem = new ArrayList<Float>();\r
+ List<Float> hotloops = new ArrayList<Float>();\r
+\r
+ MultiAnnotatedSequence<DisemblResultAnnot> disemblRes = new MultiAnnotatedSequence<DisemblResultAnnot>(\r
+ DisemblResultAnnot.class);\r
+\r
+ while (scansingle.hasNextLine()) {\r
+ String valueLine = scansingle.nextLine();\r
+ Scanner values = new Scanner(valueLine);\r
+ seqbuffer.append(values.next());\r
+ coils.add(values.nextFloat());\r
+ rem.add(values.nextFloat());\r
+ hotloops.add(values.nextFloat());\r
+ values.close();\r
+ }\r
+ disemblRes.addAnnotation(DisemblResultAnnot.COILS, coils);\r
+ disemblRes.addAnnotation(DisemblResultAnnot.REM465, rem);\r
+ disemblRes.addAnnotation(DisemblResultAnnot.HOTLOOPS, hotloops);\r
+ // TODO\r
+ // disemblRes.sequence = seqbuffer.toString();\r
+ scansingle.close();\r
+ results.add(disemblRes);\r
+ }\r
+\r
+ input.close();\r
+ return results;\r
}\r
- }\r
-\r
- public static List<AnnotatedSequence> readDisembl(final File result)\r
- throws IOException, UnknownFileFormatException {\r
- InputStream input = new FileInputStream(result);\r
- List<AnnotatedSequence> sequences = readJRonn(input);\r
- input.close();\r
- return sequences;\r
- }\r
+\r
}\r