|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object compbio.data.sequence.SequenceUtil
public final class SequenceUtil
Utility class for operations on sequences
Field Summary | |
---|---|
static java.util.regex.Pattern |
AA
Valid Amino acids |
static java.util.regex.Pattern |
AMBIGUOUS_AA
Same as AA pattern but with two additional letters - XU |
static java.util.regex.Pattern |
AMBIGUOUS_NUCLEOTIDE
Ambiguous nucleotide |
static java.util.regex.Pattern |
DIGIT
A digit |
static java.util.regex.Pattern |
NON_AA
inversion of AA pattern |
static java.util.regex.Pattern |
NON_NUCLEOTIDE
Non nucleotide |
static java.util.regex.Pattern |
NONWORD
Non word |
static java.util.regex.Pattern |
NUCLEOTIDE
Nucleotides a, t, g, c, u |
static java.util.regex.Pattern |
WHITE_SPACE
A whitespace character: [\t\n\x0B\f\r] |
Method Summary | |
---|---|
static java.lang.String |
cleanSequence(java.lang.String sequence)
Removes all whitespace chars in the sequence string |
static java.lang.String |
deepCleanSequence(java.lang.String sequence)
Removes all special characters and digits as well as whitespace chars from the sequence |
static boolean |
isAmbiguosProtein(java.lang.String sequence)
Check whether the sequence confirms to amboguous protein sequence |
static boolean |
isNonAmbNucleotideSequence(java.lang.String sequence)
Ambiguous DNA chars : AGTCRYMKSWHBVDN // differs from protein in only one (!) - B char |
static boolean |
isNucleotideSequence(FastaSequence s)
|
static boolean |
isProteinSequence(java.lang.String sequence)
|
static java.util.List<FastaSequence> |
readFasta(java.io.InputStream inStream)
Reads fasta sequences from inStream into the list of FastaSequence objects |
static void |
writeFasta(java.io.OutputStream os,
java.util.List<FastaSequence> sequences)
Writes FastaSequence in the file, each sequence will take one line only |
static void |
writeFasta(java.io.OutputStream outstream,
java.util.List<FastaSequence> sequences,
int width)
Writes list of FastaSequeces into the outstream formatting the sequence so that it contains width chars on each line |
Methods inherited from class java.lang.Object |
---|
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final java.util.regex.Pattern WHITE_SPACE
public static final java.util.regex.Pattern DIGIT
public static final java.util.regex.Pattern NONWORD
public static final java.util.regex.Pattern AA
public static final java.util.regex.Pattern NON_AA
public static final java.util.regex.Pattern AMBIGUOUS_AA
public static final java.util.regex.Pattern NUCLEOTIDE
public static final java.util.regex.Pattern AMBIGUOUS_NUCLEOTIDE
public static final java.util.regex.Pattern NON_NUCLEOTIDE
Method Detail |
---|
public static boolean isNucleotideSequence(FastaSequence s)
public static boolean isNonAmbNucleotideSequence(java.lang.String sequence)
public static java.lang.String cleanSequence(java.lang.String sequence)
sequence
-
public static java.lang.String deepCleanSequence(java.lang.String sequence)
sequence
-
public static boolean isProteinSequence(java.lang.String sequence)
sequence
-
public static boolean isAmbiguosProtein(java.lang.String sequence)
sequence
-
public static void writeFasta(java.io.OutputStream outstream, java.util.List<FastaSequence> sequences, int width) throws java.io.IOException
outstream
- sequences
- width
- - the maximum number of characters to write in one line
java.io.IOException
public static java.util.List<FastaSequence> readFasta(java.io.InputStream inStream) throws java.io.IOException
inStream
- from
java.io.IOException
public static void writeFasta(java.io.OutputStream os, java.util.List<FastaSequence> sequences) throws java.io.IOException
os
- sequences
-
java.io.IOException
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |