X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Futil%2FSequenceIdParser.java;h=d75a6dd8e6e2237a02a551cd56698f5d8b24f9c4;hb=32b66090883b7ca47347fef19152d84bd02c0b9d;hp=09e208a15aec4f705375e54178a99b492284f262;hpb=978fa1fa2b3cad823dd117d8281bf50aab8f205f;p=jalview.git diff --git a/forester/java/src/org/forester/util/SequenceIdParser.java b/forester/java/src/org/forester/util/SequenceIdParser.java index 09e208a..d75a6dd 100644 --- a/forester/java/src/org/forester/util/SequenceIdParser.java +++ b/forester/java/src/org/forester/util/SequenceIdParser.java @@ -28,21 +28,105 @@ package org.forester.util; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +import org.forester.phylogeny.data.Identifier; + public final class SequenceIdParser { - // ref_XP_002434188_1_mites___ticks_ - // ref_NP_001121530_1_frogs___toads_ + // gb_ADF31344_1_segmented_worms_ // gb_AAA96518_1 // gb_EHB07727_1_rodents_ // dbj_BAF37827_1_turtles_ // emb_CAA73223_1_primates_ // lcl_91970_unknown_ + // mites|ref_XP_002434188_1 + // ref_XP_002434188_1_mites___ticks_ + // ref_NP_001121530_1_frogs___toads_ + + //The format for GenBank Accession numbers are: + //Nucleotide: 1 letter + 5 numerals OR 2 letters + 6 numerals + //Protein: 3 letters + 5 numerals + //http://www.ncbi.nlm.nih.gov/Sequin/acc.html + private final static Pattern GENBANK_NUCLEOTIDE_AC_PATTERN_1 = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d{5})(?:[^a-zA-Z0-9]|\\Z)" ); + private final static Pattern GENBANK_NUCLEOTIDE_AC_PATTERN_2 = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}\\d{6})(?:[^a-zA-Z0-9]|\\Z)" ); + private final static Pattern GENBANK_PROTEIN_AC_PATTERN = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{3}\\d{5})(?:[^a-zA-Z0-9]|\\Z)" ); + + // RefSeq accession numbers can be distinguished from GenBank accessions + // by their distinct prefix format of 2 characters followed by an + // underscore character ('_'). For example, a RefSeq protein accession is NP_015325. + private final static Pattern REFSEQ_PATTERN = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}_\\d{6,})(?:[^a-zA-Z0-9]|\\Z)" ); + + + + /** + * Returns null if no match. + * + */ + public final static Identifier parse( final String s ) { + String v = parseGenbankAccessor( s ); + if ( !ForesterUtil.isEmpty( v ) ) { + + return new Identifier( v, Identifier.NCBI ); + } + v = parseRefSeqAccessor( s ); + if ( !ForesterUtil.isEmpty( v ) ) { + return new Identifier( v, Identifier.REFSEQ ); + } + return null; + } + + /** + * Returns null if no match. + * + */ + public static String parseGenbankAccessor( final String query ) { + Matcher m = GENBANK_NUCLEOTIDE_AC_PATTERN_1.matcher( query ); + if ( m.lookingAt() ) { + return m.group( 1 ); + } + else { + m = GENBANK_NUCLEOTIDE_AC_PATTERN_2.matcher( query ); + if ( m.lookingAt() ) { + return m.group( 1 ); + } + else { + m = GENBANK_PROTEIN_AC_PATTERN.matcher( query ); + if ( m.lookingAt() ) { + return m.group( 1 ); + } + else { + return null; + } + } + } + } + + /** + * Returns null if no match. + * + */ + private final static String parseRefSeqAccessor( final String query ) { + Matcher m = REFSEQ_PATTERN.matcher( query ); + if ( m.lookingAt() ) { + return m.group( 1 ); + } + return null; + } private SequenceIdParser() { // Hiding the constructor. } + + + }