From 6117c7791be423249668dd14e17cfee32040bb25 Mon Sep 17 00:00:00 2001 From: "cmzmasek@gmail.com" Date: Thu, 15 May 2014 00:09:51 +0000 Subject: [PATCH] Extension of the UniProtKB accession number format --- forester/java/src/org/forester/test/Test.java | 43 +++++++++++++++---- .../org/forester/util/SequenceAccessionTools.java | 45 +++++++++----------- 2 files changed, 54 insertions(+), 34 deletions(-) diff --git a/forester/java/src/org/forester/test/Test.java b/forester/java/src/org/forester/test/Test.java index 5864f61..59150d5 100644 --- a/forester/java/src/org/forester/test/Test.java +++ b/forester/java/src/org/forester/test/Test.java @@ -11322,7 +11322,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "segmented worms|gb_ADF31344" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "ADF31344" ) || !id.getSource().equals( "ncbi" ) ) { @@ -11332,7 +11331,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "segmented worms gb_ADF31344 and more" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "ADF31344" ) || !id.getSource().equals( "ncbi" ) ) { @@ -11342,7 +11340,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "gb_AAA96518_1" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "AAA96518" ) || !id.getSource().equals( "ncbi" ) ) { @@ -11352,7 +11349,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "gb_EHB07727_1_rodents_" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "EHB07727" ) || !id.getSource().equals( "ncbi" ) ) { @@ -11362,7 +11358,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "dbj_BAF37827_1_turtles_" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "BAF37827" ) || !id.getSource().equals( "ncbi" ) ) { @@ -11372,7 +11367,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "emb_CAA73223_1_primates_" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "CAA73223" ) || !id.getSource().equals( "ncbi" ) ) { @@ -11382,7 +11376,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "mites|ref_XP_002434188_1" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "XP_002434188" ) || !id.getSource().equals( "refseq" ) ) { @@ -11392,7 +11385,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "mites_ref_XP_002434188_1_bla_XP_12345" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "XP_002434188" ) || !id.getSource().equals( "refseq" ) ) { @@ -11402,7 +11394,6 @@ public final class Test { } return false; } - // id = SequenceAccessionTools.parseAccessorFromString( "P4A123" ); if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) || !id.getValue().equals( "P4A123" ) || !id.getSource().equals( "uniprot" ) ) { @@ -11418,6 +11409,40 @@ public final class Test { System.out.println( "provider=" + id.getSource() ); return false; } + // + id = SequenceAccessionTools.parseAccessorFromString( "N3B004Z009" ); + if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) + || !id.getValue().equals( "N3B004Z009" ) || !id.getSource().equals( "uniprot" ) ) { + if ( id != null ) { + System.out.println( "value =" + id.getValue() ); + System.out.println( "provider=" + id.getSource() ); + } + return false; + } + id = SequenceAccessionTools.parseAccessorFromString( "A4CAA4ZBB9" ); + if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) + || !id.getValue().equals( "A4CAA4ZBB9" ) || !id.getSource().equals( "uniprot" ) ) { + if ( id != null ) { + System.out.println( "value =" + id.getValue() ); + System.out.println( "provider=" + id.getSource() ); + } + return false; + } + id = SequenceAccessionTools.parseAccessorFromString( "ecoli_A4CAA4ZBB9_rt" ); + if ( ( id == null ) || ForesterUtil.isEmpty( id.getValue() ) || ForesterUtil.isEmpty( id.getSource() ) + || !id.getValue().equals( "A4CAA4ZBB9" ) || !id.getSource().equals( "uniprot" ) ) { + if ( id != null ) { + System.out.println( "value =" + id.getValue() ); + System.out.println( "provider=" + id.getSource() ); + } + return false; + } + id = SequenceAccessionTools.parseAccessorFromString( "Q4CAA4ZBB9" ); + if ( id != null ) { + System.out.println( "value =" + id.getValue() ); + System.out.println( "provider=" + id.getSource() ); + return false; + } } catch ( final Exception e ) { e.printStackTrace( System.out ); diff --git a/forester/java/src/org/forester/util/SequenceAccessionTools.java b/forester/java/src/org/forester/util/SequenceAccessionTools.java index 5ab000e..3efcb2b 100644 --- a/forester/java/src/org/forester/util/SequenceAccessionTools.java +++ b/forester/java/src/org/forester/util/SequenceAccessionTools.java @@ -38,38 +38,33 @@ import org.forester.phylogeny.data.Sequence; public final class SequenceAccessionTools { - // 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 - public final static Pattern GENBANK_NUC_PATTERN_1 = Pattern - .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" ); - public final static Pattern GENBANK_NUC_PATTERN_2 = Pattern - .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}\\d{6}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" ); - public final static Pattern GENBANK_PROT_PATTERN = Pattern - .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{3}\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" ); - public final static Pattern GI_PATTERN = Pattern.compile( "(?:\\b|_)(?:GI|gi)[|_=:](\\d+)(?:\\b|_)" ); - public final static Pattern UNIPROT_KB_PATTERN_0 = Pattern - .compile( "(?:\\b|_)([A-Z][0-9][A-Z0-9]{3}[0-9])(?:\\b|_)" ); - public final static Pattern UNIPROT_KB_PATTERN_1 = Pattern - .compile( "(?:\\b|_)(?:sp|tr)[\\.|\\-_=/\\\\]([A-Z][0-9][A-Z0-9]{3}[0-9])(?:\\b|_)" ); - public final static Pattern UNIPROT_KB_PATTERN_2 = Pattern - .compile( "(?:\\b|_)(?:[A-Z0-9]{2,5}|(?:[A-Z][0-9][A-Z0-9]{3}[0-9]))_(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA)(?:\\b|_)" ); - public final static Pattern ENSEMBL_PATTERN = Pattern.compile( "(?:\\b|_)(ENS[A-Z]*[0-9]+)(?:\\b|_)" ); + public final static Pattern GENBANK_NUC_PATTERN_1 = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" ); + public final static Pattern GENBANK_NUC_PATTERN_2 = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}\\d{6}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" ); + public final static Pattern GENBANK_PROT_PATTERN = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{3}\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" ); + public final static Pattern GI_PATTERN = Pattern + .compile( "(?:\\b|_)(?:GI|gi)[|_=:](\\d+)(?:\\b|_)" ); + public final static String UNIPROT_KB_BASE_PATTERN_STR = "((?:[OPQ][0-9][A-Z0-9]{3}[0-9])|(?:[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}))"; + public final static Pattern UNIPROT_KB_PATTERN_0 = Pattern.compile( "(?:\\b|_)" + + UNIPROT_KB_BASE_PATTERN_STR + "(?:\\b|_)" ); + public final static Pattern UNIPROT_KB_PATTERN_1 = Pattern.compile( "(?:\\b|_)(?:sp|tr)[\\.|\\-_=/\\\\]" + + UNIPROT_KB_BASE_PATTERN_STR + "(?:\\b|_)" ); + public final static Pattern UNIPROT_KB_PATTERN_2 = Pattern + .compile( "(?:\\b|_)(?:[A-Z0-9]{2,5}|" + + UNIPROT_KB_BASE_PATTERN_STR + + ")_(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA)(?:\\b|_)" ); + public final static Pattern ENSEMBL_PATTERN = Pattern.compile( "(?:\\b|_)(ENS[A-Z]*[0-9]+)(?:\\b|_)" ); // 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)" ); + private final static Pattern REFSEQ_PATTERN = Pattern + .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}_\\d{6,})(?:[^a-zA-Z0-9]|\\Z)" ); private SequenceAccessionTools() { // Hiding the constructor. -- 1.7.10.2