forester/java/src/org/forester/ws/uniprot/UniProtTaxonomy.java

   1 // $Id:
   2 // forester -- software libraries and applications
   3 // for genomics and evolutionary biology research.
   4 //
   5 // Copyright (C) 2010 Christian M Zmasek
   6 // Copyright (C) 2010 Sanford-Burnham Medical Research Institute
   7 // All rights reserved
   8 //
   9 // This library is free software; you can redistribute it and/or
  10 // modify it under the terms of the GNU Lesser General Public
  11 // License as published by the Free Software Foundation; either
  12 // version 2.1 of the License, or (at your option) any later version.
  13 //
  14 // This library is distributed in the hope that it will be useful,
  15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
  16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  17 // Lesser General Public License for more details.
  18 //
  19 // You should have received a copy of the GNU Lesser General Public
  20 // License along with this library; if not, write to the Free Software
  21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
  22 //
  23 // Contact: phylosoft @ gmail . com
  24 // WWW: www.phylosoft.org/forester
  25
  26 package org.forester.ws.uniprot;
  27
  28 import java.util.ArrayList;
  29 import java.util.List;
  30
  31 import org.forester.util.ForesterUtil;
  32
  33 public final class UniProtTaxonomy {
  34
  35     private final String[]              _lineage;
  36     private final String                _code;
  37     private final String                _scientific_name;
  38     private final String                _common_name;
  39     private final String                _synonym;
  40     private final String                _rank;
  41     private final String                _id;
  42     public final static UniProtTaxonomy DROSOPHILA_GENUS         = new UniProtTaxonomy( new String[] { "Eukaryota",
  43             "Metazoa", "Arthropoda", "Hexapoda", "Insecta", "Pterygota", "Neoptera", "Endopterygota", "Diptera",
  44             "Brachycera", "Muscomorpha", "Ephydroidea", "Drosophilidae"                },
  45                                                                                         "",
  46                                                                                         "fruit flies",
  47                                                                                         "Drosophila",
  48                                                                                         "",
  49                                                                                         "genus",
  50                                                                                         "7215" );
  51     public final static UniProtTaxonomy XENOPUS_GENUS            = new UniProtTaxonomy( new String[] { "Eukaryota",
  52             "Metazoa", "Chordata", "Craniata", "Vertebrata", "Euteleostomi", "Amphibia", "Batrachia", "Anura",
  53             "Mesobatrachia", "Pipoidea", "Pipidae", "Xenopodinae" }, "", "", "Xenopus", "", "genus", "8353" );
  54     public final static UniProtTaxonomy CAPITELLA_TELATA_SPECIES = new UniProtTaxonomy( new String[] { "Eukaryota",
  55             "Metazoa", "Annelida", "Polychaeta", "Scolecida", "Capitellida", "Capitellidae", "Capitella" },
  56                                                                                         "",
  57                                                                                         "",
  58                                                                                         "Capitella teleta",
  59                                                                                         "Capitella sp. I",
  60                                                                                         "species",
  61                                                                                         "283909" );
  62
  63     public UniProtTaxonomy( final String line ) {
  64         final String[] items = line.split( "\t" );
  65         if ( items.length < 5 ) {
  66             throw new IllegalArgumentException( "cannot parse uniprot taxonomy from: " + line );
  67         }
  68         _id = items[ 0 ].trim();
  69         _code = items[ 1 ].trim();
  70         _scientific_name = items[ 2 ].trim();
  71         _common_name = items[ 3 ].trim();
  72         _synonym = items[ 4 ].trim();
  73         if ( items.length > 6 ) {
  74             _rank = items[ 7 ].trim();
  75         }
  76         else {
  77             _rank = "";
  78         }
  79         String[] lin = null;
  80         if ( items.length > 7 ) {
  81             lin = items[ 8 ].split( "; " );
  82         }
  83         if ( ( lin != null ) && ( lin.length > 0 ) ) {
  84             final List<String> temp = new ArrayList<String>();
  85             for( final String t : lin ) {
  86                 if ( !ForesterUtil.isEmpty( t ) ) {
  87                     temp.add( t.trim() );
  88                 }
  89             }
  90             _lineage = new String[ temp.size() ];
  91             for( int i = 0; i < temp.size(); ++i ) {
  92                 _lineage[ i ] = temp.get( i );
  93             }
  94         }
  95         else {
  96             _lineage = new String[ 0 ];
  97         }
  98     }
  99
 100     public UniProtTaxonomy( final String[] lineage,
 101                             final String code,
 102                             final String common_name,
 103                             final String scientific_name,
 104                             final String synonym,
 105                             final String rank,
 106                             final String id ) {
 107         _lineage = lineage;
 108         _code = code;
 109         _scientific_name = scientific_name;
 110         _common_name = common_name;
 111         _synonym = synonym;
 112         _rank = rank;
 113         _id = id;
 114     }
 115
 116     /**
 117      * Creates deep copy for all fields, except lineage.
 118      *
 119      * @return
 120      */
 121     public UniProtTaxonomy copy() {
 122         return new UniProtTaxonomy( getLineage(),
 123                                     getCode() != null ? new String( getCode() ) : null,
 124                                     getCommonName() != null ? new String( getCommonName() ) : null,
 125                                     getScientificName() != null ? new String( getScientificName() ) : null,
 126                                     getSynonym() != null ? new String( getSynonym() ) : null,
 127                                     getRank() != null ? new String( getRank() ) : null,
 128                                     getId() != null ? new String( getId() ) : null );
 129     }
 130
 131     public String getCode() {
 132         return _code;
 133     }
 134
 135     public String getCommonName() {
 136         return _common_name;
 137     }
 138
 139     public String getId() {
 140         return _id;
 141     }
 142
 143     public String[] getLineage() {
 144         return _lineage;
 145     }
 146
 147     public String getRank() {
 148         return _rank;
 149     }
 150
 151     public String getScientificName() {
 152         return _scientific_name;
 153     }
 154
 155     public String getSynonym() {
 156         return _synonym;
 157     }
 158 }