2 // forester -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2010 Christian M. Zmasek
6 // Copyright (C) 2008-2010 Burnham Institute for Medical Research
8 // This library is free software; you can redistribute it and/or
9 // modify it under the terms of the GNU Lesser General Public
10 // License as published by the Free Software Foundation; either
11 // version 2.1 of the License, or (at your option) any later version.
13 // This library is distributed in the hope that it will be useful,
14 // but WITHOUT ANY WARRANTY; without even the implied warranty of
15 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 // Lesser General Public License for more details.
18 // You should have received a copy of the GNU Lesser General Public
19 // License along with this library; if not, write to the Free Software
20 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
22 // Contact: phylosoft @ gmail . com
23 // WWW: www.phylosoft.org/forester
25 package org.forester.archaeopteryx.webservices;
27 import java.util.ArrayList;
28 import java.util.List;
30 import org.forester.archaeopteryx.webservices.WebservicesManager.WsPhylogenyFormat;
31 import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
32 import org.forester.phylogeny.Phylogeny;
33 import org.forester.phylogeny.PhylogenyNode;
34 import org.forester.phylogeny.data.Accession;
35 import org.forester.phylogeny.data.Identifier;
36 import org.forester.phylogeny.data.Sequence;
37 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
38 import org.forester.phylogeny.iterators.PreorderTreeIterator;
39 import org.forester.util.ForesterUtil;
40 import org.forester.util.ForesterUtil.PhylogenyNodeField;
42 public final class WebserviceUtil {
44 public static final String TAX_CODE_TO_SCI_NAME = "tax_code_to_sci_name";
45 public static final String TREE_FAM_INST = "tree_fam";
46 public static final String PFAM_INST = "pfam";
47 public static final String TOL_WEBSERVER = "http://tolweb.org/onlinecontributors/app?service=external&page=xml/TreeStructureService&node_id="
48 + PhylogeniesWebserviceClient.QUERY_PLACEHOLDER;
49 public static final String TOL_NAME = "Tree of Life";
50 public static final String TREE_BASE_NAME = "TreeBASE";
51 public static final String TREE_FAM_NAME = "TreeFam";
52 public static final String PFAM_NAME = "Pfam";
53 public static final String PFAM_SERVER = "http://pfam.janelia.org";
55 public static List<PhylogeniesWebserviceClient> createDefaultClients() {
56 final List<PhylogeniesWebserviceClient> clients = new ArrayList<PhylogeniesWebserviceClient>();
57 clients.add( new BasicPhylogeniesWebserviceClient( TOL_NAME,
58 "Read Tree from Tree of Life...",
59 "Use ToL webservice to obtain a phylogeny",
60 "Please enter a Tree of Life node identifier\n(Examples: "
61 + "19386 for Cephalopoda, 2461 for Cnidaria, 2466 for Deuterostomia)",
62 WsPhylogenyFormat.TOL_XML_RESPONSE,
63 PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME,
64 WebserviceUtil.TOL_WEBSERVER,
68 clients.add( new BasicPhylogeniesWebserviceClient( TREE_BASE_NAME,
69 "Read Tree from TreeBASE...",
70 "Use TreeBASE to obtain a phylogeny",
71 "Please enter a TreeBASE tree identifier\n(Examples: 2654, 825, 4931, 2518, 2406, 4934)",
72 WsPhylogenyFormat.NEXUS,
73 PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME,
74 "http://purl.org/phylo/treebase/phylows/tree/TB2:Tr"
75 + PhylogeniesWebserviceClient.QUERY_PLACEHOLDER
78 "http://treebase.nescent.org",
80 clients.add( new BasicPhylogeniesWebserviceClient( PFAM_NAME,
81 "Read Gene Tree from Pfam...",
82 "Use Pfam to obtain a (full) gene tree",
83 "Please enter a Pfam (PF) accession number\n(Examples: 01849 for NAC, 00452 for Bcl-2, 00046 for Homeobox)",
84 WsPhylogenyFormat.PFAM,
86 PFAM_SERVER + "/family/tree/download?alnType=full&acc=PF"
87 + PhylogeniesWebserviceClient.QUERY_PLACEHOLDER,
91 clients.add( new BasicPhylogeniesWebserviceClient( TREE_FAM_NAME,
92 "Read Full Gene Tree from TreeFam...",
93 "Use TreeFam to obtain a (full) gene tree",
94 "Please enter a TreeFam (TF) accession number\n(Examples: 101004 for Cyclin D, 315938 for Hox, 105310 for Wnt)",
95 WsPhylogenyFormat.NHX,
97 "http://www.treefam.org/cgi-bin/getdata.pl?ac=TF"
98 + PhylogeniesWebserviceClient.QUERY_PLACEHOLDER
101 "http://www.treefam.org",
103 clients.add( new BasicPhylogeniesWebserviceClient( TREE_FAM_NAME,
104 "Read Clean Gene Tree from TreeFam...",
105 "Use TreeFam to obtain a (\"clean\") gene tree",
106 "Please enter a TreeFam (TF) accession number\n(Examples: 101004 for Cyclin D, 315938 for Hox, 105310 for Wnt)",
107 WsPhylogenyFormat.NHX,
109 "http://www.treefam.org/cgi-bin/getdata.pl?ac=TF"
110 + PhylogeniesWebserviceClient.QUERY_PLACEHOLDER
113 "http://www.treefam.org",
118 static void extractSpTremblAccFromNodeName( final Phylogeny phy, final String source ) {
119 final PreorderTreeIterator it = new PreorderTreeIterator( phy );
120 while ( it.hasNext() ) {
121 final PhylogenyNode n = it.next();
122 if ( !ForesterUtil.isEmpty( n.getName() ) ) {
123 final String name = n.getName();
124 final int i = name.lastIndexOf( "/" );
126 final String acc_str = name.substring( 0, i );
127 if ( !ForesterUtil.isEmpty( acc_str ) ) {
128 final Sequence seq = new Sequence();
129 final Accession acc = new Accession( acc_str, source );
130 seq.setAccession( acc );
131 n.getNodeData().setSequence( seq );
138 public static void processInstructions( final PhylogeniesWebserviceClient client, final Phylogeny phylogeny ) {
139 if ( client.getProcessingInstructions().equals( WebserviceUtil.TAX_CODE_TO_SCI_NAME ) ) {
140 WebserviceUtil.transferTaxonomyCodeToScientificName( phylogeny );
142 else if ( client.getProcessingInstructions().equals( WebserviceUtil.TREE_FAM_INST ) ) {
143 WebserviceUtil.transferInternalTaxonomyCodeToScientificName( phylogeny );
144 WebserviceUtil.transferExternalScientificNameToTaxonomyCode( phylogeny );
145 WebserviceUtil.transferSequenceNameToSequenceAccession( phylogeny, "ensembl" );
146 WebserviceUtil.setTaxonomyIdentifierType( phylogeny, "ncbi" );
148 else if ( client.getProcessingInstructions().equals( WebserviceUtil.PFAM_INST ) ) {
149 WebserviceUtil.extractSpTremblAccFromNodeName( phylogeny, "sptrembl" );
153 static void setTaxonomyIdentifierType( final Phylogeny phy, final String type ) {
154 final PhylogenyNodeIterator it = phy.iteratorPostorder();
155 while ( it.hasNext() ) {
156 final PhylogenyNode n = it.next();
157 if ( n.getNodeData().isHasTaxonomy() && ( n.getNodeData().getTaxonomy().getIdentifier() != null ) ) {
160 .setIdentifier( new Identifier( n.getNodeData().getTaxonomy().getIdentifier().getValue(), type ) );
165 static void transferExternalScientificNameToTaxonomyCode( final Phylogeny phy ) {
166 final PhylogenyNodeIterator it = phy.iteratorPostorder();
167 while ( it.hasNext() ) {
168 final PhylogenyNode n = it.next();
169 if ( n.isExternal() && n.getNodeData().isHasTaxonomy() ) {
170 final String name = n.getNodeData().getTaxonomy().getScientificName();
171 if ( !ForesterUtil.isEmpty( name ) && PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( name ).matches() ) {
172 n.getNodeData().getTaxonomy().setScientificName( "" );
173 n.getNodeData().getTaxonomy().setTaxonomyCode( name );
179 static void transferInternalTaxonomyCodeToScientificName( final Phylogeny phy ) {
180 final PhylogenyNodeIterator it = phy.iteratorPostorder();
181 while ( it.hasNext() ) {
182 final PhylogenyNode n = it.next();
183 if ( !n.isExternal() && n.getNodeData().isHasTaxonomy() ) {
184 final String name = n.getNodeData().getTaxonomy().getTaxonomyCode();
185 if ( !ForesterUtil.isEmpty( name ) ) {
186 n.getNodeData().getTaxonomy().setScientificName( name );
187 n.getNodeData().getTaxonomy().setTaxonomyCode( "" );
193 static void transferSequenceNameToSequenceAccession( final Phylogeny phy, final String source ) {
194 final PhylogenyNodeIterator it = phy.iteratorPostorder();
195 while ( it.hasNext() ) {
196 final PhylogenyNode n = it.next();
197 if ( n.getNodeData().isHasSequence() ) {
198 final String name = n.getNodeData().getSequence().getName();
199 if ( !ForesterUtil.isEmpty( name ) ) {
200 n.getNodeData().getSequence().setName( "" );
201 n.getNodeData().getSequence().setAccession( new Accession( name, source ) );
207 static void transferTaxonomyCodeToScientificName( final Phylogeny phy ) {
208 final PhylogenyNodeIterator it = phy.iteratorPostorder();
209 while ( it.hasNext() ) {
210 final PhylogenyNode n = it.next();
211 if ( n.getNodeData().isHasTaxonomy() ) {
212 final String name = n.getNodeData().getTaxonomy().getTaxonomyCode();
213 if ( !ForesterUtil.isEmpty( name ) ) {
214 n.getNodeData().getTaxonomy().setScientificName( name );
215 n.getNodeData().getTaxonomy().setTaxonomyCode( "" );