test/jalview/ws/dbsources/UniprotTest.java

   1 /*
   2  * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
   3  * Copyright (C) $$Year-Rel$$ The Jalview Authors
   4  *
   5  * This file is part of Jalview.
   6  *
   7  * Jalview is free software: you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License
   9  * as published by the Free Software Foundation, either version 3
  10  * of the License, or (at your option) any later version.
  11  *
  12  * Jalview is distributed in the hope that it will be useful, but
  13  * WITHOUT ANY WARRANTY; without even the implied warranty
  14  * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
  15  * PURPOSE.  See the GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with Jalview.  If not, see <http://www.gnu.org/licenses/>.
  19  * The Jalview Authors are detailed in the 'AUTHORS' file.
  20  */
  21 package jalview.ws.dbsources;
  22
  23 import static org.testng.AssertJUnit.assertEquals;
  24 import static org.testng.AssertJUnit.assertFalse;
  25 import static org.testng.AssertJUnit.assertNotNull;
  26 import static org.testng.AssertJUnit.assertNull;
  27
  28 import jalview.datamodel.PDBEntry;
  29 import jalview.datamodel.SequenceI;
  30 import jalview.datamodel.xdb.uniprot.UniprotEntry;
  31 import jalview.datamodel.xdb.uniprot.UniprotFeature;
  32 import jalview.gui.JvOptionPane;
  33
  34 import java.io.Reader;
  35 import java.io.StringReader;
  36 import java.util.Vector;
  37
  38 import org.testng.annotations.BeforeClass;
  39 import org.testng.annotations.Test;
  40
  41 public class UniprotTest
  42 {
  43
  44   @BeforeClass(alwaysRun = true)
  45   public void setUpJvOptionPane()
  46   {
  47     JvOptionPane.setInteractiveMode(false);
  48     JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
  49   }
  50
  51   // adapted from http://www.uniprot.org/uniprot/A9CKP4.xml
  52   private static final String UNIPROT_XML = "<?xml version='1.0' encoding='UTF-8'?>"
  53           + "<uniprot>"
  54           + "<entry dataset=\"TrEMBL\" created=\"2008-01-15\" modified=\"2015-03-04\" version=\"38\">"
  55           + "<accession>A9CKP4</accession>"
  56           + "<accession>A9CKP5</accession>"
  57           + "<name>A9CKP4_AGRT5</name>"
  58           + "<name>A9CKP4_AGRT6</name>"
  59           + "<protein><recommendedName><fullName>Mitogen-activated protein kinase 13</fullName><fullName>Henry</fullName></recommendedName></protein>"
  60           + "<dbReference type=\"PDB\" id=\"2FSQ\"><property type=\"method\" value=\"X-ray\"/><property type=\"resolution\" value=\"1.40\"/></dbReference>"
  61           + "<dbReference type=\"PDBsum\" id=\"2FSR\"/>"
  62           + "<dbReference type=\"EMBL\" id=\"AE007869\"><property type=\"protein sequence ID\" value=\"AAK85932.1\"/><property type=\"molecule type\" value=\"Genomic_DNA\"/></dbReference>"
  63           + "<feature type=\"signal peptide\" evidence=\"7\"><location><begin position=\"1\"/><end position=\"18\"/></location></feature>"
  64           + "<feature type=\"propeptide\" description=\"Activation peptide\" id=\"PRO_0000027399\" evidence=\"9 16 17 18\"><location><begin position=\"19\"/><end position=\"20\"/></location></feature>"
  65           + "<feature type=\"chain\" description=\"Granzyme B\" id=\"PRO_0000027400\"><location><begin position=\"21\"/><end position=\"247\"/></location></feature>"
  66           + "<feature type=\"sequence variant\"><original>M</original><variation>L</variation><location><position position=\"41\"/></location></feature>"
  67           + "<feature type=\"sequence variant\" description=\"Pathogenic\"><original>M</original><variation>L</variation><location><position position=\"41\"/></location></feature>"
  68           + "<feature type=\"sequence variant\" description=\"Pathogenic\"><original>M</original><location><position position=\"41\"/></location></feature>"
  69           + "<feature type=\"sequence variant\" description=\"Foo\"><variation>L</variation><variation>LMV</variation><original>M</original><location><position position=\"42\"/></location></feature>"
  70           + "<sequence length=\"10\" mass=\"27410\" checksum=\"8CB760AACF88FE6C\" modified=\"2008-01-15\" version=\"1\">MHAPL VSKDL</sequence></entry>"
  71           + "</uniprot>";
  72
  73   /**
  74    * Test the method that unmarshals XML to a Uniprot model
  75    */
  76   @Test(groups = { "Functional" })
  77   public void testGetUniprotEntries()
  78   {
  79     Uniprot u = new Uniprot();
  80     Reader reader = new StringReader(UNIPROT_XML);
  81     Vector<UniprotEntry> entries = u.getUniprotEntries(reader);
  82     assertEquals(1, entries.size());
  83     UniprotEntry entry = entries.get(0);
  84     assertEquals(2, entry.getName().size());
  85     assertEquals("A9CKP4_AGRT5", entry.getName().get(0));
  86     assertEquals("A9CKP4_AGRT6", entry.getName().get(1));
  87     assertEquals(2, entry.getAccession().size());
  88     assertEquals("A9CKP4", entry.getAccession().get(0));
  89     assertEquals("A9CKP5", entry.getAccession().get(1));
  90
  91     /*
  92      * UniprotSequence drops any space characters
  93      */
  94     assertEquals("MHAPLVSKDL", entry.getUniprotSequence().getContent());
  95
  96     assertEquals(2, entry.getProtein().getName().size());
  97     assertEquals("Mitogen-activated protein kinase 13", entry.getProtein()
  98             .getName().get(0));
  99     assertEquals("Henry", entry.getProtein().getName().get(1));
 100
 101     /*
 102      * Check sequence features
 103      */
 104     Vector<UniprotFeature> features = entry.getFeature();
 105     assertEquals(7, features.size());
 106     UniprotFeature sf = features.get(0);
 107     assertEquals("signal peptide", sf.getType());
 108     assertNull(sf.getDescription());
 109     assertNull(sf.getStatus());
 110     assertEquals(1, sf.getBegin());
 111     assertEquals(18, sf.getEnd());
 112     sf = features.get(1);
 113     assertEquals("propeptide", sf.getType());
 114     assertEquals("Activation peptide", sf.getDescription());
 115     assertEquals(19, sf.getPosition());
 116     assertEquals(19, sf.getBegin());
 117     assertEquals(20, sf.getEnd());
 118     sf = features.get(2);
 119     assertEquals("chain", sf.getType());
 120     assertEquals("Granzyme B", sf.getDescription());
 121     assertEquals(21, sf.getPosition());
 122     assertEquals(21, sf.getBegin());
 123     assertEquals(247, sf.getEnd());
 124
 125     sf = features.get(3);
 126     assertEquals("sequence variant", sf.getType());
 127     assertEquals("Variation: 'L' Original: 'M'", sf.getDescription());
 128     assertEquals(41, sf.getPosition());
 129     assertEquals(41, sf.getBegin());
 130     assertEquals(41, sf.getEnd());
 131
 132     sf = features.get(4);
 133     assertEquals("sequence variant", sf.getType());
 134     assertEquals("Pathogenic Variation: 'L' Original: 'M'",
 135             sf.getDescription());
 136     assertEquals(41, sf.getPosition());
 137     assertEquals(41, sf.getBegin());
 138     assertEquals(41, sf.getEnd());
 139
 140     sf = features.get(5);
 141     assertEquals("sequence variant", sf.getType());
 142     assertEquals("Pathogenic Original: 'M'", sf.getDescription());
 143     assertEquals(41, sf.getPosition());
 144     assertEquals(41, sf.getBegin());
 145     assertEquals(41, sf.getEnd());
 146
 147     sf = features.get(6);
 148     assertEquals("sequence variant", sf.getType());
 149     assertEquals("Foo Variation: 'L', Variation: 'LMV' Original: 'M'",
 150             sf.getDescription());
 151     assertEquals(42, sf.getPosition());
 152     assertEquals(42, sf.getBegin());
 153     assertEquals(42, sf.getEnd());
 154     /*
 155      * Check cross-references
 156      */
 157     Vector<PDBEntry> xrefs = entry.getDbReference();
 158     assertEquals(3, xrefs.size());
 159
 160     PDBEntry xref = xrefs.get(0);
 161     assertEquals("2FSQ", xref.getId());
 162     assertEquals("PDB", xref.getType());
 163     assertEquals("X-ray", xref.getProperty("method"));
 164     assertEquals("1.40", xref.getProperty("resolution"));
 165
 166     xref = xrefs.get(1);
 167     assertEquals("2FSR", xref.getId());
 168     assertEquals("PDBsum", xref.getType());
 169     assertFalse(xref.getProperties().hasMoreElements());
 170
 171     xref = xrefs.get(2);
 172     assertEquals("AE007869", xref.getId());
 173     assertEquals("EMBL", xref.getType());
 174     assertEquals("AAK85932.1", xref.getProperty("protein sequence ID"));
 175     assertEquals("Genomic_DNA", xref.getProperty("molecule type"));
 176   }
 177
 178   @Test(groups = { "Functional" })
 179   public void testGetUniprotSequence()
 180   {
 181     UniprotEntry entry = new Uniprot().getUniprotEntries(
 182             new StringReader(UNIPROT_XML)).get(0);
 183     SequenceI seq = new Uniprot().uniprotEntryToSequenceI(entry);
 184     assertNotNull(seq);
 185     assertEquals(6, seq.getDBRefs().length); // 2*Uniprot, PDB, PDBsum, 2*EMBL
 186
 187   }
 188
 189   /**
 190    * Test the method that formats the sequence id
 191    */
 192   @Test(groups = { "Functional" })
 193   public void testGetUniprotEntryId()
 194   {
 195     UniprotEntry entry = new Uniprot().getUniprotEntries(
 196             new StringReader(UNIPROT_XML)).get(0);
 197
 198     /*
 199      * name formatted with Uniprot Entry name
 200      */
 201     String expectedName = "A9CKP4_AGRT5|A9CKP4_AGRT6";
 202     assertEquals(expectedName,
 203             Uniprot.getUniprotEntryId(entry));
 204   }
 205
 206   /**
 207    * Test the method that formats the sequence description
 208    */
 209   @Test(groups = { "Functional" })
 210   public void testGetUniprotEntryDescription()
 211   {
 212     UniprotEntry entry = new Uniprot().getUniprotEntries(
 213             new StringReader(UNIPROT_XML)).get(0);
 214
 215     /*
 216      * recommended names concatenated with space separator
 217      */
 218     String expectedDescription = "Mitogen-activated protein kinase 13 Henry";
 219     assertEquals(expectedDescription,
 220             Uniprot.getUniprotEntryDescription(entry));
 221   }
 222 }