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           + "<sequence length=\"10\" mass=\"27410\" checksum=\"8CB760AACF88FE6C\" modified=\"2008-01-15\" version=\"1\">MHAPL VSKDL</sequence></entry>"
  70           + "</uniprot>";
  71
  72   /**
  73    * Test the method that unmarshals XML to a Uniprot model
  74    */
  75   @Test(groups = { "Functional" })
  76   public void testGetUniprotEntries()
  77   {
  78     Uniprot u = new Uniprot();
  79     Reader reader = new StringReader(UNIPROT_XML);
  80     Vector<UniprotEntry> entries = u.getUniprotEntries(reader);
  81     assertEquals(1, entries.size());
  82     UniprotEntry entry = entries.get(0);
  83     assertEquals(2, entry.getName().size());
  84     assertEquals("A9CKP4_AGRT5", entry.getName().get(0));
  85     assertEquals("A9CKP4_AGRT6", entry.getName().get(1));
  86     assertEquals(2, entry.getAccession().size());
  87     assertEquals("A9CKP4", entry.getAccession().get(0));
  88     assertEquals("A9CKP5", entry.getAccession().get(1));
  89
  90     /*
  91      * UniprotSequence drops any space characters
  92      */
  93     assertEquals("MHAPLVSKDL", entry.getUniprotSequence().getContent());
  94
  95     assertEquals(2, entry.getProtein().getName().size());
  96     assertEquals("Mitogen-activated protein kinase 13", entry.getProtein()
  97             .getName().get(0));
  98     assertEquals("Henry", entry.getProtein().getName().get(1));
  99
 100     /*
 101      * Check sequence features
 102      */
 103     Vector<UniprotFeature> features = entry.getFeature();
 104     assertEquals(6, features.size());
 105     UniprotFeature sf = features.get(0);
 106     assertEquals("signal peptide", sf.getType());
 107     assertNull(sf.getDescription());
 108     assertNull(sf.getStatus());
 109     assertEquals(1, sf.getBegin());
 110     assertEquals(18, sf.getEnd());
 111     sf = features.get(1);
 112     assertEquals("propeptide", sf.getType());
 113     assertEquals("Activation peptide", sf.getDescription());
 114     assertEquals(19, sf.getPosition());
 115     assertEquals(19, sf.getBegin());
 116     assertEquals(20, sf.getEnd());
 117     sf = features.get(2);
 118     assertEquals("chain", sf.getType());
 119     assertEquals("Granzyme B", sf.getDescription());
 120     assertEquals(21, sf.getPosition());
 121     assertEquals(21, sf.getBegin());
 122     assertEquals(247, sf.getEnd());
 123
 124     sf = features.get(3);
 125     assertEquals("sequence variant", sf.getType());
 126     assertEquals("Variation: 'L' Original: 'M'", sf.getDescription());
 127     assertEquals(41, sf.getPosition());
 128     assertEquals(41, sf.getBegin());
 129     assertEquals(41, sf.getEnd());
 130
 131     sf = features.get(4);
 132     assertEquals("sequence variant", sf.getType());
 133     assertEquals("Pathogenic Variation: 'L' Original: 'M'",
 134             sf.getDescription());
 135     assertEquals(41, sf.getPosition());
 136     assertEquals(41, sf.getBegin());
 137     assertEquals(41, sf.getEnd());
 138
 139     sf = features.get(5);
 140     assertEquals("sequence variant", sf.getType());
 141     assertEquals("Pathogenic Original: 'M'", sf.getDescription());
 142     assertEquals(41, sf.getPosition());
 143     assertEquals(41, sf.getBegin());
 144     assertEquals(41, sf.getEnd());
 145     /*
 146      * Check cross-references
 147      */
 148     Vector<PDBEntry> xrefs = entry.getDbReference();
 149     assertEquals(3, xrefs.size());
 150
 151     PDBEntry xref = xrefs.get(0);
 152     assertEquals("2FSQ", xref.getId());
 153     assertEquals("PDB", xref.getType());
 154     assertEquals("X-ray", xref.getProperty("method"));
 155     assertEquals("1.40", xref.getProperty("resolution"));
 156
 157     xref = xrefs.get(1);
 158     assertEquals("2FSR", xref.getId());
 159     assertEquals("PDBsum", xref.getType());
 160     assertFalse(xref.getProperties().hasMoreElements());
 161
 162     xref = xrefs.get(2);
 163     assertEquals("AE007869", xref.getId());
 164     assertEquals("EMBL", xref.getType());
 165     assertEquals("AAK85932.1", xref.getProperty("protein sequence ID"));
 166     assertEquals("Genomic_DNA", xref.getProperty("molecule type"));
 167   }
 168
 169   @Test(groups = { "Functional" })
 170   public void testGetUniprotSequence()
 171   {
 172     UniprotEntry entry = new Uniprot().getUniprotEntries(
 173             new StringReader(UNIPROT_XML)).get(0);
 174     SequenceI seq = new Uniprot().uniprotEntryToSequenceI(entry);
 175     assertNotNull(seq);
 176     assertEquals(6, seq.getDBRefs().length); // 2*Uniprot, PDB, PDBsum, 2*EMBL
 177
 178   }
 179
 180   /**
 181    * Test the method that formats the sequence id
 182    */
 183   @Test(groups = { "Functional" })
 184   public void testGetUniprotEntryId()
 185   {
 186     UniprotEntry entry = new Uniprot().getUniprotEntries(
 187             new StringReader(UNIPROT_XML)).get(0);
 188
 189     /*
 190      * name formatted with Uniprot Entry name
 191      */
 192     String expectedName = "A9CKP4_AGRT5|A9CKP4_AGRT6";
 193     assertEquals(expectedName,
 194             Uniprot.getUniprotEntryId(entry));
 195   }
 196
 197   /**
 198    * Test the method that formats the sequence description
 199    */
 200   @Test(groups = { "Functional" })
 201   public void testGetUniprotEntryDescription()
 202   {
 203     UniprotEntry entry = new Uniprot().getUniprotEntries(
 204             new StringReader(UNIPROT_XML)).get(0);
 205
 206     /*
 207      * recommended names concatenated with space separator
 208      */
 209     String expectedDescription = "Mitogen-activated protein kinase 13 Henry";
 210     assertEquals(expectedDescription,
 211             Uniprot.getUniprotEntryDescription(entry));
 212   }
 213 }