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.Assert.assertFalse;
  24 import static org.testng.AssertJUnit.assertEquals;
  25 import static org.testng.AssertJUnit.assertNotNull;
  26 import static org.testng.AssertJUnit.assertNull;
  27 import static org.testng.AssertJUnit.assertTrue;
  28
  29 import jalview.datamodel.DBRefEntry;
  30 import jalview.datamodel.SequenceI;
  31 import jalview.gui.JvOptionPane;
  32 import jalview.util.DBRefUtils;
  33 import jalview.xml.binding.uniprot.DbReferenceType;
  34 import jalview.xml.binding.uniprot.Entry;
  35 import jalview.xml.binding.uniprot.FeatureType;
  36 import jalview.xml.binding.uniprot.LocationType;
  37 import jalview.xml.binding.uniprot.PositionType;
  38
  39 import java.io.ByteArrayInputStream;
  40 import java.io.InputStream;
  41 import java.io.UnsupportedEncodingException;
  42 import java.math.BigInteger;
  43 import java.util.List;
  44
  45 import org.testng.Assert;
  46 import org.testng.annotations.BeforeClass;
  47 import org.testng.annotations.Test;
  48
  49 public class UniprotTest
  50 {
  51
  52   @BeforeClass(alwaysRun = true)
  53   public void setUpJvOptionPane()
  54   {
  55     JvOptionPane.setInteractiveMode(false);
  56     JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
  57   }
  58
  59   // adapted from http://www.uniprot.org/uniprot/A9CKP4.xml
  60   private static final String UNIPROT_XML = "<?xml version='1.0' encoding='UTF-8'?>"
  61           + "<uniprot xmlns=\"http://uniprot.org/uniprot\">"
  62           + "<entry dataset=\"TrEMBL\" created=\"2008-01-15\" modified=\"2015-03-04\" version=\"38\">"
  63           + "<accession>A9CKP4</accession>"
  64           + "<accession>A9CKP5</accession>"
  65           + "<name>A9CKP4_AGRT5</name>"
  66           + "<name>A9CKP4_AGRT6</name>"
  67           + "<protein><recommendedName><fullName>Mitogen-activated protein kinase 13</fullName></recommendedName></protein>"
  68           + "<dbReference type=\"PDB\" id=\"2FSQ\"><property type=\"method\" value=\"X-ray\"/><property type=\"resolution\" value=\"1.40\"/></dbReference>"
  69           + "<dbReference type=\"PDBsum\" id=\"2FSR\"/>"
  70           + "<dbReference type=\"EMBL\" id=\"AE007869\"><property type=\"protein sequence ID\" value=\"AAK85932.1\"/><property type=\"molecule type\" value=\"Genomic_DNA\"/></dbReference>"
  71           + "<feature type=\"signal peptide\" evidence=\"7\"><location><begin position=\"1\"/><end position=\"18\"/></location></feature>"
  72           + "<feature type=\"propeptide\" description=\"Activation peptide\" id=\"PRO_0000027399\" evidence=\"9 16 17 18\"><location><begin position=\"19\"/><end position=\"20\"/></location></feature>"
  73           + "<feature type=\"chain\" description=\"Granzyme B\" id=\"PRO_0000027400\"><location><begin position=\"21\"/><end position=\"247\"/></location></feature>"
  74           + "<feature type=\"sequence variant\"><original>M</original><variation>L</variation><location><position position=\"41\"/></location></feature>"
  75           + "<feature type=\"sequence variant\" description=\"Pathogenic\"><original>M</original><variation>L</variation><location><position position=\"41\"/></location></feature>"
  76           + "<feature type=\"sequence variant\" description=\"Pathogenic\"><original>M</original><location><position position=\"41\"/></location></feature>"
  77           + "<feature type=\"sequence variant\" description=\"Foo\"><variation>L</variation><variation>LMV</variation><original>M</original><location><position position=\"42\"/></location></feature>"
  78           + "<feature type=\"sequence variant\" description=\"Foo\"><variation>LL</variation><variation>LMV</variation><original>ML</original><location><begin position=\"42\"/><end position=\"43\"/></location></feature>"
  79           + "<feature type=\"sequence variant\" description=\"Foo Too\"><variation>LL</variation><variation>LMVK</variation><original>MLML</original><location><begin position=\"42\"/><end position=\"45\"/></location></feature>"
  80           + "<sequence length=\"10\" mass=\"27410\" checksum=\"8CB760AACF88FE6C\" modified=\"2008-01-15\" version=\"1\">MHAPL VSKDL</sequence></entry>"
  81           + "</uniprot>";
  82
  83   /**
  84    * Test the method that unmarshals XML to a Uniprot model
  85    *
  86    * @throws UnsupportedEncodingException
  87    */
  88   @Test(groups = { "Functional" })
  89   public void testGetUniprotEntries() throws UnsupportedEncodingException
  90   {
  91     Uniprot u = new Uniprot();
  92     InputStream is = new ByteArrayInputStream(UNIPROT_XML.getBytes());
  93     List<Entry> entries = u.getUniprotEntries(is);
  94     assertEquals(1, entries.size());
  95     Entry entry = entries.get(0);
  96     assertEquals(2, entry.getName().size());
  97     assertEquals("A9CKP4_AGRT5", entry.getName().get(0));
  98     assertEquals("A9CKP4_AGRT6", entry.getName().get(1));
  99     assertEquals(2, entry.getAccession().size());
 100     assertEquals("A9CKP4", entry.getAccession().get(0));
 101     assertEquals("A9CKP5", entry.getAccession().get(1));
 102
 103     assertEquals("MHAPL VSKDL", entry.getSequence().getValue());
 104
 105     assertEquals("Mitogen-activated protein kinase 13", entry.getProtein()
 106             .getRecommendedName().getFullName().getValue());
 107
 108     /*
 109      * Check sequence features
 110      */
 111     List<FeatureType> features = entry.getFeature();
 112     assertEquals(9, features.size());
 113     FeatureType sf = features.get(0);
 114     assertEquals("signal peptide", sf.getType());
 115     assertNull(sf.getDescription());
 116     assertNull(sf.getStatus());
 117     assertNull(sf.getLocation().getPosition());
 118     assertEquals(1, sf.getLocation().getBegin().getPosition().intValue());
 119     assertEquals(18, sf.getLocation().getEnd().getPosition().intValue());
 120     sf = features.get(1);
 121     assertEquals("propeptide", sf.getType());
 122     assertEquals("Activation peptide", sf.getDescription());
 123     assertNull(sf.getLocation().getPosition());
 124     assertEquals(19, sf.getLocation().getBegin().getPosition().intValue());
 125     assertEquals(20, sf.getLocation().getEnd().getPosition().intValue());
 126     sf = features.get(2);
 127     assertEquals("chain", sf.getType());
 128     assertEquals("Granzyme B", sf.getDescription());
 129     assertNull(sf.getLocation().getPosition());
 130     assertEquals(21, sf.getLocation().getBegin().getPosition().intValue());
 131     assertEquals(247, sf.getLocation().getEnd().getPosition().intValue());
 132
 133     sf = features.get(3);
 134     assertEquals("sequence variant", sf.getType());
 135     assertNull(sf.getDescription());
 136     assertEquals(41,
 137             sf.getLocation().getPosition().getPosition().intValue());
 138     assertNull(sf.getLocation().getBegin());
 139     assertNull(sf.getLocation().getEnd());
 140
 141     sf = features.get(4);
 142     assertEquals("sequence variant", sf.getType());
 143     assertEquals("Pathogenic", sf.getDescription());
 144     assertEquals(41,
 145             sf.getLocation().getPosition().getPosition().intValue());
 146     assertNull(sf.getLocation().getBegin());
 147     assertNull(sf.getLocation().getEnd());
 148
 149     sf = features.get(5);
 150     assertEquals("sequence variant", sf.getType());
 151     assertEquals("Pathogenic", sf.getDescription());
 152     assertEquals(41,
 153             sf.getLocation().getPosition().getPosition().intValue());
 154     assertNull(sf.getLocation().getBegin());
 155     assertNull(sf.getLocation().getEnd());
 156
 157     sf = features.get(6);
 158     assertEquals("sequence variant", sf.getType());
 159     assertEquals("Foo",
 160             sf.getDescription());
 161     assertEquals(42,
 162             sf.getLocation().getPosition().getPosition().intValue());
 163     assertNull(sf.getLocation().getBegin());
 164     assertNull(sf.getLocation().getEnd());
 165     Assert.assertEquals(Uniprot.getDescription(sf),
 166             "<html>p.Met42Leu" + "<br/>&nbsp;&nbsp;"
 167                     + "p.Met42LeuMetVal Foo</html>");
 168
 169     sf = features.get(7);
 170     assertNull(sf.getLocation().getPosition());
 171     assertEquals(42, sf.getLocation().getBegin().getPosition().intValue());
 172     assertEquals(43, sf.getLocation().getEnd().getPosition().intValue());
 173     Assert.assertEquals(Uniprot.getDescription(sf),
 174             "<html>p.MetLeu42LeuLeu" + "<br/>&nbsp;&nbsp;"
 175                     + "p.MetLeu42LeuMetVal Foo</html>");
 176
 177     sf = features.get(8);
 178     assertNull(sf.getLocation().getPosition());
 179     assertEquals(42, sf.getLocation().getBegin().getPosition().intValue());
 180     assertEquals(45, sf.getLocation().getEnd().getPosition().intValue());
 181     Assert.assertEquals(Uniprot.getDescription(sf),
 182             "<html>p.MLML42LeuLeu" + "<br/>&nbsp;&nbsp;"
 183                     + "p.MLML42LMVK Foo Too</html>");
 184
 185     /*
 186      * Check cross-references
 187      */
 188     List<DbReferenceType> xrefs = entry.getDbReference();
 189     assertEquals(3, xrefs.size());
 190
 191     DbReferenceType xref = xrefs.get(0);
 192     assertEquals("2FSQ", xref.getId());
 193     assertEquals("PDB", xref.getType());
 194     assertEquals("X-ray",
 195             Uniprot.getProperty(xref.getProperty(), "method"));
 196     assertEquals("1.40",
 197             Uniprot.getProperty(xref.getProperty(), "resolution"));
 198
 199     xref = xrefs.get(1);
 200     assertEquals("2FSR", xref.getId());
 201     assertEquals("PDBsum", xref.getType());
 202     assertTrue(xref.getProperty().isEmpty());
 203
 204     xref = xrefs.get(2);
 205     assertEquals("AE007869", xref.getId());
 206     assertEquals("EMBL", xref.getType());
 207     assertEquals("AAK85932.1",
 208             Uniprot.getProperty(xref.getProperty(), "protein sequence ID"));
 209     assertEquals("Genomic_DNA",
 210             Uniprot.getProperty(xref.getProperty(), "molecule type"));
 211   }
 212
 213   @Test(groups = { "Functional" })
 214   public void testGetUniprotSequence() throws UnsupportedEncodingException
 215   {
 216     InputStream is = new ByteArrayInputStream(UNIPROT_XML.getBytes());
 217     Entry entry = new Uniprot().getUniprotEntries(
 218             is).get(0);
 219     SequenceI seq = new Uniprot().uniprotEntryToSequence(entry);
 220     assertNotNull(seq);
 221     assertEquals(6, seq.getDBRefs().size()); // 2*Uniprot, PDB, PDBsum, 2*EMBL
 222     assertEquals(seq.getSequenceAsString(),
 223             seq.createDatasetSequence().getSequenceAsString());
 224     assertEquals(2,seq.getPrimaryDBRefs().size());
 225     List<DBRefEntry> res = DBRefUtils.searchRefs(seq.getPrimaryDBRefs(), "A9CKP4");
 226     assertEquals(1,res.size());
 227     assertTrue(res.get(0).isCanonical());
 228     assertFalse(res.get(1).isCanonical());
 229   }
 230
 231   /**
 232    * Test the method that formats the sequence id
 233    *
 234    * @throws UnsupportedEncodingException
 235    */
 236   @Test(groups = { "Functional" })
 237   public void testGetUniprotEntryId() throws UnsupportedEncodingException
 238   {
 239     InputStream is = new ByteArrayInputStream(UNIPROT_XML.getBytes());
 240     Entry entry = new Uniprot().getUniprotEntries(is).get(0);
 241
 242     /*
 243      * name formatted with Uniprot Entry name
 244      */
 245     String expectedName = "A9CKP4_AGRT5|A9CKP4_AGRT6";
 246     assertEquals(expectedName,
 247             Uniprot.getUniprotEntryId(entry));
 248   }
 249
 250   /**
 251    * Test the method that formats the sequence description
 252    *
 253    * @throws UnsupportedEncodingException
 254    */
 255   @Test(groups = { "Functional" })
 256   public void testGetUniprotEntryDescription()
 257           throws UnsupportedEncodingException
 258   {
 259     InputStream is = new ByteArrayInputStream(UNIPROT_XML.getBytes());
 260     Entry entry = new Uniprot().getUniprotEntries(is).get(0);
 261
 262     assertEquals("Mitogen-activated protein kinase 13",
 263             Uniprot.getUniprotEntryDescription(entry));
 264   }
 265
 266   @Test(groups = { "Functional" })
 267   public void testGetDescription()
 268   {
 269     FeatureType ft = new FeatureType();
 270     assertEquals("", Uniprot.getDescription(ft));
 271
 272     ft.setDescription("Hello");
 273     assertEquals("Hello", Uniprot.getDescription(ft));
 274
 275     ft.setLocation(new LocationType());
 276     ft.getLocation().setPosition(new PositionType());
 277     ft.getLocation().getPosition().setPosition(BigInteger.valueOf(23));
 278     ft.setOriginal("K");
 279     ft.getVariation().add("y");
 280     assertEquals("p.Lys23Tyr Hello", Uniprot.getDescription(ft));
 281
 282     // multiple variants generate an html description over more than one line
 283     ft.getVariation().add("W");
 284     assertEquals("<html>p.Lys23Tyr<br/>&nbsp;&nbsp;p.Lys23Trp Hello</html>",
 285             Uniprot.getDescription(ft));
 286
 287     /*
 288      * indel cases
 289      * up to 3 bases (original or variant) are shown using 3 letter code
 290      */
 291     ft.getVariation().clear();
 292     ft.getVariation().add("KWE");
 293     ft.setOriginal("KLS");
 294     assertEquals("p.LysLeuSer23LysTrpGlu Hello",
 295             Uniprot.getDescription(ft));
 296
 297     // adding a fourth original base switches to single letter code
 298     ft.setOriginal("KLST");
 299     assertEquals("p.KLST23LysTrpGlu Hello", Uniprot.getDescription(ft));
 300
 301     // adding a fourth variant switches to single letter code
 302     ft.getVariation().clear();
 303     ft.getVariation().add("KWES");
 304     assertEquals("p.KLST23KWES Hello", Uniprot.getDescription(ft));
 305
 306     ft.getVariation().clear();
 307     ft.getVariation().add("z"); // unknown variant - fails gracefully
 308     ft.setOriginal("K");
 309     assertEquals("p.Lys23z Hello", Uniprot.getDescription(ft));
 310
 311     ft.getVariation().clear(); // variant missing - is ignored
 312     assertEquals("Hello", Uniprot.getDescription(ft));
 313   }
 314 }