2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
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.
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.
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.
23 import static org.testng.Assert.assertEquals;
24 import static org.testng.Assert.assertTrue;
25 import static org.testng.AssertJUnit.assertNotNull;
26 import static org.testng.AssertJUnit.assertNull;
27 import static org.testng.AssertJUnit.assertSame;
28 import static org.testng.AssertJUnit.fail;
31 import java.io.IOException;
32 import java.net.MalformedURLException;
33 import java.util.Arrays;
34 import java.util.List;
37 import org.testng.annotations.BeforeClass;
38 import org.testng.annotations.Test;
40 import jalview.bin.Console;
41 import jalview.datamodel.DBRefEntry;
42 import jalview.datamodel.Mapping;
43 import jalview.datamodel.Sequence.DBModList;
44 import jalview.datamodel.SequenceFeature;
45 import jalview.datamodel.SequenceI;
46 import jalview.datamodel.features.SequenceFeatures;
47 import jalview.util.MapList;
49 public class EmblFlatFileTest
51 @BeforeClass(alwaysRun = true)
58 * A fairly tough test, using J03321 (circular DNA), which has 8 CDS features,
59 * one of them reverse strand
61 * @throws MalformedURLException
64 @Test(groups = "Functional")
65 public void testParse() throws MalformedURLException, IOException
67 File dataFile = new File("test/jalview/io/J03321.embl.txt");
68 FileParse fp = new FileParse(dataFile, DataSourceType.FILE);
69 EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
70 List<SequenceI> seqs = parser.getSeqs();
72 assertEquals(seqs.size(), 1);
73 SequenceI seq = seqs.get(0);
74 assertEquals(seq.getName(), "EmblTest|J03321");
75 assertEquals(seq.getLength(), 7502);
76 assertEquals(seq.getDescription(),
77 "Chlamydia trachomatis plasmid pCHL1, complete sequence");
80 * should be 9 CDS features (one is a 'join' of two exons)
82 Set<String> featureTypes = seq.getFeatures().getFeatureTypes();
83 assertEquals(featureTypes.size(), 1);
84 assertTrue(featureTypes.contains("CDS"));
87 * inspect some features (sorted just for convenience of test assertions)
89 List<SequenceFeature> features = seq.getFeatures()
90 .getAllFeatures("CDS");
91 SequenceFeatures.sortFeatures(features, true);
92 assertEquals(features.size(), 9);
94 SequenceFeature sf = features.get(0);
95 assertEquals(sf.getBegin(), 1);
96 assertEquals(sf.getEnd(), 437);
97 assertEquals(sf.getDescription(),
98 "Exon 2 for protein EMBLCDS:AAA91567.1");
99 assertEquals(sf.getFeatureGroup(), "EmblTest");
100 assertEquals(sf.getEnaLocation(), "join(7022..7502,1..437)");
101 assertEquals(sf.getPhase(), "0");
102 assertEquals(sf.getStrand(), 1);
103 assertEquals(sf.getValue("note"), "pGP7-D");
104 // this is the second exon of circular CDS!
105 assertEquals(sf.getValue("exon number"), 2);
106 assertEquals(sf.getValue("product"), "hypothetical protein");
107 assertEquals(sf.getValue("transl_table"), "11");
109 sf = features.get(1);
110 assertEquals(sf.getBegin(), 488);
111 assertEquals(sf.getEnd(), 1480);
112 assertEquals(sf.getDescription(),
113 "Exon 1 for protein EMBLCDS:AAA91568.1");
114 assertEquals(sf.getFeatureGroup(), "EmblTest");
115 assertEquals(sf.getEnaLocation(), "complement(488..1480)");
116 assertEquals(sf.getPhase(), "0");
117 assertEquals(sf.getStrand(), -1); // reverse strand!
118 assertEquals(sf.getValue("note"), "pGP8-D");
119 assertEquals(sf.getValue("exon number"), 1);
120 assertEquals(sf.getValue("product"), "hypothetical protein");
122 sf = features.get(7);
123 assertEquals(sf.getBegin(), 6045);
124 assertEquals(sf.getEnd(), 6788);
125 assertEquals(sf.getDescription(),
126 "Exon 1 for protein EMBLCDS:AAA91574.1");
127 assertEquals(sf.getFeatureGroup(), "EmblTest");
128 assertEquals(sf.getEnaLocation(), "6045..6788");
129 assertEquals(sf.getPhase(), "0");
130 assertEquals(sf.getStrand(), 1);
131 assertEquals(sf.getValue("note"), "pGP6-D (gtg start codon)");
132 assertEquals(sf.getValue("exon number"), 1);
133 assertEquals(sf.getValue("product"), "hypothetical protein");
136 * CDS at 7022-7502 is the first exon of the circular CDS
138 sf = features.get(8);
139 assertEquals(sf.getBegin(), 7022);
140 assertEquals(sf.getEnd(), 7502);
141 assertEquals(sf.getDescription(),
142 "Exon 1 for protein EMBLCDS:AAA91567.1");
143 assertEquals(sf.getFeatureGroup(), "EmblTest");
144 assertEquals(sf.getEnaLocation(), "join(7022..7502,1..437)");
145 assertEquals(sf.getPhase(), "0");
146 assertEquals(sf.getStrand(), 1);
147 assertEquals(sf.getValue("note"), "pGP7-D");
148 assertEquals(sf.getValue("exon number"), 1);
149 assertEquals(sf.getValue("product"), "hypothetical protein");
152 * Verify DBRefs, whether declared in the file or added by Jalview.
153 * There are 4 'direct' (DR) dbrefs, and numerous CDS /db_xref entries
154 * (some e.g. INTERPRO are duplicates). Jalview adds a dbref to 'self'.
155 * Sample a few here. Note DBRefEntry constructor capitalises source.
157 List<DBRefEntry> dbrefs = seq.getDBRefs();
158 assertEquals(dbrefs.size(), 32);
160 DBRefEntry selfRef = new DBRefEntry("EMBLTEST", "1", "J03321");
161 int[] range = new int[] { 1, seq.getLength() };
162 selfRef.setMap(new Mapping(null, range, range, 1, 1));
163 assertTrue(dbrefs.contains(selfRef));
165 // 1st DR line; note trailing period is removed
166 assertTrue(dbrefs.contains(new DBRefEntry("MD5", "0",
167 "d4c4942a634e3df4995fd5ac75c26a61")));
170 dbrefs.contains(new DBRefEntry("EUROPEPMC", "0", "PMC87941")));
171 // from the first CDS feature
172 assertTrue(dbrefs.contains(new DBRefEntry("GOA", "0", "P0CE19")));
173 // from the last CDS feature
175 dbrefs.contains(new DBRefEntry("INTERPRO", "0", "IPR005350")));
178 * verify mappings to, and sequences for, UNIPROT proteins
180 int uniprotCount = 0;
182 for (DBRefEntry dbref : dbrefs)
184 if ("UNIPROT".equals(dbref.getSource()))
187 Mapping mapping = dbref.getMap();
188 assertNotNull(mapping);
189 MapList map = mapping.getMap();
190 String mappedToName = mapping.getTo().getName();
191 if ("UNIPROT|P0CE16".equals(mappedToName))
193 assertEquals((ranges = map.getFromRanges()).size(), 1);
194 assertEquals(ranges.get(0)[0], 1579);
195 assertEquals(ranges.get(0)[1], 2931); // excludes stop 2934
196 assertEquals((ranges = map.getToRanges()).size(), 1);
197 assertEquals(ranges.get(0)[0], 1);
198 assertEquals(ranges.get(0)[1], 451);
199 // CDS /product carries over as protein product description
200 assertEquals(mapping.getTo().getDescription(),
201 "hypothetical protein");
203 else if ("UNIPROT|P0CE17".equals(mappedToName))
205 assertEquals((ranges = map.getFromRanges()).size(), 1);
206 assertEquals(ranges.get(0)[0], 2928);
207 assertEquals(ranges.get(0)[1], 3989); // excludes stop 3992
208 assertEquals((ranges = map.getToRanges()).size(), 1);
209 assertEquals(ranges.get(0)[0], 1);
210 assertEquals(ranges.get(0)[1], 354);
212 else if ("UNIPROT|P0CE18".equals(mappedToName))
214 assertEquals((ranges = map.getFromRanges()).size(), 1);
215 assertEquals(ranges.get(0)[0], 4054);
216 assertEquals(ranges.get(0)[1], 4845); // excludes stop 4848
217 assertEquals((ranges = map.getToRanges()).size(), 1);
218 assertEquals(ranges.get(0)[0], 1);
219 assertEquals(ranges.get(0)[1], 264);
221 else if ("UNIPROT|P0CE19".equals(mappedToName))
223 // join(7022..7502,1..437)
224 assertEquals((ranges = map.getFromRanges()).size(), 2);
225 assertEquals(ranges.get(0)[0], 7022);
226 assertEquals(ranges.get(0)[1], 7502);
227 assertEquals(ranges.get(1)[0], 1);
228 assertEquals(ranges.get(1)[1], 434); // excludes stop at 437
229 assertEquals((ranges = map.getToRanges()).size(), 1);
230 assertEquals(ranges.get(0)[0], 1);
231 assertEquals(ranges.get(0)[1], 305);
233 else if ("UNIPROT|P0CE20".equals(mappedToName))
235 // complement(488..1480)
236 assertEquals((ranges = map.getFromRanges()).size(), 1);
237 assertEquals(ranges.get(0)[0], 1480);
238 assertEquals(ranges.get(0)[1], 491); // // excludes stop at 488
239 assertEquals((ranges = map.getToRanges()).size(), 1);
240 assertEquals(ranges.get(0)[0], 1);
241 assertEquals(ranges.get(0)[1], 330);
243 else if (!"UNIPROT|P0CE23".equals(mappedToName)
244 && !"UNIPROT|P10559".equals(mappedToName)
245 && !"UNIPROT|P10560".equals(mappedToName))
247 fail("Unexpected UNIPROT dbref to " + mappedToName);
251 assertEquals(uniprotCount, 8);
255 * A fairly tough test, using J03321 (circular DNA), which has 8 CDS features,
256 * one of them reverse strand
258 * @throws MalformedURLException
259 * @throws IOException
261 @Test(groups = "Functional")
262 public void testParseToRNA() throws MalformedURLException, IOException
264 File dataFile = new File("test/jalview/io/J03321_rna.embl.txt");
265 FileParse fp = new FileParse(dataFile, DataSourceType.FILE);
266 EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
267 List<SequenceI> seqs = parser.getSeqs();
268 assertTrue(seqs.get(0).getSequenceAsString().indexOf("u") > -1);
271 @Test(groups = "Functional")
272 public void testParse_codonStartNot1()
274 // TODO verify CDS-to-protein mapping for CDS with /codon_start=2
275 // example: https://www.ebi.ac.uk/ena/browser/api/embl/EU498516
279 * Test for the case that the EMBL CDS has no UNIPROT xref. In this case
280 * Jalview should synthesize an xref to EMBLCDSPROTEIN in the hope this will
281 * allow Get Cross-References.
283 * @throws IOException
285 @Test(groups = "Functional")
286 public void testParse_noUniprotXref() throws IOException
288 // MN908947 cut down to 40BP, one CDS, length 5 peptide for test purposes
289 // plus an additional (invented) test case:
290 // - multi-line /product qualifier including escaped quotes
291 String data = "ID MN908947; SV 3; linear; genomic RNA; STD; VRL; 20 BP.\n"
292 + "DE Severe acute respiratory syndrome coronavirus 2 isolate Wuhan-Hu-1,\n"
294 + "FT /protein_id=\"QHD43415.1\"\n"
295 + "FT /product=\"orf1ab polyprotein\n"
296 + "FT \"\"foobar\"\" \"\n"
297 + "FT /translation=\"MRKLD\n"
298 + "SQ Sequence 7496 BP; 2450 A; 1290 C; 1434 G; 2322 T; 0 other;\n"
299 + " ggatGcgtaa gttagacgaa attttgtctt tgcgcacaga 40\n";
300 FileParse fp = new FileParse(data, DataSourceType.PASTE);
301 EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
302 List<SequenceI> seqs = parser.getSeqs();
303 assertEquals(seqs.size(), 1);
304 SequenceI seq = seqs.get(0);
305 DBModList<DBRefEntry> dbrefs = seq.getDBRefs();
308 * dna should have dbref to itself, and to inferred EMBLCDSPROTEIN:QHD43415.1
310 assertEquals(dbrefs.size(), 2);
313 DBRefEntry dbref = dbrefs.get(0);
314 assertEquals(dbref.getSource(), "EMBLTEST");
315 assertEquals(dbref.getAccessionId(), "MN908947");
316 Mapping mapping = dbref.getMap();
317 assertNull(mapping.getTo());
318 MapList map = mapping.getMap();
319 assertEquals(map.getFromLowest(), 1);
320 assertEquals(map.getFromHighest(), 40);
321 assertEquals(map.getToLowest(), 1);
322 assertEquals(map.getToHighest(), 40);
323 assertEquals(map.getFromRatio(), 1);
324 assertEquals(map.getToRatio(), 1);
326 // dbref to inferred EMBLCDSPROTEIN:
327 dbref = dbrefs.get(1);
328 assertEquals(dbref.getSource(), "EMBLCDSPROTEIN");
329 assertEquals(dbref.getAccessionId(), "QHD43415.1");
330 mapping = dbref.getMap();
331 SequenceI mapTo = mapping.getTo();
332 assertEquals(mapTo.getName(), "QHD43415.1");
333 // the /product qualifier transfers to protein product description
334 assertEquals(mapTo.getDescription(), "orf1ab polyprotein \"foobar\"");
335 assertEquals(mapTo.getSequenceAsString(), "MRKLD");
336 map = mapping.getMap();
337 assertEquals(map.getFromLowest(), 3);
338 assertEquals(map.getFromHighest(), 17);
339 assertEquals(map.getToLowest(), 1);
340 assertEquals(map.getToHighest(), 5);
341 assertEquals(map.getFromRatio(), 3);
342 assertEquals(map.getToRatio(), 1);
345 @Test(groups = "Functional")
346 public void testAdjustForProteinLength()
348 int[] exons = new int[] { 11, 15, 21, 25, 31, 38 }; // 18 bp
350 // exact length match:
351 assertSame(exons, EmblFlatFile.adjustForProteinLength(6, exons));
353 // patch from JAL-3725 in EmblXmlSource propagated to Flatfile
354 // match if we assume exons include stop codon not in protein:
355 int[] truncated = EmblFlatFile.adjustForProteinLength(5, exons);
356 assertEquals(Arrays.toString(truncated), "[11, 15, 21, 25, 31, 35]");
358 // truncate last exon by 6bp
359 truncated = EmblFlatFile.adjustForProteinLength(4, exons);
360 assertEquals(Arrays.toString(truncated), "[11, 15, 21, 25, 31, 32]");
362 // remove last exon and truncate preceding by 1bp (so 3bp in total)
363 truncated = EmblFlatFile.adjustForProteinLength(3, exons);
364 assertEquals(Arrays.toString(truncated), "[11, 15, 21, 24]");
366 // exact removal of exon case:
367 exons = new int[] { 11, 15, 21, 27, 33, 38 }; // 18 bp
368 truncated = EmblFlatFile.adjustForProteinLength(4, exons);
369 assertEquals(Arrays.toString(truncated), "[11, 15, 21, 27]");
371 // what if exons are too short for protein?
372 truncated = EmblFlatFile.adjustForProteinLength(7, exons);
373 assertSame(exons, truncated);
376 @Test(groups = "Functional")
377 public void testRemoveQuotes()
379 assertNull(EmblFlatFile.removeQuotes(null));
380 assertEquals(EmblFlatFile.removeQuotes("No quotes here"),
382 assertEquals(EmblFlatFile.removeQuotes("\"Enclosing quotes\""),
385 EmblFlatFile.removeQuotes("\"Escaped \"\"quotes\"\" example\""),
386 "Escaped \"quotes\" example");