3 import static org.testng.Assert.assertEquals;
4 import static org.testng.Assert.assertTrue;
5 import static org.testng.AssertJUnit.assertNotNull;
6 import static org.testng.AssertJUnit.assertSame;
7 import static org.testng.AssertJUnit.fail;
8 import static org.testng.AssertJUnit.assertNull;
11 import java.io.IOException;
12 import java.net.MalformedURLException;
13 import java.util.Arrays;
14 import java.util.List;
17 import org.testng.annotations.Test;
19 import jalview.datamodel.DBRefEntry;
20 import jalview.datamodel.Mapping;
21 import jalview.datamodel.Sequence.DBModList;
22 import jalview.datamodel.SequenceFeature;
23 import jalview.datamodel.SequenceI;
24 import jalview.datamodel.features.SequenceFeatures;
25 import jalview.util.MapList;
27 public class EmblFlatFileTest
30 * A fairly tough test, using J03321 (circular DNA), which has 8 CDS features,
31 * one of them reverse strand
33 * @throws MalformedURLException
36 @Test(groups = "Functional")
37 public void testParse() throws MalformedURLException, IOException
39 File dataFile = new File("test/jalview/io/J03321.embl.txt");
40 FileParse fp = new FileParse(dataFile, DataSourceType.FILE);
41 EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
43 List<SequenceI> seqs = parser.getSeqs();
45 assertEquals(seqs.size(), 1);
46 SequenceI seq = seqs.get(0);
47 assertEquals(seq.getName(), "EmblTest|J03321");
48 assertEquals(seq.getLength(), 7502);
49 assertEquals(seq.getDescription(),
50 "Chlamydia trachomatis plasmid pCHL1, complete sequence");
53 * should be 9 CDS features (one is a 'join' of two exons)
55 Set<String> featureTypes = seq.getFeatures().getFeatureTypes();
56 assertEquals(featureTypes.size(), 1);
57 assertTrue(featureTypes.contains("CDS"));
60 * inspect some features (sorted just for convenience of test assertions)
62 List<SequenceFeature> features = seq.getFeatures()
63 .getAllFeatures("CDS");
64 SequenceFeatures.sortFeatures(features, true);
65 assertEquals(features.size(), 9);
67 SequenceFeature sf = features.get(0);
68 assertEquals(sf.getBegin(), 1);
69 assertEquals(sf.getEnd(), 437);
70 assertEquals(sf.getDescription(),
71 "Exon 2 for protein EMBLCDS:AAA91567.1");
72 assertEquals(sf.getFeatureGroup(), "EmblTest");
73 assertEquals(sf.getEnaLocation(), "join(7022..7502,1..437)");
74 assertEquals(sf.getPhase(), "0");
75 assertEquals(sf.getStrand(), 1);
76 assertEquals(sf.getValue("note"), "pGP7-D");
77 // this is the second exon of circular CDS!
78 assertEquals(sf.getValue("exon number"), 2);
79 assertEquals(sf.getValue("product"), "hypothetical protein");
80 assertEquals(sf.getValue("transl_table"), "11");
83 assertEquals(sf.getBegin(), 488);
84 assertEquals(sf.getEnd(), 1480);
85 assertEquals(sf.getDescription(),
86 "Exon 1 for protein EMBLCDS:AAA91568.1");
87 assertEquals(sf.getFeatureGroup(), "EmblTest");
88 assertEquals(sf.getEnaLocation(), "complement(488..1480)");
89 assertEquals(sf.getPhase(), "0");
90 assertEquals(sf.getStrand(), -1); // reverse strand!
91 assertEquals(sf.getValue("note"), "pGP8-D");
92 assertEquals(sf.getValue("exon number"), 1);
93 assertEquals(sf.getValue("product"), "hypothetical protein");
96 assertEquals(sf.getBegin(), 6045);
97 assertEquals(sf.getEnd(), 6788);
98 assertEquals(sf.getDescription(),
99 "Exon 1 for protein EMBLCDS:AAA91574.1");
100 assertEquals(sf.getFeatureGroup(), "EmblTest");
101 assertEquals(sf.getEnaLocation(), "6045..6788");
102 assertEquals(sf.getPhase(), "0");
103 assertEquals(sf.getStrand(), 1);
104 assertEquals(sf.getValue("note"), "pGP6-D (gtg start codon)");
105 assertEquals(sf.getValue("exon number"), 1);
106 assertEquals(sf.getValue("product"), "hypothetical protein");
109 * CDS at 7022-7502 is the first exon of the circular CDS
111 sf = features.get(8);
112 assertEquals(sf.getBegin(), 7022);
113 assertEquals(sf.getEnd(), 7502);
114 assertEquals(sf.getDescription(),
115 "Exon 1 for protein EMBLCDS:AAA91567.1");
116 assertEquals(sf.getFeatureGroup(), "EmblTest");
117 assertEquals(sf.getEnaLocation(), "join(7022..7502,1..437)");
118 assertEquals(sf.getPhase(), "0");
119 assertEquals(sf.getStrand(), 1);
120 assertEquals(sf.getValue("note"), "pGP7-D");
121 assertEquals(sf.getValue("exon number"), 1);
122 assertEquals(sf.getValue("product"), "hypothetical protein");
125 * Verify DBRefs, whether declared in the file or added by Jalview.
126 * There are 4 'direct' (DR) dbrefs, and numerous CDS /db_xref entries
127 * (some e.g. INTERPRO are duplicates). Jalview adds a dbref to 'self'.
128 * Sample a few here. Note DBRefEntry constructor capitalises source.
130 List<DBRefEntry> dbrefs = seq.getDBRefs();
131 assertEquals(dbrefs.size(), 32);
133 DBRefEntry selfRef = new DBRefEntry("EMBLTEST", "1", "J03321");
134 int[] range = new int[] { 1, seq.getLength() };
135 selfRef.setMap(new Mapping(null, range, range, 1, 1));
136 assertTrue(dbrefs.contains(selfRef));
138 // 1st DR line; note trailing period is removed
139 assertTrue(dbrefs.contains(new DBRefEntry("MD5", "0",
140 "d4c4942a634e3df4995fd5ac75c26a61")));
143 dbrefs.contains(new DBRefEntry("EUROPEPMC", "0", "PMC87941")));
144 // from the first CDS feature
145 assertTrue(dbrefs.contains(new DBRefEntry("GOA", "0", "P0CE19")));
146 // from the last CDS feature
148 dbrefs.contains(new DBRefEntry("INTERPRO", "0", "IPR005350")));
151 * verify mappings to, and sequences for, UNIPROT proteins
153 int uniprotCount = 0;
155 for (DBRefEntry dbref : dbrefs)
157 if ("UNIPROT".equals(dbref.getSource()))
160 Mapping mapping = dbref.getMap();
161 assertNotNull(mapping);
162 MapList map = mapping.getMap();
163 String mappedToName = mapping.getTo().getName();
164 if ("UNIPROT|P0CE16".equals(mappedToName))
166 assertEquals((ranges = map.getFromRanges()).size(), 1);
167 assertEquals(ranges.get(0)[0], 1579);
168 assertEquals(ranges.get(0)[1], 2934);
169 assertEquals((ranges = map.getToRanges()).size(), 1);
170 assertEquals(ranges.get(0)[0], 1);
171 assertEquals(ranges.get(0)[1], 451);
172 // CDS /product carries over as protein product description
173 assertEquals(mapping.getTo().getDescription(),
174 "hypothetical protein");
176 else if ("UNIPROT|P0CE17".equals(mappedToName))
178 assertEquals((ranges = map.getFromRanges()).size(), 1);
179 assertEquals(ranges.get(0)[0], 2928);
180 assertEquals(ranges.get(0)[1], 3992);
181 assertEquals((ranges = map.getToRanges()).size(), 1);
182 assertEquals(ranges.get(0)[0], 1);
183 assertEquals(ranges.get(0)[1], 354);
185 else if ("UNIPROT|P0CE18".equals(mappedToName))
187 assertEquals((ranges = map.getFromRanges()).size(), 1);
188 assertEquals(ranges.get(0)[0], 4054);
189 assertEquals(ranges.get(0)[1], 4848);
190 assertEquals((ranges = map.getToRanges()).size(), 1);
191 assertEquals(ranges.get(0)[0], 1);
192 assertEquals(ranges.get(0)[1], 264);
194 else if ("UNIPROT|P0CE19".equals(mappedToName))
196 // join(7022..7502,1..437)
197 assertEquals((ranges = map.getFromRanges()).size(), 2);
198 assertEquals(ranges.get(0)[0], 7022);
199 assertEquals(ranges.get(0)[1], 7502);
200 assertEquals(ranges.get(1)[0], 1);
201 assertEquals(ranges.get(1)[1], 437);
202 assertEquals((ranges = map.getToRanges()).size(), 1);
203 assertEquals(ranges.get(0)[0], 1);
204 assertEquals(ranges.get(0)[1], 305);
206 else if ("UNIPROT|P0CE20".equals(mappedToName))
208 // complement(488..1480)
209 assertEquals((ranges = map.getFromRanges()).size(), 1);
210 assertEquals(ranges.get(0)[0], 1480);
211 assertEquals(ranges.get(0)[1], 488);
212 assertEquals((ranges = map.getToRanges()).size(), 1);
213 assertEquals(ranges.get(0)[0], 1);
214 assertEquals(ranges.get(0)[1], 330);
216 else if (!"UNIPROT|P0CE23".equals(mappedToName)
217 && !"UNIPROT|P10559".equals(mappedToName)
218 && !"UNIPROT|P10560".equals(mappedToName))
220 fail("Unexpected UNIPROT dbref to " + mappedToName);
224 assertEquals(uniprotCount, 8);
227 @Test(groups = "Functional")
228 public void testParse_codonStartNot1()
230 // TODO verify CDS-to-protein mapping for CDS with /codon_start=2
231 // example: https://www.ebi.ac.uk/ena/browser/api/embl/EU498516
235 * Test for the case that the EMBL CDS has no UNIPROT xref. In this case
236 * Jalview should synthesize an xref to EMBLCDSPROTEIN in the hope this will
237 * allow Get Cross-References.
239 * @throws IOException
241 @Test(groups = "Functional")
242 public void testParse_noUniprotXref() throws IOException
244 // MN908947 cut down to 40BP, one CDS, length 5 peptide for test purposes
245 // plus an additional (invented) test case:
246 // - multi-line /product qualifier including escaped quotes
247 String data = "ID MN908947; SV 3; linear; genomic RNA; STD; VRL; 20 BP.\n"
248 + "DE Severe acute respiratory syndrome coronavirus 2 isolate Wuhan-Hu-1,\n"
250 + "FT /protein_id=\"QHD43415.1\"\n"
251 + "FT /product=\"orf1ab polyprotein\n"
252 + "FT \"\"foobar\"\" \"\n"
253 + "FT /translation=\"MRKLD\n"
254 + "SQ Sequence 7496 BP; 2450 A; 1290 C; 1434 G; 2322 T; 0 other;\n"
255 + " ggatGcgtaa gttagacgaa attttgtctt tgcgcacaga 40\n";
256 FileParse fp = new FileParse(data, DataSourceType.PASTE);
257 EmblFlatFile parser = new EmblFlatFile(fp, "EmblTest");
259 List<SequenceI> seqs = parser.getSeqs();
260 assertEquals(seqs.size(), 1);
261 SequenceI seq = seqs.get(0);
262 DBModList<DBRefEntry> dbrefs = seq.getDBRefs();
265 * dna should have dbref to itself, and to inferred EMBLCDSPROTEIN:QHD43415.1
267 assertEquals(dbrefs.size(), 2);
270 DBRefEntry dbref = dbrefs.get(0);
271 assertEquals(dbref.getSource(), "EMBLTEST");
272 assertEquals(dbref.getAccessionId(), "MN908947");
273 Mapping mapping = dbref.getMap();
274 assertNull(mapping.getTo());
275 MapList map = mapping.getMap();
276 assertEquals(map.getFromLowest(), 1);
277 assertEquals(map.getFromHighest(), 40);
278 assertEquals(map.getToLowest(), 1);
279 assertEquals(map.getToHighest(), 40);
280 assertEquals(map.getFromRatio(), 1);
281 assertEquals(map.getToRatio(), 1);
283 // dbref to inferred EMBLCDSPROTEIN:
284 dbref = dbrefs.get(1);
285 assertEquals(dbref.getSource(), "EMBLCDSPROTEIN");
286 assertEquals(dbref.getAccessionId(), "QHD43415.1");
287 mapping = dbref.getMap();
288 SequenceI mapTo = mapping.getTo();
289 assertEquals(mapTo.getName(), "QHD43415.1");
290 // the /product qualifier transfers to protein product description
291 assertEquals(mapTo.getDescription(), "orf1ab polyprotein \"foobar\"");
292 assertEquals(mapTo.getSequenceAsString(), "MRKLD");
293 map = mapping.getMap();
294 assertEquals(map.getFromLowest(), 3);
295 assertEquals(map.getFromHighest(), 17);
296 assertEquals(map.getToLowest(), 1);
297 assertEquals(map.getToHighest(), 5);
298 assertEquals(map.getFromRatio(), 3);
299 assertEquals(map.getToRatio(), 1);
302 @Test(groups = "Functional")
303 public void testAdjustForProteinLength()
305 int[] exons = new int[] { 11, 15, 21, 25, 31, 38 }; // 18 bp
307 // exact length match:
308 assertSame(exons, EmblFlatFile.adjustForProteinLength(6, exons));
310 // match if we assume exons include stop codon not in protein:
311 assertSame(exons, EmblFlatFile.adjustForProteinLength(5, exons));
313 // truncate last exon by 6bp
314 int[] truncated = EmblFlatFile.adjustForProteinLength(4, exons);
315 assertEquals("[11, 15, 21, 25, 31, 32]", Arrays.toString(truncated));
317 // remove last exon and truncate preceding by 1bp (so 3bp in total)
318 truncated = EmblFlatFile.adjustForProteinLength(3, exons);
319 assertEquals("[11, 15, 21, 24]", Arrays.toString(truncated));
321 // exact removal of exon case:
322 exons = new int[] { 11, 15, 21, 27, 33, 38 }; // 18 bp
323 truncated = EmblFlatFile.adjustForProteinLength(4, exons);
324 assertEquals("[11, 15, 21, 27]", Arrays.toString(truncated));
326 // what if exons are too short for protein?
327 truncated = EmblFlatFile.adjustForProteinLength(7, exons);
328 assertSame(exons, truncated);
331 @Test(groups = "Functional")
332 public void testRemoveQuotes()
334 assertNull(EmblFlatFile.removeQuotes(null));
335 assertEquals(EmblFlatFile.removeQuotes("No quotes here"), "No quotes here");
336 assertEquals(EmblFlatFile.removeQuotes("\"Enclosing quotes\""), "Enclosing quotes");
337 assertEquals(EmblFlatFile.removeQuotes("\"Escaped \"\"quotes\"\" example\""), "Escaped \"quotes\" example");