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.AssertJUnit.assertEquals;
24 import static org.testng.AssertJUnit.assertFalse;
25 import static org.testng.AssertJUnit.assertNotNull;
26 import static org.testng.AssertJUnit.assertNull;
27 import static org.testng.AssertJUnit.assertTrue;
29 import jalview.datamodel.Alignment;
30 import jalview.datamodel.AlignmentI;
31 import jalview.datamodel.SequenceDummy;
32 import jalview.datamodel.SequenceFeature;
33 import jalview.datamodel.SequenceI;
34 import jalview.gui.AlignFrame;
35 import jalview.schemes.AnnotationColourGradient;
36 import jalview.schemes.GraduatedColor;
38 import java.awt.Color;
40 import java.io.IOException;
43 import org.testng.annotations.Test;
45 public class FeaturesFileTest
48 private static String simpleGffFile = "examples/testdata/simpleGff3.gff";
50 @Test(groups = { "Functional" })
51 public void testParse() throws Exception
53 File f = new File("examples/uniref50.fa");
54 AlignmentI al = readAlignmentFile(f);
55 AlignFrame af = new AlignFrame(al, 500, 500);
56 Map<String, Object> colours = af.getFeatureRenderer()
58 FeaturesFile featuresFile = new FeaturesFile(
59 "examples/exampleFeatures.txt", FormatAdapter.FILE);
60 assertTrue("Test " + "Features file test"
61 + "\nFailed to parse features file.",
62 featuresFile.parse(al.getDataset(), colours, true));
65 * Refetch the colour map from the FeatureRenderer (to confirm it has been
66 * updated - JAL-1904), and verify (some) feature group colours
68 colours = af.getFeatureRenderer().getFeatureColours();
69 assertEquals("26 feature group colours not found", 26, colours.size());
70 assertEquals(colours.get("Cath"), new Color(0x93b1d1));
71 assertEquals(colours.get("ASX-MOTIF"), new Color(0x6addbb));
74 * verify (some) features on sequences
76 SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
77 .getSequenceFeatures(); // FER_CAPAA
78 assertEquals(7, sfs.length);
79 SequenceFeature sf = sfs[0];
80 assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
81 assertEquals(39, sf.begin);
82 assertEquals(39, sf.end);
83 assertEquals("uniprot", sf.featureGroup);
84 assertEquals("METAL", sf.type);
86 assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
87 assertEquals(44, sf.begin);
88 assertEquals(44, sf.end);
89 assertEquals("uniprot", sf.featureGroup);
90 assertEquals("METAL", sf.type);
92 assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
93 assertEquals(47, sf.begin);
94 assertEquals(47, sf.end);
95 assertEquals("uniprot", sf.featureGroup);
96 assertEquals("METAL", sf.type);
98 assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
99 assertEquals(77, sf.begin);
100 assertEquals(77, sf.end);
101 assertEquals("uniprot", sf.featureGroup);
102 assertEquals("METAL", sf.type);
104 assertEquals("Fer2 Status: True Positive Pfam 8_8%LINK%",
106 assertEquals("Pfam 8_8|http://pfam.sanger.ac.uk/family/PF00111",
107 sf.links.get(0).toString());
108 assertEquals(8, sf.begin);
109 assertEquals(83, sf.end);
110 assertEquals("uniprot", sf.featureGroup);
111 assertEquals("Pfam", sf.type);
113 assertEquals("Ferredoxin_fold Status: True Positive ", sf.description);
114 assertEquals(3, sf.begin);
115 assertEquals(93, sf.end);
116 assertEquals("uniprot", sf.featureGroup);
117 assertEquals("Cath", sf.type);
120 "High confidence server. Only hits with scores over 0.8 are reported. PHOSPHORYLATION (T) 89_8%LINK%",
123 "PHOSPHORYLATION (T) 89_8|http://www.cbs.dtu.dk/cgi-bin/proview/webface-link?seqid=P83527&service=NetPhos-2.0",
124 sf.links.get(0).toString());
125 assertEquals(89, sf.begin);
126 assertEquals(89, sf.end);
127 assertEquals("netphos", sf.featureGroup);
128 assertEquals("PHOSPHORYLATION (T)", sf.type);
132 * Test parsing a features file with a mix of Jalview and GFF formatted
137 @Test(groups = { "Functional" })
138 public void testParse_mixedJalviewGff() throws Exception
140 File f = new File("examples/uniref50.fa");
141 AlignmentI al = readAlignmentFile(f);
142 AlignFrame af = new AlignFrame(al, 500, 500);
143 Map<String, Object> colours = af.getFeatureRenderer()
144 .getFeatureColours();
145 // GFF2 uses space as name/value separator in column 9
146 String gffData = "METAL\tcc9900\n" + "GFF\n"
147 + "FER_CAPAA\tuniprot\tMETAL\t44\t45\t4.0\t.\t.\tNote Iron-sulfur; Note 2Fe-2S\n"
148 + "FER1_SOLLC\tuniprot\tPfam\t55\t130\t2.0\t.\t.";
149 FeaturesFile featuresFile = new FeaturesFile(gffData,
150 FormatAdapter.PASTE);
151 assertTrue("Failed to parse features file",
152 featuresFile.parse(al.getDataset(), colours, true));
154 // verify colours read or synthesized
155 colours = af.getFeatureRenderer().getFeatureColours();
156 assertEquals("1 feature group colours not found", 1, colours.size());
157 assertEquals(colours.get("METAL"), new Color(0xcc9900));
159 // verify feature on FER_CAPAA
160 SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
161 .getSequenceFeatures();
162 assertEquals(1, sfs.length);
163 SequenceFeature sf = sfs[0];
164 assertEquals("Iron-sulfur,2Fe-2S", sf.description);
165 assertEquals(44, sf.begin);
166 assertEquals(45, sf.end);
167 assertEquals("uniprot", sf.featureGroup);
168 assertEquals("METAL", sf.type);
169 assertEquals(4f, sf.getScore(), 0.001f);
171 // verify feature on FER1_SOLLC
172 sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
173 assertEquals(1, sfs.length);
175 assertEquals("uniprot", sf.description);
176 assertEquals(55, sf.begin);
177 assertEquals(130, sf.end);
178 assertEquals("uniprot", sf.featureGroup);
179 assertEquals("Pfam", sf.type);
180 assertEquals(2f, sf.getScore(), 0.001f);
183 public static AlignmentI readAlignmentFile(File f) throws IOException
185 System.out.println("Reading file: " + f);
186 String ff = f.getPath();
187 FormatAdapter rf = new FormatAdapter();
189 AlignmentI al = rf.readFile(ff, FormatAdapter.FILE,
190 new IdentifyFile().identify(ff, FormatAdapter.FILE));
192 al.setDataset(null); // creates dataset sequences
193 assertNotNull("Couldn't read supplied alignment data.", al);
198 * Test various ways of describing a feature colour scheme
202 @Test(groups = { "Functional" })
203 public void testParseGraduatedColourScheme() throws Exception
205 FeaturesFile ff = new FeaturesFile();
208 GraduatedColor gc = ff.parseGraduatedColourScheme(
209 "BETA-TURN-IR\t9a6a94", "label");
210 assertTrue(gc.isColourByLabel());
211 assertEquals(Color.white, gc.getMinColor());
212 assertEquals(Color.black, gc.getMaxColor());
213 assertTrue(gc.isAutoScale());
215 // using colour name, rgb, etc:
216 String spec = "blue|255,0,255|absolute|20.0|95.0|below|66.0";
217 gc = ff.parseGraduatedColourScheme("BETA-TURN-IR\t" + spec, spec);
218 assertFalse(gc.isColourByLabel());
219 assertEquals(Color.blue, gc.getMinColor());
220 assertEquals(new Color(255, 0, 255), gc.getMaxColor());
221 assertFalse(gc.isAutoScale());
222 assertFalse(gc.getTolow());
223 assertEquals(20.0f, gc.getMin(), 0.001f);
224 assertEquals(95.0f, gc.getMax(), 0.001f);
225 assertEquals(AnnotationColourGradient.BELOW_THRESHOLD,
227 assertEquals(66.0f, gc.getThresh(), 0.001f);
229 // inverse gradient high to low:
230 spec = "blue|255,0,255|95.0|20.0|below|66.0";
231 gc = ff.parseGraduatedColourScheme("BETA-TURN-IR\t" + spec, spec);
232 assertTrue(gc.isAutoScale());
233 assertTrue(gc.getTolow());
237 * Test parsing a features file with GFF formatted content only
241 @Test(groups = { "Functional" })
242 public void testParse_pureGff3() throws Exception
244 File f = new File("examples/uniref50.fa");
245 AlignmentI al = readAlignmentFile(f);
246 AlignFrame af = new AlignFrame(al, 500, 500);
247 Map<String, Object> colours = af.getFeatureRenderer()
248 .getFeatureColours();
249 // GFF3 uses '=' separator for name/value pairs in colum 9
250 String gffData = "##gff-version 3\n"
251 + "FER_CAPAA\tuniprot\tMETAL\t39\t39\t0.0\t.\t.\t"
252 + "Note=Iron-sulfur (2Fe-2S);Note=another note;evidence=ECO:0000255|PROSITE-ProRule:PRU00465\n"
253 + "FER1_SOLLC\tuniprot\tPfam\t55\t130\t3.0\t.\t.\tID=$23";
254 FeaturesFile featuresFile = new FeaturesFile(gffData,
255 FormatAdapter.PASTE);
256 assertTrue("Failed to parse features file",
257 featuresFile.parse(al.getDataset(), colours, true));
259 // verify feature on FER_CAPAA
260 SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
261 .getSequenceFeatures();
262 assertEquals(1, sfs.length);
263 SequenceFeature sf = sfs[0];
264 // description parsed from Note attribute
265 assertEquals("Iron-sulfur (2Fe-2S),another note", sf.description);
266 assertEquals(39, sf.begin);
267 assertEquals(39, sf.end);
268 assertEquals("uniprot", sf.featureGroup);
269 assertEquals("METAL", sf.type);
271 "Note=Iron-sulfur (2Fe-2S);Note=another note;evidence=ECO:0000255|PROSITE-ProRule:PRU00465",
272 sf.getValue("ATTRIBUTES"));
274 // verify feature on FER1_SOLLC1
275 sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
276 assertEquals(1, sfs.length);
278 // ID used for description if available
279 assertEquals("$23", sf.description);
280 assertEquals(55, sf.begin);
281 assertEquals(130, sf.end);
282 assertEquals("uniprot", sf.featureGroup);
283 assertEquals("Pfam", sf.type);
284 assertEquals(3f, sf.getScore(), 0.001f);
288 * Test parsing a features file with Jalview format features (but no colour
289 * descriptors or startgroup to give the hint not to parse as GFF)
293 @Test(groups = { "Functional" })
294 public void testParse_jalviewFeaturesOnly() throws Exception
296 File f = new File("examples/uniref50.fa");
297 AlignmentI al = readAlignmentFile(f);
298 AlignFrame af = new AlignFrame(al, 500, 500);
299 Map<String, Object> colours = af.getFeatureRenderer()
300 .getFeatureColours();
303 * one feature on FER_CAPAA and one on sequence 3 (index 2) FER1_SOLLC
305 String featureData = "Iron-sulfur (2Fe-2S)\tFER_CAPAA\t-1\t39\t39\tMETAL\n"
306 + "Iron-phosphorus (2Fe-P)\tID_NOT_SPECIFIED\t2\t86\t87\tMETALLIC\n";
307 FeaturesFile featuresFile = new FeaturesFile(featureData,
308 FormatAdapter.PASTE);
309 assertTrue("Failed to parse features file",
310 featuresFile.parse(al.getDataset(), colours, true));
312 // verify FER_CAPAA feature
313 SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
314 .getSequenceFeatures();
315 assertEquals(1, sfs.length);
316 SequenceFeature sf = sfs[0];
317 assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
318 assertEquals(39, sf.begin);
319 assertEquals(39, sf.end);
320 assertEquals("METAL", sf.type);
322 // verify FER1_SOLLC feature
323 sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
324 assertEquals(1, sfs.length);
326 assertEquals("Iron-phosphorus (2Fe-P)", sf.description);
327 assertEquals(86, sf.begin);
328 assertEquals(87, sf.end);
329 assertEquals("METALLIC", sf.type);
332 private void checkDatasetfromSimpleGff3(AlignmentI dataset)
334 assertEquals("no sequences extracted from GFF3 file", 2,
335 dataset.getHeight());
337 SequenceI seq1 = dataset.findName("seq1");
338 SequenceI seq2 = dataset.findName("seq2");
342 "Failed to replace dummy seq1 with real sequence",
343 seq1 instanceof SequenceDummy
344 && ((SequenceDummy) seq1).isDummy());
346 "Failed to replace dummy seq2 with real sequence",
347 seq2 instanceof SequenceDummy
348 && ((SequenceDummy) seq2).isDummy());
349 String placeholderseq = new SequenceDummy("foo").getSequenceAsString();
350 assertFalse("dummy replacement buggy for seq1",
351 placeholderseq.equals(seq1.getSequenceAsString()));
352 assertFalse("dummy replacement buggy for seq2",
353 placeholderseq.equals(seq2.getSequenceAsString()));
354 assertNotNull("No features added to seq1", seq1.getSequenceFeatures());
355 assertEquals("Wrong number of features", 3,
356 seq1.getSequenceFeatures().length);
357 assertNull(seq2.getSequenceFeatures());
359 "Wrong number of features",
361 seq2.getSequenceFeatures() == null ? 0 : seq2
362 .getSequenceFeatures().length);
364 "Expected at least one CDNA/Protein mapping for seq1",
365 dataset.getCodonFrame(seq1) != null
366 && dataset.getCodonFrame(seq1).size() > 0);
370 @Test(groups = { "Functional" })
371 public void readGff3File() throws IOException
373 FeaturesFile gffreader = new FeaturesFile(true, simpleGffFile,
375 Alignment dataset = new Alignment(gffreader.getSeqsAsArray());
376 gffreader.addProperties(dataset);
377 checkDatasetfromSimpleGff3(dataset);
380 @Test(groups = { "Functional" })
381 public void simpleGff3FileClass() throws IOException
383 AlignmentI dataset = new Alignment(new SequenceI[] {});
384 FeaturesFile ffile = new FeaturesFile(simpleGffFile,
387 boolean parseResult = ffile.parse(dataset, null, false, false);
388 assertTrue("return result should be true", parseResult);
389 checkDatasetfromSimpleGff3(dataset);
392 @Test(groups = { "Functional" })
393 public void simpleGff3FileLoader() throws IOException
395 AlignFrame af = new FileLoader(false).LoadFileWaitTillLoaded(
396 simpleGffFile, FormatAdapter.FILE);
398 "Didn't read the alignment into an alignframe from Gff3 File",
400 checkDatasetfromSimpleGff3(af.getViewport().getAlignment());
403 @Test(groups = { "Functional" })
404 public void simpleGff3RelaxedIdMatching() throws IOException
406 AlignmentI dataset = new Alignment(new SequenceI[] {});
407 FeaturesFile ffile = new FeaturesFile(simpleGffFile,
410 boolean parseResult = ffile.parse(dataset, null, false, true);
411 assertTrue("return result (relaxedID matching) should be true",
413 checkDatasetfromSimpleGff3(dataset);