2f5d0c54d24a882302f08a23e23ad909e89e986b
[jalview.git] / test / jalview / io / FeaturesFileTest.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.io;
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 import static org.testng.AssertJUnit.assertTrue;
28
29 import jalview.api.FeatureColourI;
30 import jalview.api.FeatureRenderer;
31 import jalview.datamodel.Alignment;
32 import jalview.datamodel.AlignmentI;
33 import jalview.datamodel.SequenceDummy;
34 import jalview.datamodel.SequenceFeature;
35 import jalview.datamodel.SequenceI;
36 import jalview.gui.AlignFrame;
37
38 import java.awt.Color;
39 import java.io.File;
40 import java.io.IOException;
41 import java.util.Map;
42
43 import org.testng.annotations.Test;
44
45 public class FeaturesFileTest
46 {
47
48   private static String simpleGffFile = "examples/testdata/simpleGff3.gff";
49
50   @Test(groups = { "Functional" })
51   public void testParse() throws Exception
52   {
53     File f = new File("examples/uniref50.fa");
54     AlignmentI al = readAlignmentFile(f);
55     AlignFrame af = new AlignFrame(al, 500, 500);
56     Map<String, FeatureColourI> colours = af.getFeatureRenderer()
57             .getFeatureColours();
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));
63
64     /*
65      * Refetch the colour map from the FeatureRenderer (to confirm it has been
66      * updated - JAL-1904), and verify (some) feature group colours
67      */
68     colours = af.getFeatureRenderer().getFeatureColours();
69     assertEquals("26 feature group colours not found", 26, colours.size());
70     assertEquals(colours.get("Cath").getColour(), new Color(0x93b1d1));
71     assertEquals(colours.get("ASX-MOTIF").getColour(), new Color(0x6addbb));
72
73     /*
74      * verify (some) features on sequences
75      */
76     SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
77             .getSequenceFeatures(); // FER_CAPAA
78     assertEquals(8, sfs.length);
79     SequenceFeature sf = sfs[0];
80     assertEquals("Pfam family%LINK%", sf.description);
81     assertEquals(0, sf.begin);
82     assertEquals(0, sf.end);
83     assertEquals("uniprot", sf.featureGroup);
84     assertEquals("Pfam", sf.type);
85     assertEquals(1, sf.links.size());
86     assertEquals("Pfam family|http://pfam.xfam.org/family/PF00111",
87             sf.links.get(0));
88
89     sf = sfs[1];
90     assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
91     assertEquals(39, sf.begin);
92     assertEquals(39, sf.end);
93     assertEquals("uniprot", sf.featureGroup);
94     assertEquals("METAL", sf.type);
95     sf = sfs[2];
96     assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
97     assertEquals(44, sf.begin);
98     assertEquals(44, sf.end);
99     assertEquals("uniprot", sf.featureGroup);
100     assertEquals("METAL", sf.type);
101     sf = sfs[3];
102     assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
103     assertEquals(47, sf.begin);
104     assertEquals(47, sf.end);
105     assertEquals("uniprot", sf.featureGroup);
106     assertEquals("METAL", sf.type);
107     sf = sfs[4];
108     assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
109     assertEquals(77, sf.begin);
110     assertEquals(77, sf.end);
111     assertEquals("uniprot", sf.featureGroup);
112     assertEquals("METAL", sf.type);
113     sf = sfs[5];
114     assertEquals("Fer2 Status: True Positive Pfam 8_8%LINK%",
115             sf.description);
116     assertEquals("Pfam 8_8|http://pfam.xfam.org/family/PF00111",
117             sf.links.get(0));
118     assertEquals(8, sf.begin);
119     assertEquals(83, sf.end);
120     assertEquals("uniprot", sf.featureGroup);
121     assertEquals("Pfam", sf.type);
122     sf = sfs[6];
123     assertEquals("Ferredoxin_fold Status: True Positive ", sf.description);
124     assertEquals(3, sf.begin);
125     assertEquals(93, sf.end);
126     assertEquals("uniprot", sf.featureGroup);
127     assertEquals("Cath", sf.type);
128     sf = sfs[7];
129     assertEquals(
130             "High confidence server. Only hits with scores over 0.8 are reported. PHOSPHORYLATION (T) 89_8%LINK%",
131             sf.description);
132     assertEquals(
133             "PHOSPHORYLATION (T) 89_8|http://www.cbs.dtu.dk/cgi-bin/proview/webface-link?seqid=P83527&amp;service=NetPhos-2.0",
134             sf.links.get(0));
135     assertEquals(89, sf.begin);
136     assertEquals(89, sf.end);
137     assertEquals("netphos", sf.featureGroup);
138     assertEquals("PHOSPHORYLATION (T)", sf.type);
139   }
140
141   /**
142    * Test parsing a features file with a mix of Jalview and GFF formatted
143    * content
144    * 
145    * @throws Exception
146    */
147   @Test(groups = { "Functional" })
148   public void testParse_mixedJalviewGff() throws Exception
149   {
150     File f = new File("examples/uniref50.fa");
151     AlignmentI al = readAlignmentFile(f);
152     AlignFrame af = new AlignFrame(al, 500, 500);
153     Map<String, FeatureColourI> colours = af.getFeatureRenderer()
154             .getFeatureColours();
155     // GFF2 uses space as name/value separator in column 9
156     String gffData = "METAL\tcc9900\n" + "GFF\n"
157             + "FER_CAPAA\tuniprot\tMETAL\t44\t45\t4.0\t.\t.\tNote Iron-sulfur; Note 2Fe-2S\n"
158             + "FER1_SOLLC\tuniprot\tPfam\t55\t130\t2.0\t.\t.";
159     FeaturesFile featuresFile = new FeaturesFile(gffData,
160             FormatAdapter.PASTE);
161     assertTrue("Failed to parse features file",
162             featuresFile.parse(al.getDataset(), colours, true));
163
164     // verify colours read or synthesized
165     colours = af.getFeatureRenderer().getFeatureColours();
166     assertEquals("1 feature group colours not found", 1, colours.size());
167     assertEquals(colours.get("METAL").getColour(), new Color(0xcc9900));
168
169     // verify feature on FER_CAPAA
170     SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
171             .getSequenceFeatures();
172     assertEquals(1, sfs.length);
173     SequenceFeature sf = sfs[0];
174     assertEquals("Iron-sulfur,2Fe-2S", sf.description);
175     assertEquals(44, sf.begin);
176     assertEquals(45, sf.end);
177     assertEquals("uniprot", sf.featureGroup);
178     assertEquals("METAL", sf.type);
179     assertEquals(4f, sf.getScore(), 0.001f);
180
181     // verify feature on FER1_SOLLC
182     sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
183     assertEquals(1, sfs.length);
184     sf = sfs[0];
185     assertEquals("uniprot", sf.description);
186     assertEquals(55, sf.begin);
187     assertEquals(130, sf.end);
188     assertEquals("uniprot", sf.featureGroup);
189     assertEquals("Pfam", sf.type);
190     assertEquals(2f, sf.getScore(), 0.001f);
191   }
192
193   public static AlignmentI readAlignmentFile(File f) throws IOException
194   {
195     System.out.println("Reading file: " + f);
196     String ff = f.getPath();
197     FormatAdapter rf = new FormatAdapter();
198
199     AlignmentI al = rf.readFile(ff, FormatAdapter.FILE,
200             new IdentifyFile().identify(ff, FormatAdapter.FILE));
201
202     al.setDataset(null); // creates dataset sequences
203     assertNotNull("Couldn't read supplied alignment data.", al);
204     return al;
205   }
206
207   /**
208    * Test parsing a features file with GFF formatted content only
209    * 
210    * @throws Exception
211    */
212   @Test(groups = { "Functional" })
213   public void testParse_pureGff3() throws Exception
214   {
215     File f = new File("examples/uniref50.fa");
216     AlignmentI al = readAlignmentFile(f);
217     AlignFrame af = new AlignFrame(al, 500, 500);
218     Map<String, FeatureColourI> colours = af.getFeatureRenderer()
219             .getFeatureColours();
220     // GFF3 uses '=' separator for name/value pairs in colum 9
221     String gffData = "##gff-version 3\n"
222             + "FER_CAPAA\tuniprot\tMETAL\t39\t39\t0.0\t.\t.\t"
223             + "Note=Iron-sulfur (2Fe-2S);Note=another note;evidence=ECO:0000255|PROSITE-ProRule:PRU00465\n"
224             + "FER1_SOLLC\tuniprot\tPfam\t55\t130\t3.0\t.\t.\tID=$23";
225     FeaturesFile featuresFile = new FeaturesFile(gffData,
226             FormatAdapter.PASTE);
227     assertTrue("Failed to parse features file",
228             featuresFile.parse(al.getDataset(), colours, true));
229
230     // verify feature on FER_CAPAA
231     SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
232             .getSequenceFeatures();
233     assertEquals(1, sfs.length);
234     SequenceFeature sf = sfs[0];
235     // description parsed from Note attribute
236     assertEquals("Iron-sulfur (2Fe-2S),another note", sf.description);
237     assertEquals(39, sf.begin);
238     assertEquals(39, sf.end);
239     assertEquals("uniprot", sf.featureGroup);
240     assertEquals("METAL", sf.type);
241     assertEquals(
242             "Note=Iron-sulfur (2Fe-2S);Note=another note;evidence=ECO:0000255|PROSITE-ProRule:PRU00465",
243             sf.getValue("ATTRIBUTES"));
244
245     // verify feature on FER1_SOLLC1
246     sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
247     assertEquals(1, sfs.length);
248     sf = sfs[0];
249     // ID used for description if available
250     assertEquals("$23", sf.description);
251     assertEquals(55, sf.begin);
252     assertEquals(130, sf.end);
253     assertEquals("uniprot", sf.featureGroup);
254     assertEquals("Pfam", sf.type);
255     assertEquals(3f, sf.getScore(), 0.001f);
256   }
257
258   /**
259    * Test parsing a features file with Jalview format features (but no colour
260    * descriptors or startgroup to give the hint not to parse as GFF)
261    * 
262    * @throws Exception
263    */
264   @Test(groups = { "Functional" })
265   public void testParse_jalviewFeaturesOnly() throws Exception
266   {
267     File f = new File("examples/uniref50.fa");
268     AlignmentI al = readAlignmentFile(f);
269     AlignFrame af = new AlignFrame(al, 500, 500);
270     Map<String, FeatureColourI> colours = af.getFeatureRenderer()
271             .getFeatureColours();
272
273     /*
274      * one feature on FER_CAPAA and one on sequence 3 (index 2) FER1_SOLLC
275      */
276     String featureData = "Iron-sulfur (2Fe-2S)\tFER_CAPAA\t-1\t39\t39\tMETAL\n"
277             + "Iron-phosphorus (2Fe-P)\tID_NOT_SPECIFIED\t2\t86\t87\tMETALLIC\n";
278     FeaturesFile featuresFile = new FeaturesFile(featureData,
279             FormatAdapter.PASTE);
280     assertTrue("Failed to parse features file",
281             featuresFile.parse(al.getDataset(), colours, true));
282
283     // verify FER_CAPAA feature
284     SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
285             .getSequenceFeatures();
286     assertEquals(1, sfs.length);
287     SequenceFeature sf = sfs[0];
288     assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
289     assertEquals(39, sf.begin);
290     assertEquals(39, sf.end);
291     assertEquals("METAL", sf.type);
292
293     // verify FER1_SOLLC feature
294     sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
295     assertEquals(1, sfs.length);
296     sf = sfs[0];
297     assertEquals("Iron-phosphorus (2Fe-P)", sf.description);
298     assertEquals(86, sf.begin);
299     assertEquals(87, sf.end);
300     assertEquals("METALLIC", sf.type);
301   }
302
303   private void checkDatasetfromSimpleGff3(AlignmentI dataset)
304   {
305     assertEquals("no sequences extracted from GFF3 file", 2,
306             dataset.getHeight());
307   
308     SequenceI seq1 = dataset.findName("seq1");
309     SequenceI seq2 = dataset.findName("seq2");
310     assertNotNull(seq1);
311     assertNotNull(seq2);
312     assertFalse(
313             "Failed to replace dummy seq1 with real sequence",
314             seq1 instanceof SequenceDummy
315                     && ((SequenceDummy) seq1).isDummy());
316     assertFalse(
317             "Failed to replace dummy seq2 with real sequence",
318             seq2 instanceof SequenceDummy
319                     && ((SequenceDummy) seq2).isDummy());
320     String placeholderseq = new SequenceDummy("foo").getSequenceAsString();
321     assertFalse("dummy replacement buggy for seq1",
322             placeholderseq.equals(seq1.getSequenceAsString()));
323     assertFalse("dummy replacement buggy for seq2",
324             placeholderseq.equals(seq2.getSequenceAsString()));
325     assertNotNull("No features added to seq1", seq1.getSequenceFeatures());
326     assertEquals("Wrong number of features", 3,
327             seq1.getSequenceFeatures().length);
328     assertNull(seq2.getSequenceFeatures());
329     assertEquals(
330             "Wrong number of features",
331             0,
332             seq2.getSequenceFeatures() == null ? 0 : seq2
333                     .getSequenceFeatures().length);
334     assertTrue(
335             "Expected at least one CDNA/Protein mapping for seq1",
336             dataset.getCodonFrame(seq1) != null
337                     && dataset.getCodonFrame(seq1).size() > 0);
338   
339   }
340
341   @Test(groups = { "Functional" })
342   public void readGff3File() throws IOException
343   {
344     FeaturesFile gffreader = new FeaturesFile(true, simpleGffFile,
345             FormatAdapter.FILE);
346     Alignment dataset = new Alignment(gffreader.getSeqsAsArray());
347     gffreader.addProperties(dataset);
348     checkDatasetfromSimpleGff3(dataset);
349   }
350
351   @Test(groups = { "Functional" })
352   public void simpleGff3FileClass() throws IOException
353   {
354     AlignmentI dataset = new Alignment(new SequenceI[] {});
355     FeaturesFile ffile = new FeaturesFile(simpleGffFile,
356             FormatAdapter.FILE);
357   
358     boolean parseResult = ffile.parse(dataset, null, false, false);
359     assertTrue("return result should be true", parseResult);
360     checkDatasetfromSimpleGff3(dataset);
361   }
362
363   @Test(groups = { "Functional" })
364   public void simpleGff3FileLoader() throws IOException
365   {
366     AlignFrame af = new FileLoader(false).LoadFileWaitTillLoaded(
367             simpleGffFile, FormatAdapter.FILE);
368     assertTrue(
369             "Didn't read the alignment into an alignframe from Gff3 File",
370             af != null);
371     checkDatasetfromSimpleGff3(af.getViewport().getAlignment());
372   }
373
374   @Test(groups = { "Functional" })
375   public void simpleGff3RelaxedIdMatching() throws IOException
376   {
377     AlignmentI dataset = new Alignment(new SequenceI[] {});
378     FeaturesFile ffile = new FeaturesFile(simpleGffFile,
379             FormatAdapter.FILE);
380   
381     boolean parseResult = ffile.parse(dataset, null, false, true);
382     assertTrue("return result (relaxedID matching) should be true",
383             parseResult);
384     checkDatasetfromSimpleGff3(dataset);
385   }
386
387   @Test(groups = { "Functional" })
388   public void testPrintJalviewFormat() throws Exception
389   {
390     File f = new File("examples/uniref50.fa");
391     AlignmentI al = readAlignmentFile(f);
392     AlignFrame af = new AlignFrame(al, 500, 500);
393     Map<String, FeatureColourI> colours = af.getFeatureRenderer()
394             .getFeatureColours();
395     String features = "METAL\tcc9900\n"
396             + "GAMMA-TURN\tred|0,255,255|20.0|95.0|below|66.0\n"
397             + "Pfam\tred\n"
398             + "STARTGROUP\tuniprot\n"
399             + "Iron\tFER_CAPAA\t-1\t39\t39\tMETAL\n"
400             + "Turn\tFER_CAPAA\t-1\t36\t38\tGAMMA-TURN\n"
401             + "<html>Pfam domain<a href=\"http://pfam.xfam.org/family/PF00111\">Pfam_3_4</a></html>\tFER_CAPAA\t-1\t20\t20\tPfam\n"
402             + "ENDGROUP\tuniprot\n";
403     FeaturesFile featuresFile = new FeaturesFile(features,
404             FormatAdapter.PASTE);
405     featuresFile.parse(al.getDataset(), colours, false);
406
407     /*
408      * first with no features displayed
409      */
410     FeatureRenderer fr = af.alignPanel.getFeatureRenderer();
411     Map<String, FeatureColourI> visible = fr
412             .getDisplayedFeatureCols();
413     String exported = featuresFile.printJalviewFormat(
414             al.getSequencesArray(), visible);
415     String expected = "No Features Visible";
416     assertEquals(expected, exported);
417
418     /*
419      * set METAL (in uniprot group) and GAMMA-TURN visible, but not Pfam
420      */
421     fr.setVisible("METAL");
422     fr.setVisible("GAMMA-TURN");
423     visible = fr.getDisplayedFeatureCols();
424     exported = featuresFile.printJalviewFormat(al.getSequencesArray(),
425             visible);
426     expected = "METAL\tcc9900\n"
427             + "GAMMA-TURN\tff0000|00ffff|20.0|95.0|below|66.0\n"
428             + "\nSTARTGROUP\tuniprot\n"
429             + "Iron\tFER_CAPAA\t-1\t39\t39\tMETAL\t0.0\n"
430             + "Turn\tFER_CAPAA\t-1\t36\t38\tGAMMA-TURN\t0.0\n"
431             + "ENDGROUP\tuniprot\n";
432     assertEquals(expected, exported);
433
434     /*
435      * now set Pfam visible
436      */
437     fr.setVisible("Pfam");
438     visible = fr.getDisplayedFeatureCols();
439     exported = featuresFile.printJalviewFormat(al.getSequencesArray(),
440             visible);
441     /*
442      * note the order of feature types is uncontrolled - derives from
443      * FeaturesDisplayed.featuresDisplayed which is a HashSet
444      */
445     expected = "METAL\tcc9900\n"
446             + "Pfam\tff0000\n"
447             + "GAMMA-TURN\tff0000|00ffff|20.0|95.0|below|66.0\n"
448             + "\nSTARTGROUP\tuniprot\n"
449             + "Iron\tFER_CAPAA\t-1\t39\t39\tMETAL\t0.0\n"
450             + "Turn\tFER_CAPAA\t-1\t36\t38\tGAMMA-TURN\t0.0\n"
451             + "<html>Pfam domain<a href=\"http://pfam.xfam.org/family/PF00111\">Pfam_3_4</a></html>\tFER_CAPAA\t-1\t20\t20\tPfam\t0.0\n"
452             + "ENDGROUP\tuniprot\n";
453     assertEquals(expected, exported);
454   }
455 }