/*
* Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
* Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
* Jalview is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation, either version 3
* of the License, or (at your option) any later version.
*
* Jalview is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
* PURPOSE. See the GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Jalview. If not, see .
* The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.io;
import static org.testng.AssertJUnit.assertEquals;
import static org.testng.AssertJUnit.assertFalse;
import static org.testng.AssertJUnit.assertNotNull;
import static org.testng.AssertJUnit.assertNull;
import static org.testng.AssertJUnit.assertTrue;
import jalview.api.FeatureColourI;
import jalview.api.FeatureRenderer;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.SequenceDummy;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
import jalview.gui.AlignFrame;
import java.awt.Color;
import java.io.File;
import java.io.IOException;
import java.util.Map;
import org.testng.annotations.Test;
public class FeaturesFileTest
{
private static String simpleGffFile = "examples/testdata/simpleGff3.gff";
@Test(groups = { "Functional" })
public void testParse() throws Exception
{
File f = new File("examples/uniref50.fa");
AlignmentI al = readAlignmentFile(f);
AlignFrame af = new AlignFrame(al, 500, 500);
Map colours = af.getFeatureRenderer()
.getFeatureColours();
FeaturesFile featuresFile = new FeaturesFile(
"examples/exampleFeatures.txt", FormatAdapter.FILE);
assertTrue("Test " + "Features file test"
+ "\nFailed to parse features file.",
featuresFile.parse(al.getDataset(), colours, true));
/*
* Refetch the colour map from the FeatureRenderer (to confirm it has been
* updated - JAL-1904), and verify (some) feature group colours
*/
colours = af.getFeatureRenderer().getFeatureColours();
assertEquals("26 feature group colours not found", 26, colours.size());
assertEquals(colours.get("Cath").getColour(), new Color(0x93b1d1));
assertEquals(colours.get("ASX-MOTIF").getColour(), new Color(0x6addbb));
/*
* verify (some) features on sequences
*/
SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
.getSequenceFeatures(); // FER_CAPAA
assertEquals(8, sfs.length);
SequenceFeature sf = sfs[0];
assertEquals("Pfam family%LINK%", sf.description);
assertEquals(0, sf.begin);
assertEquals(0, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("Pfam", sf.type);
assertEquals(1, sf.links.size());
assertEquals("Pfam family|http://pfam.xfam.org/family/PF00111",
sf.links.get(0));
sf = sfs[1];
assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
assertEquals(39, sf.begin);
assertEquals(39, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("METAL", sf.type);
sf = sfs[2];
assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
assertEquals(44, sf.begin);
assertEquals(44, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("METAL", sf.type);
sf = sfs[3];
assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
assertEquals(47, sf.begin);
assertEquals(47, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("METAL", sf.type);
sf = sfs[4];
assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
assertEquals(77, sf.begin);
assertEquals(77, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("METAL", sf.type);
sf = sfs[5];
assertEquals("Fer2 Status: True Positive Pfam 8_8%LINK%",
sf.description);
assertEquals("Pfam 8_8|http://pfam.xfam.org/family/PF00111",
sf.links.get(0));
assertEquals(8, sf.begin);
assertEquals(83, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("Pfam", sf.type);
sf = sfs[6];
assertEquals("Ferredoxin_fold Status: True Positive ", sf.description);
assertEquals(3, sf.begin);
assertEquals(93, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("Cath", sf.type);
sf = sfs[7];
assertEquals(
"High confidence server. Only hits with scores over 0.8 are reported. PHOSPHORYLATION (T) 89_8%LINK%",
sf.description);
assertEquals(
"PHOSPHORYLATION (T) 89_8|http://www.cbs.dtu.dk/cgi-bin/proview/webface-link?seqid=P83527&service=NetPhos-2.0",
sf.links.get(0));
assertEquals(89, sf.begin);
assertEquals(89, sf.end);
assertEquals("netphos", sf.featureGroup);
assertEquals("PHOSPHORYLATION (T)", sf.type);
}
/**
* Test parsing a features file with a mix of Jalview and GFF formatted
* content
*
* @throws Exception
*/
@Test(groups = { "Functional" })
public void testParse_mixedJalviewGff() throws Exception
{
File f = new File("examples/uniref50.fa");
AlignmentI al = readAlignmentFile(f);
AlignFrame af = new AlignFrame(al, 500, 500);
Map colours = af.getFeatureRenderer()
.getFeatureColours();
// GFF2 uses space as name/value separator in column 9
String gffData = "METAL\tcc9900\n" + "GFF\n"
+ "FER_CAPAA\tuniprot\tMETAL\t44\t45\t4.0\t.\t.\tNote Iron-sulfur; Note 2Fe-2S\n"
+ "FER1_SOLLC\tuniprot\tPfam\t55\t130\t2.0\t.\t.";
FeaturesFile featuresFile = new FeaturesFile(gffData,
FormatAdapter.PASTE);
assertTrue("Failed to parse features file",
featuresFile.parse(al.getDataset(), colours, true));
// verify colours read or synthesized
colours = af.getFeatureRenderer().getFeatureColours();
assertEquals("1 feature group colours not found", 1, colours.size());
assertEquals(colours.get("METAL").getColour(), new Color(0xcc9900));
// verify feature on FER_CAPAA
SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
.getSequenceFeatures();
assertEquals(1, sfs.length);
SequenceFeature sf = sfs[0];
assertEquals("Iron-sulfur,2Fe-2S", sf.description);
assertEquals(44, sf.begin);
assertEquals(45, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("METAL", sf.type);
assertEquals(4f, sf.getScore(), 0.001f);
// verify feature on FER1_SOLLC
sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
assertEquals(1, sfs.length);
sf = sfs[0];
assertEquals("uniprot", sf.description);
assertEquals(55, sf.begin);
assertEquals(130, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("Pfam", sf.type);
assertEquals(2f, sf.getScore(), 0.001f);
}
public static AlignmentI readAlignmentFile(File f) throws IOException
{
System.out.println("Reading file: " + f);
String ff = f.getPath();
FormatAdapter rf = new FormatAdapter();
AlignmentI al = rf.readFile(ff, FormatAdapter.FILE,
new IdentifyFile().identify(ff, FormatAdapter.FILE));
al.setDataset(null); // creates dataset sequences
assertNotNull("Couldn't read supplied alignment data.", al);
return al;
}
/**
* Test parsing a features file with GFF formatted content only
*
* @throws Exception
*/
@Test(groups = { "Functional" })
public void testParse_pureGff3() throws Exception
{
File f = new File("examples/uniref50.fa");
AlignmentI al = readAlignmentFile(f);
AlignFrame af = new AlignFrame(al, 500, 500);
Map colours = af.getFeatureRenderer()
.getFeatureColours();
// GFF3 uses '=' separator for name/value pairs in colum 9
String gffData = "##gff-version 3\n"
+ "FER_CAPAA\tuniprot\tMETAL\t39\t39\t0.0\t.\t.\t"
+ "Note=Iron-sulfur (2Fe-2S);Note=another note;evidence=ECO:0000255|PROSITE-ProRule:PRU00465\n"
+ "FER1_SOLLC\tuniprot\tPfam\t55\t130\t3.0\t.\t.\tID=$23";
FeaturesFile featuresFile = new FeaturesFile(gffData,
FormatAdapter.PASTE);
assertTrue("Failed to parse features file",
featuresFile.parse(al.getDataset(), colours, true));
// verify feature on FER_CAPAA
SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
.getSequenceFeatures();
assertEquals(1, sfs.length);
SequenceFeature sf = sfs[0];
// description parsed from Note attribute
assertEquals("Iron-sulfur (2Fe-2S),another note", sf.description);
assertEquals(39, sf.begin);
assertEquals(39, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("METAL", sf.type);
assertEquals(
"Note=Iron-sulfur (2Fe-2S);Note=another note;evidence=ECO:0000255|PROSITE-ProRule:PRU00465",
sf.getValue("ATTRIBUTES"));
// verify feature on FER1_SOLLC1
sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
assertEquals(1, sfs.length);
sf = sfs[0];
// ID used for description if available
assertEquals("$23", sf.description);
assertEquals(55, sf.begin);
assertEquals(130, sf.end);
assertEquals("uniprot", sf.featureGroup);
assertEquals("Pfam", sf.type);
assertEquals(3f, sf.getScore(), 0.001f);
}
/**
* Test parsing a features file with Jalview format features (but no colour
* descriptors or startgroup to give the hint not to parse as GFF)
*
* @throws Exception
*/
@Test(groups = { "Functional" })
public void testParse_jalviewFeaturesOnly() throws Exception
{
File f = new File("examples/uniref50.fa");
AlignmentI al = readAlignmentFile(f);
AlignFrame af = new AlignFrame(al, 500, 500);
Map colours = af.getFeatureRenderer()
.getFeatureColours();
/*
* one feature on FER_CAPAA and one on sequence 3 (index 2) FER1_SOLLC
*/
String featureData = "Iron-sulfur (2Fe-2S)\tFER_CAPAA\t-1\t39\t39\tMETAL\n"
+ "Iron-phosphorus (2Fe-P)\tID_NOT_SPECIFIED\t2\t86\t87\tMETALLIC\n";
FeaturesFile featuresFile = new FeaturesFile(featureData,
FormatAdapter.PASTE);
assertTrue("Failed to parse features file",
featuresFile.parse(al.getDataset(), colours, true));
// verify FER_CAPAA feature
SequenceFeature[] sfs = al.getSequenceAt(0).getDatasetSequence()
.getSequenceFeatures();
assertEquals(1, sfs.length);
SequenceFeature sf = sfs[0];
assertEquals("Iron-sulfur (2Fe-2S)", sf.description);
assertEquals(39, sf.begin);
assertEquals(39, sf.end);
assertEquals("METAL", sf.type);
// verify FER1_SOLLC feature
sfs = al.getSequenceAt(2).getDatasetSequence().getSequenceFeatures();
assertEquals(1, sfs.length);
sf = sfs[0];
assertEquals("Iron-phosphorus (2Fe-P)", sf.description);
assertEquals(86, sf.begin);
assertEquals(87, sf.end);
assertEquals("METALLIC", sf.type);
}
private void checkDatasetfromSimpleGff3(AlignmentI dataset)
{
assertEquals("no sequences extracted from GFF3 file", 2,
dataset.getHeight());
SequenceI seq1 = dataset.findName("seq1");
SequenceI seq2 = dataset.findName("seq2");
assertNotNull(seq1);
assertNotNull(seq2);
assertFalse(
"Failed to replace dummy seq1 with real sequence",
seq1 instanceof SequenceDummy
&& ((SequenceDummy) seq1).isDummy());
assertFalse(
"Failed to replace dummy seq2 with real sequence",
seq2 instanceof SequenceDummy
&& ((SequenceDummy) seq2).isDummy());
String placeholderseq = new SequenceDummy("foo").getSequenceAsString();
assertFalse("dummy replacement buggy for seq1",
placeholderseq.equals(seq1.getSequenceAsString()));
assertFalse("dummy replacement buggy for seq2",
placeholderseq.equals(seq2.getSequenceAsString()));
assertNotNull("No features added to seq1", seq1.getSequenceFeatures());
assertEquals("Wrong number of features", 3,
seq1.getSequenceFeatures().length);
assertNull(seq2.getSequenceFeatures());
assertEquals(
"Wrong number of features",
0,
seq2.getSequenceFeatures() == null ? 0 : seq2
.getSequenceFeatures().length);
assertTrue(
"Expected at least one CDNA/Protein mapping for seq1",
dataset.getCodonFrame(seq1) != null
&& dataset.getCodonFrame(seq1).size() > 0);
}
@Test(groups = { "Functional" })
public void readGff3File() throws IOException
{
FeaturesFile gffreader = new FeaturesFile(true, simpleGffFile,
FormatAdapter.FILE);
Alignment dataset = new Alignment(gffreader.getSeqsAsArray());
gffreader.addProperties(dataset);
checkDatasetfromSimpleGff3(dataset);
}
@Test(groups = { "Functional" })
public void simpleGff3FileClass() throws IOException
{
AlignmentI dataset = new Alignment(new SequenceI[] {});
FeaturesFile ffile = new FeaturesFile(simpleGffFile,
FormatAdapter.FILE);
boolean parseResult = ffile.parse(dataset, null, false, false);
assertTrue("return result should be true", parseResult);
checkDatasetfromSimpleGff3(dataset);
}
@Test(groups = { "Functional" })
public void simpleGff3FileLoader() throws IOException
{
AlignFrame af = new FileLoader(false).LoadFileWaitTillLoaded(
simpleGffFile, FormatAdapter.FILE);
assertTrue(
"Didn't read the alignment into an alignframe from Gff3 File",
af != null);
checkDatasetfromSimpleGff3(af.getViewport().getAlignment());
}
@Test(groups = { "Functional" })
public void simpleGff3RelaxedIdMatching() throws IOException
{
AlignmentI dataset = new Alignment(new SequenceI[] {});
FeaturesFile ffile = new FeaturesFile(simpleGffFile,
FormatAdapter.FILE);
boolean parseResult = ffile.parse(dataset, null, false, true);
assertTrue("return result (relaxedID matching) should be true",
parseResult);
checkDatasetfromSimpleGff3(dataset);
}
@Test(groups = { "Functional" })
public void testPrintJalviewFormat() throws Exception
{
File f = new File("examples/uniref50.fa");
AlignmentI al = readAlignmentFile(f);
AlignFrame af = new AlignFrame(al, 500, 500);
Map colours = af.getFeatureRenderer()
.getFeatureColours();
String features = "METAL\tcc9900\n"
+ "GAMMA-TURN\tred|0,255,255|20.0|95.0|below|66.0\n"
+ "Pfam\tred\n"
+ "STARTGROUP\tuniprot\n"
+ "Iron\tFER_CAPAA\t-1\t39\t39\tMETAL\n"
+ "Turn\tFER_CAPAA\t-1\t36\t38\tGAMMA-TURN\n"
+ "Pfam domainPfam_3_4\tFER_CAPAA\t-1\t20\t20\tPfam\n"
+ "ENDGROUP\tuniprot\n";
FeaturesFile featuresFile = new FeaturesFile(features,
FormatAdapter.PASTE);
featuresFile.parse(al.getDataset(), colours, false);
/*
* first with no features displayed
*/
FeatureRenderer fr = af.alignPanel.getFeatureRenderer();
Map visible = fr
.getDisplayedFeatureCols();
String exported = featuresFile.printJalviewFormat(
al.getSequencesArray(), visible);
String expected = "No Features Visible";
assertEquals(expected, exported);
/*
* set METAL (in uniprot group) and GAMMA-TURN visible, but not Pfam
*/
fr.setVisible("METAL");
fr.setVisible("GAMMA-TURN");
visible = fr.getDisplayedFeatureCols();
exported = featuresFile.printJalviewFormat(al.getSequencesArray(),
visible);
expected = "METAL\tcc9900\n"
+ "GAMMA-TURN\tff0000|00ffff|20.0|95.0|below|66.0\n"
+ "\nSTARTGROUP\tuniprot\n"
+ "Iron\tFER_CAPAA\t-1\t39\t39\tMETAL\t0.0\n"
+ "Turn\tFER_CAPAA\t-1\t36\t38\tGAMMA-TURN\t0.0\n"
+ "ENDGROUP\tuniprot\n";
assertEquals(expected, exported);
/*
* now set Pfam visible
*/
fr.setVisible("Pfam");
visible = fr.getDisplayedFeatureCols();
exported = featuresFile.printJalviewFormat(al.getSequencesArray(),
visible);
/*
* note the order of feature types is uncontrolled - derives from
* FeaturesDisplayed.featuresDisplayed which is a HashSet
*/
expected = "METAL\tcc9900\n"
+ "Pfam\tff0000\n"
+ "GAMMA-TURN\tff0000|00ffff|20.0|95.0|below|66.0\n"
+ "\nSTARTGROUP\tuniprot\n"
+ "Iron\tFER_CAPAA\t-1\t39\t39\tMETAL\t0.0\n"
+ "Turn\tFER_CAPAA\t-1\t36\t38\tGAMMA-TURN\t0.0\n"
+ "Pfam domainPfam_3_4\tFER_CAPAA\t-1\t20\t20\tPfam\t0.0\n"
+ "ENDGROUP\tuniprot\n";
assertEquals(expected, exported);
}
}