*/
package jalview.io;
+import static org.testng.Assert.assertTrue;
import static org.testng.AssertJUnit.assertEquals;
import static org.testng.AssertJUnit.assertNotNull;
import static org.testng.AssertJUnit.assertTrue;
import static org.testng.AssertJUnit.fail;
-import jalview.datamodel.AlignmentAnnotation;
-import jalview.datamodel.AlignmentI;
-import jalview.datamodel.Annotation;
-import jalview.datamodel.SequenceFeature;
-import jalview.datamodel.SequenceI;
-import jalview.gui.JvOptionPane;
-
import java.io.File;
import java.util.Arrays;
import java.util.BitSet;
import org.testng.annotations.BeforeClass;
import org.testng.annotations.Test;
+import jalview.datamodel.Alignment;
+import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.Annotation;
+import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
+import jalview.gui.JvOptionPane;
+import jalview.util.DBRefUtils;
+
public class StockholmFileTest
{
}
/**
+ * JAL-3529 - verify uniprot refs for sequences are output for sequences
+ * retrieved via Pfam
+ */
+ @Test(groups = { "Functional" })
+ public void dbrefOutput() throws Exception
+ {
+ // sequences retrieved in a Pfam domain alignment also have a PFAM database
+ // reference
+ SequenceI sq = new Sequence("FER2_SPIOL", "AASSDDDFFF");
+ sq.addDBRef(new DBRefEntry("UNIPROT", "1", "P00224"));
+ sq.addDBRef(new DBRefEntry("PFAM", "1", "P00224.1"));
+ sq.addDBRef(new DBRefEntry("PFAM", "1", "PF00111"));
+ AppletFormatAdapter af = new AppletFormatAdapter();
+ String toStockholm = af.formatSequences(FileFormat.Stockholm,
+ new Alignment(new SequenceI[]
+ { sq }), false);
+ System.out.println(toStockholm);
+ // bleh - java.util.Regex sucks
+ assertTrue(
+ Pattern.compile(
+ "^#=GS\\s+FER2_SPIOL(/\\d+-\\d+)?\\s+AC\\s+P00224$",
+ Pattern.MULTILINE).matcher(toStockholm).find(),
+ "Couldn't locate UNIPROT Accession in generated Stockholm file.");
+ AlignmentI fromStockholm = af.readFile(toStockholm,
+ DataSourceType.PASTE, FileFormat.Stockholm);
+ SequenceI importedSeq = fromStockholm.getSequenceAt(0);
+ assertTrue(importedSeq.getDBRefs().size() == 1,
+ "Expected just one database reference to be added to sequence.");
+ assertTrue(
+ importedSeq.getDBRefs().get(0).getAccessionId()
+ .indexOf(" ") == -1,
+ "Spaces were found in accession ID.");
+ List<DBRefEntry> dbrefs = DBRefUtils.searchRefs(importedSeq.getDBRefs(),
+ "P00224");
+ assertTrue(dbrefs.size() == 1,
+ "Couldn't find Uniprot DBRef on re-imported sequence.");
+
+ }
+
+ @Test(groups = { "Functional" })
+ public void descriptionLineOutput() throws Exception
+ {
+ // quick test that sequence description is exported & reimported
+
+ SequenceI sq = new Sequence("FER2_SPIOL", "AASSDDDFFF");
+ String expected_descr = "This is a description !@&^%@£@";
+ sq.setDescription(expected_descr);
+ AppletFormatAdapter af = new AppletFormatAdapter();
+ String toStockholm = af.formatSequences(FileFormat.Stockholm,
+ new Alignment(new SequenceI[]
+ { sq }), false);
+ System.out.println(toStockholm);
+
+ // bleh - java.util.Regex sucks
+ assertTrue(toStockholm.contains(expected_descr),
+ "Couldn't locate expected description srting in generated Stockholm file.");
+
+ AlignmentI fromStockholm = af.readFile(toStockholm,
+ DataSourceType.PASTE, FileFormat.Stockholm);
+ SequenceI importedSeq = fromStockholm.getSequenceAt(0);
+ assertEquals("Description did not get reimported.", expected_descr,
+ importedSeq.getDescription());
+ }
+
+ /**
* test alignment data in given file can be imported, exported and reimported
* with no dataloss
*
al.getSequenceAt(i).createDatasetSequence();
}
String outputfile = rf.formatSequences(ioformat, al, true);
- System.out.println("Output file in '" + ioformat + "':\n"
- + outputfile + "\n<<EOF\n");
+ System.out.println("Output file in '" + ioformat + "':\n" + outputfile
+ + "\n<<EOF\n");
// test for consistency in io
AlignmentI al_input = new AppletFormatAdapter().readFile(outputfile,
DataSourceType.PASTE, ioformat);
assertTrue(
"Number of sequence associated annotations wasn't at least "
- + nminseqann, numsqswithali >= nminseqann);
+ + nminseqann,
+ numsqswithali >= nminseqann);
} catch (Exception e)
{
assertNotNull("Original alignment was null", al);
assertNotNull("Generated alignment was null", al_input);
- assertTrue("Alignment dimension mismatch: original: " + al.getHeight()
- + "x" + al.getWidth() + ", generated: " + al_input.getHeight()
- + "x" + al_input.getWidth(),
+ assertTrue(
+ "Alignment dimension mismatch: original: " + al.getHeight()
+ + "x" + al.getWidth() + ", generated: "
+ + al_input.getHeight() + "x" + al_input.getWidth(),
al.getHeight() == al_input.getHeight()
&& al.getWidth() == al_input.getWidth());
// check Alignment annotation
AlignmentAnnotation[] aa_new = al_input.getAlignmentAnnotation();
AlignmentAnnotation[] aa_original = al.getAlignmentAnnotation();
+ boolean expectProteinSS = !al.isNucleotide();
+ assertTrue(
+ "Alignments not both "
+ + (al.isNucleotide() ? "nucleotide" : "protein"),
+ al_input.isNucleotide() == al.isNucleotide());
// note - at moment we do not distinguish between alignment without any
// annotation rows and alignment with no annotation row vector
assertEqualSecondaryStructure(
"Different alignment annotation at position " + i,
aa_original[i], aa_new[i], allowNullAnnotation);
+ if (aa_original[i].hasIcons)
+ {
+ assertTrue(
+ "Secondary structure expected to be "
+ + (expectProteinSS ? "protein" : "nucleotide"),
+ expectProteinSS == !aa_original[i].isRNA());
+ }
// compare graphGroup or graph properties - needed to verify JAL-1299
assertEquals("Graph type not identical.", aa_original[i].graph,
aa_new[i].graph);
if (!ignoreRowVisibility)
{
assertEquals("Visibility not identical.",
- aa_original[i].visible,
- aa_new[i].visible);
+ aa_original[i].visible, aa_new[i].visible);
}
assertEquals("Threshold line not identical.",
aa_original[i].threshold, aa_new[i].threshold);
// graphGroup may differ, but pattern should be the same
- Integer o_ggrp = new Integer(aa_original[i].graphGroup + 2);
- Integer n_ggrp = new Integer(aa_new[i].graphGroup + 2);
+ Integer o_ggrp = Integer.valueOf(aa_original[i].graphGroup + 2);
+ Integer n_ggrp = Integer.valueOf(aa_new[i].graphGroup + 2);
BitSet orig_g = orig_groups.get(o_ggrp);
BitSet new_g = new_groups.get(n_ggrp);
if (orig_g == null)
// check sequences, annotation and features
SequenceI[] seq_original = new SequenceI[al.getSequencesArray().length];
seq_original = al.getSequencesArray();
- SequenceI[] seq_new = new SequenceI[al_input.getSequencesArray().length];
+ SequenceI[] seq_new = new SequenceI[al_input
+ .getSequencesArray().length];
seq_new = al_input.getSequencesArray();
List<SequenceFeature> sequenceFeatures_original;
List<SequenceFeature> sequenceFeatures_new;
String name = seq_original[i].getName();
int start = seq_original[i].getStart();
int end = seq_original[i].getEnd();
- System.out.println("Check sequence: " + name + "/" + start + "-"
- + end);
+ System.out
+ .println("Check sequence: " + name + "/" + start + "-" + end);
// search equal sequence
for (int in = 0; in < al_input.getSequencesArray().length; in++)
"Sequence Features were not equivalent"
+ (ignoreFeatures ? " ignoring." : ""),
ignoreFeatures
- || (seq_original[i].getSequenceFeatures() == null && seq_new[in]
- .getSequenceFeatures() == null)
- || (seq_original[i].getSequenceFeatures() != null && seq_new[in]
- .getSequenceFeatures() != null));
+ || (seq_original[i].getSequenceFeatures() == null
+ && seq_new[in]
+ .getSequenceFeatures() == null)
+ || (seq_original[i].getSequenceFeatures() != null
+ && seq_new[in]
+ .getSequenceFeatures() != null));
// compare sequence features
if (seq_original[i].getSequenceFeatures() != null
&& seq_new[in].getSequenceFeatures() != null)
.getSequenceFeatures();
sequenceFeatures_new = seq_new[in].getSequenceFeatures();
- assertEquals("different number of features", seq_original[i]
- .getSequenceFeatures().size(), seq_new[in]
- .getSequenceFeatures().size());
+ assertEquals("different number of features",
+ seq_original[i].getSequenceFeatures().size(),
+ seq_new[in].getSequenceFeatures().size());
for (int feat = 0; feat < seq_original[i].getSequenceFeatures()
.size(); feat++)
if (al.getSequenceAt(i).getAnnotation() != null
&& al_input.getSequenceAt(in).getAnnotation() != null)
{
- for (int j = 0; j < al.getSequenceAt(i).getAnnotation().length; j++)
+ for (int j = 0; j < al.getSequenceAt(i)
+ .getAnnotation().length; j++)
{
- if (al.getSequenceAt(i).getAnnotation()[j] != null
- && al_input.getSequenceAt(in).getAnnotation()[j] != null)
+ if (al.getSequenceAt(i).getAnnotation()[j] != null && al_input
+ .getSequenceAt(in).getAnnotation()[j] != null)
{
annot_original = al.getSequenceAt(i).getAnnotation()[j];
annot_new = al_input.getSequenceAt(in).getAnnotation()[j];
+ annot_new.annotations.length);
}
boolean isRna = annot_or.isRNA();
- assertTrue("Expected " + (isRna ? " valid RNA " : " no RNA ")
- + " secondary structure in the row.",
+ assertTrue(
+ "Expected " + (isRna ? " valid RNA " : " no RNA ")
+ + " secondary structure in the row.",
isRna == annot_new.isRNA());
for (int i = 0; i < annot_or.annotations.length; i++)
{
- Annotation an_or = annot_or.annotations[i], an_new = annot_new.annotations[i];
+ Annotation an_or = annot_or.annotations[i],
+ an_new = annot_new.annotations[i];
if (an_or != null && an_new != null)
{
{
if (an_or.secondaryStructure != an_new.secondaryStructure
|| ((Float.isNaN(an_or.value) != Float
- .isNaN(an_new.value)) || an_or.value != an_new.value))
+ .isNaN(an_new.value))
+ || an_or.value != an_new.value))
{
fail("Different RNA secondary structure at column " + i
+ " expected: [" + annot_or.annotations[i].toString()
{
// not RNA secondary structure, so expect all elements to match...
if ((an_or.isWhitespace() != an_new.isWhitespace())
- || !an_or.displayCharacter.trim().equals(
- an_new.displayCharacter.trim())
- || !("" + an_or.secondaryStructure).trim().equals(
- ("" + an_new.secondaryStructure).trim())
- || (an_or.description != an_new.description && !((an_or.description == null && an_new.description
- .trim().length() == 0)
- || (an_new.description == null && an_or.description
- .trim().length() == 0) || an_or.description
- .trim().equals(an_new.description.trim())))
- || !((Float.isNaN(an_or.value) && Float
- .isNaN(an_new.value)) || an_or.value == an_new.value))
+ || !an_or.displayCharacter.trim()
+ .equals(an_new.displayCharacter.trim())
+ || !("" + an_or.secondaryStructure).trim()
+ .equals(("" + an_new.secondaryStructure).trim())
+ || (an_or.description != an_new.description
+ && !((an_or.description == null
+ && an_new.description.trim()
+ .length() == 0)
+ || (an_new.description == null
+ && an_or.description.trim()
+ .length() == 0)
+ || an_or.description.trim().equals(
+ an_new.description.trim())))
+ || !((Float.isNaN(an_or.value)
+ && Float.isNaN(an_new.value))
+ || an_or.value == an_new.value))
{
fail("Annotation Element Mismatch\nElement " + i
+ " in original: " + annot_or.annotations[i].toString()
}
if (!thrown)
{
- fail("Expected difference for [" + an_orig + "] and [" + an_new + "]");
+ fail("Expected difference for [" + an_orig + "] and [" + an_new
+ + "]");
}
}
+
private AlignmentAnnotation makeAnnot(Annotation ae)
{
- return new AlignmentAnnotation("label", "description", new Annotation[]
- { ae });
+ return new AlignmentAnnotation("label", "description",
+ new Annotation[]
+ { ae });
}
- @Test(groups={"Functional"})
+ @Test(groups = { "Functional" })
public void testAnnotationEquivalence()
{
AlignmentAnnotation one = makeAnnot(new Annotation("", "", ' ', 1));
- AlignmentAnnotation anotherOne = makeAnnot(new Annotation("", "", ' ',
- 1));
- AlignmentAnnotation sheet = makeAnnot(new Annotation("","",'E',0f));
- AlignmentAnnotation anotherSheet = makeAnnot(new Annotation("","",'E',0f));
- AlignmentAnnotation sheetWithLabel = makeAnnot(new Annotation("1", "",
- 'E', 0f));
- AlignmentAnnotation anotherSheetWithLabel = makeAnnot(new Annotation(
- "1", "", 'E', 0f));
- AlignmentAnnotation rnaNoDC = makeAnnot(new Annotation("","",'<',0f));
- AlignmentAnnotation anotherRnaNoDC = makeAnnot(new Annotation("","",'<',0f));
- AlignmentAnnotation rnaWithDC = makeAnnot(new Annotation("B", "", '<',
- 0f));
- AlignmentAnnotation anotherRnaWithDC = makeAnnot(new Annotation("B",
- "", '<', 0f));
-
+ AlignmentAnnotation anotherOne = makeAnnot(
+ new Annotation("", "", ' ', 1));
+ AlignmentAnnotation sheet = makeAnnot(new Annotation("", "", 'E', 0f));
+ AlignmentAnnotation anotherSheet = makeAnnot(
+ new Annotation("", "", 'E', 0f));
+ AlignmentAnnotation sheetWithLabel = makeAnnot(
+ new Annotation("1", "", 'E', 0f));
+ AlignmentAnnotation anotherSheetWithLabel = makeAnnot(
+ new Annotation("1", "", 'E', 0f));
+ AlignmentAnnotation rnaNoDC = makeAnnot(
+ new Annotation("", "", '<', 0f));
+ AlignmentAnnotation anotherRnaNoDC = makeAnnot(
+ new Annotation("", "", '<', 0f));
+ AlignmentAnnotation rnaWithDC = makeAnnot(
+ new Annotation("B", "", '<', 0f));
+ AlignmentAnnotation anotherRnaWithDC = makeAnnot(
+ new Annotation("B", "", '<', 0f));
+
// check self equivalence
for (boolean allowNull : new boolean[] { true, false })
{
if (p != q)
{
assertNotEqualSecondaryStructure("Should be different",
- aaSet.get(p), aaSet.get(q), false);
+ aaSet.get(p), aaSet.get(q), false);
}
else
{
}
String aliFile = ">Dm\nAAACCCUUUUACACACGGGAAAGGG";
+
String annFile = "JALVIEW_ANNOTATION\n# Created: Thu May 04 11:16:52 BST 2017\n\n"
+ "SEQUENCE_REF\tDm\nNO_GRAPH\tsecondary structure\tsecondary structure\t"
+ "(|(|(|(|, .|, .|, .|, .|)|)|)|)|\t0.0\nROWPROPERTIES\t"
+ "SEQUENCE_REF\tDm\nNO_GRAPH\tsecondary structure\tsecondary structure\t"
+ "(|(|(|(||{|{||{|{||)|)|)|)||}|}|}|}|\t0.0\nROWPROPERTIES\t"
+ "secondary structure\tscaletofit=true\tshowalllabs=true\tcentrelabs=false";
+
String annFileFullWuss = "JALVIEW_ANNOTATION\n# Created: Thu May 04 11:16:52 BST 2017\n\n"
+ "SEQUENCE_REF\tDm\nNO_GRAPH\tsecondary structure\tsecondary structure\t"
+ "(|(|(|(||{|{||[|[||)|)|)|)||}|}|]|]|\t0.0\nROWPROPERTIES\t"
"Shouldn't recognise '" + ch + "' as a WUSS bracket");
}
}
+
private static void roundTripSSForRNA(String aliFile, String annFile)
throws Exception
{
// this is the single sequence alignment and the SS annotations equivalent to
// the ones in file RnaSSTestFile
- String aliFileRnaSS = ">Test.sequence/1-14\n"
- + "GUACAAAAAAAAAA";
+ String aliFileRnaSS = ">Test.sequence/1-14\n" + "GUACAAAAAAAAAA";
+
String annFileRnaSSAlphaChars = "JALVIEW_ANNOTATION\n"
+ "# Created: Thu Aug 02 14:54:57 BST 2018\n" + "\n"
+ "NO_GRAPH\tSecondary Structure\tSecondary Structure\t<,<|(,(|E,E|H,H|B,B|h,h|e,e|b,b|(,(|E,E|),)|e,e|),)|>,>|\t2.0\n"
+ "\n"
+ "ROWPROPERTIES\tSecondary Structure\tscaletofit=true\tshowalllabs=true\tcentrelabs=false\n"
+ "\n" + "\n" + "ALIGNMENT\tID=RNA.SS.TEST\tTP=RNA;";
+
String wrongAnnFileRnaSSAlphaChars = "JALVIEW_ANNOTATION\n"
+ "# Created: Thu Aug 02 14:54:57 BST 2018\n" + "\n"
+ "NO_GRAPH\tSecondary Structure\tSecondary Structure\t<,<|(,(|H,H|E,E|B,B|h,h|e,e|b,b|(,(|E,E|),)|e,e|),)|>,>|\t2.0\n"
+ "\n"
+ "ROWPROPERTIES\tSecondary Structure\tscaletofit=true\tshowalllabs=true\tcentrelabs=false\n"
+ "\n" + "\n" + "ALIGNMENT\tID=RNA.SS.TEST\tTP=RNA;";
+
@Test(groups = { "Functional" })
public void stockholmFileRnaSSAlphaChars() throws Exception
{
}
char[] shouldBe = { '<', '(', 'E', 'H', 'B', 'h', 'e', 'b', '(', 'E',
')', 'e', ')', '>' };
- Assert.assertTrue(
- Arrays.equals(As, shouldBe),
- "Annotation is " + new String(As) + " but should be "
- + new String(shouldBe));
+ Assert.assertTrue(Arrays.equals(As, shouldBe), "Annotation is "
+ + new String(As) + " but should be " + new String(shouldBe));
// this should result in the same RNA SS Annotations
- AlignmentI newAl = new AppletFormatAdapter().readFile(
- aliFileRnaSS,
+ AlignmentI newAl = new AppletFormatAdapter().readFile(aliFileRnaSS,
DataSourceType.PASTE, jalview.io.FileFormat.Fasta);
AnnotationFile aaf = new AnnotationFile();
aaf.readAnnotationFile(newAl, annFileRnaSSAlphaChars,
+ "RNA SS A 2:" + newAl.getAlignmentAnnotation()[0]);
// this should NOT result in the same RNA SS Annotations
- newAl = new AppletFormatAdapter().readFile(
- aliFileRnaSS, DataSourceType.PASTE,
- jalview.io.FileFormat.Fasta);
+ newAl = new AppletFormatAdapter().readFile(aliFileRnaSS,
+ DataSourceType.PASTE, jalview.io.FileFormat.Fasta);
aaf = new AnnotationFile();
aaf.readAnnotationFile(newAl, wrongAnnFileRnaSSAlphaChars,
DataSourceType.PASTE);
- boolean mismatch = testRnaSSAnnotationsEquivalent(al.getAlignmentAnnotation()[0],
+ boolean mismatch = testRnaSSAnnotationsEquivalent(
+ al.getAlignmentAnnotation()[0],
newAl.getAlignmentAnnotation()[0]);
Assert.assertFalse(mismatch,
"RNA SS Annotations SHOULD NOT be pair-wise equivalent (but apparently are): \n"
}
private static boolean testRnaSSAnnotationsEquivalent(
- AlignmentAnnotation a1,
- AlignmentAnnotation a2)
+ AlignmentAnnotation a1, AlignmentAnnotation a2)
{
return a1.rnaSecondaryStructureEquivalent(a2);
}
+ "\n"
+ "ROWPROPERTIES\tSecondary Structure\tscaletofit=true\tshowalllabs=true\tcentrelabs=false\n"
+ "\n" + "\n" + "ALIGNMENT\tID=RNA.SS.TEST\tTP=RNA;";
+
String annFileRnaSSWithoutSpaceChars = "JALVIEW_ANNOTATION\n"
+ "# Created: Thu Aug 02 14:54:57 BST 2018\n" + "\n"
+ "NO_GRAPH\tSecondary Structure\tSecondary Structure\t<,<|.,.|H,H|.,.|B,B|h,h|.,.|b,b|(,(|E,E|.,.|e,e|),)|>,>|\t2.0\n"
jalview.io.FileFormat.Fasta);
AnnotationFile afWithoutSpaces = new AnnotationFile();
afWithoutSpaces.readAnnotationFile(alWithoutSpaces,
- annFileRnaSSWithoutSpaceChars,
- DataSourceType.PASTE);
+ annFileRnaSSWithoutSpaceChars, DataSourceType.PASTE);
Assert.assertTrue(
testRnaSSAnnotationsEquivalent(
jalview.io.FileFormat.Fasta);
AnnotationFile wrongAfWithoutSpaces = new AnnotationFile();
wrongAfWithoutSpaces.readAnnotationFile(wrongAlWithoutSpaces,
- wrongAnnFileRnaSSWithoutSpaceChars,
- DataSourceType.PASTE);
+ wrongAnnFileRnaSSWithoutSpaceChars, DataSourceType.PASTE);
Assert.assertFalse(
testRnaSSAnnotationsEquivalent(