Skip to content

Update Handling of Sequence Variants (Part 6): SequenceVariant AreValid #969

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 40 commits into
base: master
Choose a base branch
from
Open

Update Handling of Sequence Variants (Part 6): SequenceVariant AreValid #969

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
40 commits
Select commit Hold shift + click to select a range
d09576c
rename sequence variant description as variant call format
trishorts Oct 22, 2025
acae84e
final unit test
trishorts Oct 22, 2025
ed23e20
undo accidental change of descripton to call format
trishorts Oct 22, 2025
1f5587b
more vcf tests
trishorts Oct 22, 2025
3e96598
comprehensive vcf examples
trishorts Oct 22, 2025
c0e4433
test invalid variant
trishorts Oct 22, 2025
65c8729
add line to proteindbloader
trishorts Oct 22, 2025
302b804
unit tests
trishorts Oct 22, 2025
676a892
chasing updates to variant call format
trishorts Oct 23, 2025
fb1f147
copilot suggestions
trishorts Oct 23, 2025
0c327b8
h
trishorts Oct 23, 2025
c224908
added new paramater location to proteinxmlentry to reference specific…
trishorts Oct 23, 2025
c20aa20
primitive tweaks to SequenceVariation
trishorts Oct 23, 2025
5853a1b
lets see
trishorts Oct 23, 2025
d785580
j
trishorts Oct 24, 2025
71d24a8
expand test AppliedVariants
trishorts Oct 24, 2025
c4bf454
expand test AppliedVariants_AsIBioPolymer
trishorts Oct 24, 2025
39f106b
expand test stop gained
trishorts Oct 24, 2025
6df25ed
three new tests
trishorts Oct 24, 2025
1630c76
expand test stop gained decoys and digestion
trishorts Oct 24, 2025
89d76d3
expand test SequenceVariationIsValid
trishorts Oct 24, 2025
a89da7d
expand TestThatProteinVariantsAreGeneratedDuringRead
trishorts Oct 24, 2025
39ff105
two new tests
trishorts Oct 24, 2025
dc8845d
one more
trishorts Oct 24, 2025
6a06a90
this fucking test
trishorts Oct 24, 2025
829208c
name changeroo
trishorts Oct 24, 2025
691103c
two new vcf constructors in SequenceVariation
trishorts Oct 24, 2025
36cc51b
close
trishorts Oct 24, 2025
20f9f9d
h
trishorts Oct 24, 2025
36d4df2
u
trishorts Oct 24, 2025
4f1c9b0
l
trishorts Oct 24, 2025
d14b841
it fucking works
trishorts Oct 24, 2025
f132f3d
copilot
trishorts Oct 24, 2025
b90d7b3
comments
trishorts Oct 24, 2025
28d8a93
afsd
trishorts Oct 24, 2025
193bd67
unwoops
trishorts Oct 24, 2025
8380b07
f
Oct 25, 2025
15940f0
new variant application constructor with more accurate parameters and…
Oct 25, 2025
942a930
new VariantApplication method with added maxVariantsPerIsoform
Oct 25, 2025
5cac61f
new methods to evaluate validity of sequence variants
Oct 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
330 changes: 276 additions & 54 deletions mzLib/Omics/BioPolymer/SequenceVariation.cs
View file
Open in desktop

Large diffs are not rendered by default.

420 changes: 256 additions & 164 deletions mzLib/Omics/BioPolymer/VariantApplication.cs
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion mzLib/Omics/BioPolymer/VariantCallFormat.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,7 @@ public VariantCallFormat(string description)
Description = description;

// Back-compat: if no real tabs are present but literal "\t" sequences are,
// normalize them to actual tabs for parsing only. Leave Description intact.
// normalize them to actual tabs for parsing only. Leave VariantCallFormatDataString intact.
string parseLine = NormalizeTabsForParsing(description);

// Parse description into VCF fields
Expand Down
6 changes: 3 additions & 3 deletions mzLib/Test/DatabaseTests/TestProteinReader.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,7 @@ public static void XmlTest()
Assert.AreEqual(64, ok[0].SequenceVariations.First().OneBasedEndPosition);
Assert.AreEqual(103 - 64 + 2, ok[1].SequenceVariations.First().OneBasedBeginPosition);
Assert.AreEqual(103 - 64 + 2, ok[1].SequenceVariations.First().OneBasedEndPosition);
Assert.AreNotEqual(ok[0].SequenceVariations.First().Description, ok[1].SequenceVariations.First().Description); //decoys and target variations don't have the same desc.
Assert.AreNotEqual(ok[0].SequenceVariations.First().VariantCallFormatDataString, ok[1].SequenceVariations.First().VariantCallFormatDataString); //decoys and target variations don't have the same desc.
Assert.AreEqual("Homo sapiens", ok[1].Organism);
}

Expand Down Expand Up @@ -420,8 +420,8 @@ public static void TestReverseDecoyXML_WithCustomIdentifier()

foreach (var variant in protein.AppliedSequenceVariations)
{
Assert.That(variant.Description, Does.StartWith("rev"));
Assert.That(variant.Description, Does.Not.StartWith("DECOY"));
Assert.That(variant.VariantCallFormatDataString, Does.StartWith("rev"));
Assert.That(variant.VariantCallFormatDataString, Does.Not.StartWith("DECOY"));
}

foreach (var bond in protein.DisulfideBonds)
Expand Down
8 changes: 4 additions & 4 deletions mzLib/Test/DatabaseTests/TestProteomicsReadWrite.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -504,12 +504,12 @@ public void TestFullProteinReadWrite()
Assert.AreEqual(originalProtein.TruncationProducts.First().OneBasedEndPosition, proteinReadFromXml[0].TruncationProducts.First().OneBasedEndPosition);
Assert.AreEqual(originalProtein.TruncationProducts.First().Type, proteinReadFromXml[0].TruncationProducts.First().Type.Split('(')[0]);

Assert.AreEqual(originalProtein.SequenceVariations.First().Description, proteinReadFromXml[0].SequenceVariations.First().Description);
Assert.AreEqual(originalProtein.SequenceVariations.First().VariantCallFormatDataString, proteinReadFromXml[0].SequenceVariations.First().VariantCallFormatDataString);
Assert.AreEqual(originalProtein.SequenceVariations.First().OneBasedBeginPosition, proteinReadFromXml[0].SequenceVariations.First().OneBasedBeginPosition);
Assert.AreEqual(originalProtein.SequenceVariations.First().OneBasedEndPosition, proteinReadFromXml[0].SequenceVariations.First().OneBasedEndPosition);
Assert.AreEqual(originalProtein.SequenceVariations.First().OriginalSequence, proteinReadFromXml[0].SequenceVariations.First().OriginalSequence);
Assert.AreEqual(originalProtein.SequenceVariations.First().VariantSequence, proteinReadFromXml[0].SequenceVariations.First().VariantSequence);
Assert.AreEqual(originalProtein.SequenceVariations.Last().Description, proteinReadFromXml[0].SequenceVariations.Last().Description);
Assert.AreEqual(originalProtein.SequenceVariations.Last().VariantCallFormatDataString, proteinReadFromXml[0].SequenceVariations.Last().VariantCallFormatDataString);
Assert.AreEqual(originalProtein.SequenceVariations.Last().OneBasedBeginPosition, proteinReadFromXml[0].SequenceVariations.Last().OneBasedBeginPosition);
Assert.AreEqual(originalProtein.SequenceVariations.Last().OneBasedEndPosition, proteinReadFromXml[0].SequenceVariations.Last().OneBasedEndPosition);
Assert.AreEqual(originalProtein.SequenceVariations.Last().OriginalSequence, proteinReadFromXml[0].SequenceVariations.Last().OriginalSequence);
Expand All @@ -534,7 +534,7 @@ public void TestReadWriteSeqVars()
Assert.AreEqual(ok[0].SequenceVariations.Count(), ok2[0].SequenceVariations.Count());
Assert.AreEqual(ok[0].SequenceVariations.First().OneBasedBeginPosition, ok2[0].SequenceVariations.First().OneBasedBeginPosition);
Assert.AreEqual(ok[0].SequenceVariations.First().OneBasedEndPosition, ok2[0].SequenceVariations.First().OneBasedEndPosition);
Assert.AreEqual(ok[0].SequenceVariations.First().Description, ok2[0].SequenceVariations.First().Description);
Assert.AreEqual(ok[0].SequenceVariations.First().VariantCallFormatDataString, ok2[0].SequenceVariations.First().VariantCallFormatDataString);
Assert.AreEqual(ok[0].SequenceVariations.First().OriginalSequence, ok2[0].SequenceVariations.First().OriginalSequence);
Assert.AreEqual(ok[0].SequenceVariations.First().VariantSequence, ok2[0].SequenceVariations.First().VariantSequence);
}
Expand All @@ -557,7 +557,7 @@ public void TestReadWriteSeqVars2()
Assert.AreEqual(ok[0].SequenceVariations.Count(), ok2[0].SequenceVariations.Count());
Assert.AreEqual(ok[0].SequenceVariations.First().OneBasedBeginPosition, ok2[0].SequenceVariations.First().OneBasedBeginPosition);
Assert.AreEqual(ok[0].SequenceVariations.First().OneBasedEndPosition, ok2[0].SequenceVariations.First().OneBasedEndPosition);
Assert.AreEqual(ok[0].SequenceVariations.First().Description, ok2[0].SequenceVariations.First().Description);
Assert.AreEqual(ok[0].SequenceVariations.First().VariantCallFormatDataString, ok2[0].SequenceVariations.First().VariantCallFormatDataString);
Assert.AreEqual(ok[0].SequenceVariations.First().OriginalSequence, ok2[0].SequenceVariations.First().OriginalSequence);
Assert.AreEqual(ok[0].SequenceVariations.First().VariantSequence, ok2[0].SequenceVariations.First().VariantSequence);
}
Expand Down
Loading
Loading