Safe Haskell	Safe-Inferred
Language	Haskell2010

SequenceFormats.VCF

Description

A module to help with parsing VCF files. The VCF format is defined here: https://en.wikipedia.org/wiki/Variant_Call_Format

Synopsis

data VCFheader = VCFheader {
- vcfHeaderComments :: [ByteString]
- vcfSampleNames :: [ByteString]
}
data VCFentry = VCFentry {
- vcfChrom :: Chrom
- vcfPos :: Int
- vcfId :: Maybe ByteString
- vcfRef :: ByteString
- vcfAlt :: [ByteString]
- vcfQual :: Maybe Double
- vcfFilter :: Maybe ByteString
- vcfInfo :: [ByteString]
- vcfGenotypeInfo :: Maybe ([ByteString], [[ByteString]])
}
vcfHeaderParser :: Parser VCFheader
readVCFfromStdIn :: (MonadIO m, MonadThrow m) => m (VCFheader, Producer VCFentry m ())
readVCFfromFile :: MonadSafe m => FilePath -> m (VCFheader, Producer VCFentry m ())
getGenotypes :: MonadThrow m => VCFentry -> m [ByteString]
getDosages :: MonadThrow m => VCFentry -> m [Maybe (Int, Int)]
isTransversionSnp :: ByteString -> [ByteString] -> Bool
vcfToFreqSumEntry :: MonadThrow m => VCFentry -> m FreqSumEntry
isBiallelicSnp :: ByteString -> [ByteString] -> Bool
printVCFtoStdOut :: MonadIO m => VCFheader -> Consumer VCFentry m ()
writeVCFfile :: MonadSafe m => FilePath -> VCFheader -> Consumer VCFentry m ()

Documentation

data VCFheader Source #

A datatype to represent the VCF Header. Most comments are simply parsed as entire lines, but the very last comment line, containing the sample names, is separated out

Constructors

VCFheader
Fields vcfHeaderComments :: [ByteString] A list of containing all comments starting with a single `#` vcfSampleNames :: [ByteString] The list of sample names parsed from the last comment line starting with `##`

Instances

Instances details

Show VCFheader Source #
Instance details Defined in SequenceFormats.VCF Methods showsPrec :: Int -> VCFheader -> ShowS # show :: VCFheader -> String # showList :: [VCFheader] -> ShowS #
Eq VCFheader Source #
Instance details Defined in SequenceFormats.VCF Methods (==) :: VCFheader -> VCFheader -> Bool # (/=) :: VCFheader -> VCFheader -> Bool #

data VCFentry Source #

A Datatype representing a single VCF entry.

Constructors

VCFentry

Fields

vcfChrom :: Chrom
The chromosome
vcfPos :: Int
The position
vcfId :: Maybe ByteString
The SNP ID if non-missing
vcfRef :: ByteString
The reference allele (supports also multi-character alleles for Indels)
vcfAlt :: [ByteString]
The alternative alleles, each one possible of multiple characters
vcfQual :: Maybe Double
The quality value
vcfFilter :: Maybe ByteString
The Filter value, if non-missing.
vcfInfo :: [ByteString]
A list of Info fields
vcfGenotypeInfo :: Maybe ([ByteString], [[ByteString]])
An optional tuple of format tags and genotype format fields for each sample.

Instances

Instances details

Show VCFentry Source #
Instance details Defined in SequenceFormats.VCF Methods showsPrec :: Int -> VCFentry -> ShowS # show :: VCFentry -> String # showList :: [VCFentry] -> ShowS #
Eq VCFentry Source #
Instance details Defined in SequenceFormats.VCF Methods (==) :: VCFentry -> VCFentry -> Bool # (/=) :: VCFentry -> VCFentry -> Bool #
Genomic VCFentry Source #
Instance details Defined in SequenceFormats.Genomic Methods genomicPosition :: VCFentry -> (Chrom, Int) Source # genomicChrom :: VCFentry -> Chrom Source # genomicBase :: VCFentry -> Int Source #

vcfHeaderParser :: Parser VCFheader Source #

readVCFfromStdIn :: (MonadIO m, MonadThrow m) => m (VCFheader, Producer VCFentry m ()) Source #

Reading a VCF from StdIn. Returns a VCFHeader and a Producer over VCFentries.

readVCFfromFile :: MonadSafe m => FilePath -> m (VCFheader, Producer VCFentry m ()) Source #

Reading a VCF from a file. Returns a VCFHeader and a Producer over VCFentries.

getGenotypes :: MonadThrow m => VCFentry -> m [ByteString] Source #

Extracts the genotype fields (for each sapmle) from a VCF entry

getDosages :: MonadThrow m => VCFentry -> m [Maybe (Int, Int)] Source #

Extracts the dosages (the sum of non-reference alleles) and ploidies per sample

isTransversionSnp :: ByteString -> [ByteString] -> Bool Source #

returns True if the SNp is a biallelic Transversion SNP (i.e. one of GT, GC, AT, AC)

vcfToFreqSumEntry :: MonadThrow m => VCFentry -> m FreqSumEntry Source #

Converts a VCFentry to the simpler FreqSum format

isBiallelicSnp :: ByteString -> [ByteString] -> Bool Source #

returns True if the SNP is biallelic.

printVCFtoStdOut :: MonadIO m => VCFheader -> Consumer VCFentry m () Source #

writeVCFfile :: MonadSafe m => FilePath -> VCFheader -> Consumer VCFentry m () Source #