Safe Haskell	None
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 :: [String]
- vcfSampleNames :: [String]
}
data VCFentry = VCFentry {
- vcfChrom :: Chrom
- vcfPos :: Int
- vcfId :: Maybe ByteString
- vcfRef :: ByteString
- vcfAlt :: [ByteString]
- vcfQual :: Double
- vcfFilter :: Maybe ByteString
- vcfInfo :: [ByteString]
- vcfFormatString :: [ByteString]
- vcfGenotypeInfo :: [[ByteString]]
}
readVCFfromStdIn :: (MonadIO m, MonadThrow m) => m (VCFheader, Producer VCFentry m ())
readVCFfromFile :: MonadSafe m => FilePath -> m (VCFheader, Producer VCFentry m ())
readVCFfromProd :: MonadThrow m => Producer ByteString m () -> m (VCFheader, Producer VCFentry m ())
getGenotypes :: VCFentry -> Either String [ByteString]
getDosages :: VCFentry -> Either String [Maybe Int]
isTransversionSnp :: ByteString -> [ByteString] -> Bool
vcfToFreqSumEntry :: VCFentry -> Either String FreqSumEntry
isBiallelicSnp :: ByteString -> [ByteString] -> Bool

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 :: [String] A list of containing all comments starting with a single `#` vcfSampleNames :: [String] 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 #

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 :: Double
The quality value
vcfFilter :: Maybe ByteString
The Filter value, if non-missing.
vcfInfo :: [ByteString]
A list of Info fields
vcfFormatString :: [ByteString]
A list of format tags
vcfGenotypeInfo :: [[ByteString]]
A list of format fields for each sample.

Instances

Instances details

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

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.

readVCFfromProd :: MonadThrow m => Producer ByteString m () -> m (VCFheader, Producer VCFentry m ()) Source #

reads a VCFheader and VCFentries from a text producer.

getGenotypes :: VCFentry -> Either String [ByteString] Source #

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

getDosages :: VCFentry -> Either String [Maybe Int] Source #

Extracts the dosages (the sum of non-reference alleles) per sample (returns a Left Error if it fails.)

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

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

vcfToFreqSumEntry :: VCFentry -> Either String FreqSumEntry Source #

Converts a VCFentry to the simpler FreqSum format (returns a Left Error if it fails.)

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

returns True if the SNP is biallelic.