Safe Haskell	Safe-Inferred
Language	Haskell2010

Bio.TwoBit.Tool

Synopsis

data EncodeProgress
- = EncodeProgress {
  - ep_seqname :: !ShortByteString
  - ep_position :: !Word32
  - ep_hardmasked :: !Word32
  - ep_softmasked :: !Word32
  - ep_enclength :: !Int64
  - ep_tail :: EncodeProgress
  }
- | Encoded Builder
buildFasta :: Int -> [Word8] -> Builder
faToTwoBit :: ByteString -> EncodeProgress
formatCdna :: TwoBitFile -> Cdna -> Builder
parseAnno :: String -> ByteString -> [Either GffError Cdna]
twoBitToFa :: Int -> TwoBitSequence' dir -> IO ()
vcfToTwoBit :: [ByteString] -> EncodeProgress

Documentation

data EncodeProgress Source #

Constructors

EncodeProgress
Fields ep_seqname :: !ShortByteString ep_position :: !Word32 ep_hardmasked :: !Word32 ep_softmasked :: !Word32 ep_enclength :: !Int64 ep_tail :: EncodeProgress
Encoded Builder

buildFasta :: Int -> [Word8] -> Builder Source #

faToTwoBit :: ByteString -> EncodeProgress Source #

formatCdna :: TwoBitFile -> Cdna -> Builder Source #

parseAnno :: String -> ByteString -> [Either GffError Cdna] Source #

Parses annotations in GFF format. We want to turn an annotation and a 2bit file into a FastA of the transcriptome (one sequence per annotated transcript), that looks like the stuff Lior Pachter feeds into Kallisto. Annotations come in two dialects of GFF, either GFF3 or GTF. We autodetect and understand both.

twoBitToFa :: Int -> TwoBitSequence' dir -> IO () Source #

vcfToTwoBit :: [ByteString] -> EncodeProgress Source #

Extracts the reference from a VCF. This assumes the presence of at least one record per site. The VCF must be sorted by position. When writing out, we try to match the order of the contigs as listed in the header. Unlisted contigs follow at the end with their order preserved; contigs without data are not written at all.