| Safe Haskell | None |
|---|---|
| Language | Haskell2010 |
Bio.Bam.Rec
Description
Parsers and Printers for BAM and SAM. We employ an Iteratee
interface, and we strive to support everything possible in BAM. So
far, the implementation of the nucleotides is somewhat lacking: we
do not have support for ambiguity codes, and the "=" symbol is not
understood.
- data BamRaw
- bamRaw :: FileOffset -> Bytes -> BamRaw
- virt_offset :: BamRaw -> FileOffset
- raw_data :: BamRaw -> Bytes
- data BamRec = BamRec {}
- unpackBam :: BamRaw -> BamRec
- nullBamRec :: BamRec
- getMd :: BamRec -> Maybe [MdOp]
- data Cigar = !CigOp :* !Int
- data CigOp
- alignedLength :: Vector v Cigar => v Cigar -> Int
- newtype Nucleotides = Ns {}
- data Vector_Nucs_half a
- type Extensions = [(BamKey, Ext)]
- data Ext
- extAsInt :: Int -> BamKey -> BamRec -> Int
- extAsString :: BamKey -> BamRec -> Bytes
- setQualFlag :: Char -> BamRec -> BamRec
- deleteE :: BamKey -> Extensions -> Extensions
- insertE :: BamKey -> Ext -> Extensions -> Extensions
- updateE :: BamKey -> Ext -> Extensions -> Extensions
- adjustE :: (Ext -> Ext) -> BamKey -> Extensions -> Extensions
- isPaired :: BamRec -> Bool
- isProperlyPaired :: BamRec -> Bool
- isUnmapped :: BamRec -> Bool
- isMateUnmapped :: BamRec -> Bool
- isReversed :: BamRec -> Bool
- isMateReversed :: BamRec -> Bool
- isFirstMate :: BamRec -> Bool
- isSecondMate :: BamRec -> Bool
- isAuxillary :: BamRec -> Bool
- isFailsQC :: BamRec -> Bool
- isDuplicate :: BamRec -> Bool
- isTrimmed :: BamRec -> Bool
- isMerged :: BamRec -> Bool
- isVestigial :: BamRec -> Bool
- type_mask :: Int
- progressBam :: MonadIO m => String -> Refs -> Int -> (String -> IO ()) -> Enumeratee [BamRaw] [BamRaw] m a
- data Word32 :: *
Documentation
Bam record in its native encoding along with virtual address.
bamRaw :: FileOffset -> Bytes -> BamRaw Source #
Smart constructor. Makes sure we got a at least a full record.
virt_offset :: BamRaw -> FileOffset Source #
internal representation of a BAM record
Constructors
| BamRec | |
Fields | |
nullBamRec :: BamRec Source #
Cigar line in BAM coding Bam encodes an operation and a length into a single integer, we keep those integers in an array.
alignedLength :: Vector v Cigar => v Cigar -> Int Source #
extracts the aligned length from a cigar line This gives the length of an alignment as measured on the reference, which is different from the length on the query or the length of the alignment.
newtype Nucleotides Source #
A nucleotide base in an alignment. Experience says we're dealing with Ns and gaps all the type, so purity be damned, they are included as if they were real bases.
To allow Nucleotidess to be unpacked and incorporated into
containers, we choose to represent them the same way as the BAM file
format: as a 4 bit wide field. Gaps are encoded as 0 where they
make sense, N is 15. The contained Word8 is guaranteed to be
0..15.
Instances
data Vector_Nucs_half a Source #
A vector that packs two Nucleotides into one byte, just like Bam does.
Instances
type Extensions = [(BamKey, Ext)] Source #
A collection of extension fields. The key is actually only two Chars, but that proved impractical.
(Hmm... we could introduce a Key type that is a 16 bit int, then give
it an instance IsString... practical?)
deleteE :: BamKey -> Extensions -> Extensions Source #
Deletes all occurences of some extension field.
insertE :: BamKey -> Ext -> Extensions -> Extensions Source #
Blindly inserts an extension field. This can create duplicates (and there is no telling how other tools react to that).
updateE :: BamKey -> Ext -> Extensions -> Extensions Source #
Deletes all occurences of an extension field, then inserts it with
a new value. This is safer than insertE, but also more expensive.
adjustE :: (Ext -> Ext) -> BamKey -> Extensions -> Extensions Source #
Adjusts a named extension by applying a function.
isProperlyPaired :: BamRec -> Bool Source #
isUnmapped :: BamRec -> Bool Source #
isMateUnmapped :: BamRec -> Bool Source #
isReversed :: BamRec -> Bool Source #
isMateReversed :: BamRec -> Bool Source #
isFirstMate :: BamRec -> Bool Source #
isSecondMate :: BamRec -> Bool Source #
isAuxillary :: BamRec -> Bool Source #
isDuplicate :: BamRec -> Bool Source #
isVestigial :: BamRec -> Bool Source #
progressBam :: MonadIO m => String -> Refs -> Int -> (String -> IO ()) -> Enumeratee [BamRaw] [BamRaw] m a Source #
A simple progress indicator that prints sequence id and position.
32-bit unsigned integer type
Instances