biocore (empty) → 0.1

raw patch · 5 files changed

+120/−0 lines, 5 filesdep +basedep +bytestringsetup-changed

Dependencies added: base, bytestring

Files

• Setup.hs +2/−0
• biocore.cabal +24/−0
• src/Bio/Core.hs +7/−0
• src/Bio/Core/Sequence.hs +81/−0
• src/Bio/Core/Strand.hs +6/−0

@@ -0,0 +1,2 @@+import Distribution.Simple+main = defaultMain

@@ -0,0 +1,24 @@+Name:      biocore+Version:   0.1+License:   LGPL++Cabal-Version:       >= 1.6+Author:              Ketil Malde+Maintainer:          ketil@malde.org++Category:            Bioinformatics+Synopsis:            A bioinformatics library+Description:	     A set of core definitions and data structures+		     commonly used in bioinformatics.  The intention is that bioinformatics+		     libraries will use this as a common ground to avoid needless incompatibilities+		     and duplicated work.+-- Homepage:+Tested-With:         GHC==6.12.3+Build-Type:          Simple+-- Data-Files:++Library+  Build-Depends:     base >= 3 && < 5, bytestring+  Exposed-Modules:   Bio.Core, Bio.Core.Sequence, Bio.Core.Strand+  Ghc-Options:       -Wall+  Hs-Source-Dirs:    src

@@ -0,0 +1,7 @@+{-| Re-exporting everything from sub-modules for simplicity -}++module Bio.Core ( module Bio.Core.Sequence+                , module Bio.Core.Strand ) where++import Bio.Core.Sequence+import Bio.Core.Strand

@@ -0,0 +1,81 @@+{-| This module defines common data structures for biosequences,+    i.e. data that represents nucleotide or protein sequences.++    Basically, anything resembling or wrapping a sequence should+    implement the 'BioSeq' class (and 'BioSeqQual' if quality information+    is available).++    The data types are mostly wrappers from lazy bytestrings from+    'Data.ByteString.Lazy' and 'Data.ByteString.Lazy.Char8'.+-}++{-# Language GeneralizedNewtypeDeriving #-}++module Bio.Core.Sequence (+  -- * Data definitions+  Qual (..), Offset (..),+  SeqData (..), SeqLabel (..), QualData (..),++  -- * Class definitions+  BioSeq (..), BioSeqQual (..),++  -- * Helper functions+  toFasta, toFastaQual, toFastQ+  ) where++import qualified Data.ByteString.Lazy.Char8 as LC+import qualified Data.ByteString.Lazy as L+import Data.Int+import Data.Word+import Data.String++-- | Sequence data are lazy bytestrings of ASCII characters.+newtype SeqData  = SeqData { unSD :: LC.ByteString } deriving (Eq,Ord,IsString)++-- | Sequence data are lazy bytestrings of ASCII characters.+newtype SeqLabel = SeqLabel { unSL :: LC.ByteString } deriving (Eq,Ord,IsString)++-- | A quality value is in the range 0..255.+newtype Qual     = Qual { unQual :: Word8 } deriving (Show,Eq,Ord,Num)++-- | Quality data are lazy bytestrings of 'Qual's.+newtype QualData = QualData { unQD :: L.ByteString } deriving (Eq,Ord)++-- | An 'Offset' is a zero-based index into a sequence+newtype Offset   = Offset { unOff :: Int64 } deriving (Show,Eq,Ord,Num)++-- | The 'BioSeq' class models sequence data, and any data object that+--   represents a biological sequence should implement it.+class BioSeq s where+  seqlabel  :: s -> SeqLabel+  seqdata   :: s -> SeqData+  seqlength :: s -> Offset++-- | Any 'BioSeq' can be formatted as Fasta, 60-char lines.+toFasta :: BioSeq s => s -> LC.ByteString -- any kind of string-like data type?  Use builder?+toFasta s = LC.concat (gt:unSL (seqlabel s):nl:wrap (unSD $ seqdata s))+  where wrap x = if LC.null x then [] else let (ln,rest) = LC.splitAt 60 x in ln : nl : wrap rest+        nl = LC.pack "\n"+        gt = LC.pack ">"+                                         +-- | The BioSeqQual class extends BioSeq with quality data.  Any correspondig data object+--   should be an instance, this will allow Fasta formatted quality data 'toFastaQual', as+--   well as the combined FastQ format (via 'toFastQ').+class BioSeq sq => BioSeqQual sq where+  seqqual  :: sq -> QualData++-- | Output Fasta-formatted quality data (.qual files), where quality values are output as +--   whitespace-separated integers.+toFastaQual :: BioSeqQual s => s -> LC.ByteString+toFastaQual s = LC.concat (gt:unSL (seqlabel s):nl:wrap (L.unpack $ unQD $ seqqual s))+  where wrap x = if null x then [] else let (ln,rest) = splitAt 20 x in LC.pack (unwords $ map show ln) : nl : wrap rest+        nl = LC.pack "\n"+        gt = LC.pack ">"++-- | Output FastQ-formatted data.  For simplicity, only the Sanger quality format is supported,+--   and only four lines per sequence (i.e. no line breaks in sequence or quality data).+toFastQ :: BioSeqQual s => s -> LC.ByteString+toFastQ s = LC.unlines [LC.cons '@' (unSL $ seqlabel s)+                       , unSD (seqdata s)+                       , LC.cons '+' (unSL $ seqlabel s)+                       , L.map (+33) (unQD $ seqqual s)]

@@ -0,0 +1,6 @@+{-| Define common data types for features of sequences -}++module Bio.Core.Strand (Strand(..)) where++-- | A 'Strand' is either plus (forward) or minus (reverse or reverse-complement)+data Strand = Plus | Minus deriving (Eq,Ord,Read,Show)