diff --git a/fasta.cabal b/fasta.cabal --- a/fasta.cabal +++ b/fasta.cabal @@ -10,7 +10,7 @@ -- PVP summary: +-+------- breaking API changes -- | | +----- non-breaking API additions -- | | | +--- code changes with no API change -version: 0.10.1.0 +version: 0.10.2.0 -- A short (one-line) description of the package. synopsis: A simple, mindless parser for fasta files. diff --git a/src/Data/Fasta/ByteString/Lazy/Translation.hs b/src/Data/Fasta/ByteString/Lazy/Translation.hs --- a/src/Data/Fasta/ByteString/Lazy/Translation.hs +++ b/src/Data/Fasta/ByteString/Lazy/Translation.hs @@ -9,7 +9,10 @@ module Data.Fasta.ByteString.Lazy.Translation ( chunksOf , codon2aa - , translate ) where + , customCodon2aa + , translate + , customTranslate + ) where -- Built in import Data.Char @@ -31,50 +34,60 @@ -- | Converts a codon to an amino acid -- Remember, if there is an "N" in that DNA sequence, then it is translated -- as an X, an unknown amino acid. -codon2aa :: Codon -> Either BL.ByteString BL.ByteString +codon2aa :: Codon -> Either BL.ByteString AA codon2aa x - | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right "A" - | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right "R" - | codon `elem` ["AAT", "AAC"] = Right "N" - | codon `elem` ["GAT", "GAC"] = Right "D" - | codon `elem` ["TGT", "TGC"] = Right "C" - | codon `elem` ["CAA", "CAG"] = Right "Q" - | codon `elem` ["GAA", "GAG"] = Right "E" - | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right "G" - | codon `elem` ["CAT", "CAC"] = Right "H" - | codon `elem` ["ATT", "ATC", "ATA"] = Right "I" - | codon `elem` ["ATG"] = Right "M" - | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right "L" - | codon `elem` ["AAA", "AAG"] = Right "K" - | codon `elem` ["TTT", "TTC"] = Right "F" - | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right "P" - | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right "S" - | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right "T" - | codon `elem` ["TGG"] = Right "W" - | codon `elem` ["TAT", "TAC"] = Right "Y" - | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right "V" - | codon `elem` ["TAA", "TGA", "TAG"] = Right "*" - | codon `elem` ["---", "..."] = Right "-" - | codon == "~~~" = Right "-" - | 'N' `BL.elem` codon = Right "X" - | '-' `BL.elem` codon = Right "-" - | '.' `BL.elem` codon = Right "-" + | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right 'A' + | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right 'R' + | codon `elem` ["AAT", "AAC"] = Right 'N' + | codon `elem` ["GAT", "GAC"] = Right 'D' + | codon `elem` ["TGT", "TGC"] = Right 'C' + | codon `elem` ["CAA", "CAG"] = Right 'Q' + | codon `elem` ["GAA", "GAG"] = Right 'E' + | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right 'G' + | codon `elem` ["CAT", "CAC"] = Right 'H' + | codon `elem` ["ATT", "ATC", "ATA"] = Right 'I' + | codon `elem` ["ATG"] = Right 'M' + | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right 'L' + | codon `elem` ["AAA", "AAG"] = Right 'K' + | codon `elem` ["TTT", "TTC"] = Right 'F' + | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right 'P' + | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right 'S' + | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right 'T' + | codon `elem` ["TGG"] = Right 'W' + | codon `elem` ["TAT", "TAC"] = Right 'Y' + | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right 'V' + | codon `elem` ["TAA", "TGA", "TAG"] = Right '*' + | codon `elem` ["---", "..."] = Right '-' + | codon == "~~~" = Right '-' + | 'N' `BL.elem` codon = Right 'X' + | '-' `BL.elem` codon = Right '-' + | '.' `BL.elem` codon = Right '-' | otherwise = Left errorMsg where codon = BL.map toUpper x errorMsg = BL.append "Unidentified codon: " codon +-- | Translate a codon using a custom table +customCodon2aa :: [(Codon, Char)] -> Codon -> Either BL.ByteString AA +customCodon2aa table codon = case lookup codon table of + (Just x) -> Right x + Nothing -> codon2aa codon + -- | Translates a bytestring of nucleotides given a reading frame (1, 2, or -- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns --- a bytestring with the error if the codon is invalid. -translate :: Int64 -> FastaSequence -> Either BL.ByteString FastaSequence -translate pos x +-- a bytestring with the error if the codon is invalid. Also has customized +-- codon translations as well overriding the defaults. +customTranslate :: [(Codon, AA)] + -> Int64 + -> FastaSequence + -> Either BL.ByteString FastaSequence +customTranslate table pos x | any isLeft' translation = Left $ head . lefts $ translation - | otherwise = Right $ x { fastaSeq = BL.concat + | otherwise = Right $ x { fastaSeq = BL.pack . rights $ translation } where - translation = map codon2aa + translation = map (customCodon2aa table) . filter ((== 3) . BL.length) . chunksOf 3 . BL.drop (pos - 1) @@ -82,3 +95,9 @@ $ x isLeft' (Left _) = True isLeft' _ = False + +-- | Translates a bytestring of nucleotides given a reading frame (1, 2, or +-- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns +-- a bytestring with the error if the codon is invalid. +translate :: Int64 -> FastaSequence -> Either BL.ByteString FastaSequence +translate = customTranslate [] diff --git a/src/Data/Fasta/ByteString/Lazy/Types.hs b/src/Data/Fasta/ByteString/Lazy/Types.hs --- a/src/Data/Fasta/ByteString/Lazy/Types.hs +++ b/src/Data/Fasta/ByteString/Lazy/Types.hs @@ -18,9 +18,10 @@ } deriving (Eq, Ord, Show) -- Basic +type Codon = BL.ByteString +type AA = Char type Clone = FastaSequence type Germline = FastaSequence -type Codon = BL.ByteString -- Advanced -- | A clone is a collection of sequences derived from a germline with diff --git a/src/Data/Fasta/ByteString/Translation.hs b/src/Data/Fasta/ByteString/Translation.hs --- a/src/Data/Fasta/ByteString/Translation.hs +++ b/src/Data/Fasta/ByteString/Translation.hs @@ -9,7 +9,10 @@ module Data.Fasta.ByteString.Translation ( chunksOf , codon2aa - , translate ) where + , customCodon2aa + , translate + , customTranslate + ) where -- Built in import Data.Char @@ -30,50 +33,60 @@ -- | Converts a codon to an amino acid -- Remember, if there is an "N" in that DNA sequence, then it is translated -- as an X, an unknown amino acid. -codon2aa :: Codon -> Either B.ByteString B.ByteString +codon2aa :: Codon -> Either B.ByteString AA codon2aa x - | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right "A" - | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right "R" - | codon `elem` ["AAT", "AAC"] = Right "N" - | codon `elem` ["GAT", "GAC"] = Right "D" - | codon `elem` ["TGT", "TGC"] = Right "C" - | codon `elem` ["CAA", "CAG"] = Right "Q" - | codon `elem` ["GAA", "GAG"] = Right "E" - | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right "G" - | codon `elem` ["CAT", "CAC"] = Right "H" - | codon `elem` ["ATT", "ATC", "ATA"] = Right "I" - | codon `elem` ["ATG"] = Right "M" - | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right "L" - | codon `elem` ["AAA", "AAG"] = Right "K" - | codon `elem` ["TTT", "TTC"] = Right "F" - | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right "P" - | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right "S" - | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right "T" - | codon `elem` ["TGG"] = Right "W" - | codon `elem` ["TAT", "TAC"] = Right "Y" - | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right "V" - | codon `elem` ["TAA", "TGA", "TAG"] = Right "*" - | codon `elem` ["---", "..."] = Right "-" - | codon == "~~~" = Right "-" - | "N" `B.isInfixOf` codon = Right "X" - | "-" `B.isInfixOf` codon = Right "-" - | "." `B.isInfixOf` codon = Right "-" + | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right 'A' + | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right 'R' + | codon `elem` ["AAT", "AAC"] = Right 'N' + | codon `elem` ["GAT", "GAC"] = Right 'D' + | codon `elem` ["TGT", "TGC"] = Right 'C' + | codon `elem` ["CAA", "CAG"] = Right 'Q' + | codon `elem` ["GAA", "GAG"] = Right 'E' + | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right 'G' + | codon `elem` ["CAT", "CAC"] = Right 'H' + | codon `elem` ["ATT", "ATC", "ATA"] = Right 'I' + | codon `elem` ["ATG"] = Right 'M' + | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right 'L' + | codon `elem` ["AAA", "AAG"] = Right 'K' + | codon `elem` ["TTT", "TTC"] = Right 'F' + | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right 'P' + | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right 'S' + | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right 'T' + | codon `elem` ["TGG"] = Right 'W' + | codon `elem` ["TAT", "TAC"] = Right 'Y' + | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right 'V' + | codon `elem` ["TAA", "TGA", "TAG"] = Right '*' + | codon `elem` ["---", "..."] = Right '-' + | codon == "~~~" = Right '-' + | "N" `B.isInfixOf` codon = Right 'X' + | "-" `B.isInfixOf` codon = Right '-' + | "." `B.isInfixOf` codon = Right '-' | otherwise = Left errorMsg where codon = B.map toUpper x errorMsg = B.append "Unidentified codon: " codon +-- | Translate a codon using a custom table +customCodon2aa :: [(Codon, Char)] -> Codon -> Either B.ByteString AA +customCodon2aa table codon = case lookup codon table of + (Just x) -> Right x + Nothing -> codon2aa codon + -- | Translates a bytestring of nucleotides given a reading frame (1, 2, or -- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns --- a bytestring with the error if the codon is invalid. -translate :: Int -> FastaSequence -> Either B.ByteString FastaSequence -translate pos x +-- a bytestring with the error if the codon is invalid. Also has customized +-- codon translations as well overriding the defaults. +customTranslate :: [(Codon, AA)] + -> Int + -> FastaSequence + -> Either B.ByteString FastaSequence +customTranslate table pos x | any isLeft' translation = Left $ head . lefts $ translation - | otherwise = Right $ x { fastaSeq = B.concat + | otherwise = Right $ x { fastaSeq = B.pack . rights $ translation } where - translation = map codon2aa + translation = map (customCodon2aa table) . filter ((== 3) . B.length) . chunksOf 3 . B.drop (pos - 1) @@ -81,3 +94,9 @@ $ x isLeft' (Left _) = True isLeft' _ = False + +-- | Translates a bytestring of nucleotides given a reading frame (1, 2, or +-- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns +-- a bytestring with the error if the codon is invalid. +translate :: Int -> FastaSequence -> Either B.ByteString FastaSequence +translate = customTranslate [] diff --git a/src/Data/Fasta/ByteString/Types.hs b/src/Data/Fasta/ByteString/Types.hs --- a/src/Data/Fasta/ByteString/Types.hs +++ b/src/Data/Fasta/ByteString/Types.hs @@ -18,9 +18,10 @@ } deriving (Eq, Ord, Show) -- Basic +type Codon = B.ByteString +type AA = Char type Clone = FastaSequence type Germline = FastaSequence -type Codon = B.ByteString -- Advanced -- | A clone is a collection of sequences derived from a germline with diff --git a/src/Data/Fasta/String/Translation.hs b/src/Data/Fasta/String/Translation.hs --- a/src/Data/Fasta/String/Translation.hs +++ b/src/Data/Fasta/String/Translation.hs @@ -5,7 +5,11 @@ amino acids for strings. -} -module Data.Fasta.String.Translation where +module Data.Fasta.String.Translation ( codon2aa + , customCodon2aa + , translate + , customTranslate + ) where -- Built in import Data.Either @@ -20,7 +24,7 @@ -- | Converts a codon to an amino acid -- Remember, if there is an "N" in that DNA sequence, then it is translated -- as an X, an unknown amino acid. -codon2aa :: Codon -> Either String Char +codon2aa :: Codon -> Either String AA codon2aa x | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right 'A' | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right 'R' @@ -53,15 +57,25 @@ codon = map toUpper x errorMsg = "Unidentified codon: " ++ codon +-- | Translate a codon using a custom table +customCodon2aa :: [(Codon, Char)] -> Codon -> Either String AA +customCodon2aa table codon = case lookup codon table of + (Just x) -> Right x + Nothing -> codon2aa codon + -- | Translates a string of nucleotides given a reading frame (1, 2, or -- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns --- a string with the error if the codon is invalid. -translate :: Int -> FastaSequence -> Either String FastaSequence -translate pos x +-- a string with the error if the codon is invalid. Also has customized +-- codon translations as well overriding the defaults. +customTranslate :: [(Codon, AA)] + -> Int + -> FastaSequence + -> Either String FastaSequence +customTranslate table pos x | any isLeft' translation = Left $ head . lefts $ translation | otherwise = Right $ x { fastaSeq = rights translation } where - translation = map codon2aa + translation = map (customCodon2aa table) . filter ((== 3) . length) . Split.chunksOf 3 . drop (pos - 1) @@ -69,3 +83,9 @@ $ x isLeft' (Left _) = True isLeft' _ = False + +-- | Translates a string of nucleotides given a reading frame (1, 2, or +-- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns +-- a string with the error if the codon is invalid. +translate :: Int -> FastaSequence -> Either String FastaSequence +translate = customTranslate [] diff --git a/src/Data/Fasta/String/Types.hs b/src/Data/Fasta/String/Types.hs --- a/src/Data/Fasta/String/Types.hs +++ b/src/Data/Fasta/String/Types.hs @@ -16,6 +16,7 @@ -- Basic type Codon = String +type AA = Char type Clone = FastaSequence type Germline = FastaSequence diff --git a/src/Data/Fasta/Text/Lazy/Translation.hs b/src/Data/Fasta/Text/Lazy/Translation.hs --- a/src/Data/Fasta/Text/Lazy/Translation.hs +++ b/src/Data/Fasta/Text/Lazy/Translation.hs @@ -8,7 +8,10 @@ {-# LANGUAGE OverloadedStrings #-} module Data.Fasta.Text.Lazy.Translation ( codon2aa - , translate ) where + , customCodon2aa + , translate + , customTranslate + ) where -- Built in import Data.Either @@ -21,50 +24,60 @@ -- | Converts a codon to an amino acid -- Remember, if there is an "N" in that DNA sequence, then it is translated -- as an X, an unknown amino acid. -codon2aa :: Codon -> Either T.Text T.Text +codon2aa :: Codon -> Either T.Text Char codon2aa x - | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right "A" - | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right "R" - | codon `elem` ["AAT", "AAC"] = Right "N" - | codon `elem` ["GAT", "GAC"] = Right "D" - | codon `elem` ["TGT", "TGC"] = Right "C" - | codon `elem` ["CAA", "CAG"] = Right "Q" - | codon `elem` ["GAA", "GAG"] = Right "E" - | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right "G" - | codon `elem` ["CAT", "CAC"] = Right "H" - | codon `elem` ["ATT", "ATC", "ATA"] = Right "I" - | codon `elem` ["ATG"] = Right "M" - | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right "L" - | codon `elem` ["AAA", "AAG"] = Right "K" - | codon `elem` ["TTT", "TTC"] = Right "F" - | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right "P" - | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right "S" - | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right "T" - | codon `elem` ["TGG"] = Right "W" - | codon `elem` ["TAT", "TAC"] = Right "Y" - | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right "V" - | codon `elem` ["TAA", "TGA", "TAG"] = Right "*" - | codon `elem` ["---", "..."] = Right "-" - | codon == "~~~" = Right "-" - | "N" `T.isInfixOf` codon = Right "X" - | "-" `T.isInfixOf` codon = Right "-" - | "." `T.isInfixOf` codon = Right "-" + | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right 'A' + | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right 'R' + | codon `elem` ["AAT", "AAC"] = Right 'N' + | codon `elem` ["GAT", "GAC"] = Right 'D' + | codon `elem` ["TGT", "TGC"] = Right 'C' + | codon `elem` ["CAA", "CAG"] = Right 'Q' + | codon `elem` ["GAA", "GAG"] = Right 'E' + | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right 'G' + | codon `elem` ["CAT", "CAC"] = Right 'H' + | codon `elem` ["ATT", "ATC", "ATA"] = Right 'I' + | codon `elem` ["ATG"] = Right 'M' + | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right 'L' + | codon `elem` ["AAA", "AAG"] = Right 'K' + | codon `elem` ["TTT", "TTC"] = Right 'F' + | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right 'P' + | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right 'S' + | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right 'T' + | codon `elem` ["TGG"] = Right 'W' + | codon `elem` ["TAT", "TAC"] = Right 'Y' + | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right 'V' + | codon `elem` ["TAA", "TGA", "TAG"] = Right '*' + | codon `elem` ["---", "..."] = Right '-' + | codon == "~~~" = Right '-' + | "N" `T.isInfixOf` codon = Right 'X' + | "-" `T.isInfixOf` codon = Right '-' + | "." `T.isInfixOf` codon = Right '-' | otherwise = Left errorMsg where codon = T.toUpper x errorMsg = T.append "Unidentified codon: " codon +-- | Translate a codon using a custom table +customCodon2aa :: [(Codon, Char)] -> Codon -> Either T.Text AA +customCodon2aa table codon = case lookup codon table of + (Just x) -> Right x + Nothing -> codon2aa codon + -- | Translates a text of nucleotides given a reading frame (1, 2, or -- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns --- a text with the error if the codon is invalid. -translate :: Int64 -> FastaSequence -> Either T.Text FastaSequence -translate pos x +-- a text with the error if the codon is invalid. Also has customized codon +-- translations as well overriding the defaults. +customTranslate :: [(Codon, AA)] + -> Int64 + -> FastaSequence + -> Either T.Text FastaSequence +customTranslate table pos x | any isLeft' translation = Left $ head . lefts $ translation - | otherwise = Right $ x { fastaSeq = T.concat + | otherwise = Right $ x { fastaSeq = T.pack . rights $ translation } where - translation = map codon2aa + translation = map (customCodon2aa table) . filter ((== 3) . T.length) . T.chunksOf 3 . T.drop (pos - 1) @@ -72,3 +85,9 @@ $ x isLeft' (Left _) = True isLeft' _ = False + +-- | Translates a text of nucleotides given a reading frame (1, 2, or +-- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns +-- a text with the error if the codon is invalid. +translate :: Int64 -> FastaSequence -> Either T.Text FastaSequence +translate = customTranslate [] diff --git a/src/Data/Fasta/Text/Lazy/Types.hs b/src/Data/Fasta/Text/Lazy/Types.hs --- a/src/Data/Fasta/Text/Lazy/Types.hs +++ b/src/Data/Fasta/Text/Lazy/Types.hs @@ -18,9 +18,10 @@ } deriving (Eq, Ord, Show) -- Basic +type Codon = T.Text +type AA = Char type Clone = FastaSequence type Germline = FastaSequence -type Codon = T.Text -- Advanced -- | A clone is a collection of sequences derived from a germline with diff --git a/src/Data/Fasta/Text/Translation.hs b/src/Data/Fasta/Text/Translation.hs --- a/src/Data/Fasta/Text/Translation.hs +++ b/src/Data/Fasta/Text/Translation.hs @@ -8,7 +8,10 @@ {-# LANGUAGE OverloadedStrings #-} module Data.Fasta.Text.Translation ( codon2aa - , translate ) where + , customCodon2aa + , translate + , customTranslate + ) where -- Built in import Data.Either @@ -20,50 +23,60 @@ -- | Converts a codon to an amino acid -- Remember, if there is an "N" in that DNA sequence, then it is translated -- as an X, an unknown amino acid. -codon2aa :: Codon -> Either T.Text T.Text +codon2aa :: Codon -> Either T.Text AA codon2aa x - | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right "A" - | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right "R" - | codon `elem` ["AAT", "AAC"] = Right "N" - | codon `elem` ["GAT", "GAC"] = Right "D" - | codon `elem` ["TGT", "TGC"] = Right "C" - | codon `elem` ["CAA", "CAG"] = Right "Q" - | codon `elem` ["GAA", "GAG"] = Right "E" - | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right "G" - | codon `elem` ["CAT", "CAC"] = Right "H" - | codon `elem` ["ATT", "ATC", "ATA"] = Right "I" - | codon `elem` ["ATG"] = Right "M" - | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right "L" - | codon `elem` ["AAA", "AAG"] = Right "K" - | codon `elem` ["TTT", "TTC"] = Right "F" - | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right "P" - | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right "S" - | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right "T" - | codon `elem` ["TGG"] = Right "W" - | codon `elem` ["TAT", "TAC"] = Right "Y" - | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right "V" - | codon `elem` ["TAA", "TGA", "TAG"] = Right "*" - | codon `elem` ["---", "..."] = Right "-" - | codon == "~~~" = Right "-" - | "N" `T.isInfixOf` codon = Right "X" - | "-" `T.isInfixOf` codon = Right "-" - | "." `T.isInfixOf` codon = Right "-" + | codon `elem` ["GCT", "GCC", "GCA", "GCG"] = Right 'A' + | codon `elem` ["CGT", "CGC", "CGA", "CGG", "AGA", "AGG"] = Right 'R' + | codon `elem` ["AAT", "AAC"] = Right 'N' + | codon `elem` ["GAT", "GAC"] = Right 'D' + | codon `elem` ["TGT", "TGC"] = Right 'C' + | codon `elem` ["CAA", "CAG"] = Right 'Q' + | codon `elem` ["GAA", "GAG"] = Right 'E' + | codon `elem` ["GGT", "GGC", "GGA", "GGG"] = Right 'G' + | codon `elem` ["CAT", "CAC"] = Right 'H' + | codon `elem` ["ATT", "ATC", "ATA"] = Right 'I' + | codon `elem` ["ATG"] = Right 'M' + | codon `elem` ["TTA", "TTG", "CTT", "CTC", "CTA", "CTG"] = Right 'L' + | codon `elem` ["AAA", "AAG"] = Right 'K' + | codon `elem` ["TTT", "TTC"] = Right 'F' + | codon `elem` ["CCT", "CCC", "CCA", "CCG"] = Right 'P' + | codon `elem` ["TCT", "TCC", "TCA", "TCG", "AGT", "AGC"] = Right 'S' + | codon `elem` ["ACT", "ACC", "ACA", "ACG"] = Right 'T' + | codon `elem` ["TGG"] = Right 'W' + | codon `elem` ["TAT", "TAC"] = Right 'Y' + | codon `elem` ["GTT", "GTC", "GTA", "GTG"] = Right 'V' + | codon `elem` ["TAA", "TGA", "TAG"] = Right '*' + | codon `elem` ["---", "..."] = Right '-' + | codon == "~~~" = Right '-' + | "N" `T.isInfixOf` codon = Right 'X' + | "-" `T.isInfixOf` codon = Right '-' + | "." `T.isInfixOf` codon = Right '-' | otherwise = Left errorMsg where codon = T.toUpper x errorMsg = T.append "Unidentified codon: " codon +-- | Translate a codon using a custom table +customCodon2aa :: [(Codon, Char)] -> Codon -> Either T.Text AA +customCodon2aa table codon = case lookup codon table of + (Just x) -> Right x + Nothing -> codon2aa codon + -- | Translates a text of nucleotides given a reading frame (1, 2, or -- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns --- a text with the error if the codon is invalid. -translate :: Int -> FastaSequence -> Either T.Text FastaSequence -translate pos x +-- a text with the error if the codon is invalid. Also has customized codon +-- translations as well overriding the defaults. +customTranslate :: [(Codon, AA)] + -> Int + -> FastaSequence + -> Either T.Text FastaSequence +customTranslate table pos x | any isLeft' translation = Left $ head . lefts $ translation - | otherwise = Right $ x { fastaSeq = T.concat + | otherwise = Right $ x { fastaSeq = T.pack . rights $ translation } where - translation = map codon2aa + translation = map (customCodon2aa table) . filter ((== 3) . T.length) . T.chunksOf 3 . T.drop (pos - 1) @@ -71,3 +84,9 @@ $ x isLeft' (Left _) = True isLeft' _ = False + +-- | Translates a text of nucleotides given a reading frame (1, 2, or +-- 3) -- drops the first 0, 1, or 2 nucleotides respectively. Returns +-- a text with the error if the codon is invalid. +translate :: Int -> FastaSequence -> Either T.Text FastaSequence +translate = customTranslate [] diff --git a/src/Data/Fasta/Text/Types.hs b/src/Data/Fasta/Text/Types.hs --- a/src/Data/Fasta/Text/Types.hs +++ b/src/Data/Fasta/Text/Types.hs @@ -18,9 +18,10 @@ } deriving (Eq, Ord, Show) -- Basic +type Codon = T.Text +type AA = Char type Clone = FastaSequence type Germline = FastaSequence -type Codon = T.Text -- Advanced -- | A clone is a collection of sequences derived from a germline with