diff --git a/mmtf.cabal b/mmtf.cabal --- a/mmtf.cabal +++ b/mmtf.cabal @@ -1,5 +1,5 @@ name: mmtf -version: 0.1.0.1 +version: 0.1.1.0 synopsis: Macromolecular Transmission Format implementation description: Haskell implementation of MMTF biological structure format. homepage: https://github.com/zmactep/mmtf#readme @@ -25,8 +25,9 @@ , data-msgpack >= 0.0.9 && < 0.1 , text >= 1.2.2.1 && < 1.3 , bytestring >= 0.10.8.1 && < 0.11 - , binary >= 0.8.3.0 && < 0.9 - , containers >= 0.5.7.1 && < 0.6 + , binary >= 0.8.3.0 && < 1.0 + , containers >= 0.5.7.1 && < 0.7 + , http-conduit >= 2.3 && < 2.4 default-language: Haskell2010 ghc-options: -Wall diff --git a/src/Bio/MMTF.hs b/src/Bio/MMTF.hs --- a/src/Bio/MMTF.hs +++ b/src/Bio/MMTF.hs @@ -1,14 +1,26 @@ module Bio.MMTF ( module Bio.MMTF.Type , decode + , fetch ) where import Bio.MMTF.MessagePack () import Bio.MMTF.Type -import Data.ByteString.Lazy (ByteString) -import Data.MessagePack (unpack) +import Data.ByteString.Lazy (ByteString) +import Data.MessagePack (unpack) +import Data.Monoid ((<>)) +import Data.String (IsString (..)) +import Control.Monad.IO.Class (MonadIO) +import Network.HTTP.Simple (httpLBS, getResponseBody) --- |Decodes a 'ByteString' to 'MMTF' +-- | Decodes a 'ByteString' to 'MMTF' +-- decode :: Monad m => ByteString -> m MMTF decode = unpack + +-- | Fetches MMTF structure from RSCB +fetch :: MonadIO m => String -> m MMTF +fetch pdbid = do let url = fromString $ "https://mmtf.rcsb.org/v1.0/full/" <> pdbid + resp <- httpLBS url + decode (getResponseBody resp) diff --git a/src/Bio/MMTF/Decode.hs b/src/Bio/MMTF/Decode.hs --- a/src/Bio/MMTF/Decode.hs +++ b/src/Bio/MMTF/Decode.hs @@ -11,24 +11,28 @@ import Data.MessagePack (Object) import Data.Text (Text) --- |Parses format data from ObjectMap +-- | Parses format data from ObjectMap +-- formatData :: Monad m => Map Text Object -> m FormatData formatData mp = do v <- atP mp "mmtfVersion" asStr p <- atP mp "mmtfProducer" asStr pure $ FormatData v p --- |Parses model data from ObjectMap +-- | Parses model data from ObjectMap +-- modelData :: Monad m => Map Text Object -> m ModelData -modelData mp = atP mp "chainsPerModel" asIntList >>= return . ModelData +modelData mp = ModelData <$> atP mp "chainsPerModel" asIntList --- |Parses chain data from ObjectMap +-- | Parses chain data from ObjectMap +-- chainData :: Monad m => Map Text Object -> m ChainData chainData mp = do gpc <- atP mp "groupsPerChain" asIntList cil <- codec5 . parseBinary <$> atP mp "chainIdList" asBinary cnl <- (codec5 . parseBinary <$>) <$> atPM mp "chainNameList" asBinary pure $ ChainData gpc cil cnl --- |Parses atom data from ObjectMap +-- | Parses atom data from ObjectMap +-- atomData :: Monad m => Map Text Object -> m AtomData atomData mp = do ail' <- (codec8 . parseBinary <$>) <$> atPM mp "atomIdList" asBinary all' <- (codec6 . parseBinary <$>) <$> atPM mp "altLocList" asBinary @@ -39,9 +43,10 @@ ol' <- (codec9 . parseBinary <$>) <$> atPM mp "occupancyList" asBinary pure $ AtomData ail' all' bfl' xcl' ycl' zcl' ol' --- |Parses group data from ObjectMap +-- | Parses group data from ObjectMap +-- groupData :: Monad m => Map Text Object -> m GroupData -groupData mp = do gl' <- atP mp "groupList" asObjectList >>= sequence . map (transformObjectMap >=> groupType) +groupData mp = do gl' <- atP mp "groupList" asObjectList >>= traverse (transformObjectMap >=> groupType) gtl' <- codec4 . parseBinary <$> atP mp "groupTypeList" asBinary gil' <- codec8 . parseBinary <$> atP mp "groupIdList" asBinary ssl' <- (map ssDec . codec2 . parseBinary <$>) <$> atPM mp "secStructList" asBinary @@ -49,7 +54,8 @@ sil' <- (codec8 . parseBinary <$>) <$> atPM mp "sequenceIndexList" asBinary pure $ GroupData gl' gtl' gil' ssl' icl' sil' --- |Parses group type from ObjectMap +-- | Parses group type from ObjectMap +-- groupType :: Monad m => Map Text Object -> m GroupType groupType mp = do fcl' <- atP mp "formalChargeList" asIntList anl' <- atP mp "atomNameList" asStrList @@ -61,7 +67,8 @@ cct' <- atP mp "chemCompType" asStr pure $ GroupType fcl' anl' el' bal' bol' gn' slc' cct' --- |Parses structure data from ObjectMap +-- | Parses structure data from ObjectMap +-- structureData :: Monad m => Map Text Object -> m StructureData structureData mp = do ttl' <- atPM mp "title" asStr sid' <- atPM mp "structureId" asStr @@ -75,8 +82,8 @@ sg' <- atPM mp "spaceGroup" asStr uc' <- (>>= ucDec) <$> atPM mp "unitCell" asFloatList nol' <- ((>>= asFloatList) <$>) <$> atPM mp "ncsOperatorList" asObjectList - bal' <- (>>= sequence . map (transformObjectMap >=> bioAssembly)) <$> atPM mp "bioAssemblyList" asObjectList - el' <- (>>= sequence . map (transformObjectMap >=> entity)) <$> atPM mp "entityList" asObjectList + bal' <- (>>= traverse (transformObjectMap >=> bioAssembly)) <$> atPM mp "bioAssemblyList" asObjectList + el' <- (>>= traverse (transformObjectMap >=> entity)) <$> atPM mp "entityList" asObjectList res' <- atPM mp "resolution" asFloat rf' <- atPM mp "rFree" asFloat rw' <- atPM mp "rWork" asFloat @@ -86,19 +93,22 @@ pure $ StructureData ttl' sid' dd' rd' nb' na' ng' nc' nm' sg' uc' nol' bal' el' res' rf' rw' em' btl' bol' --- |Parses bio assembly data from ObjectMap +-- | Parses bio assembly data from ObjectMap +-- bioAssembly :: Monad m => Map Text Object -> m Assembly bioAssembly mp = do nme' <- atP mp "name" asStr - tlt' <- atP mp "transformList" asObjectList >>= sequence . map (transformObjectMap >=> transform) + tlt' <- atP mp "transformList" asObjectList >>= traverse (transformObjectMap >=> transform) pure $ Assembly tlt' nme' --- |Parses transform data from ObjectMap +-- | Parses transform data from ObjectMap +-- transform :: Monad m => Map Text Object -> m Transform transform mp = do cil' <- atP mp "chainIndexList" asIntList mtx' <- atP mp "matrix" asFloatList pure $ Transform cil' mtx' --- |Parses entity data from ObjectMap +-- | Parses entity data from ObjectMap +-- entity :: Monad m => Map Text Object -> m Entity entity mp = do cil' <- atP mp "chainIndexList" asIntList dsc' <- atP mp "description" asStr diff --git a/src/Bio/MMTF/Decode/Codec.hs b/src/Bio/MMTF/Decode/Codec.hs --- a/src/Bio/MMTF/Decode/Codec.hs +++ b/src/Bio/MMTF/Decode/Codec.hs @@ -18,95 +18,111 @@ in f start : codecCommon f th rest where ith = fromIntegral th -data BinaryData = BD { binaryCodec :: Int32 - , binaryLength :: Int32 - , binaryParam :: Int32 - , binaryData :: ByteString +data BinaryData = BD { binaryCodec :: !Int32 + , binaryLength :: !Int32 + , binaryParam :: !Int32 + , binaryData :: !ByteString } --- |Parse useless header for binary data +-- | Parse useless header for binary data +-- parseBinary :: ByteString -> BinaryData parseBinary bs = let (cdc, rest1) = B.splitAt 4 bs (lnh, rest2) = B.splitAt 4 rest1 (prm, rest) = B.splitAt 4 rest2 in BD (decode cdc) (decode lnh) (decode prm) rest --- |Interpret bytes as array of 32-bit floating-point numbers. +-- | Interpret bytes as array of 32-bit floating-point numbers. +-- codec1 :: BinaryData -> [Float] codec1 = codecCommon decode 4 . binaryData --- |Interpret bytes as array of 8-bit signed integers. +-- | Interpret bytes as array of 8-bit signed integers. +-- codec2 :: BinaryData -> [Int8] codec2 = codecCommon decode 1 . binaryData --- |Interpret bytes as array of 16-bit signed integers. +-- | Interpret bytes as array of 16-bit signed integers. +-- codec3 :: BinaryData -> [Int16] codec3 = codecCommon decode 2 . binaryData --- |Interpret bytes as array of 32-bit signed integers. +-- | Interpret bytes as array of 32-bit signed integers. +-- codec4 :: BinaryData -> [Int32] codec4 = codecCommon decode 4 . binaryData --- |Interpret bytes as array of 8-bit unsigned integers, then iteratively +-- | Interpret bytes as array of 8-bit unsigned integers, then iteratively -- consume length many bytes to form a string array. +-- codec5 :: BinaryData -> [Text] codec5 bd = codecCommon decodeBytes (fromIntegral $ binaryParam bd) (binaryData bd) where decodeBytes :: ByteString -> Text decodeBytes bs = T.pack $ chr <$> filter (/=0) (fromIntegral <$> B.unpack bs) --- |Interpret bytes as array of 32-bit signed integers, then run-length +-- | Interpret bytes as array of 32-bit signed integers, then run-length -- decode into array of characters. +-- codec6 :: BinaryData -> [Char] codec6 = map (chr . fromIntegral) . codec7 --- |Interpret bytes as array of 32-bit signed integers, then run-length +-- | Interpret bytes as array of 32-bit signed integers, then run-length -- decode into array of 32-bit signed integers. +-- codec7 :: BinaryData -> [Int32] codec7 = runLengthDec . codec4 --- |Interpret bytes as array of 32-bit signed integers, then run-length +-- | Interpret bytes as array of 32-bit signed integers, then run-length -- decode into array of 32-bit signed integers, then delta decode into -- array of 32-bit signed integers. +-- codec8 :: BinaryData -> [Int32] codec8 = deltaDec . codec7 --- |Interpret bytes as array of 32-bit signed integers, then run-length +-- | Interpret bytes as array of 32-bit signed integers, then run-length -- decode into array of 32-bit signed integers, then integer decode into -- array of 32-bit floating-point numbers using the divisor parameter. +-- codec9 :: BinaryData -> [Float] codec9 bd = integerDec (binaryParam bd) $ codec7 bd --- |Interpret bytes as array of 16-bit signed integers, then unpack into +-- | Interpret bytes as array of 16-bit signed integers, then unpack into -- array of 32-bit integers, then delta decode into array of 32-bit -- integers, then integer decode into array of 32-bit floating-point -- numbers using the divisor parameter. +-- codec10 :: BinaryData -> [Float] codec10 bd = integerDec (binaryParam bd) $ map fromIntegral $ deltaDec $ codec3 bd --- |Interpret bytes as array of 16-bit signed integers, then integer +-- | Interpret bytes as array of 16-bit signed integers, then integer -- decode into array of 32-bit floating-point numbers using the divisor parameter. +-- codec11 :: BinaryData -> [Float] codec11 bd = integerDec (binaryParam bd) $ map fromIntegral $ codec3 bd --- |Interpret bytes as array of 16-bit signed integers, then unpack into +-- | Interpret bytes as array of 16-bit signed integers, then unpack into -- array of 32-bit signed integers, then integer decode into array -- of 32-bit floating-point numbers using the divisor parameter. +-- codec12 :: BinaryData -> [Float] codec12 bd = integerDec (binaryParam bd) $ recIndexDec $ codec3 bd --- |Interpret array of bytes as array of 8-bit signed integers, then +-- | Interpret array of bytes as array of 8-bit signed integers, then -- unpack into array of 32-bit signed integers, then integer decode into -- array of 32-bit floating-point numbers using the divisor parameter. +-- codec13 :: BinaryData -> [Float] codec13 bd = integerDec (binaryParam bd) $ recIndexDec $ codec2 bd --- |Interpret bytes as array of 16-bit signed integers, then unpack +-- | Interpret bytes as array of 16-bit signed integers, then unpack -- into array of 32-bit signed integers. +-- codec14 :: BinaryData -> [Int32] codec14 bd = recIndexDec $ codec3 bd --- |Interpret bytes as array of 8-bit signed integers, then unpack +-- | Interpret bytes as array of 8-bit signed integers, then unpack -- into array of 32-bit signed integers. +-- codec15 :: BinaryData -> [Int32] codec15 bd = recIndexDec $ codec2 bd @@ -115,7 +131,7 @@ runLengthDec :: Integral a => [a] -> [a] runLengthDec [] = [] runLengthDec [_] = error "List must have even length for run-length encoding" -runLengthDec (x:l:xs) = (replicate (fromIntegral l) x) ++ runLengthDec xs +runLengthDec (x:l:xs) = replicate (fromIntegral l) x ++ runLengthDec xs deltaDec :: Num a => [a] -> [a] deltaDec = snd . mapAccumL (\x y -> (x+y,x+y)) 0 @@ -145,4 +161,4 @@ ucDec :: Monad m => [Float] -> m UnitCell ucDec [a,b,c,d,e,f] = pure $ UnitCell a b c d e f -ucDec _ = fail "Wrong list format for unit cell" +ucDec _ = fail "Wrong list format for unit cell" diff --git a/src/Bio/MMTF/Decode/MessagePack.hs b/src/Bio/MMTF/Decode/MessagePack.hs --- a/src/Bio/MMTF/Decode/MessagePack.hs +++ b/src/Bio/MMTF/Decode/MessagePack.hs @@ -9,9 +9,9 @@ transformObjectMap :: Monad m => Object -> m (Map Text Object) transformObjectMap (ObjectMap kv) = let mkPair :: Monad m => (Object, Object) -> m (Text, Object) - mkPair ((ObjectStr txt), v) = pure (txt, v) + mkPair (ObjectStr txt, v) = pure (txt, v) mkPair _ = fail "Non-string key" - in fromList <$> sequence (map mkPair kv) + in fromList <$> traverse mkPair kv transformObjectMap _ = fail "Wrong MessagePack MMTF format" atP :: Monad m => Map Text Object -> Text -> (Object -> m a) -> m a @@ -41,15 +41,15 @@ asFloat _ = fail "Not a float data" asIntList :: (Monad m, Integral a) => Object -> m [a] -asIntList (ObjectArray l) = sequence $ map asInt l +asIntList (ObjectArray l) = traverse asInt l asIntList _ = fail "Not an array of ints data" asStrList :: Monad m => Object -> m [Text] -asStrList (ObjectArray l) = sequence $ map asStr l +asStrList (ObjectArray l) = traverse asStr l asStrList _ = fail "Not an array of string data" asFloatList :: Monad m => Object -> m [Float] -asFloatList (ObjectArray l) = sequence $ map asFloat l +asFloatList (ObjectArray l) = traverse asFloat l asFloatList _ = fail "Not an array of float data" asObjectList :: Monad m => Object -> m [Object] diff --git a/src/Bio/MMTF/Type.hs b/src/Bio/MMTF/Type.hs --- a/src/Bio/MMTF/Type.hs +++ b/src/Bio/MMTF/Type.hs @@ -3,129 +3,142 @@ import Data.Int (Int32, Int8) import Data.Text (Text) --- |Unit cell data -data UnitCell = UnitCell { ucA :: !Float -- ^length of side 'a' - , ucB :: !Float -- ^length of side 'b' - , ucC :: !Float -- ^length of side 'c' - , ucAlpha :: !Float -- ^alpha angle in degrees - , ucBeta :: !Float -- ^beta angle in degrees - , ucGamma :: !Float -- ^gamma angle in degrees +-- | Unit cell data +-- +data UnitCell = UnitCell { ucA :: !Float -- ^ length of side 'a' + , ucB :: !Float -- ^ length of side 'b' + , ucC :: !Float -- ^ length of side 'c' + , ucAlpha :: !Float -- ^ alpha angle in degrees + , ucBeta :: !Float -- ^ beta angle in degrees + , ucGamma :: !Float -- ^ gamma angle in degrees } deriving (Show, Eq) --- |Transform data -data Transform = Transform { chainIndexList :: ![Int32] -- ^indices into the 'chainIdList' and 'chainNameList' fields - , matrix :: ![Float] -- ^4x4 transformation matrix +-- | Transform data +-- +data Transform = Transform { chainIndexList :: ![Int32] -- ^ indices into the 'chainIdList' and 'chainNameList' fields + , matrix :: ![Float] -- ^ 4x4 transformation matrix } deriving (Show, Eq) --- |Assembly data -data Assembly = Assembly { transformList :: ![Transform] -- ^List of transform objects - , assemblyName :: !Text -- ^Name of the biological assembly +-- | Assembly data +-- +data Assembly = Assembly { transformList :: ![Transform] -- ^ List of transform objects + , assemblyName :: !Text -- ^ Name of the biological assembly } deriving (Show, Eq) --- |Entity data -data Entity = Entity { entityChainIndexList :: ![Int32] -- ^indices into the 'chainIdList' and 'chainNameList' fields - , entityDescription :: !Text -- ^Description of the entity - , entityType :: !Text -- ^Name of the entity type - , entitySequence :: !Text -- ^Sequence of the full construct in one-letter-code +-- | Entity data +-- +data Entity = Entity { entityChainIndexList :: ![Int32] -- ^ indices into the 'chainIdList' and 'chainNameList' fields + , entityDescription :: !Text -- ^ Description of the entity + , entityType :: !Text -- ^ Name of the entity type + , entitySequence :: !Text -- ^ Sequence of the full construct in one-letter-code } deriving (Show, Eq) --- |Group type data -data GroupType = GroupType { gtFormalChargeList :: ![Int32] -- ^List of formal charges - , gtAtomNameList :: ![Text] -- ^List of atom names - , gtElementList :: ![Text] -- ^List of elements - , gtBondAtomList :: ![Int32] -- ^List of bonded atom indices - , gtBondOrderList :: ![Int32] -- ^List of bond orders - , gtGroupName :: !Text -- ^The name of the group - , gtSingleLetterCode :: !Char -- ^The single letter code - , gtChemCompType :: !Text -- ^The chemical component type +-- | Group type data +-- +data GroupType = GroupType { gtFormalChargeList :: ![Int32] -- ^ List of formal charges + , gtAtomNameList :: ![Text] -- ^ List of atom names + , gtElementList :: ![Text] -- ^ List of elements + , gtBondAtomList :: ![Int32] -- ^ List of bonded atom indices + , gtBondOrderList :: ![Int32] -- ^ List of bond orders + , gtGroupName :: !Text -- ^ The name of the group + , gtSingleLetterCode :: !Char -- ^ The single letter code + , gtChemCompType :: !Text -- ^ The chemical component type } deriving (Show, Eq) --- |Protein secondary structure -data SecondaryStructure = PiHelix -- ^pi helix - | Bend -- ^bend - | AlphaHelix -- ^alpha helix - | Extended -- ^extended - | ThreeTenHelix -- ^3-10 helix - | Bridge -- ^brigde - | Turn -- ^turn - | Coil -- ^coil - | Undefined -- ^unknown structure +-- | Protein secondary structure +-- +data SecondaryStructure = PiHelix -- ^ pi helix + | Bend -- ^ bend + | AlphaHelix -- ^ alpha helix + | Extended -- ^ extended + | ThreeTenHelix -- ^ 3-10 helix + | Bridge -- ^ brigde + | Turn -- ^ turn + | Coil -- ^ coil + | Undefined -- ^ unknown structure deriving (Show, Eq) --- |MMTF format data -data FormatData = FormatData { mmtfVersion :: !Text -- ^The version number of the specification the file adheres to - , mmtfProducer :: !Text -- ^The name and version of the software used to produce the file +-- | MMTF format data +-- +data FormatData = FormatData { mmtfVersion :: !Text -- ^ The version number of the specification the file adheres to + , mmtfProducer :: !Text -- ^ The name and version of the software used to produce the file } deriving (Show, Eq) --- |Structure data -data StructureData = StructureData { title :: !(Maybe Text) -- ^A short description of the structural data included in the file - , structureId :: !(Maybe Text) -- ^An ID for the structure, for example the PDB ID if applicable - , depositionDate :: !(Maybe Text) -- ^A date that relates to the deposition of the structure in a database - , releaseDate :: !(Maybe Text) -- ^A date that relates to the release of the structure in a database - , numBonds :: !Int32 -- ^The overall number of bonds - , numAtoms :: !Int32 -- ^The overall number of atoms in the structure - , numGroups :: !Int32 -- ^The overall number of groups in the structure - , numChains :: !Int32 -- ^The overall number of chains in the structure - , numModels :: !Int32 -- ^The overall number of models in the structure - , spaceGroup :: !(Maybe Text) -- ^The Hermann-Mauguin space-group symbol - , unitCell :: !(Maybe UnitCell) -- ^Array of six values defining the unit cell - , ncsOperatorList :: !(Maybe [[Float]]) -- ^List of lists representing 4x4 transformation matrices that are stored linearly in row major order (transformation matrices describe noncrystallographic symmetry operations needed to create all molecules in the unit cell) - , bioAssemblyList :: !(Maybe [Assembly]) -- ^List of instructions on how to transform coordinates for an array of chains to create (biological) assemblies - , entityList :: !(Maybe [Entity]) -- ^List of unique molecular entities within the structure - , resolution :: !(Maybe Float) -- ^The experimental resolution in Angstrom - , rFree :: !(Maybe Float) -- ^The R-free value - , rWork :: !(Maybe Float) -- ^The R-work value - , experimentalMethods :: !(Maybe [Text]) -- ^List of experimental methods employed for structure determination - , bondAtomList :: !(Maybe [Int32]) -- ^Pairs of values represent indices of covalently bonded atoms [binary (type 4)] - , bondOrderList :: !(Maybe [Int8]) -- ^List of bond orders for bonds in 'bondAtomList' [binary (type 2)] +-- | Structure data +-- +data StructureData = StructureData { title :: !(Maybe Text) -- ^ A short description of the structural data included in the file + , structureId :: !(Maybe Text) -- ^ An ID for the structure, for example the PDB ID if applicable + , depositionDate :: !(Maybe Text) -- ^ A date that relates to the deposition of the structure in a database + , releaseDate :: !(Maybe Text) -- ^ A date that relates to the release of the structure in a database + , numBonds :: !Int32 -- ^ The overall number of bonds + , numAtoms :: !Int32 -- ^ The overall number of atoms in the structure + , numGroups :: !Int32 -- ^ The overall number of groups in the structure + , numChains :: !Int32 -- ^ The overall number of chains in the structure + , numModels :: !Int32 -- ^ The overall number of models in the structure + , spaceGroup :: !(Maybe Text) -- ^ The Hermann-Mauguin space-group symbol + , unitCell :: !(Maybe UnitCell) -- ^ Array of six values defining the unit cell + , ncsOperatorList :: !(Maybe [[Float]]) -- ^ List of lists representing 4x4 transformation matrices that are stored linearly in row major order (transformation matrices describe noncrystallographic symmetry operations needed to create all molecules in the unit cell) + , bioAssemblyList :: !(Maybe [Assembly]) -- ^ List of instructions on how to transform coordinates for an array of chains to create (biological) assemblies + , entityList :: !(Maybe [Entity]) -- ^ List of unique molecular entities within the structure + , resolution :: !(Maybe Float) -- ^ The experimental resolution in Angstrom + , rFree :: !(Maybe Float) -- ^ The R-free value + , rWork :: !(Maybe Float) -- ^ The R-work value + , experimentalMethods :: !(Maybe [Text]) -- ^ List of experimental methods employed for structure determination + , bondAtomList :: !(Maybe [Int32]) -- ^ Pairs of values represent indices of covalently bonded atoms [binary (type 4)] + , bondOrderList :: !(Maybe [Int8]) -- ^ List of bond orders for bonds in 'bondAtomList' [binary (type 2)] } deriving (Show, Eq) --- |Models data -data ModelData = ModelData { chainsPerModel :: ![Int32] -- ^List of the number of chains in each model +-- | Models data +-- +data ModelData = ModelData { chainsPerModel :: ![Int32] -- ^ List of the number of chains in each model } deriving (Show, Eq) --- |Chains data -data ChainData = ChainData { groupsPerChain :: ![Int32] -- ^List of the number of groups (aka residues) in each chain - , chainIdList :: ![Text] -- ^List of chain IDs [binary (type 5)] - , chainNameList :: !(Maybe [Text]) -- ^List of chain names [binary (type 5)] +-- | Chains data +-- +data ChainData = ChainData { groupsPerChain :: ![Int32] -- ^ List of the number of groups (aka residues) in each chain + , chainIdList :: ![Text] -- ^ List of chain IDs [binary (type 5)] + , chainNameList :: !(Maybe [Text]) -- ^ List of chain names [binary (type 5)] } deriving (Show, Eq) --- |Groups data -data GroupData = GroupData { groupList :: ![GroupType] -- ^List of groupType objects - , groupTypeList :: ![Int32] -- ^List of pointers to 'groupType' entries in 'groupList' by their keys[binary (type 4)] - , groupIdList :: ![Int32] -- ^List of group (residue) numbers [binary (type 8)] - , secStructList :: !(Maybe [SecondaryStructure]) -- ^List of secondary structure assignments [binary (type 2)] - , insCodeList :: !(Maybe [Char]) -- ^List of insertion codes, one for each group (residue) [binary (type 6)] - , sequenceIndexList :: !(Maybe [Int32]) -- ^List of indices that point into the sequence property of an entity object in the 'entityList' field that is associated with the chain the group belongs to [binary (type 8)] +-- | Groups data +-- +data GroupData = GroupData { groupList :: ![GroupType] -- ^ List of groupType objects + , groupTypeList :: ![Int32] -- ^ List of pointers to 'groupType' entries in 'groupList' by their keys [binary (type 4)] + , groupIdList :: ![Int32] -- ^ List of group (residue) numbers [binary (type 8)] + , secStructList :: !(Maybe [SecondaryStructure]) -- ^ List of secondary structure assignments [binary (type 2)] + , insCodeList :: !(Maybe [Char]) -- ^ List of insertion codes, one for each group (residue) [binary (type 6)] + , sequenceIndexList :: !(Maybe [Int32]) -- ^ List of indices that point into the sequence property of an entity object in the 'entityList' field that is associated with the chain the group belongs to [binary (type 8)] } deriving (Show, Eq) --- |Atoms data -data AtomData = AtomData { atomIdList :: !(Maybe [Int32]) -- ^List of atom serial numbers [binary (type 8)] - , altLocList :: !(Maybe [Char]) -- ^List of alternate location labels, one for each atom [binary (type 6)] - , bFactorList :: !(Maybe [Float]) -- ^List of atom B-factors in in A^2, one for each atom [binary (type 10)] - , xCoordList :: ![Float] -- ^List of x atom coordinates in A, one for each atom [binary (type 10)] - , yCoordList :: ![Float] -- ^List of y atom coordinates in A, one for each atom [binary (type 10)] - , zCoordList :: ![Float] -- ^List of z atom coordinates in A, one for each atom [binary (type 10)] - , occupancyList :: !(Maybe [Float]) -- ^List of atom occupancies, one for each atom [binary (type 9)] +-- | Atoms data +-- +data AtomData = AtomData { atomIdList :: !(Maybe [Int32]) -- ^ List of atom serial numbers [binary (type 8)] + , altLocList :: !(Maybe [Char]) -- ^ List of alternate location labels, one for each atom [binary (type 6)] + , bFactorList :: !(Maybe [Float]) -- ^ List of atom B-factors in in A^2, one for each atom [binary (type 10)] + , xCoordList :: ![Float] -- ^ List of x atom coordinates in A, one for each atom [binary (type 10)] + , yCoordList :: ![Float] -- ^ List of y atom coordinates in A, one for each atom [binary (type 10)] + , zCoordList :: ![Float] -- ^ List of z atom coordinates in A, one for each atom [binary (type 10)] + , occupancyList :: !(Maybe [Float]) -- ^ List of atom occupancies, one for each atom [binary (type 9)] } deriving (Show, Eq) --- |MMTF datatype -data MMTF = MMTF { format :: !FormatData -- ^MMTF format data - , structure :: !StructureData -- ^Biological structure data - , model :: !ModelData -- ^Models data - , chain :: !ChainData -- ^Chains data - , group :: !GroupData -- ^Groups data - , atom :: !AtomData -- ^Atoms data +-- | MMTF datatype +-- +data MMTF = MMTF { format :: !FormatData -- ^ MMTF format data + , structure :: !StructureData -- ^ Biological structure data + , model :: !ModelData -- ^ Models data + , chain :: !ChainData -- ^ Chains data + , group :: !GroupData -- ^ Groups data + , atom :: !AtomData -- ^ Atoms data } deriving (Show, Eq) diff --git a/test/Spec.hs b/test/Spec.hs --- a/test/Spec.hs +++ b/test/Spec.hs @@ -10,5 +10,5 @@ it "should parse 1FSD" $ do contents <- B.readFile "resource/1FSD.mmtf" m <- decode contents - let sid = (structureId . structure) m - sid `shouldBe` Just "1FSD" + (structureId . structure) m `shouldBe` Just "1FSD" + (numModels . structure) m `shouldBe` 41