diff --git a/Bio/PDB/Structure/Elements.hs b/Bio/PDB/Structure/Elements.hs --- a/Bio/PDB/Structure/Elements.hs +++ b/Bio/PDB/Structure/Elements.hs @@ -6,7 +6,9 @@ -- Guessing element name from atom name (for standard residues only.) guessElement, -- properties of elements - atomicNumber, atomicMass, covalentRadius, vanDerWaalsRadius) where + atomicNumber, atomicMass, + covalentRadius, maxCovalentRadius, + vanDerWaalsRadius, maxVanDerWaalsRadius) where import Prelude hiding (error, String) import Data.ByteString.Char8 as BS @@ -251,6 +253,7 @@ covalentRadius "ZR" = 1.75 covalentRadius x = defaulting ["Unknown covalent radius for element:", BS.pack $ show x] 0.0 +maxCovalentRadius = covalentRadius "FR" {-# INLINE atomicMass #-} -- | Atomic mass of a given element in g/mol @@ -481,6 +484,8 @@ vanDerWaalsRadius "ZN" = 1.39 vanDerWaalsRadius "ZR" = 2.00 vanDerWaalsRadius e = defaulting ["Do not know van der Waals radius of", BS.pack $ show e] 0.0 + +maxVanDerWaalsRadius = vanDerWaalsRadius "K" {-# INLINE assignElement #-} -- | Given a PDB 'Atom' extract or guess its 'Element' name. diff --git a/Bio/PDB/Structure/Neighbours.hs b/Bio/PDB/Structure/Neighbours.hs new file mode 100644 --- /dev/null +++ b/Bio/PDB/Structure/Neighbours.hs @@ -0,0 +1,30 @@ +{-# LANGUAGE NoMonomorphismRestriction, FlexibleContexts #-} +-- | Searching for neighbouring atoms in a 3D space using `Octree`. +module Bio.PDB.Structure.Neighbours(makeOctree, findInRadius, findNearest) +where + +import qualified Data.Octree as Oct +import Bio.PDB.Structure +import Bio.PDB.Iterable +import Data.Vector.V3 + +-- | Octree of `Atom`s. +type AtomOctree = Oct.Octree Atom + +-- | Preparing atom to be inserted into `Octree`. +extract :: Atom -> (Oct.Vector3, Atom) +extract (at@(Atom { coord = cvec, + atSerial = ser , + element = elt })) = (cvec, at) + +-- | Make an Octree of `Atom`s +makeOctree :: Iterable a Atom => a -> AtomOctree +makeOctree = Oct.fromList . Prelude.map extract . itfoldr (:) [] + +-- | Find all `Atom`s within a given radius from a point. +findInRadius :: AtomOctree -> Double -> Vector3 -> [(Vector3, Atom)] +findInRadius = Oct.withinRange + +-- | Find an `Atom`s closest to a point. +findNearest :: AtomOctree -> Vector3 -> Maybe (Vector3, Atom) +findNearest = Oct.nearest diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ ==== Haskell PDB file format parser. -[![Build Status](https://api.travis-ci.org/mgajda/hPDB.png?branch=master)](https://travis-ci.org/mgajda/hPDB) +[![Build Status](https://api.travis-ci.org/BioHaskell/hPDB.png?branch=master)](https://travis-ci.org/BioHaskell/hPDB) Protein Data Bank file format is a most popular format for holding biomolecule data. diff --git a/hPDB.cabal b/hPDB.cabal --- a/hPDB.cabal +++ b/hPDB.cabal @@ -1,14 +1,26 @@ name: hPDB -version: 1.0 +version: 1.1 synopsis: Protein Databank file format library -homepage: https://github.com/mgajda/hpdb +homepage: https://github.com/BioHaskell/hPDB stability: stable package-url: http://hackage.haskell.org/package/hPDB -description: Protein Data Bank file format is a most popular format for holding biomolecule data. +description: Protein Data Bank file format is a most popular format for holding biological macromolecular data. . - This is a very fast parser: below 7s for the largest entry in PDB - 1HTQ which is over 70MB - as compared with 11s of RASMOL 2.7.5, or 2m15s of BioPython with Python 2.6 interpreter. + This is a very fast sequential parser: . - It is aimed to not only deliver event-based interface, but also a high-level data structure for manipulating data in spirit of BioPython's PDB parser. + * below 7s for the largest entry in PDB - 1HTQ which is over 70MB - as compared with + . + * 11s of RASMOL 2.7.5, + . + * or 2m15s of BioPython with Python 2.6 interpreter. + . + In its parallel incarnation it is most probably the fastest parser for PDB format. + . + It is aimed to not only deliver event-based interface, but also a high-level data + structure for manipulating data in spirit of BioPython's PDB parser. + . + + category: Bioinformatics license: BSD3 license-file: LICENSE @@ -25,7 +37,7 @@ source-repository head type: git - location: https://github.com/mgajda/hPDB + location: https://github.com/BioHaskell/hPDB flag have-mmap description: Use mmap to read input faster. @@ -65,7 +77,7 @@ Library ghc-options: -fspec-constr-count=4 -O3 - build-depends: base>=4.0, base <4.8, ghc-prim, directory, mtl, template-haskell, vector, AC-Vector, containers, deepseq, QuickCheck >= 2.5.0.0, text>=0.11.1.13, iterable >= 2.0, parallel >= 3.0.0.0, bytestring, zlib + build-depends: base>=4.0, base <4.8, ghc-prim, directory, mtl, template-haskell, vector, AC-Vector, containers, deepseq, QuickCheck >= 2.5.0.0, text>=0.11.1.13, iterable >= 2.0, parallel >= 3.0.0.0, bytestring, zlib, Octree>= 0.5 if flag(have-sse2) ghc-options: -msse2 if flag(have-mmap) @@ -78,6 +90,6 @@ build-depends: text-format >= 0.3.1.0 other-extensions: ScopedTypeVariables OverloadedStrings BangPatterns NoMonomorphismRestriction EmptyDataDecls MagicHash CPP PatternGuards NamedFieldPuns DisambiguateRecordFields TemplateHaskell MultiParamTypeClasses FlexibleInstances FlexibleContexts other-modules: Bio.PDB.EventParser.ParseATOM, Bio.PDB.EventParser.ParseCAVEAT, Bio.PDB.EventParser.ParseCISPEP, Bio.PDB.EventParser.ParseCONECT, Bio.PDB.EventParser.ParseCRYST1, Bio.PDB.EventParser.ParseDBREF, Bio.PDB.EventParser.ParseFORMUL, Bio.PDB.EventParser.ParseHEADER, Bio.PDB.EventParser.ParseHELIX, Bio.PDB.EventParser.ParseHET, Bio.PDB.EventParser.ParseHETNAM, Bio.PDB.EventParser.ParseHYDBND, Bio.PDB.EventParser.ParseIntRecord, Bio.PDB.EventParser.ParseJRNL, Bio.PDB.EventParser.ParseLINK, Bio.PDB.EventParser.ParseListRecord, Bio.PDB.EventParser.ParseMASTER, Bio.PDB.EventParser.ParseMatrixRecord, Bio.PDB.EventParser.ParseMODRES, Bio.PDB.EventParser.ParseObsoleting, Bio.PDB.EventParser.ParseREMARK, Bio.PDB.EventParser.ParseREVDAT, Bio.PDB.EventParser.ParseSEQADV, Bio.PDB.EventParser.ParseSEQRES, Bio.PDB.EventParser.ParseSHEET, Bio.PDB.EventParser.ParseSITE, Bio.PDB.EventParser.ParseSLTBRG, Bio.PDB.EventParser.ParseSpecListRecord, Bio.PDB.EventParser.ParseSPLIT, Bio.PDB.EventParser.ParseSSBOND, Bio.PDB.EventParser.ParseTER, Bio.PDB.EventParser.ParseTITLE, Bio.PDB.EventParser.ParseTVECT, Bio.PDB.EventParser.PDBParsingAbstractions, Bio.PDB.EventParser.FastParse, Bio.PDB.Util.MissingInstances, Bio.PDB.Common, Bio.PDB.Iterable.Utils, Bio.PDB.Iterable.Instances, Bio.PDB.StructureBuilder.Internals, Bio.PDB.StructureBuilder.Parallel - exposed-modules: Bio.PDB.EventParser.PDBEvents, Bio.PDB.EventParser.PDBEventParser, Bio.PDB.EventParser.ExperimentalMethods, Bio.PDB.EventParser.HelixTypes, Bio.PDB.EventParser.StrandSense, Bio.PDB.Structure, Bio.PDB.StructureBuilder, Bio.PDB.Iterable, Bio.PDB.IO, Bio.PDB.Fasta, Bio.PDB, Bio.PDB.Structure.Vector, Bio.PDB.Structure.Elements, Bio.PDB.Structure.List, Bio.PDB.StructurePrinter, Bio.PDB.EventParser.PDBEventPrinter, Bio.PDB.IO.OpenAnyFile + exposed-modules: Bio.PDB.EventParser.PDBEvents, Bio.PDB.EventParser.PDBEventParser, Bio.PDB.EventParser.ExperimentalMethods, Bio.PDB.EventParser.HelixTypes, Bio.PDB.EventParser.StrandSense, Bio.PDB.Structure, Bio.PDB.StructureBuilder, Bio.PDB.Iterable, Bio.PDB.IO, Bio.PDB.Fasta, Bio.PDB, Bio.PDB.Structure.Vector, Bio.PDB.Structure.Elements, Bio.PDB.Structure.List, Bio.PDB.StructurePrinter, Bio.PDB.EventParser.PDBEventPrinter, Bio.PDB.IO.OpenAnyFile, Bio.PDB.Structure.Neighbours exposed: True