Add secondary structure prediction.

.gitignore

@@ -5,3 +5,4 @@ docs/build/
 docs/site/
 .DS_Store
 benchmark/tune.json
+Manifest.toml

Project.toml

@@ -1,7 +1,7 @@
 name = "BioStructures"
 uuid = "de9282ab-8554-53be-b2d6-f6c222edabfc"
 authors = ["Joe G Greener <[email protected]>"]
-version = "2.0.0"
+version = "2.0.1"
 
 [deps]
 BioAlignments = "00701ae9-d1dc-5365-b64a-a3a3ebf5695e"
@@ -10,6 +10,7 @@ BioGenerics = "47718e42-2ac5-11e9-14af-e5595289c2ea"
 BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
 BioSymbols = "3c28c6f8-a34d-59c4-9654-267d177fcfa9"
 CodecZlib = "944b1d66-785c-5afd-91f1-9de20f533193"
+DSSP_jll = "74334e00-59ce-546d-b517-81f3b7e1d491"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Downloads = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
 Format = "1fa38f19-a742-5d3f-a2b9-30dd87b9d5f8"
@@ -18,6 +19,7 @@ LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 MMTF = "259c3a9c-12c3-507f-b21f-68ecc40fcda4"
 MetaGraphs = "626554b9-1ddb-594c-aa3c-2596fe9399a5"
 RecipesBase = "3cdcf5f2-1ef4-517c-9805-6587b60abb01"
+STRIDE_jll = "850473c1-9ef0-5df9-a957-757f4cde8b8b"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 
 [compat]
@@ -27,13 +29,15 @@ BioGenerics = "0.1"
 BioSequences = "3"
 BioSymbols = "5"
 CodecZlib = "0.7"
+DSSP_jll = "4.4"
 DataFrames = "1"
 Downloads = "1"
 Format = "1.3"
 Graphs = "1"
 MMTF = "1"
 MetaGraphs = "0.7"
 RecipesBase = "1"
+STRIDE_jll = "1"
 julia = "1.6"
 
 [extras]

benchmark/benchmarks.jl

@@ -19,59 +19,95 @@ temp_filename, io = mktemp()
 close(io)
 
 pdbids = ["1AKE", "1EN2", "1SSU"]
-formats = Dict("PDB"=> PDB, "mmCIF"=> MMCIF, "MMTF"=> MMTF)
-writefunctions = Dict("PDB"=> writepdb, "mmCIF"=> writemmcif, "MMTF"=> writemmtf)
+formats = Dict("PDB" => PDB, "mmCIF" => MMCIF, "MMTF" => MMTF)
+writefunctions = Dict("PDB" => writepdb, "mmCIF" => writemmcif, "MMTF" => writemmtf)
 
 const SUITE = BenchmarkGroup(
-        [],
-        "read"   => BenchmarkGroup([], [f=> BenchmarkGroup() for f in keys(formats)]...),
-        "write"  => BenchmarkGroup([], [f=> BenchmarkGroup() for f in keys(formats)]...),
-        "dict"   => BenchmarkGroup(),
-        "model"  => BenchmarkGroup(),
-        "collect"=> BenchmarkGroup(),
-        "spatial"=> BenchmarkGroup(),
+    [],
+    "read" => BenchmarkGroup([], [f => BenchmarkGroup() for f in keys(formats)]...),
+    "write" => BenchmarkGroup([], [f => BenchmarkGroup() for f in keys(formats)]...),
+    "dict" => BenchmarkGroup(),
+    "model" => BenchmarkGroup(),
+    "collect" => BenchmarkGroup(),
+    "spatial" => BenchmarkGroup(),
 )
 
-struc = Dict{String, ProteinStructure}()
+struc = Dict{String,ProteinStructure}()
 for pdbid in pdbids
     struc[pdbid] = read(testfilepath("PDB", "$pdbid.pdb"), PDB)
 end
 
 for pdbid in pdbids
     for f in keys(formats)
         SUITE["read"][f][pdbid] = @benchmarkable read(
-                $(testfilepath(f, "$pdbid.$(pdbextension[formats[f]])")), $(formats[f]))
-        SUITE["write"][f][pdbid] = @benchmarkable $(writefunctions[f])(
-                $temp_filename, $(struc[pdbid])) teardown=(rm(temp_filename, force=true))
+            $(testfilepath(f, "$pdbid.$(pdbextension[formats[f]])")),
+            $(formats[f]),
+        )
+        SUITE["write"][f][pdbid] =
+            @benchmarkable $(writefunctions[f])($temp_filename, $(struc[pdbid])) teardown =
+                (rm(temp_filename, force = true))
     end
 end
 
-SUITE["dict"]["mmCIF"] = @benchmarkable MMCIFDict($(testfilepath("mmCIF", "1AKE.cif" )))
-SUITE["dict"]["MMTF" ] = @benchmarkable MMTFDict( $(testfilepath("MMTF" , "1AKE.mmtf")))
+SUITE["dict"]["mmCIF"] = @benchmarkable MMCIFDict($(testfilepath("mmCIF", "1AKE.cif")))
+SUITE["dict"]["MMTF"] = @benchmarkable MMTFDict($(testfilepath("MMTF", "1AKE.mmtf")))
 
-SUITE["model"]["atomaccess"  ] = @benchmarkable $(struc["1EN2"])["A"][20]["CA"]
-SUITE["model"]["sortatoms"   ] = @benchmarkable sort(ats) setup=(ats = shuffle(collectatoms(   struc["1EN2"])))
-SUITE["model"]["sortresidues"] = @benchmarkable sort(res) setup=(res = shuffle(collectresidues(struc["1EN2"])))
-SUITE["model"]["iterate"     ] = @benchmarkable for mod in $(struc["1AKE"]) for ch in mod for res in ch for at in res end end end end
-SUITE["model"]["sequence"    ] = @benchmarkable LongAA($(collectresidues(struc["1EN2"])))
-SUITE["model"]["pdbline"     ] = @benchmarkable pdbline($(struc["1EN2"]["A"][20]["CA"]))
+SUITE["model"]["atomaccess"] = @benchmarkable $(struc["1EN2"])["A"][20]["CA"]
+SUITE["model"]["sortatoms"] =
+    @benchmarkable sort(ats) setup = (ats = shuffle(collectatoms(struc["1EN2"])))
+SUITE["model"]["sortresidues"] =
+    @benchmarkable sort(res) setup = (res = shuffle(collectresidues(struc["1EN2"])))
+SUITE["model"]["iterate"] = @benchmarkable for mod in $(struc["1AKE"])
+    for ch in mod
+        for res in ch
+            for at in res
+            end
+        end
+    end
+end
+SUITE["model"]["sequence"] = @benchmarkable LongAA($(collectresidues(struc["1EN2"])))
+SUITE["model"]["pdbline"] = @benchmarkable pdbline($(struc["1EN2"]["A"][20]["CA"]))
 
-SUITE["collect"]["atoms"       ] = @benchmarkable collectatoms(   $(struc["1EN2"]))
-SUITE["collect"]["atomssel"    ] = @benchmarkable collectatoms(   $(struc["1EN2"]), calphaselector)
-SUITE["collect"]["atomsdis"    ] = @benchmarkable collectatoms(   $(struc["1EN2"]), expand_disordered=true)
-SUITE["collect"]["residues"    ] = @benchmarkable collectresidues($(struc["1EN2"]))
-SUITE["collect"]["residuessel" ] = @benchmarkable collectresidues($(struc["1EN2"]), standardselector)
-SUITE["collect"]["residuesdis" ] = @benchmarkable collectresidues($(struc["1EN2"]), expand_disordered=true)
-SUITE["collect"]["chains"      ] = @benchmarkable collectchains(  $(struc["1AKE"]))
-SUITE["collect"]["models"      ] = @benchmarkable collectmodels(  $(struc["1SSU"]))
+SUITE["collect"]["atoms"] = @benchmarkable collectatoms($(struc["1EN2"]))
+SUITE["collect"]["atomssel"] = @benchmarkable collectatoms($(struc["1EN2"]), calphaselector)
+SUITE["collect"]["atomsdis"] =
+    @benchmarkable collectatoms($(struc["1EN2"]), expand_disordered = true)
+SUITE["collect"]["residues"] = @benchmarkable collectresidues($(struc["1EN2"]))
+SUITE["collect"]["residuessel"] =
+    @benchmarkable collectresidues($(struc["1EN2"]), standardselector)
+SUITE["collect"]["residuesdis"] =
+    @benchmarkable collectresidues($(struc["1EN2"]), expand_disordered = true)
+SUITE["collect"]["chains"] = @benchmarkable collectchains($(struc["1AKE"]))
+SUITE["collect"]["models"] = @benchmarkable collectmodels($(struc["1SSU"]))
 
-SUITE["spatial"]["coordarray"    ] = @benchmarkable coordarray($(collectatoms(struc["1AKE"])))
-SUITE["spatial"]["transformation"] = @benchmarkable Transformation($(collectresidues(struc["1SSU"][5], standardselector)), $(collectresidues(struc["1SSU"][10], standardselector)))
-SUITE["spatial"]["rmsd"          ] = @benchmarkable rmsd($(coordarray(struc["1SSU"][5], heavyatomselector)), $(coordarray(struc["1SSU"][10], heavyatomselector)))
-SUITE["spatial"]["distance"      ] = @benchmarkable distance($(struc["1AKE"]["A"][50]), $(struc["1AKE"]["A"][60]))
-SUITE["spatial"]["bondangle"     ] = @benchmarkable bondangle($(struc["1AKE"]["A"][20]["N"]), $(struc["1AKE"]["A"][20]["CA"]), $(struc["1AKE"]["A"][20]["C"]))
-SUITE["spatial"]["dihedralangle" ] = @benchmarkable dihedralangle($(struc["1AKE"]["A"][20]["N"]), $(struc["1AKE"]["A"][20]["CA"]), $(struc["1AKE"]["A"][20]["C"]), $(struc["1AKE"]["A"][21]["N"]))
-SUITE["spatial"]["ramachandran"  ] = @benchmarkable ramachandranangles($(collectresidues(struc["1AKE"]["A"], standardselector)))
-SUITE["spatial"]["contactmap"    ] = @benchmarkable ContactMap($(collectatoms(struc["1AKE"]["A"], cbetaselector)), 8.0)
-SUITE["spatial"]["distancemap"   ] = @benchmarkable DistanceMap($(collectresidues(struc["1AKE"]["A"], standardselector)))
-SUITE["spatial"]["contactgraph"  ] = @benchmarkable MetaGraph($(collectatoms(struc["1AKE"]["A"], cbetaselector)), 8.0)
+SUITE["spatial"]["coordarray"] = @benchmarkable coordarray($(collectatoms(struc["1AKE"])))
+SUITE["spatial"]["transformation"] = @benchmarkable Transformation(
+    $(collectresidues(struc["1SSU"][5], standardselector)),
+    $(collectresidues(struc["1SSU"][10], standardselector)),
+)
+SUITE["spatial"]["rmsd"] = @benchmarkable rmsd(
+    $(coordarray(struc["1SSU"][5], heavyatomselector)),
+    $(coordarray(struc["1SSU"][10], heavyatomselector)),
+)
+SUITE["spatial"]["distance"] =
+    @benchmarkable distance($(struc["1AKE"]["A"][50]), $(struc["1AKE"]["A"][60]))
+SUITE["spatial"]["bondangle"] = @benchmarkable bondangle(
+    $(struc["1AKE"]["A"][20]["N"]),
+    $(struc["1AKE"]["A"][20]["CA"]),
+    $(struc["1AKE"]["A"][20]["C"]),
+)
+SUITE["spatial"]["dihedralangle"] = @benchmarkable dihedralangle(
+    $(struc["1AKE"]["A"][20]["N"]),
+    $(struc["1AKE"]["A"][20]["CA"]),
+    $(struc["1AKE"]["A"][20]["C"]),
+    $(struc["1AKE"]["A"][21]["N"]),
+)
+SUITE["spatial"]["ramachandran"] = @benchmarkable ramachandranangles(
+    $(collectresidues(struc["1AKE"]["A"], standardselector)),
+)
+SUITE["spatial"]["contactmap"] =
+    @benchmarkable ContactMap($(collectatoms(struc["1AKE"]["A"], cbetaselector)), 8.0)
+SUITE["spatial"]["distancemap"] =
+    @benchmarkable DistanceMap($(collectresidues(struc["1AKE"]["A"], standardselector)))
+SUITE["spatial"]["contactgraph"] =
+    @benchmarkable MetaGraph($(collectatoms(struc["1AKE"]["A"], cbetaselector)), 8.0)

docs/make.jl

@@ -4,14 +4,11 @@ using BioStructures
 makedocs(
     sitename = "BioStructures.jl",
     pages = [
-        "Home"         => "index.md",
-        "Documentation"=> "documentation.md",
-        "Examples"     => "examples.md",
-        "API"          => "api.md",
-    ]
+        "Home" => "index.md",
+        "Documentation" => "documentation.md",
+        "Examples" => "examples.md",
+        "API" => "api.md",
+    ],
 )
 
-deploydocs(
-    repo="github.com/BioJulia/BioStructures.jl.git",
-    push_preview=true,
-)
+deploydocs(repo = "github.com/BioJulia/BioStructures.jl.git", push_preview = true)

docs/src/documentation.md

@@ -92,6 +92,7 @@ Properties can be retrieved as follows:
 | [`resnumber`](@ref)          | Residue number of a residue or atom                           | `Int`                           |
 | [`sequentialresidues`](@ref) | Determine if the second residue follows the first in sequence | `Bool`                          |
 | [`inscode`](@ref)            | Insertion code of a residue or atom                           | `Char`                          |
+| [`ss_code`](@ref)            | Secondary Structure code of a residue or atom                 | `String`                        |
 | [`resid`](@ref)              | Residue ID of an atom or residue (`full=true` includes chain) | `String`                        |
 | [`atomnames`](@ref)          | Atom names of the atoms in a residue, sorted by serial        | `Array{String,1}`               |
 | [`atoms`](@ref)              | Dictionary of atoms in a residue                              | `Dict{String,AbstractAtom}`    |
@@ -170,6 +171,9 @@ The selectors available are:
 | [`notwaterselector`](@ref)  | `AbstractAtom` or `AbstractResidue` | Atoms/residues with residue name not HOH            |
 | [`disorderselector`](@ref)  | `AbstractAtom` or `AbstractResidue` | Atoms/residues with alternative locations           |
 | [`allselector`](@ref)       | `AbstractAtom` or `AbstractResidue` | All atoms/residues                                  |
+| [`helixselector`](@ref)     | `Atom` or `Residue`                 | Atoms/residues arising from Helix                   |
+| [`sheetselector`](@ref)     | `Atom` or `Residue`                 | Atoms/residues arising from Sheet                   |
+| [`coilselector`](@ref)      | `Atom` or `Residue`                 | Atoms/residues arising from Coil                    |
 
 To create a new [`atomnameselector`](@ref) or [`resnameselector`](@ref):
 ```julia

src/BioStructures.jl

@@ -25,11 +25,14 @@ using Graphs
 using MetaGraphs
 import MMTF: parsemmtf, writemmtf # Imported to avoid clash with MMTF name
 using RecipesBase
+using STRIDE_jll: STRIDE_jll # for secondary structure prediction
+using DSSP_jll: DSSP_jll # for secondary structure prediction
 
 include("model.jl")
 include("pdb.jl")
 include("mmcif.jl")
 include("mmtf.jl")
 include("spatial.jl")
+include("secondary.jl")
 
 end # BioStructures