Bump to 2.1.0

Project.toml

@@ -1,7 +1,7 @@
 name = "BioStructures"
 uuid = "de9282ab-8554-53be-b2d6-f6c222edabfc"
 authors = ["Joe G Greener <[email protected]>"]
-version = "2.0.1"
+version = "2.1.0"
 
 [deps]
 BioAlignments = "00701ae9-d1dc-5365-b64a-a3a3ebf5695e"

docs/src/documentation.md

@@ -92,7 +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`                        |
+| [`sscode`](@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}`    |
@@ -174,8 +174,9 @@ The selectors available are:
 | [`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                    |
+| [`sscodeselector`](@ref)    | `Atom` or `Residue`                 | Atoms/residues with ss_code in a given list         |
 
-To create a new [`atomnameselector`](@ref) or [`resnameselector`](@ref):
+To create a new [`atomnameselector`](@ref), [`resnameselector`](@ref) or [`sscodeselector`](@ref):
 ```julia
 cdeltaselector(at::AbstractAtom) = atomnameselector(at, ["CD"])
 ```
@@ -408,6 +409,39 @@ See the [Graphs docs](https://juliagraphs.org/Graphs.jl/dev) for details on how
 Similar to [`ContactMap`](@ref), contacts are found between any element type passed in.
 So if you wanted the graph of chain contacts in a protein complex you could give a [`Model`](@ref) as the first argument.
 
+## Assigning Secondary Structure
+
+The secondary structure code can be accessed after assinging the secodnary structure using [DSSP](https://github.com/PDB-REDO/dssp) or [STRIDE](https://webclu.bio.wzw.tum.de/stride/).
+
+To assign the secondary structure when reading the structure
+```julia
+# Assign secondary structure using DSSP
+read("path/to/pdb", PDB, run_dssp=true)
+
+# Assign secondary structure using STRIDE
+read("path/to/pdb", PDB, run_strude=true)
+```
+
+[`rundssp(struc)`](@ref), [`runstride(struc)`](@ref), [`rundssp!(struc)`](@ref) and [`runstride!(struc)`](@ref) can also be used to assign secondary structure to [`ProteinStructure`](@ref).
+```julia
+struc = rundssp(struc)
+
+struc = runstride(struc)
+
+rundssp!(struc)
+
+rundssp!(struc)
+```
+The assigning process may fail if the structure is too large, since we use an intermediate PDB file whose atom serial number cannot exceeds `99999`.
+
+To get access to the secondary structure code of atom/residue
+```julia
+sscode(at)
+sscode(res)
+```
+
+The sscode of an atom/residue can be changed using [`sscode!`](@ref).
+
 ## Downloading PDB files
 
 To download a PDB file to a specified directory:

src/BioStructures.jl

@@ -25,8 +25,10 @@ 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
+using STRIDE_jll
+# STRIDE_jll # for secondary structure prediction
+using DSSP_jll
+# DSSP_jll # for secondary structure prediction
 
 include("model.jl")
 include("pdb.jl")

src/mmcif.jl

@@ -271,7 +271,9 @@ function Base.read(input::IO,
             remove_disorder::Bool=false,
             read_std_atoms::Bool=true,
             read_het_atoms::Bool=true,
-            gzip::Bool=false)
+            gzip::Bool=false,
+            run_dssp::Bool=false,
+            run_stride::Bool=false,)
     mmcif_dict = MMCIFDict()
     if gzip
         gz = GzipDecompressorStream(input)
@@ -285,14 +287,18 @@ function Base.read(input::IO,
                      structure_name=structure_name,
                      remove_disorder=remove_disorder,
                      read_std_atoms=read_std_atoms,
-                     read_het_atoms=read_het_atoms)
+                     read_het_atoms=read_het_atoms,
+                     run_dssp=run_dssp,
+                     run_stride=run_stride)
 end
 
 function ProteinStructure(mmcif_dict::MMCIFDict;
             structure_name::AbstractString="",
             remove_disorder::Bool=false,
             read_std_atoms::Bool=true,
-            read_het_atoms::Bool=true)
+            read_het_atoms::Bool=true,
+            run_dssp::Bool=false,
+            run_stride::Bool=false,)
     # Define ProteinStructure and add to it incrementally
     struc = ProteinStructure(structure_name)
     if haskey(mmcif_dict, "_atom_site.id")
@@ -313,6 +319,15 @@ function ProteinStructure(mmcif_dict::MMCIFDict;
         # Generate lists for iteration
         fixlists!(struc)
     end
+
+    # Run DSSP and STRIDE if required
+    if run_dssp
+        rundssp!(struc)
+    end
+
+    if run_stride
+        runstride!(struc)
+    end
     return struc
 end
 

src/mmtf.jl

@@ -96,20 +96,26 @@ function Base.read(input::IO,
             remove_disorder::Bool=false,
             read_std_atoms::Bool=true,
             read_het_atoms::Bool=true,
-            gzip::Bool=false)
+            gzip::Bool=false,
+            run_dssp::Bool=false,
+            run_stride::Bool=false,)
     d = MMTFDict(parsemmtf(input; gzip=gzip))
     ProteinStructure(d;
                      structure_name=structure_name,
                      remove_disorder=remove_disorder,
                      read_std_atoms=read_std_atoms,
-                     read_het_atoms=read_het_atoms)
+                     read_het_atoms=read_het_atoms,
+                     run_dssp=run_dssp,
+                     run_stride=run_stride)
 end
 
 function ProteinStructure(d::MMTFDict;
             structure_name::AbstractString="",
             remove_disorder::Bool=false,
             read_std_atoms::Bool=true,
-            read_het_atoms::Bool=true)
+            read_het_atoms::Bool=true,
+            run_dssp::Bool=false,
+            run_stride::Bool=false)
     struc = ProteinStructure(structure_name)
     # Extract hetero atom information from entity list
     hets = trues(length(d["chainIdList"]))
@@ -176,6 +182,16 @@ function ProteinStructure(d::MMTFDict;
         end
     end
     fixlists!(struc)
+
+    # Run DSSP and STRIDE if required
+    if run_dssp
+        rundssp!(struc)
+    end
+
+    if run_stride
+        runstride!(struc)
+    end
+
     return struc
 end
 

src/model.jl

@@ -223,8 +223,9 @@ function Residue(name::AbstractString,
                 number::Integer,
                 ins_code::Char,
                 het_res::Bool,
-                ch::Chain)
-    return Residue(name, number, ins_code, het_res, [], Dict(), ch, "")
+                ch::Chain,
+                ss_code::String="")
+    return Residue(name, number, ins_code, het_res, [], Dict(), ch, ss_code)
 end
 
 """

src/pdb.jl

@@ -461,7 +461,9 @@ function Base.read(input::IO,
             structure_name::AbstractString="",
             remove_disorder::Bool=false,
             read_std_atoms::Bool=true,
-            read_het_atoms::Bool=true)
+            read_het_atoms::Bool=true,
+            run_dssp::Bool=false,
+            run_stride::Bool=false,)
     # Define ProteinStructure and add to it incrementally
     struc = ProteinStructure(structure_name)
     struc[1] = Model(1, struc)
@@ -501,6 +503,14 @@ function Base.read(input::IO,
     end
     # Generate lists for iteration
     fixlists!(struc)
+    # Run DSSP and STRIDE if required
+    if run_dssp
+        rundssp!(struc)
+    end
+
+    if run_stride
+        runstride!(struc)
+    end
     return struc
 end