relax PDB requirements

.github/workflows/docker_build.yml

@@ -23,7 +23,7 @@ jobs:
                      calculate_net_charge, generate_conformers,
                      mol2_to_pdbqt, nmr4md, openbabel,
                      remove_terminal_residue_name_prefixes,
-                     rename_residues_mol, combine_pdb,
+                     rename_residues_mol, combine_structure,
                      remove_terminal_residue_name_prefixes, molgan,
                      pdbbind_refined, onionnet-sfct, smina]  # No username for pdbind_refined
         # skip data/ and cwl_adapters/file_format_conversions/biosimspace/

cwl_adapters/combine_pdb.cwl → cwl_adapters/combine_structure.cwl

@@ -3,16 +3,16 @@ cwlVersion: v1.0
 
 class: CommandLineTool
 
-label: A tool that employs MDtraj to combine two PDB structures in a single PDB file.
+label: A tool that employs RDKit to combine two XYZ structures in a single PDB file.
 
 doc: |-
   None
 
-baseCommand: ['python', '/combine_pdb.py']
+baseCommand: ['python', '/combine_structure.py']
 
 hints:
   DockerRequirement:
-    dockerPull: ndonyapour/combine_pdb
+    dockerPull: ndonyapour/combine_structure
 
 inputs:
   input_structure1:
@@ -21,11 +21,10 @@ inputs:
       Input structure 1 file path
       Type: string
       File type: input
-      Accepted formats: pdb
-      Example file: https://github.com/bioexcel/biobb_structure_utils/raw/master/biobb_structure_utils/test/data/utils/cat_protein.pdb
+      Accepted formats: xyz
     type: File
     format:
-    - edam:format_1476
+    - edam:format_3877
     inputBinding:
       prefix: --input_structure1
 
@@ -35,18 +34,17 @@ inputs:
       Input structure 2 file path
       Type: string
       File type: input
-      Accepted formats: pdb
-      Example file: https://github.com/bioexcel/biobb_structure_utils/raw/master/biobb_structure_utils/test/data/utils/cat_ligand.pdb
+      Accepted formats: xyz
     type: File
     format:
-    - edam:format_1476
+    - edam:format_3877 
     inputBinding:
       prefix: --input_structure2
 
   output_structure_path:
-    label: Output protein file path
+    label: Output combined PDB file path
     doc: |-
-      Output protein file path
+      Output combined PDB file path
       Type: string
       File type: output
       Accepted formats: pdb
@@ -57,20 +55,6 @@ inputs:
     inputBinding:
       prefix: --output_structure_path
     default: system.pdb
-
-  method:
-    label: The frequency to save the outputs
-    doc: |-
-      The frequency to save the outputs
-      Type: string
-    type: string?
-    format:
-    - edam:format_2330
-    inputBinding:
-      prefix: --method
-    default: rdkit
-
-
 outputs:
   output_structure_path:
     label: Output protein file path

cwl_adapters/convert_xyz.cwl

@@ -0,0 +1,69 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+
+class: CommandLineTool
+
+label: This class is a wrapper of the Open Babel tool.
+
+doc: |-
+  Converts small molecules in 2D or 3D formats to the XYZ format.  
+
+baseCommand: obabel
+#Usage:
+#obabel[-i<input-type>] <infilename> [-o<output-type>] -O<outfilename> [Options]
+#...
+#Options, other than -i -o -O -m, must come after the input files.
+arguments: [$(inputs.input_path), "-o", "xyz", "-O", $(inputs.output_xyz_path)]
+
+hints:
+  DockerRequirement:
+    dockerPull: quay.io/biocontainers/biobb_chemistry:4.0.0--pyhdfd78af_1
+
+requirements:
+  InlineJavascriptRequirement: {}
+
+inputs:
+  input_path:
+    label: Path to the input file
+    doc: |-
+      Path to the input file
+      Type: string
+      File type: input
+      Accepted formats: gro, mol, mol2, pdb, pdbqt, sdf
+      Example file: https://github.com/bioexcel/biobb_chemistry/raw/master/biobb_chemistry/test/data/babel/babel.smi
+    type: File
+    format:
+    - edam:format_2033
+    - edam:format_3815
+    - edam:format_3816
+    - edam:format_1476
+    - edam:format_1476
+    - edam:format_3814
+
+  output_xyz_path:
+    label: Path to the output file
+    doc: |-
+      Path to the output file
+      Type: string
+      File type: output
+      Accepted formats: xyz
+    type: string
+    format:
+    - edam:format_3877 # xyz
+    default: system.xyz
+
+outputs:
+  output_xyz_path:
+    label: Path to the output file
+    doc: |-
+      Path to the output file
+    type: File
+    outputBinding:
+      glob: $(inputs.output_xyz_path)
+    format: edam:format_3877 # xyz
+
+$namespaces:
+  edam: https://edamontology.org/
+
+$schemas:
+- https://raw.githubusercontent.com/edamontology/edamontology/master/EDAM_dev.owl

cwl_adapters/pymol_align_protein_ca.cwl

@@ -28,11 +28,13 @@ inputs:
     type: File
     format:
     - edam:format_1476 # pdb
+    - edam:format_3877 # xyz
 
   input_2_path:
     type: File
     format:
     - edam:format_1476 # pdb
+    - edam:format_3877 # xyz
 
   input_3_path:
     type: File

docker/dockerBuild.sh

@@ -29,7 +29,7 @@ sudo docker build --no-cache --pull -f Dockerfile_nmr4md -t jakefennick/nmr4md .
 sudo docker build --no-cache --pull -f Dockerfile_openbabel -t jakefennick/openbabel .
 sudo docker build --no-cache --pull -f Dockerfile_remove_terminal_residue_name_prefixes -t jakefennick/remove_terminal_residue_name_prefixes .
 sudo docker build --no-cache --pull -f Dockerfile_rename_residues_mol -t jakefennick/rename_residues_mol .
-sudo docker build --no-cache --pull -f Dockerfile_combine_pdb -t ndonyapour/combine_pdb .
+sudo docker build --no-cache --pull -f Dockerfile_combine_structure -t ndonyapour/combine_structure .
 sudo docker build --no-cache --pull -f Dockerfile_molgan -t ndonyapour/molgan .
 sudo docker build --no-cache --pull -f Dockerfile_onionnet-sfct -t cyangnyu/onionnet-sfct .
 sudo docker build --no-cache --pull -f Dockerfile_smina -t cyangnyu/smina .

dockerPull.sh

@@ -23,4 +23,5 @@ docker pull jakefennick/rename_residues_mol
 docker pull ndonyapour/molgan
 docker pull cyangnyu/onionnet-sfct
 docker pull cyangnyu/smina
+docker pull ndonyapour/combine_structure
 

examples/docking/align_protein_CA_pymol.yml

@@ -1,7 +1,7 @@
 steps:
   - pymol_align_protein_ca:
       in:
-        input_1_path: '*receptor_gro.pdb'
+        input_1_path: '*receptor.xyz'
         input_2_path: '*pose_ligand_1.pdb'
         input_3_path: '*npt.gro' # Do NOT use prod.gro!
         # It is only written after the final timestep and thus cannot possibly be used for realtime analysis!

examples/docking/docking.yml

@@ -76,23 +76,21 @@ steps:
         output_pdbqt_path: '&pose_ligand.pdbqt'
         config:
           model: 1 # NOTE: score, rmsd l.b., rmsd u.b. stored in REMARK lines
-  - babel_convert:
+  - convert_xyz:
       in:
         input_path: '*pose_ligand.pdbqt'
-        output_path: '&pose_ligand.pdb'
-
+        output_xyz_path: '&pose_ligand.xyz'
 # Molecular Dynamics combine receptor & ligand
   - append_ligand:
       in:
         input_itp_path: '*ligand_GMX.itp'
         input_top_zip_path: '*receptor.zip'
         output_top_zip_path: '&complex_vac.zip'
-  - combine_pdb:
+  - combine_structure:
       in:
-        input_structure1: '*receptor_gro.pdb' # '*receptor_hydrogens.pdb'
-        input_structure2: '*pose_ligand.pdb'
+        input_structure1: '*receptor.xyz' # '*receptor_hydrogens.pdb'
+        input_structure2: '*pose_ligand.xyz'
         output_structure_path: '&complex_vac.pdb'
-        method: rdkit  # Must use rdkit! See combine_pdb.py
 
 wic:
    graphviz:
@@ -122,15 +120,15 @@ wic:
        wic:
          graphviz:
            label: Extract Best\nDocking Pose
-     (9, babel_convert):
+     (9, convert_xyz):
        wic:
          graphviz:
-           label: Convert Complex\npdb to pdbqt
+           label: Convert Complex\npdbqt to xyz
      (10, append_ligand):
        wic:
          graphviz:
            label: Append Ligand Topology\nto Receptor Topology
-     (11, combine_pdb):
+     (11, combine_structure):
        wic:
          graphviz:
            label: Append Ligand Coordinates\nto Receptor Coordinates

examples/docking/gen_topol_params.yml

@@ -3,10 +3,10 @@ inputs:
     type: File
     format:
     - edam:format_1476
-  input_receptor_pdb_path:
+  input_receptor_xyz_path:
     type: File
     format:
-    - edam:format_1476
+    - edam:format_3877
   input_top_zip_path:
     type: File
     format:
@@ -37,7 +37,7 @@ steps:
       # need to use these coordinates with autodock because they are
       # sorted to agree with the *.itp topology include file.
       # Otherwise, we will get the grompp atom name warning (see below).
-#      output_gro_path: '&ligand_GMX.gro'
+      output_gro_path: '&ligand_GMX.gro'
 #      output_top_path: '&ligand_GMX.top'
       charge_method: user # take charges from mol2 file
 # NOTE: acpype doesn't add forcefield or water topology #include lines.
@@ -51,23 +51,21 @@ steps:
 #      input_top_path: '*ligand_GMX_includes.top'
       input_itp_path: '*ligand_GMX.itp'
 #      output_top_zip_path: '&ligand_GMX.zip'
-- babel_convert:
+- convert_xyz:
     in:
-#      input_path: '*ligand_GMX.gro' #'*pose_ligand.pdbqt'
-      output_path: '&pose_ligand.pdb'
-
+      input_path: '*ligand_GMX.gro' #'*pose_ligand.pdbqt'
+      output_xyz_path: '&pose_ligand.xyz'
 # Molecular Dynamics combine receptor & ligand
 - append_ligand:
     in:
 #      input_itp_path: '*ligand_GMX.itp'
       input_top_zip_path: ~input_top_zip_path #'*receptor.zip'
       output_top_zip_path: '&complex_vac.zip'
-- combine_pdb:
+- combine_structure:
     in:
-      input_structure1: ~input_receptor_pdb_path # '*receptor_hydrogens.pdb'
-      input_structure2: '*pose_ligand.pdb'
+      input_structure1: ~input_receptor_xyz_path
+      input_structure2: '*pose_ligand.xyz'
       output_structure_path: '&complex_vac.pdb'
-      method: rdkit  # Must use rdkit! See combine_pdb.py
 
 wic:
   graphviz:
@@ -93,15 +91,15 @@ wic:
       wic:
         graphviz:
           label: Create Topology\nZip File
-    (6, babel_convert):
-      wic:
-        graphviz:
-          label: Convert to\nPDB format
+    (6, convert_xyz):
+       wic:
+         graphviz:
+           label: Convert to\nXYZ format
     (7, append_ligand):
       wic:
         graphviz:
           label: Combine Receptor\nLigand Topologies
-    (8, combine_pdb):
+    (8, combine_structure):
       wic:
         graphviz:
           label: Combine Receptor\nLigand Coordinates

examples/docking/setup_pdb.yml

@@ -102,11 +102,10 @@ steps:
         # "Warning: atom name nnn in *.top and *.g96 does not match"
         output_top_zip_path: '&receptor.zip'
         config: '*config_tag_pdb2gmx'
-  - babel_convert:
+  - convert_xyz:
       in:
         input_path: '*receptor.gro'
-        output_path: '&receptor_gro.pdb'
-
+        output_xyz_path: '&receptor.xyz'
 wic:
    graphviz:
      label: Receptor Modeling + Docking + Initial Topology Setup
@@ -147,7 +146,7 @@ wic:
        wic:
          graphviz:
            label: Generate Initial\nReceptor Topology
-     (10, babel_convert):
+     (10, convert_xyz):
        wic:
          graphviz:
-           label: Convert Receptor\ngro to pdb
+           label: Convert Receptor\ngro to xyz