files for comparing topology workflow

Author: Brandon Duane Walker

cwl_adapters/extract_ligand_protein.cwl

@@ -82,4 +82,4 @@ $namespaces:
   edam: https://edamontology.org/
 
 $schemas:
-- https://raw.githubusercontent.com/edamontology/edamontology/master/EDAM_dev.owl
+- https://raw.githubusercontent.com/edamontology/edamontology/master/EDAM_dev.owl

examples/docking/compare_extract_protein_pdbbind.wic

@@ -0,0 +1,49 @@
+steps:
+- id: extract_pdbbind_refined
+  in:
+    # https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.query.html
+    # The query() method uses a slightly modified Python syntax by default.
+    # For example, the & and | (bitwise) operators have the precedence of their
+    # boolean cousins, and and or. This is syntactically valid Python, however
+    # the semantics are different.
+    query: !ii '(Kd_Ki == "Kd") and (value < 0.2)'
+    max_row: !ii 1000 #25 # Use 1 for CI
+    convert_Kd_dG: !ii True
+    output_txt_path: !ii binding_data.txt
+  out:
+  - output_txt_path: !& binding_data.txt
+  - output_pdb_paths: !& pdbbind_pdbs
+  - output_sdf_paths: !& pdbbind_sdfs
+  - experimental_dGs: !& exp_dGs
+  - pdb_ids: !& pdbids
+
+- id: extract_protein
+  scatter: [input_pdb_path]
+  in:
+    input_pdb_path: !* pdbbind_pdbs
+    output_pdb_path: !ii pdbbind_protein_openmm.pdb
+  out:
+  - output_pdb_path: !& pdbbind_protein_openmm.pdb
+
+- id: extract_ligand_protein
+  scatter: [input_pdb_path]
+  in:
+    input_pdb_path: !* pdbbind_pdbs
+    output_pdb_path: !ii pdbbind_protein_mdanalysis.pdb
+  out:
+  - output_pdb_path: !& pdbbind_protein_mdanalysis.pdb
+
+- id: topology_check
+  scatter: [file1,file2]
+  scatterMethod: dotproduct
+  in:
+    file1: !* pdbbind_protein_openmm.pdb
+    file2: !* pdbbind_protein_mdanalysis.pdb
+    topology_changed: !ii test_valid
+  out:
+  - topology_changed: !& test_valid
+
+# - count_results:
+#     in:
+#       ids: !* pdbids
+#       results: !* test_valid