Merge pull request nf-core#332 from tlitfin-unsw/report-align-noH

fix superpositon bug in reports

Author: JoseEspinosa

CHANGELOG.md

@@ -45,6 +45,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[PR #316](https://github.com/nf-core/proteinfold/pull/316)] - Add process_gpu label to modules which use GPU.
 - [[PR #319](https://github.com/nf-core/proteinfold/pull/319)] - Update boltz workflow to accept YAML as input.
 - [[PR #322](https://github.com/nf-core/proteinfold/pull/322)] - Updates and reorganises the reference database directory structure.
+- [[PR #332](https://github.com/nf-core/proteinfold/pull/332)] - Fix rare superposition bug in reports.
 - [[PR #333](https://github.com/nf-core/proteinfold/pull/333)] - Updates the RFAA dockerfile for better versioning and smaller image size.
 - [[PR #335](https://github.com/nf-core/proteinfold/pull/335)] - Update pipeline template to [nf-core/tools 3.3.1](https://github.com/nf-core/tools/releases/tag/3.3.1).
 

bin/generate_comparison_report.py

@@ -122,7 +122,7 @@ def align_structures(structures):
 
     def get_atom_ids(structure):
         # Note: this is a *set* of atom_ids due to the {} surrounding the comprehension
-        return {(atom.get_parent().get_id(), atom.name) for atom in structure.get_atoms()}
+        return {(atom.get_parent().get_parent().get_id(), atom.get_parent().get_id(), atom.name) for atom in structure.get_atoms() if atom.element != 'H'}
 
     # TODO: do we want to raise and error if the structures are not identical atomically, or keep the ability to sub-align?
     # Update the atoms shared between structures with progressive intersections
@@ -137,7 +137,7 @@ def get_atom_ids(structure):
     #print(common_atoms)
     def extract_atoms(structure, atom_ids):
         # Note: this comprehension returns an atom *object* for each atom in the structure
-        return [atom for atom in structure.get_atoms() if (atom.get_parent().get_id(), atom.name) in atom_ids]
+        return [atom for atom in structure.get_atoms() if (atom.get_parent().get_parent().get_id(), atom.get_parent().get_id(), atom.name) in atom_ids]
 
     ref_atoms = extract_atoms(ref_structure, common_atoms)
     # The aligned structures will be the parsed structures aligned to the common atoms of the reference structure

bin/generate_report.py

@@ -219,21 +219,22 @@ def align_structures(structures):
     ref_structure = structures[0]
 
     common_atoms = set(
-        f"{atom.get_parent().get_id()[1]}-{atom.name}"
-        for atom in ref_structure.get_atoms()
+        f"{atom.get_parent().get_parent().get_id()}-{atom.get_parent().get_id()[1]}-{atom.name}"
+        for atom in ref_structure.get_atoms() if not atom.element == 'H'
     )
+    #print(common_atoms)
     for i, structure in enumerate(structures[1:], start=1):
         common_atoms = common_atoms.intersection(
             set(
-                f"{atom.get_parent().get_id()[1]}-{atom.name}"
+                f"{atom.get_parent().get_parent().get_id()}-{atom.get_parent().get_id()[1]}-{atom.name}"
                 for atom in structure.get_atoms()
             )
         )
 
     ref_atoms = [
         atom
         for atom in ref_structure.get_atoms()
-        if f"{atom.get_parent().get_id()[1]}-{atom.name}" in common_atoms
+        if f"{atom.get_parent().get_parent().get_id()}-{atom.get_parent().get_id()[1]}-{atom.name}" in common_atoms
     ]
     # print(ref_atoms)
     super_imposer = PDB.Superimposer()
@@ -243,7 +244,7 @@ def align_structures(structures):
         target_atoms = [
             atom
             for atom in structure.get_atoms()
-            if f"{atom.get_parent().get_id()[1]}-{atom.name}" in common_atoms
+            if f"{atom.get_parent().get_parent().get_id()}-{atom.get_parent().get_id()[1]}-{atom.name}" in common_atoms
         ]
 
         super_imposer.set_atoms(ref_atoms, target_atoms)