# ## Read PDB and filter by resolution and only include proteins
# In[3]:
pdb = mmtfReader.read_sequence_file(path, sc)
pdb = pdb.filter(Resolution(minResolution=0.0, maxResolution=2.0)).filter(
ContainsLProteinChain(exclusive=True))
# ## Setup criteria for metal interactions
# In[4]:
interactions_filter = InteractionFilter()
interactions_filter.set_distance_cutoff(3.0)
interactions_filter.set_normalized_b_factor_cutoff(1.645)
interactions_filter.set_min_interactions(2)
interactions_filter.set_max_interactions(4)
interactions_filter.set_query_groups(True, ["HOH"])
interactions_filter.set_query_elements(True, "O") # Only use water oxygen
interactions_filter.set_target_elements(True, ["O", "N", "S"])
# ## Exclude "uninteresting" ligands
# In[5]:
prohibitedGroups = ExcludedLigandSets.ALL_GROUPS
if not includeWaters:
prohibitedGroups.add("HOH")
interactions_filter.set_prohibited_target_groups(prohibitedGroups)
# ## Calculate interactions
# In[12]:
pdb = mmtfReader.read_sequence_file(path, sc)
pdb = pdb.filter(Pisces(sequenceIdentity = sequenceIdentityCutoff, resolution = resolution))
# ## Setup criteria for metal interactions
# In[13]:
interactions_filter = InteractionFilter()
interactions_filter.set_distance_cutoff(distanceCutoff)
interactions_filter.set_min_interactions(minInteractions)
interactions_filter.set_max_interactions(maxInteractions)
interactions_filter.set_query_groups(True, metals)
#Exclude non-polar interactions
interactions_filter.set_target_elements(False, ['H','C','P'])
# ## Tabulate interactions in a Dataframe
# In[14]:
interactions = GroupInteractionExtractor().get_interactions(pdb,interactions_filter).cache()
print(f"Metal interactions: {interactions.count()}")