-
Notifications
You must be signed in to change notification settings - Fork 0
Open
Description
I noticed that in the Python code, there are .fixed.sdf files for small molecules, like this:
generalization_benchmark/split_dataset/cluster/SCV/protein_seq_smi_cluster.py
Lines 278 to 285 in 6273801
for pdbid in pdbid_list: | |
structure= pdb_parser.get_structure(pdbid, "./"+str(pdbid)+"/"+str(pdbid)+"_protein.pdb") ## load correct path to protein files | |
seqs = getResidueStrings(structure) | |
protein_seq.append(seqs) | |
supplier = Chem.SDMolSupplier("./"+str(pdbid)+"/"+str(pdbid)+"_ligand.fixed.sdf", sanitize=False, removeHs=False) ## load correct path to ligand files | |
mol = supplier[0] | |
fp = FingerprintMols.FingerprintMol(mol) | |
fingerprints[pdbid] = fp |
If I changed it to the original sdf files in PDBBind dataset, the code will throw errors. Thus, could you release the fixed small molecule files so that users could run the code locally with different parameters.
Thank you!
Metadata
Metadata
Assignees
Labels
No labels