Fig. 6

Standardization workflow used to strip salts and neutralize charges: The ‘RDKit’ Salt Stripper is used to split unconnected fragments according to predefined rules. The ‘Connectivity’ node (CDK) is used to list all the unconnected structures and list them in separate columns (‘Split Collection Column’ node). The output is joined together (‘Joiner’ node followed by the ‘Column Filter’ node to drop redundant columns). The ‘RDKit Structure Normalizer’ node is used to neutralize charges (if applicable). As an output of this part of the workflow, the neutralized molecule and the unconnected fragment(s) (if applicable) are listed in separate columns