Mol Prep

Mol Prep is the first stage of the HEDGEHOG pipeline. It standardizes input molecules and removes entries that are unsuitable for downstream descriptor, synthesis, and docking analysis.

What Mol Prep Does

The stage combines normalization and strict filtering:

converts input SMILES into RDKit molecules
removes salts and solvents
keeps the largest fragment
disconnects metals
normalizes and reionizes molecules
neutralizes charges
canonicalizes tautomers
removes stereochemistry
filters out radicals, isotopes, charged molecules, and multi-fragment inputs when configured

This stage is intentionally conservative because it defines the clean molecular population that later stages see.

Why It Matters for Partial Runs

Even when you request another stage through --stage, HEDGEHOG may still run Mol Prep first if Mol Prep is enabled in its config. This ensures downstream stages operate on standardized molecules rather than raw input.

Key Configuration Areas

Mol Prep is controlled by config_mol_prep.yml.

Important sections:

steps.* controls normalization and cleanup operations
filters.* controls hard rejection rules
output.write_duplicates_removed controls whether duplicate removals are written to disk

Example:


run: true
steps:
  standardize_mol:
    enabled: true
    disconnect_metals: true
    normalize: true
    reionize: true
    uncharge: true
  remove_stereochemistry: true
filters:
  allowed_atoms: [C, N, O, S, F, Cl, Br, I, P, H]
  reject_radicals: true
  require_neutral: true
  reject_isotopes: true
  require_single_fragment: true

Output

Mol Prep writes its output under:


stages/00_mol_prep/

Typical artifacts include:

filtered_molecules.csv
failed_molecules.csv
duplicates_removed.csv when duplicate-output writing is enabled

If Mol Prep finishes successfully but produces zero molecules, the pipeline exits early instead of running later stages on an empty set.