Medchem Agent Skill

uv pip install medchem datamol

mamba install -c conda-forge lilly-medchem-rules

import medchem as mc

mc.rules.RuleFilters.list_available_rules_names()
# ['rule_of_five', 'rule_of_five_beyond', 'rule_of_four', 'rule_of_three', ...]

import datamol as dm
import medchem as mc

smiles = "CC(=O)OC1=CC=CC=C1C(=O)O"  # aspirin
mc.rules.basic_rules.rule_of_five(smiles)   # True
mc.rules.basic_rules.rule_of_cns(smiles)    # True
mc.rules.basic_rules.rule_of_veber(smiles)  # True

import datamol as dm
import medchem as mc

mols = [dm.to_mol(s) for s in smiles_list]

rfilter = mc.rules.RuleFilters(
    rule_list=["rule_of_five", "rule_of_oprea", "rule_of_cns", "rule_of_leadlike_soft"]
)
df = rfilter(mols=mols, n_jobs=-1, progress=True, keep_props=False)

# Columns: mol, pass_all, pass_any, rule_of_five, rule_of_oprea, ...
passing = df[df["pass_all"]]

import medchem as mc

alert_filter = mc.structural.CommonAlertsFilters()
df = alert_filter(mols=mol_list, n_jobs=-1, progress=True)
# df columns: mol, pass_filter, status, reasons

clean = df[df["pass_filter"]]

nibr_filter = mc.structural.NIBRFilters()
df = nibr_filter(mols=mol_list, n_jobs=-1, progress=True)
# df columns: mol, pass_filter, status, severity, reasons, n_covalent_motif, special_mol

import medchem as mc

# List available named catalogs
mc.catalogs.list_named_catalogs()
# ['tox', 'pains', 'pains_a', 'brenk', 'nibr', 'zinc', ...]

# Functional API — True means molecule passes (no alert match)
passes = mc.functional.alert_filter(mols=mol_list, alerts=["pains"], n_jobs=-1)

# Or via catalog objects
passes = mc.functional.catalog_filter(
    mols=mol_list,
    catalogs=[mc.catalogs.NamedCatalogs.pains()],
    n_jobs=-1,
)

import medchem as mc

mc.functional.rules_filter(mols=mol_list, rules=["rule_of_five", "rule_of_cns"], n_jobs=-1)
mc.functional.nibr_filter(mols=mol_list, max_severity=10, n_jobs=-1)
mc.functional.alert_filter(mols=mol_list, alerts=["pains", "brenk"], n_jobs=-1)
mc.functional.complexity_filter(mols=mol_list, complexity_metric="bertz", limit="99", n_jobs=-1)

import medchem as mc

# Browse available group collections
mc.groups.list_default_chemical_groups()
# ['privileged_scaffolds', 'common_warhead_covalent_inhibitors', 'rings_in_drugs', ...]

group = mc.groups.ChemicalGroup(groups=["privileged_scaffolds"])
group.has_match(mol)                          # bool
group.get_matches(mol)                        # dict of group → atom indices
group.filter(mols)                            # molecules matching the group

# Returns molecules that do NOT match the group
mc.functional.chemical_group_filter(mols=mol_list, chemical_group=group, n_jobs=-1)

import medchem as mc

# Single molecule
cf = mc.complexity.ComplexityFilter(limit="99", complexity_metric="bertz")
cf(mol)  # True if below 99th-percentile threshold

# Batch via functional API
mc.functional.complexity_filter(
    mols=mol_list,
    complexity_metric="bertz",  # also: sas, qed, whitlock, barone, smcm, twc
    limit="99",
    n_jobs=-1,
)

# Direct metric functions
mc.complexity.WhitlockCT(mol)
mc.complexity.BaroneCT(mol)

import datamol as dm
import medchem as mc

core = dm.to_mol("c1ccccc1")
constraints = mc.constraints.Constraints(
    core=core,
    constraint_fns={"query": lambda mol, atom_idx, query: ...},
)
constraints(mol)

import medchem as mc

# Rule + alert combination
qf = mc.query.QueryFilter('MATCHRULE("rule_of_five") AND NOT HASALERT("pains")')
mask = qf(mols=mol_list, n_jobs=-1)  # list[bool]

# CNS-like with property bounds
qf = mc.query.QueryFilter('MATCHRULE("rule_of_cns") AND HASPROP("tpsa", <=, 90)')
mask = qf(mols=mol_list, n_jobs=-1)

import datamol as dm
import medchem as mc
import pandas as pd

df = pd.read_csv("compounds.csv")
mols = [dm.to_mol(s) for s in df["smiles"]]

# Drug-likeness rules
rules_df = mc.rules.RuleFilters(rule_list=["rule_of_five", "rule_of_veber"])(mols=mols, n_jobs=-1)

# PAINS + common alerts via query
qf = mc.query.QueryFilter('MATCHRULE("rule_of_five") AND NOT HASALERT("pains")')
pass_mask = qf(mols=mols, n_jobs=-1)

df["passes_rules"] = rules_df["pass_all"].values
df["drug_like"] = pass_mask
filtered_df = df[df["drug_like"]]
filtered_df.to_csv("filtered_compounds.csv", index=False)

import medchem as mc

rules_df = mc.rules.RuleFilters(rule_list=["rule_of_leadlike_soft"])(mols=candidates, n_jobs=-1)
nibr_df = mc.structural.NIBRFilters()(mols=candidates, n_jobs=-1)
complex_mask = mc.functional.complexity_filter(
    mols=candidates, complexity_metric="bertz", limit="95", n_jobs=-1
)

passes = (
    rules_df["pass_all"]
    & nibr_df["pass_filter"]
    & complex_mask
)

import medchem as mc

group = mc.groups.ChemicalGroup(groups=["common_warhead_covalent_inhibitors"])
matches = [group.has_match(mol) for mol in mol_list]
warhead_mols = [mol for mol, m in zip(mol_list, matches) if m]

uv run python scripts/filter_molecules.py input.csv \
  --rules rule_of_five,rule_of_cns --pains --nibr --output filtered.csv