Version Compatibility

Reference examples tested with: AiZynthFinder 4.4+, Chemformer 1.3+, RDKit 2024.09+, RDChiral 1.1+, Aizynthtrain 1.0+, ASKCOS Lite 0.5+.

Before using code patterns, verify installed versions match. If versions differ:

• Python: pip show <package> then help(module.function) to check signatures
• CLI: aizynthcli --version

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Retrosynthesis

Hard rules

1. No fabricated citations. Every cited work must resolve to a verifiable
2. No claim without provenance. Every quantitative or factual claim
3. No silent failure. Every script invocation, API call, or tool use must declare its exit status and what to do on non-zero. A skill that silently swallows errors is a violation.

When to use

Load this skill when the user asks a question that matches its declared trigger conditions (see the frontmatter description for the most common ones). Do not load it for questions outside its scope — defer to the appropriate ORS skill instead.

When NOT to use

Do not load this skill if the question is in a sibling skill's domain (see ## Cross-references), if the user explicitly asks for a different tool, or if the task is outside the skill's declared category.

Method Taxonomy

Decision: For most users, AiZynthFinder 4.4 with USPTO + USPTO-50k templates is the open-source standard. For high-stakes routes, validate with Molecular Transformer forward prediction.

AiZynthFinder Setup

Goal: Configure AiZynthFinder with USPTO templates and a building-block stock; run MCTS retrosynthesis on a target SMILES.

Approach: Build a configuration dict pointing to policy templates and a stock HDF5, instantiate AiZynthFinder, set the target SMILES, then call tree_search() followed by build_routes().

from aizynthfinder.aizynthfinder import AiZynthFinder

config_dict = {
    'policy': {
        'files': {
            'uspto': ['policy/uspto_model.onnx', 'templates/uspto_templates.csv'],
        }
    },
    'stock': {
        'files': {
            'zinc': 'stock/zinc.h5',
        }
    },
    'finder': {
        'algorithm': 'mcts',
        'iteration_limit': 100,
        'time_limit': 120,
    }
}

finder = AiZynthFinder(configdict=config_dict)
finder.target_smiles = 'CC(=O)Nc1ccc(C(=O)Nc2cccc(C(F)(F)F)c2)cc1'
finder.tree_search()
finder.build_routes()

Route Output Analysis

for route in finder.routes:
    print(f'Depth: {route.depth}, Score: {route.score:.2f}')
    print(f'In-stock: {sum(node.in_stock for node in route.leafs())}')
    print(f'Building blocks: {[node.smiles for node in route.leafs()]}')

Critical metrics:

• Depth: synthetic steps (1-3 typical for medchem)
• Score: AiZynthFinder route score (0-1)
• In-stock: how many leaf nodes are commercially available

Route Scoring (MO-MCTS)

AiZynthFinder 4.0 supports multi-objective scoring:

config_dict['finder']['algorithm'] = 'mo_mcts'
config_dict['finder']['mo_mcts'] = {
    'objectives': [
        {'name': 'state_score', 'weight': 0.5},
        {'name': 'broken_bonds_score', 'weight': 0.3},
        {'name': 'route_length', 'weight': 0.2, 'maximize': False},
    ]
}

Building Block Stocks

aizynthtrain build-stock --input zinc_building_blocks.smi --output zinc.h5

Forward Validation with Molecular Transformer

from molecular_transformer import predict_forward

precursors = route.leafs()
predicted_product = predict_forward(precursors)
match = (Chem.CanonSmiles(predicted_product) ==
         Chem.CanonSmiles(finder.target_smiles))

Routes where the forward prediction reproduces the target are highest confidence. ~30-50% of AiZynthFinder routes pass forward validation.

Template-Free with Chemformer

from chemformer import Chemformer

cf = Chemformer.load_pretrained('USPTO_RETROSYNTHESIS_TEMPLATE_FREE')
predictions = cf.predict('CC(=O)Nc1ccc(C(=O)Nc2cccc(C(F)(F)F)c2)cc1',
                         beam_search=10)

Trade-off: Template-free is more flexible but harder to debug. Combining with AiZynthFinder template MCTS gives best of both.

Disconnection-Aware Design (DAD)

aizynthcli --smiles compounds.smi --output routes.json \
           --config config.yaml --policy uspto --stock zinc

For each compound, returns top-K routes. Score-feasibility for generative design:"

• "Synthesizable" = in-stock leaves >= 2 in best route
• "Routable" = at least one route depth <= 5
• "Easy" = at least one route depth <= 3 with all leaves in-stock

References

• Saigiridharan et al., J. Cheminform. 16:57 -- AiZynthFinder 4.0.
• Irwin et al., 2022 -- Chemformer.
• Schwaller et al. -- Molecular Transformer.

Related Skills

• chemoinformatics/generative-design - Generative design with feasibility scoring
• chemoinformatics/reaction-enumeration - Forward direction
• chemoinformatics/scaffold-analysis - R-group decomposition

Cross-references

Other skills in this category:

• admet-prediction
• conformer-generation
• covalent-design
• docking-rescoring
• free-energy-calculations
• generative-design
• molecular-descriptors
• molecular-io
• molecular-standardization
• pharmacophore-modeling
• pose-validation
• protac-degraders
• qsar-modeling
• scaffold-analysis
• shape-similarity
• similarity-searching
• substructure-search
• virtual-screening

Changelog

• 1.1.0 (migration) — Bulk-migrated to v0.4.0 schema: canonical metadata block, base Hard rules, Cross-references. Body content unchanged; author should review and fill in any domain-specific extensions to the Hard rules.
• 1.0.0 — Initial release.