AiZynthFinder
AstraZeneca Molecular AI
Multi-step retrosynthetic planning tool using Monte Carlo tree search guided by neural network policies. Recursively breaks down target molecules into purchasable precursors. Production-used at AstraZeneca.
Best For
Full retrosynthetic route planning with commercial building block validation
License
Open Source (MIT)
Strengths
- +MCTS-based multi-step planning
- +Production-used at AstraZeneca
- +MIT license
- +Extensible policy framework
Limitations
- −Route quality depends on policy model training data
- −Does not predict reaction conditions
- −Requires stock/building block database
R&D Pipeline Coverage
Related Tools
RetroTRAE
KNU LCBC (Kyungpook National University)
Single-step retrosynthesis prediction using fragment-based tokenization of atomic environments and a Transformer architecture. Mimics chemical reasoning by learning changes in atom environments between products and reactants.
REINVENT4
AstraZeneca Molecular AI
RL + transformer platform for de novo small molecule design. Supports scaffold decoration, R-group replacement, linker design, and multi-parameter optimization.
More in Retrosynthesis
RetroTRAE
KNU LCBC (Kyungpook National University)
Single-step retrosynthesis prediction using fragment-based tokenization of atomic environments and a Transformer architecture. Mimics chemical reasoning by learning changes in atom environments between products and reactants.
TorchDrug
DeepGraphLearning (Mila / Université de Montréal)
PyTorch-based ML platform for drug discovery covering graph neural networks, geometric deep learning, knowledge graphs, generative models, and retrosynthesis. Provides unified API for property prediction, generation, and synthesis planning.
Stay updated on AiZynthFinder
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.