Molecular Fingerprints for Robust and Efficient ML-Driven Molecular Generation
Ruslan N. Tazhigulov, Schiller, Joshua, Jacob Oppenheim, Max Winston · arXiv (Cornell University) · 2022
We propose a novel molecular fingerprint-based variational autoencoder applied for molecular generation on real-world drug molecules. We define more suitable and pharma-relevant baseline metrics and tests, focusing on the generation of diverse, drug-like, novel small molecules and scaffolds. When we apply these molecular generation metrics to our novel model, we observe a substantial improvement in chemical synthetic accessibility ($Δ\bar{SAS}$ = -0.83) and in computational efficiency up to 5.9x in comparison to an existing state-of-the-art SMILES-based architecture.