FastFlows: Flow-Based Models for Molecular Graph Generation
This work addresses the need for fast and efficient molecular generation in high-throughput virtual screening for drug discovery, though it appears incremental as it builds on existing flow-based and optimization methods.
The authors tackled the problem of generating small molecules for drug discovery by proposing FastFlows, a flow-based framework that efficiently generates thousands of chemically valid molecules in seconds from a small training set of only 100 molecules.
We propose a framework using normalizing-flow based models, SELF-Referencing Embedded Strings, and multi-objective optimization that efficiently generates small molecules. With an initial training set of only 100 small molecules, FastFlows generates thousands of chemically valid molecules in seconds. Because of the efficient sampling, substructure filters can be applied as desired to eliminate compounds with unreasonable moieties. Using easily computable and learned metrics for druglikeness, synthetic accessibility, and synthetic complexity, we perform a multi-objective optimization to demonstrate how FastFlows functions in a high-throughput virtual screening context. Our model is significantly simpler and easier to train than autoregressive molecular generative models, and enables fast generation and identification of druglike, synthesizable molecules.