SILVR: Guided Diffusion for Molecule Generation. (arXiv:2304.10905v1 [q-bio.BM])

Computationally generating novel synthetically accessible compounds with high
affinity and low toxicity is a great challenge in drug design. Machine-learning
models beyond conventional pharmacophoric methods have shown promise in
generating novel small molecule compounds, but require significant tuning for a
specific protein target. Here, we introduce a method called selective iterative
latent variable refinement (SILVR) for conditioning an existing diffusion-based
equivariant generative model without retraining. The model allows the
generation of new molecules that fit into a binding site of …

arxiv beyond bio challenge design diffusion drug design generative iterative low machine molecules novel protein small toxicity