Chaitanya K. Joshi - gRNAde - a Geometric Deep Learning pipeline for 3D RNA inverse design скачать в хорошем качестве

Chaitanya K. Joshi - gRNAde - a Geometric Deep Learning pipeline for 3D RNA inverse design

RNA CASP Special Interest Group (SIG) #12 Tuesday January 30 2024 Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. In this talk, I will present gRNAde, a geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. Under the hood, gRNAde is a Graph Neural Network that generates candidate RNA sequences conditioned on one or more 3D backbone structures where the identities of the bases are unknown. On a fixed backbone re-design benchmark of 14 RNA structures from the PDB identified by Das et al. (2011), gRNAde obtains higher native sequence recovery rates (54% on average) compared to Rosetta (45% on average), taking under a second to produce designs compared to the reported hours for Rosetta. We envision gRNAde to be useful for inverse design of structured RNAs of interest for therapeutics and biotechnology, including riboswitches, aptamers, and ribozymes.