Exploring the applications of Neural Cellular Automata in molecular sciences
Keywords: Neural Cellular Automata, Geometric Deep Learning, voxelized Molecule Represenations
TL;DR: This work introduces the application of Neural Cellular Automata to molecule representations for tasks like designing small-molecule interactors, reconstructing protein backbones, and modeling physical transformations.
Abstract: In recent years, Cellular Automata have been merged with developments in deep learning to replace the traditional update rules with a neural network. These Neural Cellular Automata (NCAs) have been applied for 2D, and 3D object generation, morphogenesis, as well as the orchestration of goal-directed behavioural responses. While there have been numerous examples of applying NCAs to emoji-like, and common gameplay objects (like houses or trees in Minecraft), their adaption to molecule representations has yet to be explored. In this work, we present an adaptation of 3D NCAs to voxelized representations of small- and bio-molecules. We present three exemplary applications of NCAs to design small-molecule interactors, reconstruct missing parts of protein backbones, and model physical transformations.
Submission Track: Original Research
Submission Number: 128
Loading