Differentiable Scaffolding Tree for Molecular Optimization
This addresses the problem of discrete and non-differentiable molecule structures in drug discovery and chemical engineering, offering a novel approach for domain-specific applications.
The paper tackles the challenge of molecular optimization by proposing a differentiable scaffolding tree (DST) that converts discrete chemical structures into locally differentiable ones, enabling gradient-based optimization and achieving effective and sample-efficient results.
The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and combinatorial optimization methods achieve initial success but still struggle with directly modeling discrete chemical structures and often heavily rely on brute-force enumeration. The challenge comes from the discrete and non-differentiable nature of molecule structures. To address this, we propose differentiable scaffolding tree (DST) that utilizes a learned knowledge network to convert discrete chemical structures to locally differentiable ones. DST enables a gradient-based optimization on a chemical graph structure by back-propagating the derivatives from the target properties through a graph neural network (GNN). Our empirical studies show the gradient-based molecular optimizations are both effective and sample efficient. Furthermore, the learned graph parameters can also provide an explanation that helps domain experts understand the model output.