Innovative Drug-like Molecule Generation from Flow-based Generative Model

TL;DR

This paper introduces a flow-based generative model for drug-like molecule creation that incorporates protein dynamics, aiming to improve the accuracy of binding affinity predictions compared to previous rigid-protein models.

Contribution

The study extends GraphBP by integrating protein dynamics from the Protein Data Bank into the generative process, enhancing the realism and potential effectiveness of generated molecules.

Findings

Generated molecules show higher validity rates.

Binding affinity predictions outperform traditional docking methods.

Incorporating protein dynamics improves molecule relevance.

Abstract

To design a drug given a biological molecule by using deep learning methods, there are many successful models published recently. People commonly used generative models to design new molecules given certain protein. LiGAN was regarded as the baseline of deep learning model which was developed on convolutional neural networks. Recently, GraphBP showed its ability to predict innovative "real" chemicals that the binding affinity outperformed with traditional molecular docking methods by using a flow-based generative model with a graph neural network and multilayer perception. However, all those methods regarded proteins as rigid bodies and only include a very small part of proteins related to binding. However, the dynamics of proteins are essential for drug binding. Based on GraphBP, we proposed to generate more solid work derived from protein data bank. The results will be evaluated by validity and binding affinity by using a computational chemistry algorithm.