Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
This work addresses the challenge of efficient molecule design in chemistry, but it is incremental as it builds on existing genetic algorithms with neural network enhancements.
The paper tackled the problem of exploring chemical space for designing organic materials by enhancing a genetic algorithm with a deep neural network discriminator, resulting in improved diversity and performance over other generative models in optimization tasks.
Challenges in natural sciences can often be phrased as optimization problems. Machine learning techniques have recently been applied to solve such problems. One example in chemistry is the design of tailor-made organic materials and molecules, which requires efficient methods to explore the chemical space. We present a genetic algorithm (GA) that is enhanced with a neural network (DNN) based discriminator model to improve the diversity of generated molecules and at the same time steer the GA. We show that our algorithm outperforms other generative models in optimization tasks. We furthermore present a way to increase interpretability of genetic algorithms, which helped us to derive design principles.