Deep Molecular Dreaming: Inverse machine learning for de-novo molecular design and interpretability with surjective representations

Abstract

Computer-based de-novo design of functional molecules is one of the most prominent challenges in cheminformatics today. As a result, generative and evolutionary inverse designs from the field of artificial intelligence have emerged at a rapid pace, with aims to optimize molecules for a particular chemical property. These models 'indirectly' explore the chemical space; by learning latent spaces, policies, distributions or by applying mutations on populations of molecules. However, the recent development of the SELFIES string representation of molecules, a surjective alternative to SMILES, have made possible other potential techniques. Based on SELFIES, we therefore propose PASITHEA, a direct gradient-based molecule optimization that applies inceptionism techniques from computer vision. PASITHEA exploits the use of gradients by directly reversing the learning process of a neural network, which is trained to predict real-valued chemical properties. Effectively, this forms an inverse regression model, which is capable of generating molecular variants optimized for a certain property. Although our results are preliminary, we observe a shift in distribution of a chosen property during inverse-training, a clear indication of PASITHEA's viability. A striking property of inceptionism is that we can directly probe the model's understanding of the chemical space it was trained on. We expect that extending PASITHEA to larger datasets, molecules and more complex properties will lead to advances in the design of new functional molecules as well as the interpretation and explanation of machine learning models.

arXiv comment9 pages, 6 figures; comments welcome

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Automatic chemical design using a data-driven continuous representation of molecules
• Explainable Machine Learning for Scientific Insights and Discoveries
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Discovering physical concepts with neural networks
• MolGAN: An implicit generative model for small molecular graphs
• Optimization of Molecules via Deep Reinforcement Learning
• Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

Cited by in corpus (4)

• On scientific understanding with artificial intelligence
• SELFIES and the future of molecular string representations
• Regression Transformer: Concurrent sequence regression and generation for molecular language modeling
• Inverse molecular design and parameter optimization with Hückel theory using automatic differentiation