Optimizing Molecules using Efficient Queries from Property Evaluations

Abstract

Machine learning based methods have shown potential for optimizing existing molecules with more desirable properties, a critical step towards accelerating new chemical discovery. Here we propose QMO, a generic query-based molecule optimization framework that exploits latent embeddings from a molecule autoencoder. QMO improves the desired properties of an input molecule based on efficient queries, guided by a set of molecular property predictions and evaluation metrics. We show that QMO outperforms existing methods in the benchmark tasks of optimizing small organic molecules for drug-likeness and solubility under similarity constraints. We also demonstrate significant property improvement using QMO on two new and challenging tasks that are also important in real-world discovery problems: (i) optimizing existing potential SARS-CoV-2 Main Protease inhibitors toward higher binding affinity; and (ii) improving known antimicrobial peptides towards lower toxicity. Results from QMO show high consistency with external validations, suggesting effective means to facilitate material optimization problems with design constraints.

arXiv commentPreprint version to be published at Nature Machine Intelligence; Github: https://github.com/IBM/QMO

References in corpus (16)

• Auto-Encoding Variational Bayes
• Categorical Reparameterization with Gumbel-Softmax
• Automatic chemical design using a data-driven continuous representation of molecules
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• GuacaMol: Benchmarking Models for De Novo Molecular Design
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Machine Learning Unifies the Modelling of Materials and Molecules
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
• Optimization of Molecules via Deep Reinforcement Learning
• Autonomous discovery in the chemical sciences part II: Outlook
• ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations
• CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
• ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
• Hierarchical Graph-to-Graph Translation for Molecules
• A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning

Cited by in corpus (5)

• Computer-Aided Multi-Objective Optimization in Small Molecule Discovery
• Accelerating Material Design with the Generative Toolkit for Scientific Discovery
• Deep Extrapolation for Attribute-Enhanced Generation
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Text-guided multi-property molecular optimization with a diffusion language model