DeepAI AI Chat
Log In Sign Up

MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization

by   Tianfan Fu, et al.

Molecule optimization is a fundamental task for accelerating drug discovery, with the goal of generating new valid molecules that maximize multiple drug properties while maintaining similarity to the input molecule. Existing generative models and reinforcement learning approaches made initial success, but still face difficulties in simultaneously optimizing multiple drug properties. To address such challenges, we propose the MultI-constraint MOlecule SAmpling (MIMOSA) approach, a sampling framework to use input molecule as an initial guess and sample molecules from the target distribution. MIMOSA first pretrains two property agnostic graph neural networks (GNNs) for molecule topology and substructure-type prediction, where a substructure can be either atom or single ring. For each iteration, MIMOSA uses the GNNs' prediction and employs three basic substructure operations (add, replace, delete) to generate new molecules and associated weights. The weights can encode multiple constraints including similarity and drug property constraints, upon which we select promising molecules for next iteration. MIMOSA enables flexible encoding of multiple property- and similarity-constraints and can efficiently generate new molecules that satisfy various property constraints and achieved up to 49.6


page 1

page 2

page 3

page 4


Composing Molecules with Multiple Property Constraints

Drug discovery aims to find novel compounds with specified chemical prop...

Optimizing Molecules using Efficient Queries from Property Evaluations

Machine learning has shown potential for optimizing existing molecules w...

Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets

Deep generative models have achieved tremendous success in designing nov...

Controlled Molecule Generator for Optimizing Multiple Chemical Properties

Generating a novel and optimized molecule with desired chemical properti...

RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design

De novo molecule generation often results in chemically unfeasible molec...

Utilizing Reinforcement Learning for de novo Drug Design

Deep learning-based approaches for generating novel drug molecules with ...

Grammars and reinforcement learning for molecule optimization

We seek to automate the design of molecules based on specific chemical p...