It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Jeff, Schwaller, Philippe
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909350234161152
author Guo, Jeff
Schwaller, Philippe
author_facet Guo, Jeff
Schwaller, Philippe
contents Constrained synthesizability is an unaddressed challenge in generative molecular design. In particular, designing molecules satisfying multi-parameter optimization objectives, while simultaneously being synthesizable and enforcing the presence of specific commercial building blocks in the synthesis. This is practically important for molecule re-purposing, sustainability, and efficiency. In this work, we propose a novel reward function called TANimoto Group Overlap (TANGO), which uses chemistry principles to transform a sparse reward function into a dense and learnable reward function -- crucial for reinforcement learning. TANGO can augment general-purpose molecular generative models to directly optimize for constrained synthesizability while simultaneously optimizing for other properties relevant to drug discovery using reinforcement learning. Our framework is general and addresses starting-material, intermediate, and divergent synthesis constraints. Contrary to most existing works in the field, we show that incentivizing a general-purpose (without any inductive biases) model is a productive approach to navigating challenging optimization scenarios. We demonstrate this by showing that the trained models explicitly learn a desirable distribution. Our framework is the first generative approach to tackle constrained synthesizability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11527
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Design
Guo, Jeff
Schwaller, Philippe
Biomolecules
Machine Learning
Constrained synthesizability is an unaddressed challenge in generative molecular design. In particular, designing molecules satisfying multi-parameter optimization objectives, while simultaneously being synthesizable and enforcing the presence of specific commercial building blocks in the synthesis. This is practically important for molecule re-purposing, sustainability, and efficiency. In this work, we propose a novel reward function called TANimoto Group Overlap (TANGO), which uses chemistry principles to transform a sparse reward function into a dense and learnable reward function -- crucial for reinforcement learning. TANGO can augment general-purpose molecular generative models to directly optimize for constrained synthesizability while simultaneously optimizing for other properties relevant to drug discovery using reinforcement learning. Our framework is general and addresses starting-material, intermediate, and divergent synthesis constraints. Contrary to most existing works in the field, we show that incentivizing a general-purpose (without any inductive biases) model is a productive approach to navigating challenging optimization scenarios. We demonstrate this by showing that the trained models explicitly learn a desirable distribution. Our framework is the first generative approach to tackle constrained synthesizability.
title It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Design
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2410.11527