Text-guided Diffusion Model for 3D Molecule Generation

TL;DR

TextSMOG is introduced, a new Text-guided Small Molecule Generation Approach via 3D Diffusion Model which integrates language and diffusion models for text-guided small molecule generation, enhancing both stability and diversity.

Abstract

The de novo generation of molecules with targeted properties is crucial in biology, chemistry, and drug discovery. Current generative models are limited to using single property values as conditions, struggling with complex customizations described in detailed human language. To address this, we propose the text guidance instead, and introduce TextSMOG, a new Text-guided Small Molecule Generation Approach via 3D Diffusion Model which integrates language and diffusion models for text-guided small molecule generation. This method uses textual conditions to guide molecule generation, enhancing both stability and diversity. Experimental results show TextSMOG's proficiency in capturing and utilizing information from textual descriptions, making it a powerful tool for generating 3D molecular structures in response to complex textual customizations.

Figures (6)

• Figure 1: Architecture of Our Text-guided Small Molecule Generation via Diffusion Model (TextSMOG). The model starts with an initial geometry (${\mathcal{G}}_{T}$) and gradually denoises it to generate the final molecular geometry. The reference geometry (${\bm{c}}_{\textbf{P}}$), updated at each step based on the textual prompt ($\textbf{P}$), is employed to integrate the textual information into the conditional signal of diffusion models. Flame denotes tunable modules, while snowflake indicates frozen modules.
• Figure 2: Comparison of MAE for the Generated Molecules Targeted to Desired Property. Statistics of baselines are from their original papers. The performance of EEGSDE varies depending on the scaling factor, and we report its best results. The numerical values are provided in the supplementary information.
• Figure 3: Comparison of Novelty (Novel, %), Atom Stability (A. Stable,%), and Molecule Stability (M. Stable,%) on Generated Molecules Targeted to the Desired Property. Statistics of baselines are from EEGSDE. The performance of EEGSDE varies depending on the scaling factor, and we report its best results.
• Figure 4: Generated molecules targeted to text description excerpts.
• Figure S1: As a supplement to Figure 4, random examples of molecules generated for the text description, random examples of generated molecules targeted to text description "This molecule is a simple chain structure with at least one carboxyl group and is soluble in water."