Mol-CADiff: Causality-Aware Autoregressive Diffusion for Molecule Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahamed, Md Atik, Ye, Qiang, Cheng, Qiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910863743516672
author Ahamed, Md Atik
Ye, Qiang
Cheng, Qiang
author_facet Ahamed, Md Atik
Ye, Qiang
Cheng, Qiang
contents The design of novel molecules with desired properties is a key challenge in drug discovery and materials science. Traditional methods rely on trial-and-error, while recent deep learning approaches have accelerated molecular generation. However, existing models struggle with generating molecules based on specific textual descriptions. We introduce Mol-CADiff, a novel diffusion-based framework that uses causal attention mechanisms for text-conditional molecular generation. Our approach explicitly models the causal relationship between textual prompts and molecular structures, overcoming key limitations in existing methods. We enhance dependency modeling both within and across modalities, enabling precise control over the generation process. Our extensive experiments demonstrate that Mol-CADiff outperforms state-of-the-art methods in generating diverse, novel, and chemically valid molecules, with better alignment to specified properties, enabling more intuitive language-driven molecular design.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05499
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mol-CADiff: Causality-Aware Autoregressive Diffusion for Molecule Generation
Ahamed, Md Atik
Ye, Qiang
Cheng, Qiang
Machine Learning
The design of novel molecules with desired properties is a key challenge in drug discovery and materials science. Traditional methods rely on trial-and-error, while recent deep learning approaches have accelerated molecular generation. However, existing models struggle with generating molecules based on specific textual descriptions. We introduce Mol-CADiff, a novel diffusion-based framework that uses causal attention mechanisms for text-conditional molecular generation. Our approach explicitly models the causal relationship between textual prompts and molecular structures, overcoming key limitations in existing methods. We enhance dependency modeling both within and across modalities, enabling precise control over the generation process. Our extensive experiments demonstrate that Mol-CADiff outperforms state-of-the-art methods in generating diverse, novel, and chemically valid molecules, with better alignment to specified properties, enabling more intuitive language-driven molecular design.
title Mol-CADiff: Causality-Aware Autoregressive Diffusion for Molecule Generation
topic Machine Learning
url https://arxiv.org/abs/2503.05499