Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Ziyu, Zhang, Zijian, Wang, Liang, Liu, Zhiyuan, Liu, Qiang, Wu, Shu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911686051495936
author Xu, Ziyu
Zhang, Zijian
Wang, Liang
Liu, Zhiyuan
Liu, Qiang
Wu, Shu
Wang, Liang
author_facet Xu, Ziyu
Zhang, Zijian
Wang, Liang
Liu, Zhiyuan
Liu, Qiang
Wu, Shu
Wang, Liang
contents When reliable target structures are unavailable at scale or phenotypes arise from dysregulated pathways, transcriptomic perturbations provide a system-level functional readout for drug action. In this work, we formalize \emph{Transcriptome-based Drug Design (TBDD)} as a generative inverse problem: designing drug molecules conditioned on desired transcriptomic state transitions. We analyze the inherently ill-posed nature of this task, which is further complicated by the profound domain gap between biology and chemistry and by the sparsity of transcriptomic signals. To address these challenges, we propose \textbf{\themodel{}} (A \textbf{C}ell\textbf{U}lar \textbf{R}esponse \textbf{E}ngine), a multi-resolution transcriptome-guided diffusion framework. \themodel{} features a specialized \textbf{Transcriptome Perturbation Functional Feature Extractor (TFE)} that (1) distills function-oriented perturbation embeddings from pre/post states, (2) aligns these signatures to dual chemical views to bridge the cross-modal gap, and (3) performs heterogeneity-aware aggregation to extract robust state-specific signals from noisy transcriptomic data. Extensive evaluations on both standard benchmarks and rigorous out-of-distribution protocols demonstrate that \themodel{} consistently outperforms strong baselines in structural quality and functional consistency. Furthermore, we validate its practical utility via a zero-shot gene-inhibitor design task, highlighting the potential of phenotype-driven generative discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15243
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design
Xu, Ziyu
Zhang, Zijian
Wang, Liang
Liu, Zhiyuan
Liu, Qiang
Wu, Shu
Wang, Liang
Machine Learning
Artificial Intelligence
Biomolecules
Molecular Networks
Quantitative Methods
When reliable target structures are unavailable at scale or phenotypes arise from dysregulated pathways, transcriptomic perturbations provide a system-level functional readout for drug action. In this work, we formalize \emph{Transcriptome-based Drug Design (TBDD)} as a generative inverse problem: designing drug molecules conditioned on desired transcriptomic state transitions. We analyze the inherently ill-posed nature of this task, which is further complicated by the profound domain gap between biology and chemistry and by the sparsity of transcriptomic signals. To address these challenges, we propose \textbf{\themodel{}} (A \textbf{C}ell\textbf{U}lar \textbf{R}esponse \textbf{E}ngine), a multi-resolution transcriptome-guided diffusion framework. \themodel{} features a specialized \textbf{Transcriptome Perturbation Functional Feature Extractor (TFE)} that (1) distills function-oriented perturbation embeddings from pre/post states, (2) aligns these signatures to dual chemical views to bridge the cross-modal gap, and (3) performs heterogeneity-aware aggregation to extract robust state-specific signals from noisy transcriptomic data. Extensive evaluations on both standard benchmarks and rigorous out-of-distribution protocols demonstrate that \themodel{} consistently outperforms strong baselines in structural quality and functional consistency. Furthermore, we validate its practical utility via a zero-shot gene-inhibitor design task, highlighting the potential of phenotype-driven generative discovery.
title Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design
topic Machine Learning
Artificial Intelligence
Biomolecules
Molecular Networks
Quantitative Methods
url https://arxiv.org/abs/2605.15243