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

2026-05-14

AI Summary

This work addresses the challenge of drug design in scenarios where target structures are unavailable or disease phenotypes arise from pathway dysregulation by proposing a function-oriented small-molecule generation approach grounded in transcriptomic perturbations. The task is formulated as a conditional generative inverse problem, tackled via a multi-resolution transcriptome-guided diffusion framework. Central to this framework is the Cell Response Engine (CURE), which enables cross-modal alignment between transcriptional perturbations and molecular structures. The method integrates a transcriptomic functional feature extractor, a heterogeneity-aware aggregation mechanism, dual-view chemical alignment, and a zero-shot gene inhibitor design strategy. Experimental results demonstrate that the proposed approach significantly outperforms strong baselines in both standard and out-of-distribution evaluations, excelling in molecular structural validity and functional consistency, and successfully enabling de novo design of zero-shot gene inhibitors.

Abstract

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.

Problem

• Transcriptome-based Drug Design
• generative inverse problem
• transcriptomic perturbations
• function-oriented drug design
• cross-modal gap

Innovation

• Transcriptome-based Drug Design
• Molecular Diffusion
• Perturbation Embedding
• Cross-modal Alignment
• Generative Inverse Problem