AI Insight
This paper introduces CURE (A Cellular Response Engine), a generative AI framework that designs drug molecules based on desired transcriptomic state transitions — that is, targeted changes in gene expression patterns — rather than relying on known 3D protein structures. The authors formalize this approach as Transcriptome-based Drug Design (TBDD), a generative inverse problem complicated by the domain gap between biological signals and chemical representations, as well as the sparsity and noise inherent in transcriptomic data. CURE employs a multi-resolution diffusion model with a specialized Transcriptome Perturbation Functional Feature Extractor (TFE) that bridges these challenges, demonstrating superior performance over baseline models in both structural quality and functional consistency, including a zero-shot gene-inhibitor design task.
Why it matters
This approach could accelerate drug discovery for diseases driven by dysregulated biological pathways — such as cancer or complex genetic disorders — where traditional structure-based methods are insufficient, by enabling phenotype-driven molecular design at scale without requiring reliable protein structure data.
arXiv:2605.15243v1 Announce Type: cross
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}elltextbf{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.