LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
This work addresses the problem of generating realistic scRNA-seq data for biological researchers, offering a robust tool for downstream applications, but it appears incremental as it builds on existing diffusion and graph-based methods with specific enhancements.
The paper tackles the challenge of generating high-fidelity and biologically plausible synthetic single-cell RNA sequencing (scRNA-seq) data with conditional control by introducing LapDDPM, a conditional Graph Diffusion Probabilistic Model that integrates graph-based representations with a score-based diffusion model and spectral adversarial perturbations, achieving superior performance and setting a new benchmark for this task.
Generating high-fidelity and biologically plausible synthetic single-cell RNA sequencing (scRNA-seq) data, especially with conditional control, is challenging due to its high dimensionality, sparsity, and complex biological variations. Existing generative models often struggle to capture these unique characteristics and ensure robustness to structural noise in cellular networks. We introduce LapDDPM, a novel conditional Graph Diffusion Probabilistic Model for robust and high-fidelity scRNA-seq generation. LapDDPM uniquely integrates graph-based representations with a score-based diffusion model, enhanced by a novel spectral adversarial perturbation mechanism on graph edge weights. Our contributions are threefold: we leverage Laplacian Positional Encodings (LPEs) to enrich the latent space with crucial cellular relationship information; we develop a conditional score-based diffusion model for effective learning and generation from complex scRNA-seq distributions; and we employ a unique spectral adversarial training scheme on graph edge weights, boosting robustness against structural variations. Extensive experiments on diverse scRNA-seq datasets demonstrate LapDDPM's superior performance, achieving high fidelity and generating biologically-plausible, cell-type-specific samples. LapDDPM sets a new benchmark for conditional scRNA-seq data generation, offering a robust tool for various downstream biological applications.