BioinformaticsArrayPeer-reviewed
CLOP-DiT: Structured-Metadata-Conditioned Single-Cell Latent Generation via Contrastive Language-Omics Pretraining and Diffusion Transformers
Zeyu Fu, Yiyao Liu, Junping Wang, Song Wang
CLOP-DiT generates synthetic single-cell gene expression profiles from structured biological metadata using contrastive alignment and diffusion models, achieving high steering accuracy but limited cross-dataset variability.