SAD: Sparse-Aware Diffusion Model for Single-Cell Gene Expression Completion

doi:10.1109/TCBBIO.2026.3674362

SAD: Sparse-Aware Diffusion Model for Single-Cell Gene Expression Completion

2026-05-01

0

PRE

AI

DOI：10.1109/TCBBIO.2026.3674362

Original

Original request for help

Save

Abstract

En 中文

Single-cell RNA sequencing (scRNA-seq) is entering an era of foundation models that accept the complete gene atlas as input, yet most current datasets cover only 10–12 k genes and contain numerous technical zeros, severely limiting the generalization of these models in downstream tasks. To address this, we pioneer the gene-completion task for scRNA-seq and present SAD, a diffusion-based framework tailored to extremely sparse data, capable of completing genes and correcting sparsity bias under high missing rates. Unlike imputation or reconstruction methods that rely on the i.i.d. assumption, SAD's completion paradigm can generate gene entries originally absent from the expression profile, be aware of and rectify sparsity-distribution bias, and supply foundation models with consistent, reliable inputs of more than 30 k genes. Extensive benchmarks show that SAD significantly outperforms existing methods across multiple completion metrics, particularly in extreme scenarios with missing rates above 80%. This provides a data foundation for reusing missing scRNA-seq information and for precision-medicine applications.

Keywords:

Sparse-aware diffusion

dynamic domain correction

tolerance optimization

single-cell gene completion

SAD: Sparse-Aware Diffusion Model for Single-Cell Gene Expression Completion

Abstract

Journal

Organization