arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.13182cs.LGcs.AIq-bio.GN
收藏

SpaDiT:利用scRNA-seq进行空间基因表达预测的扩散Transformer

SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq

the School of Information Science;Engineering , Yunnan University , 650091 , Kunming, Yunnan , China;College of Nursing Health Sciences , Yunnan Open University , 650599 , Kunming , China

Xiaoyu Li, Fangfang Zhu, Wenwen Min

AI总结:

SpaDiT利用扩散Transformer模型整合scRNA-seq与空间转录组数据,预测未检测基因并生成空间结构,在多项指标上超越八种基线方法,达到最先进性能。

摘要:

空间转录组学(ST)技术的快速发展正在彻底改变我们对生物组织空间组织的理解。当前的ST方法分为基于下一代测序(seq-based)和基于荧光原位杂交(image-based)两类,为生物组织的功能动态提供了创新见解。然而,这些方法受限于其细胞分辨率和可检测的基因数量。为解决这些限制,我们提出了SpaDiT,一种利用扩散生成模型整合scRNA-seq和ST数据以预测未检测基因的深度学习方法。通过采用基于Transformer的扩散模型,SpaDiT不仅能准确预测未知基因,还能有效生成ST基因的空间结构。我们通过在seq-based和image-based ST数据上的大量实验证明了SpaDiT的有效性。SpaDiT以其创新方法对ST基因预测方法做出了显著贡献。与八种领先的基线方法相比,SpaDiT在多个指标上达到了最先进的性能,突显了其重要的生物信息学贡献。

英文摘要:

The rapid development of spatial transcriptomics (ST) technologies is revolutionizing our understanding of the spatial organization of biological tissues. Current ST methods, categorized into next-generation sequencing-based (seq-based) and fluorescence in situ hybridization-based (image-based) methods, offer innovative insights into the functional dynamics of biological tissues. However, these methods are limited by their cellular resolution and the quantity of genes they can detect. To address these limitations, we propose SpaDiT, a deep learning method that utilizes a diffusion generative model to integrate scRNA-seq and ST data for the prediction of undetected genes. By employing a Transformer-based diffusion model, SpaDiT not only accurately predicts unknown genes but also effectively generates the spatial structure of ST genes. We have demonstrated the effectiveness of SpaDiT through extensive experiments on both seq-based and image-based ST data. SpaDiT significantly contributes to ST gene prediction methods with its innovative approach. Compared to eight leading baseline methods, SpaDiT achieved state-of-the-art performance across multiple metrics, highlighting its substantial bioinformatics contribution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑