{"title":"SpaDiT:利用 scRNA-seq 进行空间基因表达预测的扩散变换器","authors":"Xiaoyu Li, Fangfang Zhu, Wenwen Min","doi":"arxiv-2407.13182","DOIUrl":null,"url":null,"abstract":"The rapid development of spatial transcriptomics (ST) technologies is\nrevolutionizing our understanding of the spatial organization of biological\ntissues. Current ST methods, categorized into next-generation sequencing-based\n(seq-based) and fluorescence in situ hybridization-based (image-based) methods,\noffer innovative insights into the functional dynamics of biological tissues.\nHowever, these methods are limited by their cellular resolution and the\nquantity of genes they can detect. To address these limitations, we propose\nSpaDiT, a deep learning method that utilizes a diffusion generative model to\nintegrate scRNA-seq and ST data for the prediction of undetected genes. By\nemploying a Transformer-based diffusion model, SpaDiT not only accurately\npredicts unknown genes but also effectively generates the spatial structure of\nST genes. We have demonstrated the effectiveness of SpaDiT through extensive\nexperiments on both seq-based and image-based ST data. SpaDiT significantly\ncontributes to ST gene prediction methods with its innovative approach.\nCompared to eight leading baseline methods, SpaDiT achieved state-of-the-art\nperformance across multiple metrics, highlighting its substantial\nbioinformatics contribution.","PeriodicalId":501070,"journal":{"name":"arXiv - QuanBio - Genomics","volume":"27 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq\",\"authors\":\"Xiaoyu Li, Fangfang Zhu, Wenwen Min\",\"doi\":\"arxiv-2407.13182\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The rapid development of spatial transcriptomics (ST) technologies is\\nrevolutionizing our understanding of the spatial organization of biological\\ntissues. Current ST methods, categorized into next-generation sequencing-based\\n(seq-based) and fluorescence in situ hybridization-based (image-based) methods,\\noffer innovative insights into the functional dynamics of biological tissues.\\nHowever, these methods are limited by their cellular resolution and the\\nquantity of genes they can detect. To address these limitations, we propose\\nSpaDiT, a deep learning method that utilizes a diffusion generative model to\\nintegrate scRNA-seq and ST data for the prediction of undetected genes. By\\nemploying a Transformer-based diffusion model, SpaDiT not only accurately\\npredicts unknown genes but also effectively generates the spatial structure of\\nST genes. We have demonstrated the effectiveness of SpaDiT through extensive\\nexperiments on both seq-based and image-based ST data. SpaDiT significantly\\ncontributes to ST gene prediction methods with its innovative approach.\\nCompared to eight leading baseline methods, SpaDiT achieved state-of-the-art\\nperformance across multiple metrics, highlighting its substantial\\nbioinformatics contribution.\",\"PeriodicalId\":501070,\"journal\":{\"name\":\"arXiv - QuanBio - Genomics\",\"volume\":\"27 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Genomics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.13182\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Genomics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.13182","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
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认识。目前的空间转录组学方法分为基于下一代测序的方法(基于测序)和基于荧光原位杂交的方法(基于图像),这些方法提供了对生物组织功能动态的创新见解。为了解决这些局限性,我们提出了一种深度学习方法SpaDiT,它利用扩散生成模型整合scRNA-seq和ST数据,预测未检测到的基因。通过采用基于变压器的扩散模型,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。我们在基于序列和图像的 ST 数据上进行了大量实验,证明了 SpaDiT 的有效性。与八种领先的基线方法相比,SpaDiT 在多个指标上都达到了最先进的水平,凸显了它在生物信息学方面的巨大贡献。
SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq
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.