Protocol to estimate cell type proportions from bulk RNA-seq using DAISM-DNNXMBD

Yating Lin; Shangze Wu; Xu Xiao; Jingbo Zhao; Minshu Wang; Haojun Li; Kejia Wang; Minwei Zhang; Frank Zheng; Wenxian Yang; Lei Zhang; Jiahuai Han; Rongshan Yu

doi:10.1016/j.xpro.2022.101587

Protocol to estimate cell type proportions from bulk RNA-seq using DAISM-DNN^XMBD

STAR Protoc. 2022 Jul 31;3(3):101587. doi: 10.1016/j.xpro.2022.101587. eCollection 2022 Sep 16.

Authors

Yating Lin¹, Shangze Wu¹, Xu Xiao², Jingbo Zhao³, Minshu Wang⁴, Haojun Li¹, Kejia Wang⁵, Minwei Zhang⁶, Frank Zheng³, Wenxian Yang⁷, Lei Zhang⁸, Jiahuai Han⁹, Rongshan Yu¹⁰

Affiliations

¹ School of Informatics, Xiamen University, Xiamen 361005, China.
² School of Informatics, Xiamen University, Xiamen 361005, China; National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China.
³ Amoy Diagnostics, Xiamen 361000, China.
⁴ National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China; School of Medicine, Xiamen University, Xiamen 361102, China.
⁵ School of Medicine, Xiamen University, Xiamen 361102, China.
⁶ Department of Critical Care Medicine, The First Affiliated Hospital of Xiamen University, Xiamen 361003, China.
⁷ Aginome Scientific, Xiamen 361005, China.
⁸ School of Life Science, Xiamen University, Xiamen 361102, China. Electronic address: zhanglei@xmu.edu.cn.
⁹ Research Unit of Cellular Stress of CAMS, Cancer Research Center of Xiamen University, School of Medicine, Xiamen University, Xiamen 361102, China. Electronic address: jhan@xmu.edu.cn.
¹⁰ School of Informatics, Xiamen University, Xiamen 361005, China; National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China; Aginome Scientific, Xiamen 361005, China. Electronic address: rsyu@xmu.edu.cn.

Abstract

Computational protocols for cell type deconvolution from bulk RNA-seq data have been used to understand cellular heterogeneity in disease-related samples, but their performance can be impacted by batch effect among datasets. Here, we present a DAISM-DNN protocol to achieve robust cell type proportion estimation on the target dataset. We describe the preparation of calibrated samples from human blood samples. We then detail steps to train a dataset-specific deep neural network (DNN) model and cell type proportion estimation using the trained model. For complete details on the use and execution of this protocol, please refer to Lin et al. (2022).

Keywords: Bioinformatics; Cell Biology; Flow Cytometry/Mass Cytometry; Gene Expression; Immunology; RNAseq; Sequence analysis.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Humans
Neural Networks, Computer*
RNA-Seq