Ensemble learning models that predict surface protein abundance from single-cell multimodal omics data
AffiliationSchool of Information Science and Technology, ShanghaiTech University, Shanghai, 201210, China.
MetadataShow full item record
AbstractSingle-cell protein abundance is a fundamental type of information to characterize cell states. Due to high cost and technical barriers, however, direct quantification of proteins is difficult. Single-cell RNA sequencing (scRNA-seq) data, serving as a cost-effective substitute of single-cell proteomics, may not accurately reflect protein expression levels due to measurement error, noise, post-transcriptional and translational regulation, etc. The recently emerging single-cell multimodal omics data, e.g. CITE-seq and REAP-seq, can simultaneously profile RNA and protein abundances in single cells, providing labeled data for predictive modeling in a supervised learning framework. Deep neural network-based transfer learning method has been applied to imputation of surface protein abundance from single-cell transcriptomic data. However, it is unclear if the artificial neural network is the best model, and it is desirable to improve the prediction performance (e.g. accuracy, interpretability) of machine learning models. In this paper, we compared several tree-based ensemble learning methods with neural network models, and found that ensemble learning often performed better than neural network, and Random Forest (RF) performed the best overall. Moreover, we used the feature importance scores from RF to interpret biological mechanisms underlying the prediction. Our study demonstrates the effectiveness of ensemble learning for reliable protein abundance prediction using single-cell multimodal omics data, and paves the way for knowledge discovery by mining single-cell multi-omics data in large scale.
CitationXu F, Wang S, Dai X, Mundra PA, Zheng J. Ensemble learning models that predict surface protein abundance from single-cell multimodal omics data. Methods. 2020.
- RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach.
- Authors: Pan X, Shen HB
- Issue date: 2017 Feb 28
- scNPF: an integrative framework assisted by network propagation and network fusion for preprocessing of single-cell RNA-seq data.
- Authors: Ye W, Ji G, Ye P, Long Y, Xiao X, Li S, Su Y, Wu X
- Issue date: 2019 May 8
- Architectures and accuracy of artificial neural network for disease classification from omics data.
- Authors: Yu H, Samuels DC, Zhao YY, Guo Y
- Issue date: 2019 Mar 4
- A deep learning-based multi-model ensemble method for cancer prediction.
- Authors: Xiao Y, Wu J, Lin Z, Zhao X
- Issue date: 2018 Jan
- DeepImpute: an accurate, fast, and scalable deep neural network method to impute single-cell RNA-seq data.
- Authors: Arisdakessian C, Poirion O, Yunits B, Zhu X, Garmire LX
- Issue date: 2019 Oct 18