NRTPredictor: identifying rice root cell state in single-cell RNA-seq via ensemble learning

Abstract

Abstract Background Single-cell RNA sequencing (scRNA-seq) measurements of gene expression show great promise for studying cellular heterogeneity of rice root. How precisely annotating cell identity is a major unresolved problem in plant scRNA-seq analysis due to the inherent high dimensionality and sparsity.Results To address this challenge, we present NRTPredictor, an ensemble-learning system, to predict rice root cell stage and mine biomarkers through complete model interpretability. The performance of NRTPredictor was evaluated using an external dataset, with 98.01% accuracy and 95.45% recall. With the power of the interpretability provided by NRTPredictor, our model recognizes 110 important marker genes, partially involved in the phenylpropanoid biosynthesis, that domain knowledge does not consider. Expression patterns of rice root could be mapped by the above-mentioned candidate genes, showing the superiority of NRTPredictor. Integrative bulk RNA-seq analysis we revealed aberrant expression of Epidermis and Cortex cell subpopulations in flooding, Pi stress and salt stress.Conclusion Taken together, our results demonstrate that NRTPredictor is a useful tool for automated prediction of rice root cell stage and provides a valuable resource for deciphering the rice root cellular heterogeneity and the molecular mechanisms of flooding, Pi stress and salt stress. Based on the proposed model, a free webserver has been established, which is available at http://bio.germplasmai.com.