PhytoCell: An ensemble learning framework for identifying cell states in plant scRNA-seq data

PhytoCell: An ensemble learning framework for identifying cell states in plant scRNA-seq data. Wang, H., Yan, S., Ma, X., Si, H., Lu, Q., Chen, Y., Liu, L., Hong, J., Xu, X., Fang, W., He, Q., Zan, Y., & Yang, A. The Crop Journal, March, 2026.

Paper doi abstract bibtex

Single-cell transcriptome sequencing (scRNA-seq) can reveal the roles of diverse cells in an organism, but accurately classifying cell subpopulations and their marker genes remains a challenge. Here, we present PhytoCell, an ensemble learning framework that combines feature selection engineering with machine learning to uncover cell markers and annotate cell subpopulations. We evaluated our approach on 120,000 cells from corollas of the dicotyledonous plant species coyote tobacco (Nicotiana attenuata) and eight tissues from the monocotyledonous plant species rice (Oryza sativa). Comprehensive evaluation across species and tissues demonstrated that PhytoCell effectively eliminates redundant information, identifies key cell markers, improves clustering performance, and accurately classifies cell subpopulations. Importantly, PhytoCell did not rely on prior biological knowledge for selecting cell markers, preserving the biological landscape of the original data. For broader accessibility, we developed a user-friendly web interface that provides convenient tools for users to access cell marker resources and perform predictions for cell type. PhytoCell is freely accessible at https://cgris.net/phyto. PhytoCell is scalable to different sizes of single-cell datasets, representing a valuable resource for precise identification in cell research.

@article{wang_phytocell_2026,
	title = {{PhytoCell}: {An} ensemble learning framework for identifying cell states in plant {scRNA}-seq data},
	issn = {2214-5141},
	shorttitle = {{PhytoCell}},
	url = {https://www.sciencedirect.com/science/article/pii/S2214514126000760},
	doi = {10.1016/j.cj.2026.02.021},
	abstract = {Single-cell transcriptome sequencing (scRNA-seq) can reveal the roles of diverse cells in an organism, but accurately classifying cell subpopulations and their marker genes remains a challenge. Here, we present PhytoCell, an ensemble learning framework that combines feature selection engineering with machine learning to uncover cell markers and annotate cell subpopulations. We evaluated our approach on 120,000 cells from corollas of the dicotyledonous plant species coyote tobacco (Nicotiana attenuata) and eight tissues from the monocotyledonous plant species rice (Oryza sativa). Comprehensive evaluation across species and tissues demonstrated that PhytoCell effectively eliminates redundant information, identifies key cell markers, improves clustering performance, and accurately classifies cell subpopulations. Importantly, PhytoCell did not rely on prior biological knowledge for selecting cell markers, preserving the biological landscape of the original data. For broader accessibility, we developed a user-friendly web interface that provides convenient tools for users to access cell marker resources and perform predictions for cell type. PhytoCell is freely accessible at https://cgris.net/phyto. PhytoCell is scalable to different sizes of single-cell datasets, representing a valuable resource for precise identification in cell research.},
	urldate = {2026-05-19},
	journal = {The Crop Journal},
	author = {Wang, Hao and Yan, Shen and Ma, Xiaoding and Si, Huan and Lu, Qiong and Chen, Yanqing and Liu, Lijia and Hong, Jingpeng and Xu, Xingjian and Fang, Wei and He, Qiang and Zan, Yanjun and Yang, Aiguo},
	month = mar,
	year = {2026},
	keywords = {Cell subpopulations, Ensemble learning, Machine learning, PhytoCell, scRNA-seq},
}

Downloads: 0

{"_id":"cACNY9DhBNL3F8ezW","bibbaseid":"wang-yan-ma-si-lu-chen-liu-hong-etal-phytocellanensemblelearningframeworkforidentifyingcellstatesinplantscrnaseqdata-2026","author_short":["Wang, H.","Yan, S.","Ma, X.","Si, H.","Lu, Q.","Chen, Y.","Liu, L.","Hong, J.","Xu, X.","Fang, W.","He, Q.","Zan, Y.","Yang, A."],"bibdata":{"bibtype":"article","type":"article","title":"PhytoCell: An ensemble learning framework for identifying cell states in plant scRNA-seq data","issn":"2214-5141","shorttitle":"PhytoCell","url":"https://www.sciencedirect.com/science/article/pii/S2214514126000760","doi":"10.1016/j.cj.2026.02.021","abstract":"Single-cell transcriptome sequencing (scRNA-seq) can reveal the roles of diverse cells in an organism, but accurately classifying cell subpopulations and their marker genes remains a challenge. Here, we present PhytoCell, an ensemble learning framework that combines feature selection engineering with machine learning to uncover cell markers and annotate cell subpopulations. We evaluated our approach on 120,000 cells from corollas of the dicotyledonous plant species coyote tobacco (Nicotiana attenuata) and eight tissues from the monocotyledonous plant species rice (Oryza sativa). Comprehensive evaluation across species and tissues demonstrated that PhytoCell effectively eliminates redundant information, identifies key cell markers, improves clustering performance, and accurately classifies cell subpopulations. Importantly, PhytoCell did not rely on prior biological knowledge for selecting cell markers, preserving the biological landscape of the original data. For broader accessibility, we developed a user-friendly web interface that provides convenient tools for users to access cell marker resources and perform predictions for cell type. PhytoCell is freely accessible at https://cgris.net/phyto. PhytoCell is scalable to different sizes of single-cell datasets, representing a valuable resource for precise identification in cell research.","urldate":"2026-05-19","journal":"The Crop Journal","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Hao"],"suffixes":[]},{"propositions":[],"lastnames":["Yan"],"firstnames":["Shen"],"suffixes":[]},{"propositions":[],"lastnames":["Ma"],"firstnames":["Xiaoding"],"suffixes":[]},{"propositions":[],"lastnames":["Si"],"firstnames":["Huan"],"suffixes":[]},{"propositions":[],"lastnames":["Lu"],"firstnames":["Qiong"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Yanqing"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Lijia"],"suffixes":[]},{"propositions":[],"lastnames":["Hong"],"firstnames":["Jingpeng"],"suffixes":[]},{"propositions":[],"lastnames":["Xu"],"firstnames":["Xingjian"],"suffixes":[]},{"propositions":[],"lastnames":["Fang"],"firstnames":["Wei"],"suffixes":[]},{"propositions":[],"lastnames":["He"],"firstnames":["Qiang"],"suffixes":[]},{"propositions":[],"lastnames":["Zan"],"firstnames":["Yanjun"],"suffixes":[]},{"propositions":[],"lastnames":["Yang"],"firstnames":["Aiguo"],"suffixes":[]}],"month":"March","year":"2026","keywords":"Cell subpopulations, Ensemble learning, Machine learning, PhytoCell, scRNA-seq","bibtex":"@article{wang_phytocell_2026,\n\ttitle = {{PhytoCell}: {An} ensemble learning framework for identifying cell states in plant {scRNA}-seq data},\n\tissn = {2214-5141},\n\tshorttitle = {{PhytoCell}},\n\turl = {https://www.sciencedirect.com/science/article/pii/S2214514126000760},\n\tdoi = {10.1016/j.cj.2026.02.021},\n\tabstract = {Single-cell transcriptome sequencing (scRNA-seq) can reveal the roles of diverse cells in an organism, but accurately classifying cell subpopulations and their marker genes remains a challenge. Here, we present PhytoCell, an ensemble learning framework that combines feature selection engineering with machine learning to uncover cell markers and annotate cell subpopulations. We evaluated our approach on 120,000 cells from corollas of the dicotyledonous plant species coyote tobacco (Nicotiana attenuata) and eight tissues from the monocotyledonous plant species rice (Oryza sativa). Comprehensive evaluation across species and tissues demonstrated that PhytoCell effectively eliminates redundant information, identifies key cell markers, improves clustering performance, and accurately classifies cell subpopulations. Importantly, PhytoCell did not rely on prior biological knowledge for selecting cell markers, preserving the biological landscape of the original data. For broader accessibility, we developed a user-friendly web interface that provides convenient tools for users to access cell marker resources and perform predictions for cell type. PhytoCell is freely accessible at https://cgris.net/phyto. PhytoCell is scalable to different sizes of single-cell datasets, representing a valuable resource for precise identification in cell research.},\n\turldate = {2026-05-19},\n\tjournal = {The Crop Journal},\n\tauthor = {Wang, Hao and Yan, Shen and Ma, Xiaoding and Si, Huan and Lu, Qiong and Chen, Yanqing and Liu, Lijia and Hong, Jingpeng and Xu, Xingjian and Fang, Wei and He, Qiang and Zan, Yanjun and Yang, Aiguo},\n\tmonth = mar,\n\tyear = {2026},\n\tkeywords = {Cell subpopulations, Ensemble learning, Machine learning, PhytoCell, scRNA-seq},\n}\n\n\n\n\n\n\n\n","author_short":["Wang, H.","Yan, S.","Ma, X.","Si, H.","Lu, Q.","Chen, Y.","Liu, L.","Hong, J.","Xu, X.","Fang, W.","He, Q.","Zan, Y.","Yang, A."],"key":"wang_phytocell_2026","id":"wang_phytocell_2026","bibbaseid":"wang-yan-ma-si-lu-chen-liu-hong-etal-phytocellanensemblelearningframeworkforidentifyingcellstatesinplantscrnaseqdata-2026","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S2214514126000760"},"keyword":["Cell subpopulations","Ensemble learning","Machine learning","PhytoCell","scRNA-seq"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/upscpub","dataSources":["9cGcv2t8pRzC92kzs"],"keywords":["cell subpopulations","ensemble learning","machine learning","phytocell","scrna-seq"],"search_terms":["phytocell","ensemble","learning","framework","identifying","cell","states","plant","scrna","seq","data","wang","yan","ma","si","lu","chen","liu","hong","xu","fang","he","zan","yang"],"title":"PhytoCell: An ensemble learning framework for identifying cell states in plant scRNA-seq data","year":2026}