Related Experiment Video
Updated: Aug 23, 2025
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
Published on: November 19, 2018
Characterization of spleen and lymph node cell types via CITE-seq and machine learning methods
Hao Li1, Deling Wang2, Xianchao Zhou3
1College of Biological and Food Engineering, Jilin Engineering Normal University, Changchun, China.
Insights
Machine learning accurately identified diverse human spleen and lymph node cell types using single-cell CITE-seq data. Key proteins and genes were discovered, enhancing immune system understanding.
Area of Science:
- Immunology
- Computational Biology
- Genomics
Background:
- The spleen and lymph nodes are crucial for the human immune system.
- Identifying diverse cell types within these organs is vital for understanding immune mechanisms.
- The heterogeneity of spleen and lymph node cell types presents a significant analytical challenge.
Purpose of the Study:
- To computationally analyze and classify cell types in human spleen and lymph nodes.
- To leverage machine learning algorithms for dissecting immune cell heterogeneity.
- To identify key molecular markers (proteins and genes) associated with specific cell types.
Main Methods:
- Utilized single-cell CITE-seq sequencing data from 28,211 cells.
- Applied Boruta and minimum redundancy maximum relevance (mRMR) for feature selection.
- Employed incremental feature selection (IFS) with deep forest, random forest, K-nearest neighbor, and decision tree algorithms for classification.
Main Results:
- The deep forest algorithm, with optimal features identified through IFS, achieved the highest classification performance.
- Identified essential features including proteins (CD4, TCRb, CD103, CD43, CD23) and genes (Nkg7, Thy1) for cell type classification.
- Derived classification rules using the decision tree algorithm.
Conclusions:
- Machine learning effectively classifies diverse spleen and lymph node cell types.
- The study highlights critical protein and gene markers contributing to immune cell heterogeneity.
- Findings provide valuable insights into the complexity of the human immune system's cellular landscape.
Abstract:
The spleen and lymph nodes are important functional organs for human immune system. The identification of cell types for spleen and lymph nodes is helpful for understanding the mechanism of immune system. However, the cell types of spleen and lymph are highly diverse in the human body. Therefore, in this study, we employed a series of machine learning algorithms to computationally analyze the cell types of spleen and lymph based on single-cell CITE-seq sequencing data. A total of 28,211 cell data (training vs. test = 14,435 vs. 13,776) involving 24 cell types were collected for this study. For the training dataset, it was analyzed by Boruta and minimum redundancy maximum relevance (mRMR) one by one, resulting in an mRMR feature list. This list was fed into the incremental feature selection (IFS) method, incorporating four classification algorithms (deep forest, random forest, K-nearest neighbor, and decision tree). Some essential features were discovered and the deep forest with its optimal features achieved the best performance. A group of related proteins (CD4, TCRb, CD103, CD43, and CD23) and genes (Nkg7 and Thy1) contributing to the classification of spleen and lymph nodes cell types were analyzed. Furthermore, the classification rules yielded by decision tree were also provided and analyzed. Above findings may provide helpful information for deepening our understanding on the diversity of cell types.
More Related Videos
09:34A Combinatorial Single-cell Approach to Characterize the Molecular and Immunophenotypic Heterogeneity of Human Stem and Progenitor Populations
Published on: October 25, 2018
10:23Single-cell Gene Expression Using Multiplex RT-qPCR to Characterize Heterogeneity of Rare Lymphoid Populations
Published on: January 19, 2017
