Polar Gini Curve: a Technique to Discover Single-cell Biomarker Using 2D Visual Information
Nguyen, T. M.; Jeevan, J. J.; Xu, N.; Chen, J. Y.
Show abstract
In this work, we design the Polar Gini Curve (PGC) technique, which combines the gene expression and the 2D embedded visual information to detect biomarkers from single-cell data. Theoretically, a Polar Gini Curve characterizes the shape and evenness of cell-point distribution of cell-point set. To quantify whether a gene could be a marker in a cell cluster, we can combine two Polar Gini Curves: one drawn upon the cell-points expressing the gene, and the other drawn upon all cell-points in the cluster. We hypothesize that the closers these two curves are, the more likely the gene would be cluster markers. We demonstrate the framework in several simulation case-studies. Applying our framework in analyzing neonatal mouse heart single-cell data, the detected biomarkers may characterize novel subtypes of cardiac muscle cells. The source code and data for PGC could be found at https://figshare.com/projects/Polar_Gini_Curve/76749.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- GCNCDA: A New Method for Predicting CircRNA-Disease Associations Based on Graph Convolutional Network Algorithm 97%
- scPADGRN: A preconditioned ADMM approach for reconstructing dynamic gene regulatory network using single-cell RNA sequencing data 96%
- A novel single-cell based method for breast cancer prognosis 96%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.