Random Forest Factorization Reveals Latent Structure in Single Cell RNA Sequencing Data
Brenerman, B. M.; Shapiro, B.; Schatz, M.; Battle, A.
Show abstract
Single-cell RNA sequencing data contain patterns of correlation that are poorly captured by techniques that rely on linear estimation or assumptions of Gaussian behavior. We apply random forest regression to scRNAseq data from mouse brains, which identifies the co-regulation of genes within specific cellular contexts. By analyzing the estimators of the random forest, we identify several novel candidate gene regulatory networks and compare these networks in aged and young mice. We demonstrate that cell populations have cell-type specific phenotypes of aging that are not detected by other methods, including the collapse of differentiating oligodendrocytes but not precursors or mature oligodendrocytes.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- NS-Forest: A machine learning method for the objective identification of minimum marker gene combinations for cell type determination from single cell RNA sequencing 95%
- Tree-based differential testing using inferentialuncertainty for RNA-Seq 94%
- Linear-time cluster ensembles of large-scale single-cell RNA-seq and multimodal data 94%
"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.