Back

Cell-attribute aware community detection improves differential abundance testing from single-cell RNA-Seq data

Teschendorff, A. E.; Maity, A.

2023-04-29 bioinformatics
10.1101/2023.04.28.538653 bioRxiv
Show abstract

Variations of cell-type proportions within tissues could be informative of biological aging and disease risk. Single-cell RNA-sequencing offers the opportunity to detect such differential abundance (DA) patterns, yet this task can be statistically challenging due to the noise in single-cell data, inter-sample variability and because DA patterns are often of small effect size. Here we present a DA-testing paradigm called ELVAR that uses cell attribute aware clustering when inferring differentially enriched communities within the single-cell manifold. Using simulated and real single-cell and single-nucleus RNA-Seq datasets, we benchmark ELVAR against an analogous DA algorithm that uses Louvain for clustering, as well as local neighborhood-based DA-testing methods, demonstrating that ELVAR improves the sensitivity to detect DA-shifts in relation to aging, precancerous states and Covid-19 phenotypes. In effect, leveraging cell attribute information when inferring cell communities can denoise single-cell data, avoid the need for batch correction and help retrieve more robust cell states for subsequent DA-testing. ELVAR is available as an open-source R-package.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.