Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?
This addresses the challenge of technical biases in RNA sequencing data for researchers in computational biology, though it appears incremental as it builds on prior work for a specific noise type.
The paper tackled the problem of fitting multi-axis models corrupted by multiplicative noise, which occurs in domains like single-cell RNA sequencing, and demonstrated that their MED-MAGMA algorithm learns networks with better local and global structure on all public datasets in the Single Cell Expression Atlas under a certain size.
In this paper we develop a graph-learning algorithm, MED-MAGMA, to fit multi-axis (Kronecker-sum-structured) models corrupted by multiplicative noise. This type of noise is natural in many application domains, such as that of single-cell RNA sequencing, in which it naturally captures technical biases of RNA sequencing platforms. Our work is evaluated against prior work on each and every public dataset in the Single Cell Expression Atlas under a certain size, demonstrating that our methodology learns networks with better local and global structure. MED-MAGMA is made available as a Python package (MED-MAGMA).