A Multi-Domain Multi-Task Approach for Feature Selection from Bulk RNA Datasets
This work addresses feature selection for multi-domain biological data analysis, but it is incremental as it applies known multi-task learning concepts to a specific RNA-seq dataset without broad methodological innovation.
The paper tackled feature selection in bulk RNA-seq data from mouse immune response to Salmonella infection, using a multi-domain multi-task algorithm to extract discriminative features across spleen and liver domains, proving its viability and identifying new feature subsets not found with single-domain methods.
In this paper a multi-domain multi-task algorithm for feature selection in bulk RNAseq data is proposed. Two datasets are investigated arising from mouse host immune response to Salmonella infection. Data is collected from several strains of collaborative cross mice. Samples from the spleen and liver serve as the two domains. Several machine learning experiments are conducted and the small subset of discriminative across domains features have been extracted in each case. The algorithm proves viable and underlines the benefits of across domain feature selection by extracting new subset of discriminative features which couldn't be extracted only by one-domain approach.