Fig. 1: Overall pipeline of GLARE: Gene LAb Representation learning pipelinE.
From: GLARE: discovering hidden patterns in spaceflight transcriptome using representation learning
a Illustration of GLARE, starting with a verification study followed by representation learning and ensemble clustering. GLARE provides implementation of representation learning models, including the state-of-the-art SAE model pre-trained with high-throughput single-cell data. Retrieved data representation is then processed through ensemble clustering to find the hidden patterns within the data. Results from the verification study and ensemble clustering are then used for post-pipeline analysis. b Model architecture illustration of the employed SAE for both training with and without pre-training. c Ensemble clustering using three base clustering algorithms based on different statistical methodologies. Evidence accumulation clustering is used to derive consensus clusters from these algorithms.
