id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
10_1101-2021_02_08_428881	Lu, Yang Young	ACE: Explaining cluster from an adversarial perspective	2021	12	.pdf	application/pdf	7909	790	66	A common workflow in single-cell RNA-seq analysis is to project the data to a latent space, cluster the cells in that space, and identify sets of marker genes that explain the differences among the nonlinear embedding model which maps the gene expression to the low-dimensional representation where the groups A notable feature of ACE's approach is that, by identifying genes jointly, the method moves away from the notion Input: gene expression matrix Deep autoencoder learns low-dimensional representation Embedding clustering Clustering is neuralized and concatenated with the encoder Differentiation analysis by ACE Output: gene relevance ACE takes as input a single-cell gene expression matrix and learns a low-dimensional representation for each Next, a neuralized version of the k-means algorithm is applied to the learned representation to identify cell groups. input gene expression profile that lead the neuralized clustering model to alter the assignment from one group to the other.	./cache/10_1101-2021_02_08_428881.pdf	./txt/10_1101-2021_02_08_428881.txt