ACE: Explaining cluster from an adversarial perspective
Lu, Y. Y.; Yu, T.; Bonora, G.; Noble, W. S.
Show abstract
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 discovered clusters. A primary drawback to this three-step procedure is that each step is carried out independently, thereby neglecting the effects of the nonlinear embedding and inter-gene dependencies on the selection of marker genes. Here we propose an integrated deep learning framework, Adversarial Clustering Explanation (ACE), that bundles all three steps into a single work-flow. The method thus moves away from the notion of "marker genes" to instead identify a panel of explanatory genes. This panel may include genes that are not only enriched but also depleted relative to other cell types, as well as genes that exhibit differences between closely related cell types. Empirically, we demonstrate that ACE is able to identify gene panels that are both highly discriminative and nonredundant, and we demonstrate the applicability of ACE to an image recognition task. 1
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluating discrepancies in dimensionality reduction for time-series single-cell RNA-sequencing data 96%
- Sincast: a computational framework to predict cell identities in single cell transcriptomes using bulk atlases as references 96%
- Deep learning of gene interactions from single cell time-course expression data 96%
Similar papers in this journal
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 97%
- Hierarchical confounder discovery in the experiment-machine learning cycle 96%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 95%
"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.