Summary of Scghsom: Hierarchical Clustering and Visualization Of Single-cell and Crispr Data Using Growing Hierarchical Som, by Shang-jung Wen et al.
scGHSOM: Hierarchical clustering and visualization of single-cell and CRISPR data using growing hierarchical SOM
by Shang-Jung Wen, Jia-Ming Chang, Fang Yu
First submitted to arxiv on: 24 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Information Retrieval (cs.IR); Genomics (q-bio.GN)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel unsupervised clustering approach, Growing Hierarchical Self-Organizing Map (GHSOM), is proposed to analyze high-dimensional single-cell data from sequencing and CRISPR screens. The method identifies gene-cell dependencies by applying GHSOM to cluster samples in a hierarchical structure. A Significant Attributes Identification Algorithm pinpoints key attributes that distinguish clusters, allowing for targeted data retrieval and downstream analysis. Two visualization tools, Cluster Feature Map and Cluster Distribution Map, are introduced to facilitate rapid visual assessment of cluster uniqueness based on chosen features. The approach is evaluated using three single-cell datasets and one CRISPR dataset, with GHSOM performing well in both internal and external evaluations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GHSOM helps scientists understand how cells work together by grouping them into clusters based on their gene activity. This makes it easier to find important genes that are different between cell types. The method also includes tools to help visualize the results, making it easier to identify patterns and trends in the data. GHSOM is tested on several datasets and shows promising results. |
Keywords
» Artificial intelligence » Clustering » Feature map » Unsupervised
