51. Dimensionality reduction methods for extracting functional networks from large‐scale CRISPR screens.
- Author
-
Hassan, Arshia Zernab, Ward, Henry N, Rahman, Mahfuzur, Billmann, Maximilian, Lee, Yoonkyu, and Myers, Chad L
- Subjects
CRISPRS ,PRINCIPAL components analysis ,MEDICAL screening ,GENOME editing ,DOMINANCE (Genetics) ,INFORMATION networks - Abstract
CRISPR‐Cas9 screens facilitate the discovery of gene functional relationships and phenotype‐specific dependencies. The Cancer Dependency Map (DepMap) is the largest compendium of whole‐genome CRISPR screens aimed at identifying cancer‐specific genetic dependencies across human cell lines. A mitochondria‐associated bias has been previously reported to mask signals for genes involved in other functions, and thus, methods for normalizing this dominant signal to improve co‐essentiality networks are of interest. In this study, we explore three unsupervised dimensionality reduction methods—autoencoders, robust, and classical principal component analyses (PCA)—for normalizing the DepMap to improve functional networks extracted from these data. We propose a novel "onion" normalization technique to combine several normalized data layers into a single network. Benchmarking analyses reveal that robust PCA combined with onion normalization outperforms existing methods for normalizing the DepMap. Our work demonstrates the value of removing low‐dimensional signals from the DepMap before constructing functional gene networks and provides generalizable dimensionality reduction‐based normalization tools. Synopsis: Dimensionality reduction‐based methods are proposed for normalizing Cancer Dependency Map (DepMap) genome‐wide CRISPR screen data to enhance the functional information in co‐essentiality networks extracted from DepMap.Low‐dimensional patterns introduce dominant covariation in gene networks derived from DepMap data, obscuring more subtle functional relationships.Applying dimensionality reduction approaches to remove low‐dimensional signal, including robust and classical principal component analysis or autoencoders, can increase functional information captured by similarity networks derived from DepMap data.Onion normalization, which integrates several normalized data layers into a single network, outperforms existing methods for constructing co‐essentiality networks from the DepMap. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF