Department of Biomedical Engineering, Pennsylvania State University, State College, PA, USA.
Quantalarity Research Group, Houston, TX, USA.
Nat Commun. 2022 Feb 2;13(1):625. doi: 10.1038/s41467-022-28045-w.
A genetic knockout can be lethal to one human cell type while increasing growth rate in another. This context specificity confounds genetic analysis and prevents reproducible genome engineering. Genome-wide CRISPR compendia across most common human cell lines offer the largest opportunity to understand the biology of cell specificity. The prevailing viewpoint, synthetic lethality, occurs when a genetic alteration creates a unique CRISPR dependency. Here, we use machine learning for an unbiased investigation of cell type specificity. Quantifying model accuracy, we find that most cell type specific phenotypes are predicted by the function of related genes of wild-type sequence, not synthetic lethal relationships. These models then identify unexpected sets of 100-300 genes where reduced CRISPR measurements can produce genome-scale loss-of-function predictions across >18,000 genes. Thus, it is possible to reduce in vitro CRISPR libraries by orders of magnitude-with some information loss-when we remove redundant genes and not redundant sgRNAs.
一种基因敲除可能对一种人类细胞类型具有致命性，而对另一种细胞类型的生长速度却有促进作用。这种上下文特异性使基因分析变得复杂，并阻碍了可重复的基因组工程。最常见的人类细胞系的全基因组 CRISPR 文库提供了最大的机会来了解细胞特异性的生物学。当遗传改变产生独特的 CRISPR 依赖性时，就会出现合成致死性这一普遍观点。在这里，我们使用机器学习对细胞类型特异性进行了无偏分析。通过量化模型准确性，我们发现大多数细胞类型特异性表型是由野生型序列相关基因的功能预测的，而不是合成致死关系。这些模型随后确定了一组意外的 100-300 个基因，在这些基因中，减少 CRISPR 测量值可以在 >18000 个基因中产生全基因组功能丧失预测。因此，当我们去除冗余基因而不是冗余 sgRNA 时，可以将体外 CRISPR 文库减少几个数量级——尽管会有一些信息丢失。
