New research published in Nature Biotechnology reveals that artificial intelligence (AI) has the ability to predict both on-target and off-target activity of CRISPR tools that target RNA instead of DNA. The study, conducted by researchers from New York University, Columbia Engineering, and the New York Genome Center, utilises a deep learning model combined with CRISPR screens to manipulate the expression of human genes. This precise control over gene expression could pave the way for the development of innovative CRISPR-based therapies.
CRISPR technology has diverse applications in biomedicine and beyond, ranging from treating genetic disorders like sickle cell anaemia to enhancing the properties of agricultural produce. Traditionally, CRISPR operates by targeting DNA using an enzyme called Cas9. However, scientists have recently discovered a different type of CRISPR that targets RNA using an enzyme called Cas13.
RNA-targeting CRISPRs offer numerous possibilities, including RNA editing, gene silencing by blocking the expression of specific genes, and high-throughput screening to identify potential drug candidates. Researchers at NYU and the New York Genome Center have developed a platform for RNA-targeting CRISPR screens that employ Cas13. This platform aims to enhance our understanding of RNA regulation and uncover the functions of non-coding RNAs. Additionally, since RNA serves as the primary genetic material in viruses like SARS-CoV-2 and influenza, RNA-targeting CRISPRs hold promise for the development of novel methods to prevent or treat viral infections. Furthermore, in human cells, gene expression initiates with the creation of RNA from the DNA in the genome.
The primary objective of this study is to maximise the efficiency of RNA-targeting CRISPRs in targeting the intended RNA while minimising off-target activity that could have adverse effects on the cell. Off-target activity encompasses mismatches between the guide RNA and the target RNA, as well as insertion and deletion mutations. Previous studies on RNA-targeting CRISPRs mainly focused on on-target activity and mismatches, neglecting the prediction of off-target activity, particularly insertion and deletion mutations. As one in five mutations in human populations involves insertions or deletions, these potential off-target effects are crucial considerations in CRISPR design.
Neville Sanjana, co-senior author of the study and an associate professor at NYU, NYU Grossman School of Medicine, and the New York Genome Center, states that RNA-targeting CRISPRs, like Cas13, are anticipated to have a significant impact in molecular biology and biomedical applications in the years to come. Accurate guide prediction and identification of off-target effects are of immense value in this emerging field and for therapeutic purposes.
In their research published in Nature Biotechnology, Sanjana and his team conducted a series of pooled RNA-targeting CRISPR screens in human cells. They measured the activity of 200,000 guide RNAs that targeted essential genes in human cells, including both "perfect match" guide RNAs and those with off-target mismatches, insertions, and deletions.
Sanjana's lab collaborated with the lab of machine learning expert David Knowles to develop a deep learning model called TIGER (Targeted Inhibition of Gene Expression via guide RNA design), which was trained using the data from the CRISPR screens. By comparing the predictions generated by the deep learning model with laboratory tests conducted on human cells, TIGER successfully predicted both on-target and off-target activity, surpassing previous models designed for Cas13 on-target guide design. This marks the first tool capable of predicting off-target activity of RNA-targeting CRISPRs.
Click here to read the original news story.