AI Joins Forces with CRISPR: Emergence of Precision RNA-Targeting and Gene Regulation

A new study reveals the development of RNA-focused predictive models that leverage artificial intelligence (AI) to gauge the on- and off-target functionality of CRISPR tools which target RNA rather than DNA. The goal of this model is to enable meticulous regulation of gene expression, which holds the potential to significantly advance the creation of novel CRISPR-based treatments.

The research introduces an AI model, named TIGER, that estimates the on- and off-target operations of RNA-targeting CRISPR tools. Detailed in the recently published study in Nature Biotechnology, this breakthrough can precisely design guide RNAs, regulate gene expression, and is set to accelerate progress in CRISPR-based therapies.

A study published today (July 3) in Nature Biotechnology reports that AI can forecast on- and off-target activity of CRISPR tools targeting RNA instead of DNA.

The study, conducted by researchers from New York University, Columbia Engineering, and the New York Genome Center, couples a deep learning model with CRISPR screens to dictate the expression of human genes in various ways—similar to the fine control provided by a light dimmer switch, rather than a simple on/off switch. This precise gene manipulation could be utilized to formulate new CRISPR-based treatments.

CRISPR, a gene-editing technology with multiple applications from treating sickle cell anemia to engineering more palatable mustard greens, typically operates by targeting DNA using an enzyme known as Cas9. However, in recent years, scientists discovered another form of CRISPR that targets RNA with an enzyme named Cas13.

The utility of RNA-targeting CRISPRs extends to numerous applications such as RNA editing, RNA knockdown to inhibit gene expression, and high-throughput screening to determine promising drug candidates. Researchers at NYU and the New York Genome Center developed a platform for RNA-targeting CRISPR screens utilizing Cas13 to gain a deeper understanding of RNA regulation and to decipher the role of non-coding RNAs. Since RNA is the main genetic material in viruses, including SARS-CoV-2 and flu, RNA-targeting CRISPRs also present the potential for creating novel methods to prevent or treat viral infections. Moreover, in human cells, RNA creation from DNA in the genome is among the initial steps when a gene is expressed.

The study aims to optimize the activity of RNA-targeting CRISPRs on the intended target RNA and minimize undesired activity on other RNAs, which could potentially harm the cell. Off-target activity includes mismatches between the guide and target RNA as well as insertions and deletions. Previous research of RNA-targeting CRISPRs focused solely on on-target activity and mismatches; prediction of off-target activity, particularly insertion and deletion mutations, remains less explored. Considering that about one in five mutations in human populations are insertions or deletions, these mutation types are crucial off-targets to take into account when designing CRISPR tools.

In their Nature Biotechnology publication, the researchers performed a series of pooled RNA-targeting CRISPR screens in human cells, examining the activity of 200,000 guide RNAs targeting essential genes, including both perfect match guide RNAs and off-target mismatches, insertions, and deletions.

To develop TIGER, Sanjana’s lab collaborated with David Knowles’ lab, specializing in machine learning. TIGER, a deep learning model, was trained using data from CRISPR screens. When comparing the predictions made by TIGER with laboratory tests in human cells, the model was able to predict both on-target and off-target activity, exceeding the performance of earlier models created for Cas13 on-target guide design, and offering the first tool for predicting off-target activity of RNA-targeting CRISPRs.

Through the combination of artificial intelligence and an RNA-targeting CRISPR screen, the researchers believe that TIGER’s predictions will help reduce unwanted off-target CRISPR activity and further inspire the development of a new wave of RNA-targeting treatments.

Reference: 3 July 2023, Nature Biotechnology.
DOI: 10.1038/s41587-023-01830-8

Additional authors of the study include Alejandro Méndez-Mancilla and Sydney K. Hart of NYU and the New York Genome Center, and Eric J. Kim of Columbia University. The research received support from grants from the National Institutes of Health (DP2HG010099, R01CA218668, R01GM138635), DARPA (D18AP00053), the Cancer Research Institute, and the Simons Foundation for Autism Research Initiative.

Frequently Asked Questions (FAQs) about RNA-targeting CRISPR

More about RNA-targeting CRISPR

• Artificial Intelligence
• CRISPR Technology
• Nature Biotechnology Journal
• Gene Modulation
• New York Genome Center
• RNA-targeting with CRISPR