CRISPR is a gene-editing technique that has many applications in biomedical and beyond, from treating sickle cell anemia to creating tastier mustard greens. They often work by targeting DNA with an enzyme known as Cas9. Recently, scientists identified another form of his CRISPR that uses an enzyme called Cas13 to target RNA. RNA-targeted CRISPR has many applications, including RNA editing, knockdown of RNA to limit gene expression, and high-throughput screening to identify promising drug candidates.
Deep learning algorithms and CRISPR screens are used to control how human genes are expressed in a variety of ways, including turning lights on and off and adjusting lamp brightness. These precise gene controls could be used to create new CRISPR-based therapeutics.
Researchers at New York University and the New York Genome Center have developed a Cas13-based RNA-targeted CRISPR screening platform to better understand RNA regulation and discover the role of noncoding RNAs. Since RNA is the major genetic material of viruses such as SARS-CoV-2 and influenza, CRISPR targeting RNA may develop new approaches to prevent or treat viral infections. Furthermore, when genes are expressed in human cells, one of the first processes is the formation of RNA from DNA within the genome.
The goal of the new research is to maximize the activity of RNA-targeting CRISPR on the target RNA of choice and minimize its activity on other RNAs that may adversely affect the cell. Mismatches between guide and target RNA, insertion and deletion mutations are examples of off-target effects.
To date, RNA-targeted CRISPR research has focused solely on on-target activity and mismatches. Prediction of off-target activity, especially insertion and deletion mutations, has received less attention. Approximately 1 in 5 mutations in the human population are insertions or deletions, so these are important types of potential off-targets to consider in CRISPR design.
Groundbreaking research conducted by Neville Sanjana, associate professor of biology at New York University, and a team at New York University has opened up a world of possibilities for RNA-targeted CRISPR in biomedicine. Their latest work not only deepens our understanding of these potential applications of CRISPR, but also paves the way for important advances in human genetics and drug discovery.
By developing guide RNA design rules, the research team provided an important framework for effectively targeting RNAs from a variety of organisms, including notorious viruses like SARS-CoV-2. . Additionally, their expertise extends to the design of protein and RNA therapeutics, providing promising avenues for new therapeutics.
Additionally, they harnessed the power of single-cell biology to discover synergistic drug combinations with immense potential in combating leukemia. With this comprehensive approach and constant pursuit of innovation,
she said, “Like CRISPR targeting DNA such as Cas9, we anticipate that CRISPR targeting RNA such as Cas13 will have a tremendous impact on molecular biology and biomedical applications in the coming years. Predictive guidance and identification of off-targets will be of great value to this emerging field and therapy.”
The researchers and his team used a series of pooled RNA-targeting CRISPR screens in human cells to monitor the activity of 200,000 guide RNAs directed against key human cellular genes.
They collaborated with machine learning expert David Knowles to create a deep learning model TIGER (Targeted Inhibition of Gene Expression by Guide RNA Design) trained using information from CRISPR screens. TIGER surpassed previous models created for Cas13 on-target guide designs. He provided the first tool for predicting the off-target activity of RNA-targeted CRISPR when comparing predictions generated by deep learning models and clinical testing in human cells.
David Knowles, principal faculty member at the New York Genome Center and assistant professor of computer science and systems biology at Columbia University’s School of Engineering and Applied Sciences, said: “Machine learning and deep learning are showing their strength in the genomics field because they can take advantage of the huge datasets that can be generated by modern high-throughput experiments. , we were also able to understand why the model predicted that a particular guide would perform well. ”
The researchers also demonstrate that TIGER’s off-target prediction may be used to precisely control gene dosage in cells with mismatched guides by enabling partial repression of gene production. bottom. This is due to the lack of copies of the gene, such as Down syndrome, certain schizophrenia, Charcot-Marie-Tooth disease (an inherited neurological disorder), or tumors where aberrant gene expression can lead to uncontrolled tumor growth. May be beneficial for too many diseases.
Hans Hermann (Harm) Wessels, co-first author of the study, a senior fellow at the New York Genome Center and a former postdoctoral fellow in the Sanjana lab, said: “In our previous work, we demonstrated how to design Cas13 guides that knockdown specific RNAs. We can now design a Cas13 guide to take.”
Dr. Andrew Stern, a student at the Columbia School of Engineering and the New York Genome Center, and co-first author of the study, said: “Our deep learning model not only tells us how to design a guide RNA that completely knocks down a transcript, but also allows us to ‘tune’ it. For example, you can choose to generate only 70% of transcripts for a particular gene. ”
By combining artificial intelligence with RNA-targeted CRISPR screening, the researchers hope that TIGER predictions can help circumvent unwanted off-target CRISPR activity and accelerate the development of a new generation of RNA-targeted therapeutics. ing.
According to researchers, the opportunities to use advanced machine learning models are expanding rapidly as we get more meaningful datasets from CRISPR screens. We are lucky that David’s lab is next door to ours. Because this wonderful interdisciplinary collaboration has become possible.
The ability to precisely control gene dosage using TIGER opens up a number of exciting new applications for RNA-targeting CRISPR in biomedicine. The New York University team is revolutionizing the biomedical field, propelling us into a future where CRISPR-based therapies are an integral part of medical practice.
Reference magazines:
- Wessels, HH., Stirn, A., Méndez-Mancilla, A. et al. Prediction of on- and off-target activity of CRISPR-Cas13d guide RNAs using deep learning. nature biotechnology. DOI: 10.1038/s41587-023-01830-8
