Researchers at New York University (NYU), Columbia University, and the New York Genome Center have developed an artificial intelligence (AI) platform that can predict the on-target and off-target activity of CRISPR tools that target RNA rather than DNA.
Combining deep learning models with CRISPR screens, the researchers worked in various ways, such as flicking a light switch to turn it off completely, or using a dimming knob to partially dampen gene activity. controlled the expression of human genes. The resulting neural network, called Targeted Inhibition of Gene Expression by gRNA Design (TIGER), was able to predict effects from guide sequences and context. The researchers suggest that this new technology could pave the way for the development of precise gene regulation for use in CRISPR-based therapies.
“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. We can have only 70% of the generated.” Andrew Stern, Ph.D. student at Columbia Engineering and the New York Genome Center. Stern is the co-first author of a paper the researchers published in 2016. nature biotechnology, titled ‘Prediction of on- and off-target activities of CRISPR-Cas13d guide RNAs using deep learning’. In their paper, the researchers wrote, “TIGER prediction enables ranking and ultimately avoiding unwanted off-target binding sites and nuclease activation, further facilitating the development of RNA-targeted therapeutics.” I believe it will,” he concludes.
CRISPR gene-editing technology has many applications in biomedical and beyond, from treating sickle cell anemia to producing tastier mustard greens. Some of his CRISPR techniques use an enzyme called Cas9 to target DNA, but in recent years scientists have instead discovered another type of his CRISPR that uses an enzyme called Cas13 to target RNA. I found “New CRISPR technology holds great promise for a new generation of therapeutics,” the authors said. “Among them, CRISPR proteins that target RNA have recently been shown to offer therapeutic value in disease models.”
RNA-targeted CRISPR can be used for a wide range of applications, including RNA editing, knockdown of RNA to block expression of specific genes, and high-throughput screening to determine potential drug candidates. Researchers at New York University and the New York Genome Center previously created a platform for RNA-targeted CRISPR screening using Cas13 to better understand RNA regulation and identify the function of noncoding RNAs. Since RNA is the major genetic material of viruses such as SARS-CoV-2 and influenza, CRISPR targeting RNA is also expected to develop new methods to prevent or treat viral infections. Also, in human cells, one of the first steps in gene expression is the creation of RNA from the DNA in the genome.
“Like CRISPR targeting DNA, such as Cas9, CRISPR targeting RNA, such as Cas13, is expected to have a profound impact on molecular biology and biomedical applications in the coming years,” said New York University. Dr. Neville Sanjana, associate professor of biology at , associate professor of neuroscience and physiology at New York University’s Grossman School of Medicine, core faculty member at the New York Genome Center, and co-senior author of this study. “Precise guide prediction and off-target identification will be of great value to this emerging field and therapy.”
A key goal of the research team’s newly reported study is to maximize the activity of RNA-targeting CRISPR against its intended target RNA, or “on-target” activity, and “off-target” activity, which may have detrimental aspects to other RNAs. The target was to minimize ‘activity’. Effects on cells. “High precision is key to the safety of therapeutic CRISPR drugs that target RNA,” the researchers noted. Off-target activity includes both insertion and deletion mutations, as well as mismatches between guide and target RNA.
However, early studies of RNA-targeted CRISPR mainly focused on on-target activity and mismatches, and off-target activity, especially prediction of insertion and deletion mutations, was poorly studied. . 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.
For their work described in nature biotechnologySanjana et al. performed a series of pooled RNA-targeted CRISPR screens in human cells. They measured the activity of 200,000 guide RNAs targeting essential genes in human cells, including both ‘perfect match’ guide RNAs and off-target mismatches, insertions and deletions. “In this study, we generated a large Cas13d dataset measuring the activity of ~200,000 gRNAs across multiple human cell lines and performed a comprehensive assessment of the on-target and off-target activities of Cas13d gRNAs. Sanjana’s lab collaborated with machine learning expert and co-senior author Dr. David Knowles’ lab to design a deep learning model called TIGER that was trained on data from CRISPR screens. bottom.
Comparing predictions generated by deep learning models and laboratory tests on human cells, TIGER was able to predict both on-target and off-target activity, compared to previous models developed for Cas13 on-target guide design. It provided the first tool for outperforming models and predicting off-target. – Target activity of CRISPR targeting RNA. “Machine learning and deep learning are showing their strengths in genomics because they can take advantage of the huge datasets that modern high-throughput experiments can generate,” says Knowles, assistant professor of computer science and systems biology at Columbia University. said. He majored in engineering and applied sciences and is a core faculty member at the New York Genome Center. “Importantly, we were also able to use ‘interpretable machine learning’ to understand why the model predicted that a particular guide would work well.”
Dr. Hans-Hermann Wessels, co-first author and Senior Fellow at the New York Genome Center, added: “Our previous work demonstrated a method to design Cas13 guides that can knockdown specific RNAs. We can now design a Cas13 guide that takes .” Wessels was previously a postdoctoral fellow in Sanjana’s lab.
The researchers envision that combining artificial intelligence with RNA-targeted CRISPR screening could help predict TIGER to avoid unwanted off-target CRISPR activity, further facilitating the development of a new generation of RNA-targeted therapeutics. .
The researchers also used TIGER’s off-target prediction to precisely measure gene dosage (the amount of a particular gene expressed) by allowing partial inhibition of gene expression in cells with mismatched guides. I have proven that it is adjustable. This could be useful in diseases such as Down syndrome, certain schizophrenia, Charcot-Marie-Tooth disease (an inherited neurological disorder) where there are too many copies of a gene, and cancers caused by abnormal gene expression. There is a nature. Uncontrolled tumor growth. “…our model can be used for precise regulation of large-scale target RNA knockdown,” they said. “In particular, our study suggests that RNA-targeted CRISPR perturbations can be exploited to systematically study the effects of gene dosage at the RNA level,” the researchers said.
“As we collect larger datasets from CRISPR screens, we are seeing more and more opportunities to apply sophisticated machine learning models,” says Sanjana. “We are fortunate to have David’s lab next door to ours, facilitating this great cross-disciplinary collaboration. And the ability to precisely modulate gene dosage enables many exciting new applications of RNA-targeting CRISPR in biomedicine.”
This latest work builds on previous work by the New York University team to develop design rules for guide RNAs and target RNAs for diverse organisms, including viruses like SARS-CoV-2 and engineered proteins. , further advancing the broad applicability of RNA-targeted CRISPR to human genetics and drug discovery. and RNA therapeutics, exploiting single-cell biology to reveal synergistic drug combinations against leukemia.
The authors conclude in their paper: “Together, the ability to model the effects of nucleotide mismatches will not only improve our understanding of gRNA on-target specificity and off-target evasion, but also enable precise knockdown of the target.” A defined degree that helps in the application of tome engineering. “
