Russian bioinformaticians have proposed a novel neural network architecture capable of assessing the extent to which a guide RNA has been chosen for a gene editing experiment. Their approach will facilitate more efficient DNA modification with the popular CRISPR / Cas method and therefore help develop new strategies to create genetically modified organisms and find ways to treat serious inherited disorders. The study, funded by a grant from the Russian Science Foundation, was published in the Nucleic Acid Research newspaper.
Genome editing, and the CRISPR / Cas method in particular, is widely used in various fields of experimental biology, as well as in agriculture and biotechnology.
CRISPR / Cas is one of the many weapons bacteria use to fight viruses. As infection occurs, the pathogen’s DNA enters the cell, and because its sequences differ from that of the bacteria, Cas proteins recognize it as foreign hereditary material and cleave it. In order for the bacteria to respond more quickly to the virus, the cell stores fragments of the pathogen’s DNA, much like a computer antivirus keeps a collection of viral signatures, and passes them on to subsequent generations so that its case can thwart. other attacks.
In 2011-2013, teams from different laboratories (Jennifer Doudna, Emmanuelle Charpentier and Feng Zhang in the United States, and Virginijus Å ikÅ¡nys in Lithuania) independently of each other adapted the CRISPR / Cas system to the task of introducing changes arbitrary DNA sequences in human and animal cells, making genomic editing much easier and more efficient. Central to the system are guide RNA, which “marks the spot”, and the Cas9 protein, which cleaves DNA at that position. The cell then “repairs the wound” but the changes in the genetic code have already been made.
The problem is that guide RNA targeting is not always precise and can mislead Cas9. Transforming CRISPR / Cas technology into a practical, high-precision tool is very important, especially when it comes to medical interventions.
Skoltech researchers led by Konstantin Severinov used deep learning, Gaussian processes and other methods to make the selection of optimal guide RNAs more precise. The team produced a set of neural networks, that is, trainable mathematical models implemented as sequential matrix multiplication, large arrays of numbers with a complex internal structure. A neural network is able to learn because it has “memory” in the form of numbers that are changed in a particular way each time the system performs a learning mode calculation. The team trained the models on different datasets containing tens of thousands of experimentally validated guide RNAs that had shown high precision performance in human and animal cells.
The researchers proposed an algorithm that estimates the probability of DNA cleavage for a given guide RNA. The scores obtained can guide the experimental design for any CRISPR / Cas-based application. The team used their neural networks to come up with a set of guide RNAs for making precise changes to genes on the 22nd human chromosome. This was made possible by the high precision of the cleavage frequency prediction and a prediction uncertainty estimation function, which none of the existing methods provided.
âOur results can be used for a variety of CRISPR / Cas-based technology applications, such as the treatment of genetic disorders, agricultural technologies and basic research experiments,â commented Skoltech Ph.D. student Bogdan Kirillov , one of the creators of the new method and the first author of the study.
New findings on the link between CRISPR gene editing and mutated cancer cells
Bogdan Kirillov et al, Uncertain and interpretable assessment of the specificity of Cas9-gRNA and Cas12a-gRNA for fully matched targets and partially incompatible with Deep Kernel Learning, Nucleic Acid Research (2021). DOI: 10.1093 / nar / gkab1065
Provided by the Skolkovo Institute of Science and Technology
Quote: New Neural Network for More Accurate DNA Editing (2021, December 30) retrieved January 2, 2022 from https://medicalxpress.com/news/2021-12-neural-network-accurate-dna. html
This document is subject to copyright. Other than fair use for private study or research purposes, no part may be reproduced without written permission. The content is provided for information only.