MSGID: 1:317/3 64a3a084   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    AI and CRISPR precisely control gene expression    
    RNA-based predictive models developed    
      
     Date:   
         July 3, 2023   
     Source:   
         Columbia University School of Engineering and Applied Science   
     Summary:   
         The study combines a deep learning model with CRISPR screens to   
         control the expression of human genes in different ways -- such as   
         flicking a light switch to shut them off completely or by using a   
         dimmer knob to partially turn down their activity. These precise   
         gene controls could be used to develop new CRISPR-based therapies.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   Artificial intelligence can predict on- and off-target activity of CRISPR   
   tools that target RNA instead of DNA, according to new research published   
   in Nature Biotechnology.   
      
   The study by researchers at New York University, Columbia Engineering,   
   and the New York Genome Center, combines a deep learning model with CRISPR   
   screens to control the expression of human genes in different ways --   
   such as flicking a light switch to shut them off completely or by using   
   a dimmer knob to partially turn down their activity. These precise gene   
   controls could be used to develop new CRISPR-based therapies.   
      
   CRISPR is a gene editing technology with many uses in biomedicine and   
   beyond, from treating sickle cell anemia to engineering tastier mustard   
   greens. It often works by targeting DNA using an enzyme called Cas9. In   
   recent years, scientists discovered another type of CRISPR that instead   
   targets RNA using an enzyme called Cas13.   
      
   RNA-targeting CRISPRs can be used in a wide range of applications,   
   including RNA editing, knocking down RNA to block expression of a   
   particular gene, and high-throughput screening to determine promising drug   
   candidates. Researchers at NYU and the New York Genome Center created a   
   platform for RNA-targeting CRISPR screens using Cas13 to better understand   
   RNA regulation and to identify the function of non-coding RNAs. Because   
   RNA is the main genetic material in viruses including SARS-CoV-2 and flu,   
   RNA-targeting CRISPRs also hold promise for developing new methods to   
   prevent or treat viral infections. Also, in human cells, when a gene is   
   expressed, one of the first steps is the creation of RNA from the DNA   
   in the genome.   
      
   A key goal of the study is to maximize the activity of RNA-targeting   
   CRISPRs on the intended target RNA and minimize activity on other   
   RNAs which could have detrimental side effects for the cell. Off-target   
   activity includes both mismatches between the guide and target RNA as well   
   as insertion and deletion mutations. Earlier studies of RNA-targeting   
   CRISPRs focused only on on-target activity and mismatches; predicting   
   off-target activity, particularly insertion and deletion mutations, has   
   not been well-studied. In human populations, about one in five mutations   
   are insertions or deletions, so these are important types of potential   
   off-targets to consider for CRISPR design.   
      
   "Similar to DNA-targeting CRISPRs such as Cas9, we anticipate that RNA-   
   targeting CRISPRs such as Cas13 will have an outsized impact in molecular   
   biology and biomedical applications in the coming years," said Neville   
   Sanjana, associate professor of biology at NYU, associate professor of   
   neuroscience and physiology at NYU Grossman School of Medicine, a core   
   faculty member at New York Genome Center, and the study's co-senior   
   author. "Accurate guide prediction and off-target identification will   
   be of immense value for this newly developing field and therapeutics."   
   In their study inNature Biotechnology, Sanjana and his colleagues   
   performed a series of pooled RNA-targeting 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.   
      
   Sanjana's lab teamed up with the lab of machine learning expert David   
   Knowles to engineer a deep learning model they named TIGER (Targeted   
   Inhibition of Gene Expression via guide RNA design) that was trained on   
   the data from the CRISPR screens. Comparing the predictions generated   
   by the deep learning model and laboratory tests in human cells,   
   TIGER was able to predict both on-target and off-target activity,   
   outperforming previous models developed for Cas13 on- target guide   
   design and providing the first tool for predicting off-target activity   
   of RNA-targeting CRISPRs.   
      
   "Machine learning and deep learning are showing their strength in   
   genomics because they can take advantage of the huge datasets that can   
   now be generated by modern high-throughput experiments. Importantly, we   
   were also able to use "interpretable machine learning" to understand why   
   the model predicts that a specific guide will work well," said Knowles,   
   assistant professor of computer science and systems biology at Columbia   
   Engineering, a core faculty member at New York Genome Center, and the   
   study's co-senior author.   
      
   "Our earlier research demonstrated how to design Cas13 guides that can   
   knock down a particular RNA. With TIGER, we can now design Cas13 guides   
   that strike a balance between on-target knockdown and avoiding off-target   
   activity," said Hans-Hermann (Harm) Wessels, the study's co-first author   
   and a senior scientist at the New York Genome Center, who was previously   
   a postdoctoral fellow in Sanjana's laboratory.   
      
   The researchers also demonstrated that TIGER's off-target predictions   
   can be used to precisely modulate gene dosage -- the amount of a   
   particular gene that is expressed -- by enabling partial inhibition   
   of gene expression in cells with mismatch guides. This may be useful   
   for diseases in which there are too many copies of a gene, such as Down   
   syndrome, certain forms of schizophrenia, Charcot-Marie-Tooth disease (a   
   hereditary nerve disorder), or in cancers where aberrant gene expression   
   can lead to uncontrolled tumor growth.   
      
   "Our deep learning model can tell us not only how to design a guide   
   RNA that knocks down a transcript completely, but can also 'tune' it --   
   for instance, having it produce only 70% of the transcript of a specific   
   gene," said Andrew Stirn, a PhD student at Columbia Engineering and the   
   New York Genome Center, and the study's co-first author.   
      
   By combining artificial intelligence with an RNA-targeting CRISPR screen,   
   the researchers envision that TIGER's predictions will help avoid   
   undesired off- target CRISPR activity and further spur development of   
   a new generation of RNA- targeting therapies.   
      
   "As we collect larger datasets from CRISPR screens, the opportunities   
   to apply sophisticated machine learning models are growing rapidly. We   
   are lucky to have David's lab next door to ours to facilitate this   
   wonderful, cross-disciplinary collaboration. And, with TIGER, we can   
   predict off-targets and precisely modulate gene dosage which enables many   
   exciting new applications for RNA- targeting CRISPRs for biomedicine,"   
   said Sanjana.   
      
   Additional study authors include Alejandro Me'ndez-Mancilla and Sydney   
   K. Hart of NYU and the New York Genome Center, and Eric J. Kim of   
   Columbia University.   
      
   The research was supported by grants from the National Institutes of   
   Health (DP2HG010099, R01CA218668, R01GM138635), DARPA (D18AP00053),   
   the Cancer Research Institute, and the Simons Foundation for Autism   
   Research Initiative.   
      
       * RELATED_TOPICS   
             o Health_&_Medicine   
                   # Human_Biology # Genes # Personalized_Medicine   
             o Plants_&_Animals   
                   # CRISPR_Gene_Editing # Genetics # Biology   
             o Matter_&_Energy   
                   # Organic_Chemistry # Biochemistry # Engineering   
             o Computers_&_Math   
                   # Computer_Modeling # Neural_Interfaces #   
                   Computational_Biology   
       * RELATED_TERMS   
             o Gene o Computational_genomics o BRCA2 o BRCA1 o Gene_therapy   
             o Bioluminescence o Soil_pH o DNA_microarray   
      
   ==========================================================================   
      
    Print   
      
    Email   
      
    Share   
   ==========================================================================   
   ****** 1 ****** ***** 2 ***** **** 3 ****   
   *** 4 *** ** 5 ** Breaking this hour   
   ==========================================================================   
       * Screens_More_Versatile_Than_LED:_Fins_and_...   
      
       * GM_Pig_Heart_in_a_Human_Patient:_Update *   
       Multiple_Sclerosis_Severity * Wind_Farm_Noise_and_Road_Traffic_Noise   
       * Mavericks_and_Horizontal_Gene_Transfer *   
       Early_Reading_for_Pleasure:_Brains,_...   
      
       * New_Light_Shed_On_Evolution_of_Animals *   
       Gullies_On_Mars_from_Liquid_Meltwater?   
       * DNA_Organization_in_Real-Time *   
       How_the_Cat_Nose_Knows_What_It's_Smelling   
      
   Trending Topics this week   
   ==========================================================================   
   PLANTS_&_ANIMALS Birds Animal_Learning_and_Intelligence Molecular_Biology   
   EARTH_&_CLIMATE Water Weather Climate FOSSILS_&_RUINS Dinosaurs   
   Early_Mammals Origin_of_Life   
      
      
   ==========================================================================   
      
   Strange & Offbeat   
   ==========================================================================   
   PLANTS_&_ANIMALS   
   Squash_Bugs_Are_Attracted_to_and_Eat_Each_Other's_Poop_to_Stock_Their   
   Microbiome How_Urea_May_Have_Been_the_Gateway_to_Life   
   Octopus_Sleep_Is_Surprisingly_Similar_to_Humans_and_Contains_a_Wake-Like_Stage   
   EARTH_&_CLIMATE   
   Turning_Old_Maps_Into_3D_Digital_Models_of_Lost_Neighborhoods   
   Orangutans_Can_Make_Two_Sounds_at_the_Same_Time,_Similar_to_Human_Beatboxing,   
   Study_Finds Do_Hummingbirds_Drink_Alcohol?_More_Often_Than_You_Think   
   FOSSILS_&_RUINS Newly_Discovered_Jurassic_Fossils_in_Texas   
   Megalodon_Was_No_Cold-Blooded_Killer   
   'We're_All_Asgardians':_New_Clues_About_the_Origin_of_Complex_Life   
   Story Source: Materials provided by   
   Columbia_University_School_of_Engineering_and_Applied Science. Note:   
   Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Hans-Hermann Wessels, Andrew Stirn, Alejandro Me'ndez-Mancilla,   
      Eric J.   
      
         Kim, Sydney K. Hart, David A. Knowles, Neville   
         E. Sanjana. Prediction of on-target and off-target activity of   
         CRISPR-Cas13d guide RNAs using deep learning. Nature Biotechnology,   
         2023; DOI: 10.1038/s41587-023-01830-8   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/07/230703133058.htm   
      
   --- up 1 year, 18 weeks, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 291/111 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45 5075/35   
   PATH: 317/3 229/426