Researchers have developed BigRNA, a groundbreaking deep learning model capable of predicting RNA behavior, including tissue-specific expression and splicing, directly from genomic DNA sequences. The model excels in identifying pathogenic variants and could be a game-changer in the development of personalized RNA-based therapies for treating genetic diseases.
By Hugo Francisco de SouzaSep 28 2023Reviewed by Susha Cheriyedath, M.Sc. In a recent preprint* uploaded to the bioRxiv server, researchers developed and trained a foundational model to predict tissue-specific RNA expression, splicing, RNA binding protein specificity, and microRNA sites from genomic DNA sequences. Their model, termed "BigRNA," could identify and predict pathogenic non-coding DNA variants across a broad spectrum of mechanistic cases.
RNA modeling and the advantages of deep learning Research aimed at designing machine learning algorithms capable of predicting RNA outcomes from DNA sequences is longstanding and plentiful yet has to be proven successful. Recent advancements in deep learning have allowed for significant strides in current research in the field of RNA predictions and present computational approaches that would have been impossible just a decade ago.
About the study The present study used extensive WGS and RNA-seq data to design and train a deep learning model named "BigRNA" aimed at predicting RNA expression and the mechanistic interactions that result in observed RNA expression levels. Researchers began by compiling GTEx consortium data comprising both WGS and RNA-seq information from 70 individuals with diverse hereditary.
Related StoriesBigRNA was then trained on the 70 DNA-RNA pairs separately, allowing for independent learning from each of the sampled individuals after accounting for phenotypic differences arising from haplotypes. Researchers added individual-agnostic per-tissue outputs to BigRNA's training regiments, encouraging the model to begin predicting the genotype resulting in the observed RNA-seq data.
"A key challenge in human genetics is to predict the impact of sequence variants that may be found within the human population. Many deep learning models that do well on unseen genes using certain metrics, such as AlphaFold, struggle to predict variant effects. While some accurate methods exist for predicting the pathogenic impact of rare missense variants, non-coding variants, such as those located within the 3' and 5' untranslated regions of genes, remain difficult to interpret.
"The ability of BigRNA to understand regulatory mechanisms affecting splicing and gene expression may allow it to design therapeutic interventions that rescue pathogenic variant effects."
Österreich Neuesten Nachrichten, Österreich Schlagzeilen
Similar News:Sie können auch ähnliche Nachrichten wie diese lesen, die wir aus anderen Nachrichtenquellen gesammelt haben.
Researchers propose novel model for surgical action triplets recognitionA research group led by Prof. Jia Fucang from the Shenzhen Institute of Advanced Technology (SIAT) of the Chinese Academy of Sciences has proposed a multi-task fine-grained spatiotemporal model that can effectively identify action triplets in laparoscopic gallbladder removal surgery videos.
Weiterlesen »
Researchers discover disease-causing stem cells in lungs of cystic fibrosis patientsTwo nationally recognized experts in cloning and stem cell science from the University of Houston, Wa Xian and Frank McKeon, are reporting that five lung stem cell variants dominate the lungs of patients with advanced cystic fibrosis (CF), and that these variants drive key aspects of CF pathology including inflammation, fibrosis and mucin secretion.
Weiterlesen »
Researchers discover new link to pancreatic hormone in type 1 diabetesResearchers have found evidence of inherent changes to the pancreas in people with type 1 diabetes. Published recently in Scientific Reports, these new findings help explain how low blood glucose occurs in type 1 diabetes.
Weiterlesen »
Researchers discover that heart cells in developing zebrafish start beating suddenly and all at onceBecoming a full-fledged organism out of a handful of cells, complete with functioning tissues and organs, is a messy yet highly synchronized process that requires cells to organize themselves in a precise manner and begin working together.
Weiterlesen »
Nobody knows how consciousness works, but top researchers are fighting over which theories are really scienceScience is hard. The science of consciousness is particularly hard, beset with philosophical difficulties and a scarcity of experimental data.
Weiterlesen »
Researchers develop new way to boost immune cells' ability to fight TBTuberculosis is old-;ancient even. The infectious bacterial disease that plagued Old Testament Israelites and took down pharaohs was eventually stunted by vaccinations, antibiotics, and public health measures like isolation, but it hasn't been cured yet.
Weiterlesen »