echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Biochemistry News > Biotechnology News > Machine learning methods build a predictive model of the shear regulation of RNA-binding proteins.

    Machine learning methods build a predictive model of the shear regulation of RNA-binding proteins.

    • Last Update: 2020-08-06
    • Source: Internet
    • Author: User
    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
    Genomic studies have shown that more than 90 percent of genes in the human body have selective shears.
    the process is strictly regulated in different tissues and at different physiological stages, and its disorders can lead to the occurrence of a variety of diseases. the inviviable regulation of
    selective shearis is mainly achieved by the recruitment of trans-acting slicing factors (cis-elements) in the precursor mRNA.
    typically, the trans-cutting factor has a modular composition consisting of one or more RNA binding domains as well as different functional modules.
    but currently scientists have studied these functional domains on a few typical splicing factors, such as the SR protein family and the hnRNP protein family, but little is known about the functional modules in the vast range of other RNA binding proteins.
    and a deeper understanding of these functional modules could provide the basis for scientists to further study and even synthesize new RNA splicing factors from scratch. on November 7,
    , Wang Zefeng research team of the Institute of Computational Biology of the Shanghai Institute of Nutrition and Health of the Chinese Academy of Sciences, the Center for Excellence in Molecular Cell Science, and the RNA Systems Biology Group of the Key Laboratory of computing biology of the Chinese Academy of Sciences published an online study entitled Modeling and Predicting the activity of the campaign of trans-acting splicing factory with machine machine.
    in this work, the researchers used machine learning methods for the first time to construct a predictive model of the shear regulation of RNA binding proteins, revealed the effect of the sequence composition preference of RNA binding proteins on its regulatory effect, and provided important guiding significance for studying the slicing activity of RNA binding proteins, as well as feasibility for synthetic shear factors.
    in previous studies, the team found a large number of low-complex regions of the sequence in RNA binding proteins.
    on this basis, the study systematically studies the function of these sequences in the role of low and complex regions in RNA selective shear.
    researchers detected splicing activity at different RNA locations in up to 12 representative sequences of low-complex regions by constructing artificial shear factors, and found that these low-complex regions had positional dependence (context dependent) in RNA selective shears and similar sequence compositions had similar shearing activities.
    the researchers constructed a predictive model of polypeptide splicing activity with machine learning as the core, based on the sequence preference of these function modules and their shearing activity.
    using the machine learning model, they also found previously unreported sequence features with shear activity.
    and based on this sequence of characteristics, they have achieved a very high success rate (10/11) in the world for the first time in the world by synthesizing artificial shear factors with specific activity.
    the study's findings also remove obstacles to the future development of gene therapy based on artificial shear factors.
    the research was carried out in collaboration with the Institute of Computational Biology of the Chinese Academy of Sciences-Map Society, The East China University of Technology, and the National Institute of Environmental Health Sciences (NIEHS).
    the work, under the guidance of researcher Wang Zefeng, was completed by the East China University of Technology in the joint training of PhD student smhttples, Hu Wei and Yang Wei of the Institute of Computational Biology, and received strong support from Yang Wei, a professor at East China University of Technology, and The Associated Press of NIEHS.
    the research was supported by the National Fund Committee, the Shanghai Science and Technology Commission and the National Study Abroad Fund Committee.
    Source: Shanghai Institute of Nutrition and Health.
    This article is an English version of an article which is originally in the Chinese language on echemi.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to service@echemi.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.

    Contact Us

    The source of this page with content of products and services is from Internet, which doesn't represent ECHEMI's opinion. If you have any queries, please write to service@echemi.com. It will be replied within 5 days.

    Moreover, if you find any instances of plagiarism from the page, please send email to service@echemi.com with relevant evidence.