echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Active Ingredient News > Study of Nervous System > elife: Cytological research helps reveal the health and abnormal behavior of individual cells

    elife: Cytological research helps reveal the health and abnormal behavior of individual cells

    • Last Update: 2021-04-28
    • Source: Internet
    • Author: User
    Tags

    author

    draw

    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
    March 19, 2021 //---When studying the causes and potential treatments of neurodegenerative diseases such as Alzheimer’s disease or Parkinson’s disease, neuroscientists often strive to accurately identify the need to understand the brain Cells needed for activity that can cause behavioral changes, such as decreased memory or decreased balance and tremor.

    A multidisciplinary team of neuroscience researchers at the Georgia Institute of Technology borrowed existing tools such as graphical models to discover a better way to identify cells and understand the mechanisms of diseases, which may lead to better understanding and diagnosis.
    And treatment.
    (Image source: Www.
    pixabay.
    com)

    Their findings were reported in eLife magazine on February 24.
    The research was supported by the National Institutes of Health and the National Science Foundation.
    Traditionally, scientists often establish a coordinate system by comparing individual cell images with the entire brain atlas to map the location of each cell, but the so-called idea in the literature that "all brains look the same is absolutely incorrect.
    of".
    In other words, this method mainly faces two challenges: first, the number of cells is huge; second, the cell characteristics vary from individual to individual.
    Article author Lu said: "This is the bottleneck of current research.
    Although we can record all the desired neuron activity, if we don’t know which cell is doing, it’s difficult to compare brains or conditions and draw conclusions.
    Meaningful conclusion.
    ” According to Shivesh Chaudhary, a graduate researcher, the data also contains noise, which makes it difficult to establish a correspondence between two different areas of the brain.
    He said: "There may be some distortion in the data, or some parts of the shape may be missing.
    "
    In order to overcome these challenges, researchers at Georgia Institute of Technology used graphical models and metric geometry methods in machine learning for mathematical shape matching, and established a computational method to identify cells in their model biological nematodes.
    The team uses frameworks in other fields such as natural language processing to build its own modeling software.
    In natural language processing, the computer can determine the meaning of a sentence by capturing the correlation between words in the sentence.
    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321




    (Image source: Www.
    pixabay.
    com)

    Their findings were reported in eLife magazine on February 24.
    The research was supported by the National Institutes of Health and the National Science Foundation.
    Traditionally, scientists often establish a coordinate system by comparing individual cell images with the entire brain atlas to map the location of each cell, but the so-called idea in the literature that "all brains look the same is absolutely incorrect.
    of".
    In other words, this method mainly faces two challenges: first, the number of cells is huge; second, the cell characteristics vary from individual to individual.
    Article author Lu said: "This is the bottleneck of current research.
    Although we can record all the desired neuron activity, if we don’t know which cell is doing, it’s difficult to compare brains or conditions and draw conclusions.
    Meaningful conclusion.
    ” According to Shivesh Chaudhary, a graduate researcher, the data also contains noise, which makes it difficult to establish a correspondence between two different areas of the brain.
    He said: "There may be some distortion in the data, or some parts of the shape may be missing.
    "
    In order to overcome these challenges, researchers at Georgia Institute of Technology used graphical models and metric geometry methods in machine learning for mathematical shape matching, and established a computational method to identify cells in their model biological nematodes.
    The team uses frameworks in other fields such as natural language processing to build its own modeling software.
    In natural language processing, the computer can determine the meaning of a sentence by capturing the correlation between words in the sentence.
    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321


    Traditionally, scientists often establish a coordinate system by comparing individual cell images with the entire brain atlas to map the location of each cell, but the so-called idea in the literature that "all brains look the same is absolutely incorrect.
    of".
    In other words, this method mainly faces two challenges: first, the number of cells is huge; second, the cell characteristics vary from individual to individual.
    Article author Lu said: "This is the bottleneck of current research.
    Although we can record all the desired neuron activity, if we don’t know which cell is doing, it’s difficult to compare brains or conditions and draw conclusions.
    Meaningful conclusion.
    ” According to Shivesh Chaudhary, a graduate researcher, the data also contains noise, which makes it difficult to establish a correspondence between two different areas of the brain.
    He said: "There may be some distortion in the data, or some parts of the shape may be missing.
    "
    In order to overcome these challenges, researchers at Georgia Institute of Technology used graphical models and metric geometry methods in machine learning for mathematical shape matching, and established a computational method to identify cells in their model biological nematodes.
    The team uses frameworks in other fields such as natural language processing to build its own modeling software.
    In natural language processing, the computer can determine the meaning of a sentence by capturing the correlation between words in the sentence.
    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321


    Article author Lu said: "This is the bottleneck of current research.
    Although we can record all the desired neuron activity, if we don’t know which cell is doing, it’s difficult to compare brains or conditions and draw conclusions.
    Meaningful conclusion.
    ” According to Shivesh Chaudhary, a graduate researcher, the data also contains noise, which makes it difficult to establish a correspondence between two different areas of the brain.
    He said: "There may be some distortion in the data, or some parts of the shape may be missing.
    "
    In order to overcome these challenges, researchers at Georgia Institute of Technology used graphical models and metric geometry methods in machine learning for mathematical shape matching, and established a computational method to identify cells in their model biological nematodes.
    The team uses frameworks in other fields such as natural language processing to build its own modeling software.
    In natural language processing, the computer can determine the meaning of a sentence by capturing the correlation between words in the sentence.
    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321


    In order to overcome these challenges, researchers at Georgia Institute of Technology used graphical models and metric geometry methods in machine learning for mathematical shape matching, and established a computational method to identify cells in their model biological nematodes.
    The team uses frameworks in other fields such as natural language processing to build its own modeling software.
    In natural language processing, the computer can determine the meaning of a sentence by capturing the correlation between words in the sentence.
    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321


    The team uses frameworks in other fields such as natural language processing to build its own modeling software.
    In natural language processing, the computer can determine the meaning of a sentence by capturing the correlation between words in the sentence.
    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321

    Lu said: "Using the relationship between cells is actually more useful to define the identity of a cell.
    If you define one, it will have the meaning of the identity of other cells.
    "
    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321

    The research team said that this method is much more accurate than current identification methods.
    Although the algorithm is not perfect, its performance is much better when the data is not perfect, and it can reduce noise or errors.
    In addition, the algorithm has great significance for many developmental diseases.
    Once scientists understand the mechanism of the disease, they can find interventions.
    (Bioon.
    com)
    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321

    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321

    Information source: com/news/2021-03-cells-healthy-diseased-behavior.
    html">Identifying cells to better understand healthy and diseased behavior

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321

    Original source: Shivesh Chaudhary et al, org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife (2021).
    DOI: 10.
    7554/eLife.
    60321
    Original source: org/articles/60321">Graphical-model framework for automated annotation of cell identities in dense cellular images, eLife
    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.