Remember meForgot password?
    Log in with Twitter

article imageEssential Science: AI aids automatic monitoring of cells

By Tim Sandle     Oct 22, 2018 in Science
Artificial intelligence is reshaping many aspects of business and society. It is also impacting in the sciences. Researchers have demonstrated how AI can aid the automatic monitoring of single molecules in cells.
A new study from Osaka University shows how an artificial intelligence platform can be used to automatically image single molecules within living cells. The new system makes use of machine learning via neural networks. Machine Learning is the form of AI that enables machine to learn without being specifically programmed for each instance. This form of technology allows scientists to focus on samples and to automatically search for cells.
In addition the artificial intelligence can be used to visualize images of fluorescently labeled single molecules and track cell movements. In tests the researchers succeeded in achieving the automated determination of various pharmacological parameters and examine the effects of biomolecules on cell targets.
An illustration of a neurone
An illustration of a neurone
Dr. Vincent Daria
Recent developments in the field of artificial intelligence and machine learning (are transforming many aspects of biology, technology and engineering. With the application of AI in biomedical research, the fuzziness and randomness in handling such type of data has significantly reduced.
For example, deep-learning algorithms have been used to collect raw features from very large data sets, like genomes, and use this data to develop predictive tools based on patterns unraveled from the information buried inside.
Furthermore, the large quantities of data generated by the Human Genome Project has created a challenging pool of data, which artificial intelligence is assisting with. Such tools assist with areas like genetic sequence analysis, protein structure representation and prediction, automated data analysis aids, and simulation of biological systems.
Deep learning architectures like deep neural networks have produced results comparable to and in some cases superior to human experts. Most modern deep learning models are based on an artificial neural network; these are computing systems vaguely inspired by the biological neural networks that constitute animal brains.
With the new research into cells, Osaka University scientists working with the RIKEN institute in Japan developed a system for automatically tracking single molecules within living cells. The output to date demonstrates that machine learning systems can analyse hundreds of thousands of single molecules contained within hundreds of cells in a short period of time. This provides providing reliable data on molecules of interest.
Specifically, the researchers team tested their machine learning system on a receptor protein termed EGFR. This protein moves freely along the plasma membrane of a cell, depending on whether it has undergone modification. The research showed that the system is capable of differentiating between modifying and non-modifying conditions by tracking movement.
According to lead researcher Masashiro Ueda: “We used the results obtained by our system to calculate pharmacological parameters, such as those reflecting the efficacy of drugs and the speed with which molecules diffuse away from their initial location.”
She adds: “The findings matched the values obtained in earlier studies using traditional labor-intensive methods, supporting the value of this system. The automation provided by this approach means that a large number of targets exposed to such molecules can be characterized at low cost, increasing the reliability of the results."
The adoption of the technology will assist new investigations for biological and medical sciences. The research has been published in the journal Nature Communications. The research paper is titled “Automated single-molecule imaging in living cells.”
Essential Science
Playing video games
A man playing video games
Rebecca Pollard (CC BY 2.0)
This article is part of Digital Journal's regular Essential Science columns. Each week Tim Sandle explores a topical and important scientific issue. Last week we reviewed new studies that considered into how playing video games can affect the brain indicated that regular gaming can trigger changes across several brain regions, boosting efficiency but also fueling addiction.
The week before we reviewed how scientists have used 3D printing technology to develop a super-strong form of cement. This is based on the addition of an ingredient that becomes stronger the more pressure that is applied to it.
More about Artificial intelligence, Cells, Biology, molecules
More news from