AI reveals previously unknown neighborhoods

AI-based technology is revealing previously unknown cellular components that may provide new clues to human evolution and disease.

Most human diseases can be traced back to malfunctioning parts of the cell — a tumor is able to grow because a gene has not been accurately translated into a specific protein or a metabolic disease arises because mitochondria do not activate properly, for example. But to understand which parts of a cell can go wrong in disease, scientists first need a complete list of the parts.

By combining microscopy, biochemistry and artificial intelligence techniques, researchers at the University of California San Diego School of Medicine and collaborators have taken what they believe may be a major leap forward in understanding human cells.

The technology, known as Multi-Scale Integrated Cell (MuSIC), was described on November 24, 2021, in temper nature.

“If you imagine a cell, you probably picture the color diagram in a cell biology book, with mitochondria, endoplasmic reticulum and nucleus. But is that the whole story? “Absolutely not,” said Trey Edecker, PhD, a professor at the University of California, San Diego School of Medicine and the Morris Cancer Center. “Scientists have long recognized that there is more we don’t know than we know, but now we have a way to look deeper.”

Ideker led the study with Emma Lundberg, Ph.D., from KTH Royal Institute of Technology in Stockholm, Sweden and Stanford University.

Classic Cell مقابل MuSIC

Left: Diagrams of conventional textbooks cells indicate that all parts are visible and clearly marked. (Credit: OpenStax/Wikimedia). Right: A new cellular map generated by MuSIC technology reveals several new components. Gold nodes represent known cellular components, while purple nodes represent new ones. Nodule size reflects the number of distinct proteins in this component. Credit: University of California, San Diego Health Sciences

In the pilot study, MuSIC revealed nearly 70 components found in the human kidney cell line, half of which had never been seen before. In one example, researchers discovered a group of proteins that form an unfamiliar structure. Working with UCSD colleague Jin Yu, Ph.D., they eventually determined that the structure is a new complex of proteins that bind

Ribonucleic acid (RNA) is a polymeric molecule similar to DNA that is essential in various biological roles in coding, decoding, regulation and expression of genes. Both are nucleic acids, but unlike DNA, RNA is single-stranded. An RNA strand has a backbone made of alternating sugar (ribose) and phosphate groups. Attached to each sugar is one of four bases—adenine (A), uracil (U), cytosine (C), or guanine (G). Different types of RNA exist in the cell: messenger RNA (mRNA), ribosomal RNA (rRNA), and transfer RNA (tRNA).

“> RNA. The complex is likely to be involved in splicing, an important cellular event that enables the translation of genes into proteins, and helps determine which genes are activated and at what time.

The insides of cells — and many of the proteins that are there — are usually studied using one of two methods: microscopy or biophysical correlation. By imaging, researchers add fluorescent tags of different colors to proteins of interest and track their movements and associations across the microscope’s field of view. To look at biophysical associations, researchers might use an antibody specific to a protein to pull it out of the cell and see what else it binds to.

The team has been interested in mapping the inner workings of cells for many years. What differs from MuSIC is the use of deep learning to map a cell directly from cell microscopy images.

“The combination of these techniques is unique and powerful because it is the first time that measurements at completely different scales have been combined,” said study first author Yue Qin, a graduate student in bioinformatics and systems biology in Ideker’s lab.

Microscopes allow scientists to see at the level of one micron, the size of some organelles, such as mitochondria. Smaller elements, such as individual proteins and protein complexes, cannot be seen through a microscope. Biochemical techniques, which start with a single protein, allow scientists to reach the nanometer scale. (A nanometer is one billionth of a meter, or 1,000 microns.)

But how do you bridge this gap from the nanometer scale to the micron scale? “It’s always been a huge hurdle in the biological sciences,” said Edeker, who is also the founder of the University of California Cancer Cell Map Initiative and the San Diego Center for Computational Biology and Bioinformatics. “It turns out that you can do this with AI — looking at data from multiple sources and asking the system to aggregate it into a cell model.”

The team trained the MuSIC AI platform to look at all the data and create a cell model. The system has not yet mapped cell contents to specific locations, such as a textbook outline, in part because their locations are not necessarily fixed. Instead, the locations of the components are fluid and change by cell type and situation.

Edecker noted that this was a pilot study of the MuSIC test. They only looked at 661 proteins and one cell type.

“The obvious next step is to inflate the entire human cell, and then move on to different types of cells, people, and species,” Edecker said. Ultimately, we may be able to better understand the molecular basis of many diseases by comparing what is different between healthy and diseased cells.

Reference: “Multiscale map of cell structure incorporating images of proteins and interactions” by Yu Chen, Edward L. Hotlin, Casper F. Winsens, Maya L. Guztaila, Ludivine Wachul, Marcus R. Kelly, Stephen M. Blue, Van Zing, Michael Chen, Leah F. Shaffer, Catherine Lecon, Anna Backstrom, Laura Pontano Weitz, John J. Lee, Wei Ouyang, Sophie N. Liu, Tian Zhang, Erica Silva, Jisoo Park, Adriana Petty, Jason F. Kreisberg, Stephen B. Gigi, Jianzo Ma, J. Wade Harper , Jane W.U., Dennis LJ Lafontaine, Emma Lundberg and Trey Edecker, November 24, 2021, temper nature.
DOI: 10.1038 / s41586-021-04115-9

Co-authors are: Maya L. Guztaila, Marcus R. Kelly, Stephen M. Adriana Pitea, Jason F. Kreisberg, UC San Diego; Edward L. Hotlin, Laura Pontano Weitz, Tian Zhang, Stephen B. Gigi, J.; Wade Harper, Harvard Medical School; Casper F. Winsnes, Anna Bäckström, Wei Ouyang, KTH Royal Institute of Technology; Ludivine Wacheul, Denis LJ Lafontaine, Université Libre de Bruxelles; and Jianzhou Ma, Peking University.

Funding for this research came, in part, from the National Institutes of Health (Grants U54CA209891, U01MH115747, F99CA264422, P41GM103504, R01HG009979, U24HG006673, U41HG009889, R01HL137223, R01HG004659 Erutling, R50CA248527, Grant 2017 Swedish Wall0204 Foundation Research Council, 20160204). ), the Free University of Belgium in Brussels, the Joint European Program for Rare Diseases, the Région Wallonne, the Internationale Brachet Stiftung and the Epitran COST Procedure (grant CA16120).

Disclosures: Trey Ideker is Co-Founder, on the Scientific Advisory Board and has a stake in Data4Cure, Inc. Jin Yu is co-founder and board member of the Scientific Advisory Board, stockholder, and paid advisor to Locanabio and Eclipse BioInnovations. Yu is also a visiting professor at the National University of Singapore. The terms of these arrangements have been reviewed and approved by the University of California San Diego in accordance with its conflict of interest policies. Emma Lundberg is a member of the Scientific Advisory Boards in Mapping Biology, Nautilus Biotechnology and Interline Therapeutics, and has equal interests in Mapping Biology. J. Wade Harper is a co-founder of the Scientific Advisory Board and has a stake in Caraway Therapeutics. Harper is also the founding scientific advisor for Interdisciplinary Therapies.

The post AI reveals previously unknown neighborhoods appeared first on Archyde.

Source link

Leave a Comment