Inside every cell of the human body is a constellation of proteins, millions of them. They are all jostling about, they are quickly assembled, folded, packaged, shipped, cut and recycled into a hive of activities that work in a heat to keep us alive and ticking.
But without a full inventory of the protein universe in our cells, scientists are hard-pressed to evaluate on a molecular level what goes wrong with our bodies leading to disease.
Now, researchers have developed a new technique that uses artificial intelligence to assimilate data from single-cell microscopy images and biochemical analyzes, to create an ‘unified map’ of subcellular components – half of which, it turns out, we have never seen before. .
“Scientists have long realized that there is more that we do not know as we know it, but now we finally have a way to look deeper,” says computer scientist and network biologist Trey Ideker of the University of California (UK) San Diego.
Microscopes, powerful as they are, allow scientists to peer inside single cells, down to the level of organs such as mitochondria, the power packs of cells, and ribosomes, the protein factories. We can even add fluorescent dyes to easily combine and trace proteins.
Biochemistry techniques can go deeper still, hoping for single proteins by using, for example, targeted antibodies that bind the protein, pull it out of the cell, and see what else is attached to it.
Integrating these two approaches is a challenge for cell biologists.
“How do you bridge that gap from nanometer to micro-scale? This has long been a big hurdle in the biological sciences,” explains Ideker.
“Shows that you can do this with artificial intelligence – looking at data from multiple sources and requesting the system to assemble it into a model of a cell.”
The result: Ideker and colleagues have flipped textbook maps of globular cells that give us a birds-eye view of candy-colored organs in an intricate web of protein-protein interactions, organized by the tension distances between them.
Classic view of a eukaryote cross section. (Mariana Ruiz / LadyofHats / Wikimedia)
Fusing image data from a library called the Human Protein Atlas and existing maps of protein interactions, the machine learning algorithm was tasked with computing the distances between protein pairs.
The aim was to identify communities of proteins, called assemblies, that co-exist in cells of different scales, from very small (less than 50 nm) to very ‘large’ (more than 1 μm).
One shy of 70 protein communities were classified by the algorithm, which was trained with a reference library of proteins with known or estimated diameters, and validated with further experiments.
Approximately half of the identified protein components are seemingly unknown to science, never documented in the published literature, the researchers suggest.
In the mix was one group of proteins forming an unfamiliar structure, which the researchers found was likely responsible for splicing and dicing newly made transcripts of the genetic code that were used to make proteins.
Other protein mapped included transmembrane transport systems that pump supplies in and out of cells, families of proteins that help organize bulky chromosomes, and protein complexes whose job it is to make, well, more proteins.
A hefty effort, it is not the first time that scientists have tried to map the inner workings of human cells.
Other efforts to create reference maps of protein interactions have yielded similarly mind-boggling numbers and attempted to measure protein levels across tissues of the human body.
Researchers have also developed techniques for visualizing and tracking the interaction and movement of proteins in cells.
The pilot study goes a step further by applying machine learning to cellular microscopy images that find proteins relative to large cellular landmarks such as the nucleus, and data from protein interaction studies that identify the nearest nano-scale neighbors of a protein.
“The combination of these technologies is unique and powerful because it is the first time measurements in vast different scales have been brought together,” says bioinformatist Yu Qin, also from UK San Diego.
In doing so, the multi-scale integrated cell technique or music “increases the resolution of imaging while giving protein interactions a spatial dimension, paving the way for incorporating diverse types of data into proteome-wide cell maps,” Qin, Ideker and colleagues write.
To be clear, the research is very preliminary: the team focused on validating their method and only looked at the available data of 661 proteins in one cell type, a kidney cell line that scientists have cultured in the laboratory for five decades.
The researchers plan to apply their new-fangled technique to other cell types, says Ideker.
But in the meantime, we will have to humbly accept that we are only interlopers in our own cells, which can understand a small fraction of the total proteome.
“Eventually we may be able to better understand the molecular basis of many diseases by comparing what is different between healthy and diseased cells,” says Ideker.
The study was published in Nature.
Source link
