Member Login

Biologists Employ Machine Learning and Mass Spectrometry Imaging to Map Proteins

Scientists have used machine learning and mass spectrometry imaging to produce a co-regulation map of the human proteome, the entire complement of human proteins. Living cells rely on proteins to carry out nearly every task needed for life, including managing the composition, purpose, and regulation of organs and tissue. Having a complete picture of these proteins, and what they can do, could prove to be especially valuable in biological and medical fields. ? Mass Spectrometry Imaging Made It All Possible To identify how proteins in the body relate to one another, researchers had to track the changes of 10,323 human proteins as they responded to 294 biological perturbations. These observations were made possible by mass spectrometry imaging. Scientists involved in the study used a machine-learning algorithm to analyze the data and identify the functional associations between proteins. ? Mass spectrometry imaging allows for the visualization of the spatial distribution of molecules. It can image thousands of molecules without labeling. Requiring only minimal sample preparation, the mass spectrometer then ionizes molecules on the surface of the sample and collects a mass spectrum at each pixel on the section. Sophisticated software is then used to process and visualize the captured data. ? The study also repurposed thousands of mass spectrometry experiments published by other laboratories. A machine learning algorithm mined the data and was able to assign biological functions to proteins that were formerly uncharacterized. ? Scientists Design the Proteome Map for Discovery The new proteome co-regulation map is interactive. Researchers formatted the map in such a way that users can search for a protein. Its position is then displayed on the map along with its partners. Users can zoom in and out and navigate throughout the map. Its creators planned for it to be used to validate existing hypotheses and create new ones. ? While exploring the new co-regulation map, a group of researchers found some unexpected partners, including peroxisomal membrane protein PEX11? with mitochondrial respiration factors. This finding, in turn, led to the discovery of an interaction between mitochondria and peroxisomes. The two appear to function in metabolic cooperation, crosstalk, and may also help transfer metabolites during mitochondrial energy production. ? The team says a key takeaway from this study is that one should never throw away old data. It can often be repurposed and recycled in the quest for knowledge. Knowing the relationships of the entire complement of human proteins will help researchers to assign functions to proteins that have yet to be characterized. Both mass spectrometry imaging and machine learning made this study possible. ? Discover how mass spectrometry combined with artificial intelligence (AI) is expanding capabilities for the research and analysis of proteins in the field of proteomics.Scientists have used machine learning and mass spectrometry imaging to produce a co-regulation map of the human proteome, the entire complement of human proteins. Living cells rely on proteins to carry out nearly every task needed for life, including managing the composition, purpose, and regulation of organs and tissue. Having a complete picture of these proteins, and what they can do, could prove to be especially valuable in biological and medical fields.

Mass Spectrometry Imaging Made It All Possible

To identify how proteins in the body relate to one another, researchers had to track the changes of 10,323 human proteins as they responded to 294 biological perturbations. These observations were made possible by mass spectrometry imaging. Scientists involved in the study used a machine-learning algorithm to analyze the data and identify the functional associations between proteins.

Mass spectrometry imaging allows for the visualization of the spatial distribution of molecules. It can image thousands of molecules without labeling. Requiring only minimal sample preparation, the mass spectrometer then ionizes molecules on the surface of the sample and collects a mass spectrum at each pixel on the section. Sophisticated software is then used to process and visualize the captured data.

The study also repurposed thousands of mass spectrometry experiments published by other laboratories. A machine learning algorithm mined the data and was able to assign biological functions to proteins that were formerly uncharacterized.

Scientists Design the Proteome Map for Discovery

The new proteome co-regulation map is interactive. Researchers formatted the map in such a way that users can search for a single protein. Its position is then displayed on the map along with its partners. Users can zoom in and out and navigate throughout the map. Its creators planned for it to be used to validate existing hypotheses and create new ones.

While exploring the new co-regulation map, a group of researchers found some unexpected partners, including peroxisomal membrane protein PEX11β with mitochondrial respiration factors. This finding, in turn, led to the discovery of an interaction between mitochondria and peroxisomes. The two appear to function in metabolic cooperation, crosstalk, and may also help transfer metabolites during mitochondrial energy production.

The team says a key takeaway from this study is that one should never throw away old data. It can often be repurposed and recycled in the quest for knowledge. Knowing the relationships of the entire complement of human proteins will help researchers to assign functions to proteins that have yet to be characterized. Both mass spectrometry imaging and machine learning made this study possible.

Discover how mass spectrometry combined with artificial intelligence (AI) is expanding capabilities for the research and analysis of proteins in the field of proteomics.

Search AIA:


Browse by Products:


Browse by Company Type: