Aided by AI, sensor shows ability to quantify alpha-synuclein in its various forms
A sensor chip that can distinguish harmless single units of proteins tied to diseases like Parkinson’s from those whose toxic aggregates are thought to drive disease — including alpha-synuclein — could help in diagnosing conditions before symptoms are evident, when treatments can work best, a study suggests.
In addition to identifying a disease biomarker, combining the sensor with artificial intelligence (AI) allows for more accurate assessments of the amount of these proteins and their distinct forms in a sample, even when mixed together. This could help in determining progression in neurodegenerative diseases like Parkinson’s, or how well a treatment is working.
“Although most [neurodegenerative diseases] start 10 to 15 years before the manifestation of the clinical diagnostic symptoms,” and are marked by the “common mechanism” of protein misfolding, the researchers wrote, “we still lack a reliable diagnostic method for early detection or monitoring of disease progression, thus precluding any effort for early intervention.”
The study, “Artificial intelligence–coupled plasmonic infrared sensor for detection of structural protein biomarkers in neurodegenerative diseases,” was published in Science Advances by researchers at École polytechnique fédérale de Lausanne (EPFL), in Switzerland.
Diagnosing Parkinson’s early can be challenging due to the limited availability of tools capable of detecting it before disease symptoms are manifest. Like most neurodegenerative diseases, however, it’s marked by proteins that become misshapen (misfolded) and clump together, forming aggregates that damage nerve cells and contribute to how the disease progresses over time.
In Parkinson’s, monomers or single units of the alpha-synuclein protein begin to clump into toxic clusters of a few units, known as oligomers. These clusters then can spread and grow to form fibrils, or long and thread-like fibers.
Tau and amyloid-beta proteins undergo similar changes in people with Alzheimer’s, another neurodegenerative disease.
“The disease process is tightly associated with changes in protein structure,” Hilal Lashuel, PhD, who heads the EPFL’s Laboratory of Molecular Neurobiology and Neuroproteomics, said in a news release.
While ways exist to measure these protein biomarkers, they do not distinguish monomers from toxic oligomers or fibrils. For this reason, the researchers developed a sensor chip able to identify a protein’s different forms, or structures, by looking at the way they absorb light.
Current ways of measuring protein biomarkers, the researchers wrote, “do not allow the assessment of the actual amounts of aggregates or the ratio of oligomers to fibrils in body fluids.” As such, “they lack the capability to enable prodromal [early] diagnosis, monitor disease progression and differentiate” among neurodegenerative diseases with “overlapping pathologies.”
The sensor chip is made up of a thin sheet of material that’s sensitive to infrared light, making it easier to detect. It’s coated with tiny, rod-shaped particles of gold attached to antibodies that only bind to a specific protein, such as alpha-synuclein.
When a sample containing alpha-synuclein is run through the sensor chip, the protein will bind to the antibodies, changing how much of infrared light is absorbed. This change can be measured and, because different forms absorb infrared light differently, be used to determine the presence and amount of alpha-synuclein in each of its forms.
The technology combines an immunoassay (a test that uses the binding of antibodies to identify a specific protein or other type of molecule) with surface-enhanced infrared absorption (SEIRA) spectroscopy, and was dubbed immunoSEIRA.
Alpha and beta motifs are patterns found in proteins that help them fold into specific forms. The alpha motif consists of helices, while the beta motif contains strands. The way they absorb infrared light helps in mapping a signature to each alpha-synuclein form.
Indeed, when monomers, oligomers, and fibrils were introduced one by one to the sensor chip, three different wave number signatures came out. Wave number is the number of light waves in a unit of distance, or a measure of how close these waves are to each other.
To find out if the sensor chip could be used to determine the amount of oligomers and fibrils in a sample, the researchers mixed them in different ratios. These mixes were used to train an AI neural network, a computer system that can make sense of data and learn patterns.
The AI-aided sensor chip was “robust and structurally sensitive” and predicted the amount of oligomers and fibrils “with excellent accuracy,” the researcher wrote. This “could pave the way to detect and quantify [alpha-synuclein] oligomers and fibrils and correlate their ratios during disease progression.”
The technology also proved useful in detecting alpha-synuclein at the same time as tau, a protein linked to nerve cell damage in Parkinson’s, when present among a complex mixture of proteins in a sample of cerebrospinal fluid, which surrounds the brain and spinal cord.
Moreover, it’s designed to work with microfluidics, meaning it can handle very small amounts of body fluids.
Researchers now plan “to continue to expand its capabilities and evaluate its diagnostic potential in Parkinson’s disease and the growing number of diseases caused by protein misfolding and aggregation,” said Hatice Altug, PhD, who heads EPFL’s Bionanophotonic Systems Laboratory.
Get regular updates to your inbox.
3 W Garden St
Pensacola, FL 32502
Email: [email protected]
This site is strictly a news and information website about the disease. It does not provide medical advice, diagnosis or treatment. This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition. Never disregard professional medical advice or delay in seeking it because of something you have read on this website.