AI boosts biosensor for Parkinson’s disease
Researchers at EPFL in Switzerland have developed an AI-enhanced biosensor that can detect the proteins linked to Parkinson’s and Alzheimer’s disease.
Combining protein biochemistry, optofluidics, nanotechnology, and artificial intelligence (AI) into a single system allows the ImmunoSEIRA sensor to test for degenerative diseases such as Parkinson’s.
This detects the protein markers for neurodegenerative diseases (NDDs) such as Parkinson’s disease (PD) and Alzheimer’s disease (AD). Neural networks quantify disease stages and progression, promising not only for early detection and monitoring of NDDs, but also for assessing treatment options at various stages of the disease’s progression.
- Melexis looks to connected smart biosensors
- World’s smallest Deep Brain Stimulation device in clinical trials
Misfolded proteins circulate in the brain and biofluids and also accumulate as deposits in the brains of deceased NDD sufferers. But the development of tools to detect these biomarkers has remained elusive until now. The hurdles to accurate detection are multiple, including limits of current technology to accurately separate and quantify different protein aggregates in sufferers of Parkinson’s disease.
Surface-enhanced infrared absorption (SEIRA) spectroscopy is the key technology for the sensor developed at Professor Hatice Altug’s Bionanophotonic Systems Laboratory (BIOS) and Professor Hilal Lashuel’s Laboratory of Molecular Neurobiology and Neuroproteomics (LMNN).
The ImmunoSEIRA sensor developed at EPFL in Switzerland
This uses gold nanorod arrays with antibodies for specific protein detection. It enables real-time specific capture and structural analysis of target biomarkers from extremely small samples. Neural networks are then employed to identify the presence of specific misfolded protein forms, the oligomeric and fibrillary aggregates, achieving an unprecedented level of detection accuracy as the Parkinson’s and AD progress.
“Unlike current biochemical approaches which rely on measuring the levels of these molecules, our approach is focused on detecting their abnormal structures. This technology also allows us to differentiate the levels of the two main abnormal forms implicated in the development and progression of NDDs, oligomers and fibrils,” says Lashuel.
“In our paper, we present a technological solution that integrates nanoplasmonics, cleanroom nanofabrication, microfluidics, immunoassay, AI, and advanced biochemical methods,” says PhD student and main author of the paper Deepthy Kavungal. “Our ImmunoSEIRA sensor exhibits structural sensitivity and the capability to monitor a panel of complementary biomarkers with high specificity from small sample volumes in complex biomatrices.”
The EPFL research team went a step further to show that the ImmunoSEIRA sensor can be used in real clinical settings with biofluids. They were able to accurately identify the specific signature of abnormal fibrils, a key indicator of neurodegenerative diseases, even in complex fluids like human cerebrospinal fluid (CSF).
The next step is 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.
DOI: 10.1126/sciadv.adg9644; www.epfl.ch
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
