The pattern reveals it: In the future, the pattern of a drying sample droplet could reveal whether a person has early-stage Alzheimer’s disease. The researchers found that if the sample contains misfolded beta-amyloid proteins, it changes the drying pattern of the solution in a characteristic way. In the first tests, a trained algorithm recognized this “fingerprint” with 99% accuracy – and that without the need for complex processing and analysis methods.
Alzheimer’s disease is the most common neurodegenerative disease in the elderly. However, by the time a diagnosis can be made, brain cell degradation is often well advanced. Indeed, there is currently no objective and easy-to-test biomarker for early detection. The first signs of dementia can be recognized by brain waves, intestinal flora or even blood tests. However, these methods are still in the testing phase and often require complex procedures and equipment.
Drylands as indicators?
But there may also be an easier way: Azam Jeihanipour and Jörg Lahann at the Karlsruhe Institute of Technology (KIT) have developed a method that could easily indicate the presence of pathologically altered beta-amyloid proteins in blood samples or of cerebrospinal fluid. These misfolded beta-amyloids are considered indicators of Alzheimer’s disease. They cannot be broken down properly in the brain, so they form clumps that damage and kill neurons.
The new method is based on so-called “coffee ring” stains – the stains that a dried solution leaves on a surface. The structure of these dry areas is strongly influenced by the chemical properties of the ingredients – and therefore also by the three-dimensional folding and protein structure. “Published speckle patterns of peptide and protein solutions range from homogeneous films to branched and lattice patterns to more complex arrangements,” Jeihanipour and Lahann explain.
Amyloid droplets tested
To find out if healthy and diseased amyloid beta variants can also be distinguished based on this drying pattern, the researchers dissolved various amyloid variants in a bicarbonate buffer solution and applied two microliters of each as drops to a specially coated glass surface. The drops were then dried for 40 minutes under controlled conditions.
The result is dry spots about two millimeters in size, which show a characteristic pattern under the polarizing microscope. The salt crystals from the buffer solution are mainly deposited in the center of the spots, while the peptides and salt crystals form a relatively homogeneous border on the outer edge. In the middle zone, however, branched structures can be seen that extend from the inside out and seemed to be specific for each peptide variant.
“However, recognizing the differences between these models with the naked eye is quite a challenge because they look very similar,” explain the researchers. They therefore used an adaptive algorithm. This deep learning system was first trained with approximately 400 dot pattern records per amyloid variant. Then the algorithm should automatically classify 720 new images of the eight peptide configurations.
99% accuracy
And indeed: the AI system was able to correctly recognize and assign the structure and folding of the beta-amyloid chains only from the drypoints. “The dot patterns were not only distinctive and reproducible, but also resulted in classification with more than 99% predictive accuracy,” Lahann reports. “Since the structures are very similar and difficult to distinguish with the naked eye, it was quite surprising that the neural networks were so efficient.”
According to the researchers, this demonstrates that the different amyloid variants relevant to Alzheimer’s disease can also be identified using this relatively simple and quick method. “The speckle patterns of amyloid-beta peptides represent fingerprints that reflect the structural and spatial identity of the peptide,” says Lahann.
This method therefore has great potential to be used as a rapid and simple test for the early detection of Alzheimer’s disease and Parkinson’s disease. (Advanced Materials, 2022; doi:10.1002/adma.202110404)
Source: Karlsruhe Institute of Technology
#Alzheimers #droplet #pattern #reveals #misfolding