AI improves drug screening for Alzheimer’s

GDJ / Pixabay

Source: GDJ / Pixabay

in a new way studyresearchers at the University of California, San Francisco (UCSF) apply Artificial intelligence (AI) Machine learning to find valuable hidden data in archival disease databases that may help accelerate biotechnology research and drug discovery for Alzheimer’s (AD) and other conditions.

“Despite extensive drug discovery efforts, there are no effective treatments that prevent or even slow the progression of Alzheimer’s disease,” the researchers wrote. Among the many therapeutic targets under investigation, pathogenic dysfunction and accumulation of tau protein in neurofibrillary tangles (NFTs) has emerged as a target mechanism.

Alzheimer’s disease accounts for 60-80 percent of mental illness It is the most common cause of dementia, according to the Alzheimer’s Association. Dementia is a decrease in mental ability that interferes with activities of daily living with symptoms that may affect a person’s ability to remember, think and reason. It is estimated that 139 million people worldwide will live with dementia by 2050 and more than 55 million people globally will have dementia in 2020 according to Alzheimer’s Disease International. according to Women’s Alzheimer’s Movement (WAM), An organization founded by Maria Shriver, an estimated 6 million Americans have Alzheimer’s disease, two-thirds of whom are women, and scientists don’t know why.

This study applied machine learning to a high-content archival database to screen content containing information on the phenotypic effects of small molecules for the treatment of Alzheimer’s disease.

The researchers sought to improve the extraction of biological insights from imaging data collected from the High Content Screening (HCS), a method vital to the drug discovery process.

Their hypothesis was that AI machine learning could find actionable data within HCS that could provide valuable insights into an organism’s biochemical properties which in turn could accelerate biotechnology research and drug discovery.

In microbiology, high content screening (HCS), also known as an automated microscope-based screening, is used for research and toxicity screening for drug discovery. It was developed in the mid-1990s and is often used in systems biology research and to discover whether candidate drugs alter the course of disease by enabling scientists to measure and understand the functions of proteins, genesand RNA and other components of living cells.

High content examination is mostly a technique of fluorescence microscopy of cells and organisms in which light-emitting fluorescent materials are examined under a microscope. The live cell of the sample is usually stained with a fluorescence dye that glows with exposure to short wavelength light such as blue or ultraviolet (UV) light and can be seen through filters that remove unwanted wavelengths of light.

The current standard methodology to obtain more information from higher content screening data is to introduce additional biological markers. The drawback is that it can be expensive, time consuming, or too tedious to add more biomarkers for tracking. Furthermore, this approach will not work for large archival datasets in which search has already ended.

The researcher reported that by using the machine learning method of artificial intelligence, they were able to identify novel compounds that effectively prevented the aggregation of tau that had not been found previously using current screening methods without synthesis. intelligence.

“We overcome these computational limitations of markers by directly learning the phenotypic relationships between an informative but cumbersome marker and other similar, easily accessible markers,” the researchers wrote. “These hidden relationships were then shown in de novo images displaying the desired fluorescent signal of the stressed marker.”

In addition, the machine learning algorithm can be used for other diseases, not just Alzheimer’s disease and can be used to search for information hidden in other archival micrograph datasets. The scientists evaluated the generalizability of the AI ​​algorithm to a dataset based on cancer, a different biological environment. Specifically, they applied machine learning to a functional genomics screen in a common type of bone cancer, osteosarcoma, streak.

By combining machine learning with artificial intelligence, fluorescence microscopy, and life science databases, disease researchers now have a powerful tool to help accelerate drug discovery and the development of new treatments in the future.

Copyright © 2022 Cami Rosso