AI tool finds hundreds of genes related to human motor neuron disease
Breakthrough could lead to development of drugs to target illness
A machine-learning algorithm has helped scientists find 690 human genes associated with a higher risk of developing motor neuron disease, according to research published in Cell this week.
Neuronal cells in the central nervous system and brain break down and die in people with motor neuron disease, like amyotrophic lateral sclerosis (ALS) more commonly known as Lou Gehrig's disease, named after the baseball player who developed it. They lose control over their bodies, and as the disease progresses patients become completely paralyzed. There is currently no verified cure for ALS.
Motor neuron disease typically affects people in old age and its causes are unknown. Johnathan Cooper-Knock, a clinical lecturer at the University of Sheffield in England and leader of Project MinE, an ambitious effort to perform whole genome sequencing of ALS, believes that understanding how genes affect cellular function could help scientists develop new drugs to treat the disease.
But before scientists can do that, they need to pinpoint which genes are responsible for motor neuron disease. In their paper, Cooper-Knock and his colleagues describe a machine-learning tool, based on a hierarchical Bayesian network, capable of identifying 690 genes related to ALS by comparing epigenetic data from tens of thousands of people with and without the disease.
“The basic idea is to identify areas of the genome which are active in a normal motor neuron; many areas of the genome are actually tightly packed and unused although the specific regions which are active vary between cell types,” Cooper-Knock explained to The Register. “The logic is that areas of the genome which are not important for motor neuron function normally are unlikely to be relevant to motor neuron disease.”
The tool, known as RefMap, helped the team narrow in on the genomes active in ALS so they could identify the genes involved. “We were able to reduce the search space by over 90 per cent and so increase our statistical power for discovery of genetic changes linked to disease,” said Cooper-Knock.
The group paid particular attention to genes that were more closely associated with motor neurons and found a common one that seemed particularly promising.
- AI-enhanced frog stem cells start to replicate in entirely new ways
- Academics tell Brit MPs to check the software used when considering reproducibility in science and tech research
- US drug watchdog green-lights first prostate-cancer-predicting AI software
- Facebook pulls plug on mind-reading neural interface that restored a user's speech
The gene, codenamed KANK1, was not known to be associated with ALS before. Cooper-Knock said KANK1 was “the top hit” with RefMap because it was most common in the genetic variations of people sequenced with the motor neuron disease. The researchers decided to perform experiments to see how KANK1 affected real motor neuron cells in a laboratory.
“We took motor neuron cells, derived from human skin cells, and used CRISPR to introduce mutations found in ALS patients. We then grew these edited cells into mature motor neurons. We showed that the edited cells died at a higher rate but also that they were electrically dysfunctional and that they showed mislocalisation of TDP-43,” he told us. TDP-43 is a protein that has previously been shown to be affect cellular function in ALS and dementia. “TDP-43 is important because it is the hallmark of ALS.”
The academics believe that each gene identified by the RefMap is a potential target in the development of new drugs. “We have two aims going forward: to develop our discovered gene targets into drugs which could be administered to patients based on their specific genetic profile. And also we want to use our genetic discoveries to produce a prediction model to allow earlier diagnosis of ALS,” Cooper-Knock concluded.
The tool is general and can be applied to other types of diseases too. A similar team of scientists have used it to study COVID-19. ®