Doctors diagnose 10 million new cases of dementia every year, and that number is expected to triple by 2050. Dementia is most commonly caused by Alzheimer’s disease, and research has made little progress in battling it for over of a century. Now, using cutting-edge bioinformatics and computational biology, researchers at Arizona Health Sciences University have identified promising new candidates for the treatment of Alzheimer’s disease as well as new strategies to optimize prevention.
Although they have studied Alzheimer’s disease since its documentation in 1906, scientists still have only a limited understanding of it, and there are no proven preventions or treatments for it today.
Tomorrow, however, there could be.
In just five years, Rui Chang, Ph.D.and Francesca Vitali, PhDresearchers at the UArizona Health Sciences Center for Innovation in Brain Science, have made incredible progress in identifying molecular compounds that show significant potential to help prevent Alzheimer’s disease and even reverse its effects.
A fast track to preventing Alzheimer’s disease
Dr. Vitali, associate director of bioinformatics at the Brain Science Innovation Center, focused on the preclinical phase of Alzheimer’s disease: the window in which the disease progresses undiagnosed, which can extend over 20 years. In a new strategy she named Targeted-Risk Alzheimer’s Disease Prevention (TRAP), Dr. Vitali relied on scientific papers and drug information repositories to identify drug products approved by the FDA and show promise for the prevention of Alzheimer’s disease.
First, Dr. Vitali used natural language processing to extract information from over 10,000 published medical studies and reports. Simply put, natural language processing allows computers to “read” large amounts of text, finding patterns and information that would otherwise be obscured by the sheer magnitude of the content. Through this process, she has identified more than 300 diseases and conditions linked to a higher risk of Alzheimer’s disease.
Dr. Vitali then used data mining in drug information repositories to identify more than 600 approved drugs used to treat these conditions. Through further evaluation, she ultimately zeroed in on 46 drugs for a system biology analysis that revealed the complex way they work in the body – unique effects as well as interconnected biological mechanisms.
“Based on these results, we believe that early interventions that strategically target known risks for developing Alzheimer’s disease could make it a preventable disease by 2025,” said Dr. Vitali, assistant research professor at the College of Medicine – Tucson’s Department of Neurology and a member of the BIO5 Institute.
His analysis also showed which therapeutics, alone or in combination, might work best for patients with specific genetic profiles: a platform for a precision medicine approach to preventing Alzheimer’s disease. And while Dr. Vitali developed the TRAP strategy for Alzheimer’s disease, it can also be applied to other diseases lacking prevention and treatment, such as Parkinson’s disease, multiple sclerosis and Lou Gehrig, also known as amyotrophic lateral sclerosis or ALS.
Repairing the Damage of Alzheimer’s Disease
In a similar strategy, Dr. Chang, a computational biology researcher at the Center for Innovation in Brain Science, used artificial intelligence (AI) to analyze multiomics datasets: information about DNA, proteins, the microbiome and Moreover. The data was drawn from thousands of postmortem brain tissue samples provided by the Accelerating Medicines Partnership Program for Alzheimer’s Disease, a consortium recently created by the National Institutes of Health.
The key innovation in Dr. Chang’s research, however, is the network model he created for the many ways genes and proteins influence each other. Dysregulation of a single gene, for example, has ripple effects throughout the body, altering disease pathways. Scientists who study brain tissue only see downstream terminal gene expressions, without understanding how these states came about. Because the samples come from people who have lived with Alzheimer’s disease for varying periods of time, they collectively represent rich timelines of disease progression.
“My network model is able to identify upstream causes of disease pathology,” explained Dr. Chang, associate professor of neurology at the College of Medicine – Tucson. “I am able to show exactly which upstream gene has become deregulated, what network changes it has caused and therefore what might be a cure – which gene or genes to disrupt to bring the whole network back to normal. healthy.”
The analyzes identified 6,000 potential targets and over 3,000 potential compounds for treatment. These were narrowed down to 170 compounds that protect neurons from dying or activate the brain’s innate defense system to consume amyloid plaques and neurofibril tangles, which have been a focus of Alzheimer’s disease research. over the past two decades.
Ultimately, Dr. Chang’s study converged on three treatments that significantly improved the working memory of mice with Alzheimer’s disease. Two of the compounds are substances produced naturally in all mammals and one is derived from plants. All reduce the brain plaques and protein tangles that have been a focus of Alzheimer’s disease research for the past two decades.
But while other compounds might also reduce plaques and tangles (the landmark study in this line of inquiry has recently been questioned), they have never been shown to improve cognitive deficits. In contrast, the mice treated by Dr. Chang improved their brain function so dramatically that they nearly “caught up” to the disease-free control group of mice.
Natural language processing, AI, and network analytics can accelerate discovery by overcoming natural biases and blind spots intrinsic to human analysis, revealing connections that often only make sense in hindsight.
All three compounds are now on track for clinical trials, and since neurodegenerative diseases appear to have overlapping mechanisms, Dr. Chang believes they could also lead to treatments for other diseases, including Alzheimer’s disease. Parkinson’s and Lewy body dementia. He also believes his methodology could lead to cures for comparatively complex problems like cancer, now recognized as more than 100 similar diseases.
Discovery of rollover acceleration
As a rule, therapeutics begins with discoveries in the laboratory. Pharmaceutical scientists learn that a compound has a biological effect, then try to match that effect to known causes and symptoms of health problems.
Researchers like Drs. Chang and Vitali flip this model, seeking treatments and cures by first considering the known factors underlying disease. They then use technology to analyze reams of data looking for patterns that suggest certain compounds might impact these biological foundations.
The approach offers benefits demonstrated in their successes: the sheer size of the datasets would take decades to process without these technologies and working with so much data has the added benefit of establishing greater confidence in the results. The inverted model also accelerates discovery: Dr. Chang’s discoveries were achieved in just five years, Dr. Vitali’s in two.
Perhaps most importantly, natural language processing, AI, and network analytics can accelerate discovery by overcoming the natural biases and blind spots intrinsic to human analysis, revealing connections that often only make sense. ‘in hindsight. The initial 6,000 targets highlighted by Dr. Chang, for example, certainly included many that had not been considered relevant to Alzheimer’s disease.
“Today, there are two camps in medical research,” Dr. Chang said. “One is traditional biology, the other is AI and data science, but it’s critical that these two camps collaborate, not compete.”
Data scientists can offer hypotheses, but biologists are key to validating those hypotheses, Dr. Chang said. And even the most advanced computers are no substitute for insight, intuition and imagination. Biologists bring and inspire new ideas, and no level of computing power today can replace that.
“It all comes down to the fact that AI is data-driven and biologists are knowledge-driven,” Dr. Chang said. “Our research works best when we bring these two approaches together. We need each other, and I hope to see even more collaboration in the future.”