As the world of artificial intelligence continues to evolve, a New Jersey biotech company is taking AI capabilities to the next level.
After decades of working with AI-based phenotypic platforms to develop drugs for mental illnesses, PsychoGenics has made a breakthrough with a compound that aims to treat schizophrenia.
PsychoGenics President and CEO Emer Leahy spoke with Fox News Digital during a recent on-camera interview, explaining that she and her team are closer than ever to developing what she said to be the very first drug discovered by AI.
AI-POWERED MENTAL HEALTH DIAGNOSTIC TOOL COULD BE FIRST OF ITS KIND FOR PREDICTING AND TREATING DEPRESSION
“This is the first de novo drug, I believe, to hit the market,” she said.
Scientists from Yale University’s Department of Psychiatry founded PsychoGenics in 1999. They first worked with “transgenic mouse models” to better understand and respond to psychiatric disorders, Paramus-based Leahy explained.
Emer Leahy is President and CEO of PsychoGenics, a New Jersey biotechnology company. They are nearing the development of what she said is the very first drug discovered by AI. (Psychogenetics)
“We basically started with the mission to examine the behavior of these genetically engineered mice for neuropsychiatric disorders,” she said.
“Then we started to provide a service to the pharmaceutical and biotechnology industry in general.”
AI TOOL GIVES DOCTORS PERSONALIZED ALZHEIMER TREATMENT PLANS FOR PATIENTS WITH DEMENTIA
PsychoGenics has since expanded its capabilities to offer a “broad suite” of preclinical offerings, Leahy said, to support central nervous system (CNS) drug discovery.
In 2002, when PsychoGenics was just an eight-person team, the company embarked on the discovery of new drugs based on its expertise in rodent behavioral testing.
Leahy has worked in the pharmaceutical and biotechnology industry for over 30 years. She says she pushed her team to “industrialize” her method.
This illustration from PsychoGenics of New Jersey shows the complexity of neuropsychiatric disorders. (Psychogenetics)
“It was the pinnacle of the genomics revolution,” she said. “Everyone was chasing targets and genes – and basically what I was saying was, ‘Let’s not do this. Let’s use behavior, the output of the brain, to drive discovery efforts, and look for patterns of behavior that will allow us to predict new treatments.'”
The then-small PsychoGenics team took their “big ideas” to Carnegie Mellon University in Pittsburgh, Pennsylvania, in search of high-tech tools to develop the first platform, now known as from SmartCube.
A BRAIN HEALTH EXPERT RESPONDS TO THE LONELY EPIDEMIC: HERE ARE EASY WAYS TO FIGHT IT
She said SmartCube “has been tasked with bringing a number of treatments to clinical trials.”
The most advanced of those to come out of SmartCube is Ulotaront, which sets out to treat schizophrenia.
The drug is being developed by Sunovion Pharmaceuticals and is in phase three trials, which is when it is being monitored for “efficacy and monitoring for adverse effects,” according to the FDA.
How the AI-powered SmartCube works
SmartCube combines robotics, computer vision and artificial intelligence in a box-like mechanism.
The cube presents its subjects (injected mice) with a series of challenges to influence their behavior.
“The ground will change configuration, (the mouse) will get a puff of air that will startle it,” Leahy explained. “Different things happen in the course of an hour.
She detailed how multiple cameras in the box capture “everything the mouse does in session.”
Millions of data points are condensed into a few thousand “behavioral characteristics,” from which, Leahy explained, a drug signature is extracted. (Stock)
“We collect a few million data points in one session,” she said. “You can’t use parametric statistics to make sense of this kind of data, so we use machine learning.”
Those millions of data points are then condensed into a few thousand “behavioral characteristics,” from which, Leahy explained, a drug signature is extracted.
“We can identify the behavioral characteristics that predominate in the animal in response to different treatment,” she said.
CHATGPT FOUND TO GIVE BETTER MEDICAL ADVICE THAN REAL DOCTORS IN BLIND STUDY: ‘IT WILL CHANGE THE GAME’
CEO Leahy mentioned that PsychoGenics has built a “benchmark database”.
It is based on a variety of other compounds – such as antidepressants, anxiolytics, mood stabilizers and other antipsychotics – to be compared to the new drug being tested.
“We can test thousands of compounds in SmartCube and we can predict their potential therapeutic utility,” she said.
“There is a real need for better treatment for schizophrenia,” said Leahy, CEO of PsychoGenics. The company is working to fill a need in the untapped market for schizophrenia treatments, which it shared with Fox News Digital. (Stock)
Leahy revealed that approximately 40% of compounds will show a “signature” that indicates their potential for a new drug discovery program.
Ulotaront is a “great example” of how this process works, Leahy added, as PsychoGenics sought to fill an untapped market need for schizophrenia treatments.
“There is a real need for better treatment for schizophrenia,” she said.
AI HEALTH CARE PLATFORM PREDICTS DIABETES WITH HIGH ACCURACY BUT ‘WILL NOT REPLACE PATIENT CARE’
All currently available antipsychotics work by targeting D2, the dopamine receptor for antipsychotic drugs, according to Leahy — and there haven’t been any new mechanisms for about 60 years.
PsychoGenics was able to go “a step further” by targeting the development of a drug for schizophrenia that did not target D2.
A patient has a therapy session with a psychologist. “Existing treatments,” Leahy said, “have minimal impact on what are called the ‘negative symptoms’ of schizophrenia…the apathy, social withdrawal, flat effects. They treat the ‘positive symptoms’- hearing voices, psychosis – but not the “negative symptoms”, which are very debilitating.” (Stock)
The problem with D2 is that about a third of patients don’t respond to it, Leahy explained.
“These existing treatments have minimal impact on what are called the ‘negative symptoms’ of schizophrenia…the apathy, social withdrawal, flat effects,” she said.
“They address the ‘positive symptoms’ – hearing voices, psychosis – but not the ‘negative symptoms’, which are very debilitating.”
TEENS TURN TO SNAPCHAT ‘MY AI’ FOR MENTAL HEALTH SUPPORT — AGAINST WHAT DOCTORS WARN
Patients also sometimes refuse these treatments because of side effects, which can often lead to a relapse, Leahy said.
As chemists worked to identify several potential drug “hits,” in partnership with Sunovion, PsychoGenics ended up with “just a handful of compounds” that fit the bill, Leahy said.
“We finally identified Ulotaront,” Leahy said.
“And we predicted that Ulotaront would have effects on negative symptoms, and it would have a better safety profile.”
If phase three trial results are positive, Ulotaront could hit the market in 2024. “We’re very excited about this,” Leahy said. “It’s going to provide what we think is a better treatment for patients who are suffering from this seriously debilitating disease.” (Stock)
Ulotaront had an “outstanding result” after phase two clinical trials, according to Leahy, showing it could improve both positive and negative symptoms of schizophrenia.
PsychoGenics expects the compound to “read” through multiple phase three trials later this year, which means the data will be made public.
AI LIFE HACKS: HOW TRAVELERS USE CHATGPT TO PLAN TRIP ON A BUDGET
If the results are positive, Ulotaront could hit the market in 2024.
“We’re very excited about this,” Leahy said. “It’s going to provide what we think is a better treatment for patients who are suffering from this seriously debilitating disease.”
ArtificialIhealth intelligence
Leahy said the industry has seen an “explosion” in the use of AI in drug development in recent years.
AI is “as good as the data you feed it”.
With the advent of SmartCube, PsychoGenics has become one of the first healthcare companies, if not the first, to use AI in drug discovery, according to Leahy.
“Instead of what is typically 2,500 compounds tested, before we can nominate a compound to go into toxicology studies and clinical trials, we get there in about 300,” she said.
VSCLICK HERE TO SUBSCRIBE TO OUR HEALTH NEWSLETTER
“We’ll get there in less than three years, compared to about five plus years, and at a fraction of the cost of other approaches.”
This informational guide provided by PsychoGenics details the cost of mental health in America, according to the National Institute of Mental Health. (Psychogenetics)
After decades of dealing with cutting-edge technology and machine learning, Leahy noted that AI is “as good as the data you feed it.”
She added, “What we’re doing…is looking at patterns – patterns that a human being can’t do. A human being can’t take 2,000 behavioral characteristics and distill them into a drug signature. , then make predictions… So it’s a very powerful tool. We’re going to see tremendous growth.”
CLICK HERE TO GET THE FOX NEWS APP
Leahy said there is “tremendous potential” for improvement in the field of mental health, as AI has the ability to mine the literature to develop new hypotheses and identify potential new treatments.