San Francisco-based Verge Genomics has begun a Phase 1 human trial for its ALS drug candidate.
Any candidate for ALS is good news, even at such an early stage, but Verge’s compound is unique: it was not discovered by animal or cell testing, but by an AI analyzing millions and millions of human data points.
The trial is among the first for a drug discovered in this way, the company said.
Verge Genomics has started a phase 1 trial for its new ALS drug candidate.
“We are proud to be not only one of the few AI-focused biotech companies to reach the clinical stage, but also one of the first to deliver a new clinical compound against a new target, which has been fully discovered and developed. internally on our platform,” Verge CEO Alice Zhang said in a statement.
The field has been a bit hot lately, with everyone from Alphabet to ambitious teenagers entering the fray, looking for a wide range of new drugs. The idea is to leverage the vast amounts of medical data available through AI to help create a shortcut to finding molecules that can treat disease.
The challenge: Drug discovery is… frustrating, for simplicity. Just finding a potential candidate can be expensive and time-consuming, and the success rate is extremely low – like stormtroopers shooting heroes. Of 10,000 drug candidates identified, perhaps five will make it to trial.
And, of course, those five could hit a number of hurdles before they get approved — many drugs that look good in animal tests fail in human trials, especially when they’re used. are complex neurological diseases such as Alzheimer’s disease.
Verge’s compound is unique: it was not discovered by animal or cell testing, but by AI analyzing millions and millions of human data points.
“Animal models have been poor predictors of efficacy in clinical trials for neurodegenerative diseases,” Alix Lacoste, director of AI computational biology at genetic testing company Invitae, told the Financial Times.
The idea behind Verge’s use of AI is that by starting with human patient data, you’ll be more likely to find compounds with a higher chance of working in people, and you’ll be able to better understand how the condition actually works in human beings.
“Hypotheses usually come from academic findings or publications and are tested sequentially, mostly in animals, mice, or even cell models to predict which of these drugs would actually work in humans,” Zhang told the Financial Times. . “Hundreds of millions of dollars later, you enter clinical trials and, unsurprisingly, the drug fails.”
Human data, computer information: Verge began by creating a database of tissue samples from the brains and spines of people with neurodegenerative diseases, including ALS, Parkinson’s disease and Alzheimer’s disease.
Starting with human data and human models “provides unique insights into the biological underpinnings of ALS,” Verge Genomics CSO Robert H. Scannevin said in the company’s statement.
The company’s AI platform, CONVERGE, analyzed a night sky’s worth of millions of data points to arrive at its conclusions, finding constellations among chemical stars.
First, he identified a new mechanism that may be behind ALS: loss of function in the endolysosomal system of cells – a group of organelles inside cells.
From there, he identified an enzyme called PIKfyve as a potential drug target to ward off this loss of function. Finally, he suggested a small molecule called VRG50635 (catchy!), which inhibits PIKfyve, as a possible drug candidate. The whole process took four years.
The hope is that, starting from human data, the drug will be more likely to work.
Let the trial begin: The hope is that starting from this human data, VRG50635 will be more likely to work.
“Using human data from day one means we start with higher quality targets that are more likely to be successful in the clinic,” Zhang told the Financial Times.
It’s an uphill battle, especially when it comes to ALS; at least 50 tries over the past 20 years have come to nothing, reports the pink journal.
The trial is a placebo-controlled, randomized, double-blind phase 1 designed to test the basics of the drug – is it safe? How does it move through the body? What effects does this have and what motivates them? — in healthy patients and patients with ALS.
Rolling with the CONVERGE targets could be a first win for this new approach to drug discovery; of course, we still have no idea if the AI drug worksand won’t for a while.
“This is just the beginning of our plan to develop a strong clinical pipeline of new drugs demonstrating that a human-to-human rather than animal-based approach has the potential to transform clinical success rates,” Zhang said in the release. .
We would love to hear from you! If you have a comment about this article or have a tip for a future Freethink story, please email us at [email protected]