AI Is Transforming Drug Matching for Cancer, Rare Diseases — Here's How One AI pharmaceutical startup works backward, starting from drugs already on the market.
By Sherin Shibu
Key Takeaways
- Transcripta Bio attempts to take on rare diseases by matching older, existing drugs to newer use cases.
- The startup's unusual approach could be a more cost-effective solution to drug matching.
- AI is being used in healthcare settings across the private and public sectors.
AI tools are changing how pharmaceutical companies and public health institutions think about finding drugs to treat rare diseases.
For example, Transcripta Bio, a Silicon Valley-based pharmaceutical startup, is using AI to match existing medications with new use cases, according to a profile in Bloomberg this week.
The company uses AI software to identify drugs that could alleviate the effects of rare diseases. Instead of narrowing in on one condition to see if an experimental drug works on the genes associated with that condition, Transcripta works backward by starting from drugs already on the market.
Related: AI Is Changing How Businesses Recruit for Open Roles — and How Candidates Are Gaming the System
The startup tests drugs identified as a good match by its AI software to determine if those drugs have additional use cases and also affect genes associated with rare diseases.
Transcripta's unusual approach could be more cost-effective. The company claims that it can conduct screenings across all known rare genetic diseases for about $2 million, which is what a pharmaceutical company might pay to start research on a new drug for one disease, per Bloomberg.
The company has raised about $30 million to date.
"It's now much more capital efficient," Chris Moxham, chief executive officer and chief scientific officer at Transcripta, told the publication. "It's not just one disease at a time."
Other startups, including Century Health, which secured $2 million in pre-seed funding last month, are also trying to harness existing data about drugs for new, real-time applications. Century Health in particular is working to commercialize drug breakthroughs for diseases like Alzheimer's with its AI platform.
It's not just startups that are interested in AI applications for healthcare. AI chip giant Nvidia created an AI cloud service specifically for AI-aided drug development and released two dozen new AI tools last month for healthcare.
One standout tool was a bot called Hippocratic that outperformed real nurses in all areas, including how a medication impacted labs and how a lab value compared to a target range.
Related: Microsoft's New AI Can Make Photographs Sing and Talk
On the public health side, researchers at the National Cancer Institute (NCI), which is part of the National Institutes of Health (NIH), created an AI tool last week called PERCEPTION that showed promise in predicting if a patient would respond to certain cancer treatment drugs over others.
In a study published in Nature Cancer on Thursday, the researchers wrote that PERCEPTION outperformed the industry standard for predictors "in all clinical cohorts."
