- Lantern’s RADR(R) AI platform is helping identify optimal indications and pathways for precision cancer therapies.
- Dr. Schalop reflects on lessons from developing ONC201, approved for H3K27M-mutant glioma, after a 16-year journey.
- Both leaders highlight the potential for AI to accelerate regulatory reviews and clinical trial design.
- The conversation underscores how AI could reduce oncology drug timelines and costs, improving patient access to new treatments, and how STAR-001, Lantern’s new CNS cancer drug, can benefit from these AI-driven insights.
In oncology, the path from molecule discovery to patient treatment often stretches over a decade and can consume hundreds of millions of dollars. Lantern Pharma (NASDAQ: LTRN), a clinical-stage biotechnology company leveraging artificial intelligence and machine learning to redefine oncology drug development, aims to challenge that timeline.
In a recent discussion titled “From Discovery to Clinical Trials to Patients: Key Decisions Shaping Novel CNS Oncology Medicines,” Lantern CEO Panna Sharma and new board member Dr. Lee Schalop, co-founder of Oncoceutics and a key figure behind the development of ONC201 (dordaviprone), explored how data science and machine learning could shorten the journey from lab to clinic in central nervous system (“CNS”) oncology (https://ibn.fm/vC0Ma).
Dr. Schalop, who began his career on Wall Street before earning a medical degree in his 40s, said his unique background helped him bridge science and strategy. “I realized I could probably do more by combining my business background with my new medical knowledge,” he said. That blend of experience ultimately led him to co-found Oncoceutics, where ONC201 became one of the first drugs approved for H3K27M-mutant glioma, a rare and aggressive brain cancer. Now joining Lantern’s board, Schalop brings both a cautionary and optimistic view of how the next generation of CNS drugs can be developed faster and smarter, especially through the use of artificial intelligence.
ONC201’s development began with phenotypic screening: testing compounds for general anti-cancer activity without knowing their mechanism of action. Working with the Broad Institute, Schalop’s team discovered that the molecule showed particular efficacy against brain cancer.
However, identifying the precise genetic context (the H3K27M mutation) took years of additional preclinical and clinical work. The breakthrough came during a Phase 2 trial at Harvard, when one patient’s tumor disappeared. That patient, it turned out, was the only one with the H3K27M mutation. “An AI-type program would have known about this, because it was known at this time, although just not well known,” Schalop said. “And it would have immediately put the pieces together and said, ‘Aha, this patient had it, no one else did. This is where you should devote your effort.’”
Sharma agreed that machine learning systems could have accelerated those insights. Lantern’s own platform, RADR(R) is designed to perform precisely that function. Built to analyze vast genomic and clinical datasets, RADR(R) identifies which cancer subtypes and mutations are most likely to respond to specific compounds. The platform supports Lantern’s three lead drug candidates and an antibody-drug conjugate (“ADC”) program across 12 cancer indications.
For Sharma, the promise of AI isn’t just speed, but accuracy and the ability to select the right patient populations early and design smarter trials. He cited STAR-001, a Lantern program targeting CNS cancers, as a candidate that could follow a more efficient path than traditional drug development.
The discussion also turned to the U.S. Food and Drug Administration and how regulators might use AI to shorten the pre-review phase of drug approvals. Schalop explained that it took 16 years to get ONC201 from discovery to approval. Even if the FDA can shorten its review timeline, the real opportunity is to make the 10 years before that faster, he added.
Both speakers mentioned growing interest in artificial intelligence uses within the agency, as current commissioner Marty Makary has discussed using AI to process and analyze complex scientific submissions more efficiently. Sharma added that Lantern is already deploying AI internally to summarize trial data in hours rather than weeks. “Scientific review and biomedical literature review and data review and analysis take a long time for humans to do well,” he said. “If you can get systems to do it even better and do it within minutes, as opposed to weeks or months,” that is a real game changer.
Oncoceutics’ lean approach (roughly $25 million in equity and a similar amount in grants) kept control in the founders’ hands but extended the timeline. Eventually, the company was acquired by Chimerix and later by Jazz Pharmaceuticals, which brought ONC201 to approval at a total cost of around $300-$400 million.
By contrast, AI-assisted development could lower both timelines and costs. Identifying optimal indications early reduces the number of unsuccessful trials, while predicting effective combinations may limit expensive exploratory work.
Schalop noted that AI could also make combination trials more feasible: “If you can figure out how something will probably work, as opposed to might work, it will be worth spending the time and money to try that combination.”
Both Sharma and Schalop emphasized that the ultimate goal of these technologies is to improve outcomes for patients with rare, hard-to-treat cancers. Each year, roughly 2,000 U.S. patients are diagnosed with H3K27M-mutant glioma, the same group now eligible for ONC201 treatment.
For Sharma, the message is clear: oncology’s future depends on integrating clinical experience with data science. “I think it’s a great time to be in medicine. There’s just so much data and people are publishing so much. It’s an exciting time. And hopefully it translates more and more into better patient outcomes,” he concluded.
For more information, visit the company’s website at www.LanternPharma.com.
NOTE TO INVESTORS: The latest news and updates relating to LTRN are available in the company’s newsroom at https://ibn.fm/LTRN
About QualityStocks
QualityStocks (“QS”) is a specialized communications platform with a focus on private and public companies and the investment community. It is one of 70+ brands within the Dynamic Brand Portfolio @ IBN that delivers: (1) access to a vast network of wire solutions via InvestorWire to efficiently and effectively reach a myriad of target markets, demographics and diverse industries; (2) article and editorial syndication to 5,000+ outlets; (3) enhanced press release enhancement to ensure maximum impact; (4) social media distribution via IBN to millions of social media followers; and (5) a full array of tailored corporate communications solutions. With broad reach and a seasoned team of contributing journalists and writers, QS is uniquely positioned to best serve private and public companies that want to reach a wide audience of investors, influencers, consumers, journalists and the general public. By cutting through the overload of information in today’s market, QS brings its clients unparalleled recognition and brand awareness. QS is where breaking news, insightful content and actionable information converge.
For more information, please visit https://www.QualityStocks.com
Please see full terms of use and disclaimers on the QualityStocks website applicable to all content provided by QS, wherever published or re-published: https://www.QualityStocks.com/Disclaimer
QualityStocks
Austin, Texas
www.QualityStocks.com
512.354.7000 Office
Editor@QualityStocks.com
QualityStocks is powered by IBN
