On July 15, 2025 Lantern Pharma Inc. (NASDAQ: LTRN), a pioneering artificial intelligence (AI) company transforming oncology drug discovery and development, reported the launch of an innovative AI-powered module within its proprietary RADR platform, designed to predict the activity and efficacy of combination regimens involving DNA-damaging agents (DDAs) and DNA damage response inhibitors (DDRis) in clinical cancer treatment (Press release, Lantern Pharma, JUL 15, 2025, View Source [SID1234654385]). With the global market for combination cancer therapies projected to exceed $50 billion by 2030, growing at a CAGR of 8.5%, this module represents a significant advancement in precision oncology, enabling faster, more cost-effective development of tailored therapeutic regimens. Leveraging this AI-driven framework, Lantern Pharma has successfully architected and achieved FDA clearance for a Phase 1B/2 clinical trial in triple-negative breast cancer (TNBC), focusing on a novel DDA-DDRi combination regimen with promising preclinical efficacy.
Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:
Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing
Schedule Your 30 min Free Demo!
In a peer-reviewed study published in Frontiers in Oncology, Clinical outcomes of DNA-damaging agents and DNA damage response inhibitors combinations in cancer: a data-driven review, Lantern Pharma researchers systematically analyzed 221 DDA-DDRi combination-arm clinical trials, involving 22 DDAs and 46 DDRis, to develop this module. The study categorized DDAs into eight subclasses (e.g., alkylating agents, interstrand cross-linkers) and DDRis into 14 subclasses (e.g., PARP, ATR, WEE1 inhibitors). From these, 89 trials with interpretable outcomes were scored for clinical effectiveness, safety, and biomarker-driven responses, providing a robust dataset to train the AI module.1
Transforming Cancer Combination Therapy Development
The new AI module represents a paradigm shift in precision oncology, leveraging machine learning to predict which drug combinations will be most effective for specific patient populations while minimizing toxicity risks. This data-driven approach has already demonstrated its value by successfully guiding the design of Lantern’s FDA-cleared Phase 1B/2 clinical trial combining LP-184 with olaparib in triple-negative breast cancer (TNBC).
"This AI-powered module is a transformative step in our mission to deliver personalized cancer treatments," said Panna Sharma, CEO & President of Lantern Pharma. "By leveraging our RADR platform to analyze complex multi-omics and clinical trial data, we identified optimal DDA-DDRi combinations that guided the development of our TNBC trial. We believe this approach could reduce combination therapy development timelines and costs by one-third compared to traditional methods."
The module integrates genomic, transcriptomic, and clinical data to predict synergistic drug interactions, optimize therapeutic outcomes, and identify biomarker-defined patient subpopulations likely to respond to specific combinations. This data-driven approach directly informed the design of Lantern’s FDA-cleared Phase 1B/2 trial in TNBC for LP-184 and olaparib, with potential to improve response rates and reduce toxicity.
Key insights from the study powering the AI module include:
Non-PARP Inhibitor Promise: Non-PARP DDRi combinations, particularly WEE1 inhibitors like adavosertib with platinum agents, showed an 80% positive outcome rate in interstrand cross-linker trials, with strong efficacy in TP53-mutated cancers, directly informing future trial design.
Biomarker-Driven Success: Biomarkers such as TP53 mutations and HRD signatures were critical predictors of response, enabling patient stratification to maximize efficacy.
Toxicity Mitigation: The use of novel formulations like liposomal doxorubicin in combination regimens reduced cardiotoxicity, providing a safer backbone for combination strategies.
Emerging Trends: The analysis emphasizes the patterns in treatment effectiveness, safety, and emerging trends across various cancer types and discusses the potential of biomarkers to guide treatment selection and improve patient outcomes.
The module’s multi-agentic framework integrates specialized AI agents for data aggregation, drug classification, predictive modeling, biomarker identification, and optimization, creating a dynamic system that is planned to evolve along with new data. The system’s continuous learning capability ensures adaptability, enabling Lantern to refine regimens and accelerate future trials across diverse cancer indications. The company is exploring licensing and commercialization opportunities to expand the application of this technology, further revolutionizing combination therapy development.