Lantern Pharma Introduces AI-Driven Antibody-Drug Conjugate Development
AI identifies 82 potential targets and 729 payloads for antibody-drug conjugates, including 22 already validated.
Lantern Pharma (NASDAQ: LTRN) has announced advancements in its RADR platform, integrating a new AI-powered module designed to accelerate and optimize the development of antibody-drug conjugates (ADCs). ADCs are targeted cancer therapies that combine antibodies specific to tumor cells with potent cytotoxic payloads. Reportedly, the global ADC market is expected to reach $30.4 billion by 2028, driven by growing demand for more effective cancer treatments and multiple ADCs achieving blockbuster status.
See also: How AI Enables Precision Oncology
Lantern's new module leverages RADR to identify promising ADC targets and payload combinations. A recent peer-reviewed study published in PLOS ONE details how the platform identified 82 ADC targets, including 22 that are clinically validated, along with 60 novel targets with potential for intellectual property and portfolio expansion. RADR also screened over 50,000 compounds, validating 729 payload molecules with therapeutic potential.
These payloads demonstrated potency at GI50 values ranging from picomolar to 10 nanomolar concentrations, a critical measure of their effectiveness in inhibiting cancer cell growth. GI50, or Growth Inhibition 50, represents the concentration of a substance required to inhibit cell growth by 50%, serving as a standard metric to evaluate the potency of therapeutic compounds.
“Response Algorithm for Drug Positioning & Rescue”
The RADR platform integrates complex datasets, including transcriptomics, proteomics, and mutation profiles across 22 tumor types. This capability allows it to identify mutation-specific responses, enabling more precise patient stratification in clinical trials. Lantern estimates that the AI-powered ADC module could reduce ADC development timelines by 30–50% and lower costs by up to 60% compared to traditional methods.
RADR is an AI-powered drug discovery platform designed to analyze complex genomic and transcriptomic datasets. It uses over 25 billion oncology-specific data points, including 154 drug-tumor interactions and 130,000 patient records, to reveal mechanisms of action (MoAs), identify biomarkers, and predict patient responses. This precision approach enhances clinical trial success rates by selecting patient groups most likely to benefit from a therapy. More in our case study.
RADR has been integral to Lantern’s pipeline. For example, the platform supported the development of LP-184, a synthetically lethal molecule targeting advanced solid tumors and brain cancers, which recently received FDA clearance for a Phase 1A trial. RADR also informed the design of LP-300, a lung cancer therapy currently in Phase 2 trials, targeting non-smokers with advanced non-small cell lung cancer (NSCLC).
ADC Development and Collaboration
In collaboration with the MAGICBULLET::Reloaded initiative at the University of Bielefeld, Lantern is advancing multiple ADC candidates through preclinical development. The integration of AI-driven data insights is being used to optimize payload potency, improve targeting selectivity, and expand the therapeutic window of ADCs.
Panna Sharma, CEO & President of Lantern Pharma
“This breakthrough demonstrates how AI can transform the traditionally costly and time-consuming process of ADC development. By simultaneously analyzing multiple data types and integrating mutation profiles with target expression, our team was able to identify optimal therapeutic combinations that have the potential to be more effective and safer for specific patient populations.”
Key Highlights of the ADC Module
Identification of 82 ADC targets, including 22 clinically validated ones.
Discovery of 60 novel targets for intellectual property, portfolio expansion, and licensing opportunities.
Validation of 729 payload molecules with exceptional potency for ADCs.
Development of mutation-specific targeting capabilities to improve clinical trial design and patient response predictions.
Estimated reductions of 30–50% in ADC development timelines and up to 60% in costs.
The full study, “Expanding the repertoire of Antibody Drug Conjugate (ADC) targets with improved tumor selectivity and range of potent payloads through in-silico analysis”, is available in PLOS ONE.