Unlock stock picks and a broker-level newsfeed that powers Wall Street.

LTRN: M&A Illuminates GBM Value

In This Article:

By John Vandermosten, CFA

NASDAQ:LTRN

READ THE FULL LTRN RESEARCH REPORT

Lantern Pharma, Inc (NASDAQ:LTRN) continues to enroll its HARMONIC trial for LP-300 at sites around the globe with the most recent focus on Taiwan and Japan, where the prevalence of never-smoker non-small cell lung cancer (NSCLC) is from two to three times higher than in the United States. Lantern’s RADR (Response Algorithm for Drug Positioning & Rescue) platform continues to break ground with new capabilities in predicting blood brain barrier (BBB) permeability of drug candidates and improving the development of antibody drug conjugate (ADC) design. Lantern’s LP-184 gains another Fast Track designation for triple negative breast cancer (TNBC) following the receipt of the same designation for glioblastoma last October. The company also angled a spotlight towards its STAR-001 (LP-184) program at the Society for Neuro-Oncology (SNO) 2024 conference. The associated poster provided support for the combination of spironolactone with the next-generation acylfulvene in glioblastoma multiforme (GBM) and clarified the path forward for STAR-001 with the candidate’s trial design. GBM also made an appearance in a recent transaction where Jazz Pharmaceuticals (NASDAQ:JAZZ) made a bid to acquire Chimerix (NASDAQ:CMRX) for its brain cancer drug for almost $1 billion. The deal should provide an additional framework for determining the value of Lantern’s STAR-001 asset in GBM.

AI-Model Activity

Patent Application

Lantern’s Patent Cooperation Treaty (PCT) patent application entitled Machine Learning System and Method for Predicting Blood Brain Barrier Permeability was published by the World Intellectual Property Organization (WIPO) as reported in a February 19th press release. The PCT application enables Lantern to pursue patent protection in major markets worldwide, with potential coverage extending 20 years from the filing date. The application describes a machine learning system and method for predicting blood-brain barrier permeability. It obtains samples of data associated with molecules from various data sources, converts the samples into structural representations, and generates features from the structural representations. Tests are conducted to determine blood-brain barrier permeability dependency. The system analyzes the ratio of permeable to non-permeable samples in the data and augments them with synthetic data to create a balanced dataset if an imbalance between the types of samples is detected. The system reduces the features utilized for training the machine learning utilizing a technique to create a selected set of features for the balanced dataset. The system trains a machine learning model using the balanced dataset, utilizing the machine learning model to predict blood-brain barrier permeability for the candidate molecule.