
How I Use LLMs for Data Harmonization: A Strategic, Limited Approach
A technical walkthrough of how I used LLMs strategically to improve name harmonization for clinical trial sponsors while minimizing non-determinism.
In-depth, data-driven analysis on biotech companies and markets.
Technical content, news, and opinions on the biotech industry.
Tutorials on biotech industry research methods and details about data sources and regulatory filings.

A technical walkthrough of how I used LLMs strategically to improve name harmonization for clinical trial sponsors while minimizing non-determinism.

After Lundbeck’s $2B acquisition of Longboard, investors scrambled for serotonin analogs. Here’s why Bright Minds was the target and what it says about the future of rare epilepsy drug development.

Drug exclusivity is an important metric to track when monitoring pharma portfolios. RxDataLab has created a dashboard to monitor estimated drug patent and exclusivity expiration in the US.
Visualizing the rise in Investigational New Drug (IND) receipts and active INDs during 2019-2020. With no major regulatory changes, the spike appears linked to the COVID-19 pandemic, raising questions about how it shaped drug development.

The drug development process consists of 5 distinct steps, and there are data sources available to learn more about each step. Here I will cover some of the most important for our work.
81% of drugs approved in 2000 have generic equivalents in 2024. We will dive into how we used the Orange Book to answer this question, and how we approach these problems.
The FTC recently challenged over 100 Orange Book patent listings for drugs including blockbuster Ozempic. In fact, up to 89% of claimed patents were challenged for certain drugs. Here we dive into what was challenged, whether it matters, and what happens now.

The FDA Orange Book, formally "Approved Drug Products with Therapeutic Equivalence Evaluations", is the authoritative reference for approved drug products, therapeutic equivalents, and the patent and exclusivity records that govern generic entry. Published since 1980, it is the primary source for understanding when brand-name drugs face generic competition.
Brief rundown of the Center for Drug Evaluation and Research (CDER), the center that handles approvals and monitoring for new drug applications, generics, and more at FDA.
Understand the various types of exclusivity and intellectual property protections surround pharmaceutical products in the United States
Glucagon-Like Peptide-1 (GLP-1), Semaglutide, and other GLP-1 targeting drugs are involved in many clinical trials as of July 2024. Here, we cover some of the conditions with active clinical trials that may not be getting as much attention as the weight loss and diabetes cases.
RxDataLab
Get the data behind the analysis
We deliver primary-source biotech datasets for BD teams, investors, and the AI tools they're building. Tell us what you're tracking.
or email [email protected]