Tevogen ("Tevogen Bio Holdings Inc." or "Company") (NASDAQ:TVGN) today announced performance advancements for its artificial intelligence platform, operated through Tevogen.AI.
Tevogen.AI was built to solve a critical challenge in drug development: identifying biological targets which are most likely to work in patients, before entering costly clinical trials.
Over the past year, the Company has built a proprietary database of more than 655 million peptide sequences derived from approximately 24 million proteins, representing nearly 16 billion data points across multiple disease areas. This database is continuously enriched using analysis of 37 million scientific publications.
Improved Prediction Accuracy
In recent beta testing of its PredicTcell™ model, Tevogen reported:
- Recall improved from 87% to 92% (the model is finding more of the right targets)
- Precision improved from 40% to 48% (fewer incorrect predictions)
- Higher overall accuracy scores
- Increased true positives and reduced missed targets
- Dramatically expanded training sample size
Login to comment