No Priors: Artificial Intelligence | Technology | Startups Virtual Cell Models, Tahoe-100 and Data for AI-in-Bio with Vevo Therapeutics and the Arc Institute
44 snips
Feb 25, 2025 
In this engaging discussion, Nima Alidoust, CEO of Vevo Therapeutics, and Patrick Hsu, CEO of the Arc Institute, dive into the revolutionary Tahoe-100M dataset that is reshaping drug discovery. They explore the fascinating potential of virtual cell models and AI in understanding disease behaviors at a cellular level. The conversation highlights challenges in data collection and the critical need for high-quality datasets in biomedical research. They also discuss the importance of open-sourcing data to foster collaboration and innovation in the biotech field.
AI Snips
Chapters
Transcript
Episode notes
Virtual Cell Models vs. Protein Language Models
- Virtual cell models predict cellular behavior in disease and drug response.
- Protein language models predict structure and interactions, but lack biological context.
Importance of Perturbational Data
- Perturbational data reveals causal relationships between genes and cell states, not just correlation.
- This is crucial for truly understanding biological mechanisms and how cells respond to changes.
Scale of Tahoe 100
- Tahoe 100 dataset doubles existing single-cell RNA sequencing data, covering diverse cancer models and drug treatments.
- This scale enables machine learning applications in biology, moving beyond smaller, information-poor datasets.