Hi! My name is Ana-Maria Istrate, and I’m a Staff Research Scientist in AI/ML at the Chan Zuckerberg Initiative, working at the intersection of machine learning, biology, and reasoning. My work focuses on developing virtual cell models and reasoning-based ML frameworks that integrate knowledge from experimental data, language, and world models of biology. I’m particularly interested in how language as a modality interacts with other forms of biological representation. These ideas drive my current work on rBio and scGenePT, efforts I’ve led at CZI.
Previously, I built NLP models for mining scientific literature at scale, contributing to large-scale open-source datasets such as the CZ Software Mentions Dataset, Open Global Data Citation Corpus, and Global Biodata Resource Inventory. Before that, I worked in Software Engineering roles at at Amazon, after graduating from Stanford with degrees in Applied Math and Computer Science (with a Specialization in AI). I enjoy speaking publicly about virtual cell models and machine learning for science.
Email: anamariaistratedl [at] gmail [dot] com | | ORCID