Define the need.
Identify the patients, where current treatment falls short, and what a new therapy must achieve to make a meaningful difference.
The agentic biotech
Biologics expertise. AI agents. A clearer path from clinical evidence to therapeutic opportunity.
Explore our approachThe question that comes first
The choice of what to make deserves the same rigor as the science of making it.
Hecate Bio starts with the patients, the clinical evidence and the unmet need. We combine experience in biologics development with AI agents to evaluate opportunities before committing to a target or molecular format.
Our goal: choose a differentiated therapeutic opportunity, understand the risks, and direct experiments toward the questions that matter.
Our approach
Each decision builds on the one before it—and can challenge it when the evidence points elsewhere.
Identify the patients, where current treatment falls short, and what a new therapy must achieve to make a meaningful difference.
Read the clinical landscape, biology and competitive field together. Assess individual targets and combinations, with the evidence behind each judgment.
Define the therapeutic requirements first. Use them to guide the molecular format and the experiments needed to resolve uncertainty.
The Scientific Mind Engine
The Scientific Mind Engine is Hecate’s internal system for evaluating therapeutic opportunities. AI agents organize evidence and challenge assumptions; human scientific judgment sets direction.
Facts are linked to their sources. Judgment is identified as judgment. Unknowns stay visible.
Clinical results help us locate promising biology nearby—and distinguish it from crowded or untested ground.
We are building toward molecular specifications and experimental plans that connect each experiment to a decision.
Today, the engine supports target evaluation and target product profiles. Molecular specification and experimental planning are the next layers in development.
Founder
Founder, Hecate Bio
Drew brings fifteen years of experience in drug discovery and development, including a decade working on bispecifics, antibody–drug conjugates and T-cell engagers.
At Merck, he served as Senior Director of Machine Learning and Protein Engineering and built the in-silico discovery function. Previously, he worked on ADCs and T-cell engagers at Seagen and built the protein engineering group at Systimmune.
His experience spans structural biology, protein engineering, translational research and machine learning—from target selection through clinical development.
Get in touch
For scientific collaborations, partnerships and investor conversations.