Molecular representation
What information does a model need to reason about a molecule?
Explore representations that connect chemical structure to properties and interactions relevant to the research question.
Research / Pharmaceutical research
Explore molecules.
Investigate possibility.
Bringing AI and physical reasoning together to study molecular systems and inform experimental discovery.
The space of possible molecules is vast. A useful question makes it navigable.
Our research direction connects molecular representations, physical interactions, and the selection of informative experiments. The ambition is to help researchers reason about potential compounds in the context of a specific biological mechanism.
Questions guiding this frontier
Physical modeling
Where can a physical description improve an investigation?
Study how physical constraints and quantum descriptions of molecular systems can complement data-driven models, with methods chosen for a clearly defined purpose.
Experimental selection
Which molecular ideas deserve closer study?
Investigate ways to prioritize experiments that can clarify activity, selectivity, and practical development questions rather than optimize a single score in isolation.
The standard of evidence
Keep the claim
close to the evidence.
A computational prediction does not establish that a compound is safe or effective. This research direction is distinct from experimental validation, preclinical development, and clinical evaluation.
The next question
changes everything.
Bring a scientific challenge. Let’s explore what becomes possible when disciplines work together.
Start a collaboration