Research / Protein Science & Folding

Protein Science
& Folding

Structure prediction and de novo protein design tools decode how proteins fold, function, and fail — opening new frontiers for enzyme engineering, antibody design, and disease understanding.

The Protein Folding Problem — Solved, Then Extended

For 50 years, predicting a protein's 3D structure from its amino acid sequence was one of biology's hardest unsolved problems. AI cracked it — and in doing so, opened a larger question: not just how proteins fold, but how to design entirely new ones that evolution never explored.

Our protein science programs extend state-of-the-art structure prediction into protein design, enzyme engineering, and functional modeling — asking not only "what shape does this sequence make?" but "what sequence makes the shape we need?"

Structure Prediction
Atomic-Resolution Models in Seconds

Our structure models predict 3D protein conformations at sub-angstrom accuracy, faster than any experimental method — enabling structural insights across entire proteomes.

Protein Design
De Novo Protein Engineering

Generative protein models design novel sequences with specified functions — enzymes with new catalytic activities, antibodies with improved binding, and scaffold proteins with custom geometries.

Functional Modeling
Protein–Protein Interaction Mapping

AI models predict which proteins interact, where they bind, and how mutations disrupt those interactions — critical for understanding disease mechanisms and identifying therapeutic intervention points.

Active Protein Science Programs

01
FoldBase — Proteome-Scale Structure Repository
AI-powered structure prediction pipeline processing complete proteomes of human disease-associated pathogens and cell-type-specific human proteins, building an open structural database for therapeutic targeting.
Protein Science
02
DesignLab — Generative Protein Design Platform
Inverse folding and sequence generation models that produce novel protein sequences for specified 3D backbone geometries, enabling the design of antibodies, enzymes, and binding proteins from scratch.
Protein Science
03
EnzymeAI — Industrial Enzyme Engineering
Machine learning pipeline for engineering enzymes with enhanced thermostability, substrate specificity, and catalytic efficiency for applications in biomanufacturing, biosensing, and green chemistry.
Protein Science
04
InteractomeNet — Protein Interaction Network AI
Deep learning system mapping the human interactome at disease-specific resolution — predicting how mutations rewire interaction networks in cancer, neurodegeneration, and autoimmune conditions.
Protein Science
← All Research Areas All Programs
An initiative of the Odegard Foundation · Founded 2017 by Philip Odegard