De novo protein design—From new structures to programmable functions
Problem
Designing new proteins with shapes and molecular functions not found in nature, requiring precise control over conformation and molecular recognition.
Why it matters
Designed proteins could enable new medicines, materials, and synthetic cellular functions.
What the AI did
AI methods trained on large sequence and structure datasets can 'write' new proteins de novo, combined with physics-based modeling and engineering principles.
Results
not stated in source
Impact
AI-designed protein folds and assemblies are experimentally achievable, though many challenges remain unsolved.
Record
| Venue | Cell |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Tanja Kortemme |
| Citations | 344 (OpenAlex, at import time) |
| References | 130 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1016/j.cell.2023.12.028 |
| Open access | hybrid |
| Keywords | de novo protein design, artificial intelligence, protein folds, molecular recognition, synthetic biology |
Importance rating
major — millions of lives, an industry or a field
AI can write proteins with new shapes and molecular functions de novo, a foundational capability for protein science with potential in synthetic cellular functions; abstract states no scale.