This Project Grant awarded by the National Science Foundation (CFDA 47.074 - Biological Sciences) provides $980,943 to Purdue University to develop new artificial intelligence (AI) tools for interpreting cryogenic electron microscopy (cryo-EM) data into accurate 3D molecular structures and assessing their quality. The key objectives are to: (1) create a deep learning-based method for constructing protein-DNA/RNA complex structures and identifying unknown proteins and nucleic acids in cryo-EM maps; (2) expand the model quality assessment score framework to evaluate backbone, side-chain, and non-protein molecular errors in high-resolution EM maps; and (3) develop a new biomolecular modeling and assembly method for medium to low-resolution cryo-EM maps. The expected outcomes include open-source software, a publicly accessible online computing web service, and an expanded quality-assessment database. These advancements aim to overcome current limitations in biomolecular modeling for cryo-EM data, which is crucial for understanding how biomolecules function and accelerating drug discovery efforts. The award period is from August 1, 2025 to July 31, 2029.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $0 | 7/14/25 | ||
| Not listed | $980.9k | 7/11/25 |