Graph identification of proteins in tomograms (GRIP‐Tomo) 2.0: Topologically aware classification for proteins
Chengxuan Li, August George, Reece Neff, Doo Nam Kim, Trevor Moser, Kate Baldwin, Malio Nelson, Arsam Firoozfar, James E. Evans, Margaret S. Cheung · 2026
Read Graph identification of proteins in tomograms (GRIP‐Tomo) 2.0: Topologically aware classification for proteins by Chengxuan Li, August George, Reece Neff, Doo Nam Kim, Trevor Moser, Kate Baldwin, Malio Nelson, Arsam Firoozfar, James E. Evans, Margaret S. Cheung (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13454385.txt.
Description
Chengxuan Li and nine co-authors present a faster, smarter tool for finding proteins in cryo-electron tomography images, in a research paper from 2026. This imaging method shows molecules in near-native settings, but its 3D volumes are noisy and costly to interpret, above all for small proteins.
Their pipeline, GRIP-Tomo 2.0, reads the shape-based fingerprints that proteins leave in a volume. Upgrades include synthetic training images with realistic noise, graph-based feature extraction, and high-performance computing speedups. Accuracy topped ninety percent on synthetic data and eighty percent on real samples. The authors see it as a step toward automated visual proteomics.
Catalog record
| CREATOR | Chengxuan Li, August George, Reece Neff, Doo Nam Kim, Trevor Moser, Kate Baldwin, Malio Nelson, Arsam Firoozfar, James E. Evans, Margaret S. Cheung |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 74 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |