The combined focal loss and dice loss function improves the segmentation of beta-sheets in medium-resolution cryo-electron-microscopy density maps
Yongcheng Mu, Thu Nguyen, Bryan Hawickhorst, Willy Wriggers, Jiangwen Sun, Jing He · 2024
Read The combined focal loss and dice loss function improves the segmentation of beta-sheets in medium-resolution cryo-electron-microscopy density maps by Yongcheng Mu, Thu Nguyen, Bryan Hawickhorst, Willy Wriggers, Jiangwen Sun, Jing He (2024) 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-11590252.txt.
Description
Mu and coauthors improve neural detection of sheet structures in electron density maps. Many nets have been built to find protein structures in such maps. Standard loss functions suffer when classes are imbalanced. Sheet voxels are far rarer and harder than helix voxels.
Five loss functions were tested in one network design. The data set held 1,355 cropped map and structure pairs. A new loss blends focal and dice terms in one function. That blend gave the best overall detection accuracy. Sheet detection gained the most from the new loss. The method may sharpen protein model building.
Catalog record
| CREATOR | Yongcheng Mu, Thu Nguyen, Bryan Hawickhorst, Willy Wriggers, Jiangwen Sun, Jing He |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |