Transcription factor prediction using protein 3D secondary structures
Jeanine Liebold, Fabian Neuhaus, Janina Geiser, Stefan Kurtz, Jan Baumbach, Khalique Newaz, Pier Luigi Martelli · 2025
Read Transcription factor prediction using protein 3D secondary structures by Jeanine Liebold, Fabian Neuhaus, Janina Geiser, Stefan Kurtz, Jan Baumbach, Khalique Newaz, Pier Luigi Martelli (2025) 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-11769678.txt.
Description
Jeanine Liebold and co-authors predict transcription factors from a protein's three-dimensional shape rather than its sequence alone. The head of the text dates the work to 2024, though the catalog lists 2025. Transcription factors switch genes on and off by binding DNA. Older predictors flag any protein carrying a known binding domain, so they miss genuinely new factors with unfamiliar domains.
Their deep learning method, StrucTFactor, is the first to use 3D secondary structure for this task. Tested on about 525,000 proteins across twelve data sets, it beat current sequence-based methods with clear statistical confidence. The gain over the closest rival reached seventeen percent on a balanced accuracy measure. Structure, the authors argue, carries signal that sequence hides.
Catalog record
| CREATOR | Jeanine Liebold, Fabian Neuhaus, Janina Geiser, Stefan Kurtz, Jan Baumbach, Khalique Newaz, Pier Luigi Martelli |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |