Training PBertKla on an Integrated Multi-Source Dataset with a Machine-Learning Layer for Lysine Lactylation Site Prediction
Seung Beom Jin, Junghee Park, Summer Dabin Lee, Ji Hye Han, Seung-Hyun Myung, Kichul Park, Jisoo Yun · 2026
Read Training PBertKla on an Integrated Multi-Source Dataset with a Machine-Learning Layer for Lysine Lactylation Site Prediction by Seung Beom Jin, Junghee Park, Summer Dabin Lee, Ji Hye Han, Seung-Hyun Myung, Kichul Park, Jisoo Yun (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/PMC13362394.txt.
Description
Seung Beom Jin and co-authors present a 2026 study on a tool that predicts where a chemical tag called lactylation lands on proteins. The tag affects how cells use energy and switch genes, but finding its sites by lab tests is slow. The team retrained an existing protein model and added a light machine learning layer on top.
They also built the largest checked dataset for this tag so far, with 26,034 samples from nine sources. On blind tests the tool scored about 0.91 for sorting true sites from false ones, matching the best rival tool. Strict checks with no overlap between training and test data held up, so the tool looks fit for real lab use.
Catalog record
| CREATOR | Seung Beom Jin, Junghee Park, Summer Dabin Lee, Ji Hye Han, Seung-Hyun Myung, Kichul Park, Jisoo Yun |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38042 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |