Multi-task gradient boosting with multi-modal molecular representations for simultaneous prediction of drug clearance and volume of distribution
Gyu-Seong Lee, Hyeong-Gyu Choi, Dae-Keun Park, Hyo Young Kim · 2026
Read Multi-task gradient boosting with multi-modal molecular representations for simultaneous prediction of drug clearance and volume of distribution by Gyu-Seong Lee, Hyeong-Gyu Choi, Dae-Keun Park, Hyo Young Kim (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/plos-pone-0348173.txt.
Description
Gyu-Seong Lee and colleagues tackle two linked questions in early drug development in this 2026 PLOS ONE paper: how fast the body clears a drug, and how widely it spreads through tissues. Both properties decide dosing, and they influence each other, yet most prediction tools treat them separately and use only one kind of molecular description.
Their multi-task boosting model predicts both at once, blending three views of a molecule: learned structural patterns, computed descriptors, and measured lab properties. It beat single-task versions on both targets across repeated tests, with one weak spot for very low distribution volumes. Predicting the pair together could save costly lab work when screening candidate medicines.
Catalog record
| CREATOR | Gyu-Seong Lee, Hyeong-Gyu Choi, Dae-Keun Park, Hyo Young Kim |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41954 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |