Robust parameter estimation and identifiability analysis with hybrid neural ordinary differential equations in computational biology
Stefano Giampiccolo, Federico Reali, Anna Fochesato, Giovanni Iacca, Luca Marchetti · 2024
Read Robust parameter estimation and identifiability analysis with hybrid neural ordinary differential equations in computational biology by Stefano Giampiccolo, Federico Reali, Anna Fochesato, Giovanni Iacca, Luca Marchetti (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-11604934.txt.
Description
Stefano Giampiccolo, Federico Reali, Anna Fochesato, Giovanni Iacca, and Luca Marchetti fit biology models that are only partly known in a 2024 paper. Parameter estimation is a core task in computational biology. Often only part of a system's structure is known at all. Their method embeds the known part in neural differential equations.
Neural parts fill in the unknown pieces of the system. Two risks come with that freedom in fitting. Search may miss the best fit in a wide space. Flexible nets may also hide which parameters truly matter. The team treats key parameters as settings for global search. A later check then tests which ones can be pinned down. Three test cases mimic noisy, real-world data.
Catalog record
| CREATOR | Stefano Giampiccolo, Federico Reali, Anna Fochesato, Giovanni Iacca, Luca Marchetti |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 98 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |