Automated Discovery of Novel Drug Formulations Using Predictive Iterated High Throughput Experimentation
Filippo Caschera, Gianluca Gazzola, Mark A. Bedau et al. · 2010
Read Automated Discovery of Novel Drug Formulations Using Predictive Iterated High Throughput Experimentation by Filippo Caschera, Gianluca Gazzola, Mark A. Bedau et al. (2010) 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-0008546.txt.
Description
Filippo Caschera and co-authors use robots to find new drug mixes in a 2010 PLOS ONE paper. Their test case is a liposomal drug, a drug wrapped in tiny fat bubbles. Such a mix has many parts that act on each other. The parts can help or hinder each other in ways no one can predict. Trial and error by hand would be very slow. The team use a loop of fast tests guided by a computer model.
Each round of tests teaches the model which mixes work best. The model then picks the next round of mixes to try. The loop finds good mixes far faster than blind search. The same method could help tune other complex mixes.
Catalog record
| CREATOR | Filippo Caschera, Gianluca Gazzola, Mark A. Bedau et al. |
|---|---|
| YEAR | 2010 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PLOS ONE |
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0008546