CAESAR models for developmental toxicity.
Cassano A, Manganaro A, Martin T, Young D, Piclin N, Pintore M, Bigoni D, Benfenati E. · 2010
Read CAESAR models for developmental toxicity. by Cassano A, Manganaro A, Martin T, Young D, Piclin N, Pintore M, Bigoni D, Benfenati E. (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/europmc-pmc2913331.txt.
Description
Cassano and co-authors built in 2010 computer models that predict whether a chemical can harm a developing baby, for Europe's REACH chemical safety law. REACH demands assessment of thousands of market chemicals, and developmental toxicity testing is among the slowest, costliest, and most animal-heavy. Their CAESAR project trained quantitative structure-activity models, which infer toxicity from molecular structure, on curated experimental data.
Two models using different mathematics, a random forest and a fuzzy partitioning method, both classified chemicals well. The designers deliberately tuned them to minimize false negatives, the dangerous error of clearing a harmful chemical, even at the price of extra false alarms. The random forest model was placed in a free online application, so industry chemists and regulators can screen a structure in seconds before any animal test.
Catalog record
| CREATOR | Cassano A, Manganaro A, Martin T, Young D, Piclin N, Pintore M, Bigoni D, Benfenati E. |
|---|---|
| YEAR | 2010 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |