Modelling In vitro Mutagenicity Using Multi-Task Deep Learning and REACH Data

Under REACH, mutagenicity assessment relies on in vitro testing (gene mutation test in bacteria and/or mammalian cells, as well as chromosomal aberration or micronucleus assays in mammalian cells) followed by in vivo testing if necessary. This study explored the...

Full description

Saved in:

Bibliographic Details
Main Author:	Panagiotis G. Karamertzanis (1274853) (author)
Other Authors:	Mike Rasenberg (5570368) (author), Imran Shah (49110) (author), Grace Patlewicz (1845178) (author)
Published:	2025
Subjects:	Microbiology Genetics Biological Sciences not elsewhere classified validation balanced accuracy specific bacterial strains reduced molecular embeddings molecular structure representation metabolic activation modes gene mutation detection 73 – 84 72 – 78 several public sources predicted negative genotoxicity mutagenicity assessment relies gene mutation test extensive genotoxicity dataset task model achieved task deep learning least 200 positives mutagenicity using multi test sets stringent assessment positive genotoxicity literature sources distinguish positives vivo </ vitro </ study explored mammalian cells inherent correlation improvements ranging genotoxicity information create multi construct external cluster structures chromosomal aberration chemical fingerprints average 8 assay outcomes also used also retrieved 200 negatives 000 substances
Tags:	Add Tag No Tags, Be the first to tag this record!

Modelling <i>In vitro</i> Mutagenicity Using Multi-Task Deep Learning and REACH Data

Similar Items