Studying and mitigating the effects of data drifts on ML model performance at the example of chemical toxicity data

Machine learning models are widely applied to predict molecular properties or the biological activity of small molecules on a specific protein. Models can be integrated in a conformal prediction (CP) framework which adds a calibration step to estimate the confidence of the predictions. CP models pre...

Descripción completa

Detalles Bibliográficos
Autores principales: Morger, Andrea, Garcia de Lomana, Marina, Norinder, Ulf, Svensson, Fredrik, Kirchmair, Johannes, Mathea, Miriam, Volkamer, Andrea
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9068909/
https://www.ncbi.nlm.nih.gov/pubmed/35508546
http://dx.doi.org/10.1038/s41598-022-09309-3

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9068909/
https://www.ncbi.nlm.nih.gov/pubmed/35508546
http://dx.doi.org/10.1038/s41598-022-09309-3

Ejemplares similares