ELISA validation in the pharmaceutical industry: a mixed-effects models approach with R

In the first part of this work, a methodology to gain insight into ELISA performance and finally obtain accuracy and precision estimates using linear mixed effects models is presented. Also, in the second part, non-linear mixed effects models are applied as a tool to establish parallelism between te...

Descripción completa

Detalles Bibliográficos
Autor: Mayola Coromina, Albert
Tipo de recurso: tesis de maestría
Fecha de publicación:2018
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/91346
Acceso en línea:http://hdl.handle.net/10609/91346
Access Level:acceso abierto
Palabra clave:mixed effects models
ELISA
models d'efectes mixtes
modelos de efectos mixtos
Bioinformatics -- TFM
Bioinformàtica -- TFM
Bioinformática -- TFM
Descripción
Sumario:In the first part of this work, a methodology to gain insight into ELISA performance and finally obtain accuracy and precision estimates using linear mixed effects models is presented. Also, in the second part, non-linear mixed effects models are applied as a tool to establish parallelism between test and reference product preparations when conducting full dose-response assays. Overall, both linear and non-linear mixed effects have demonstrated to be complex yet extremely powerful and versatile tools. Great knowledge on the impact of potential nuisance factors has been extracted using the workflows presented and more precise estimates of important assay parameters have been established. The work has been developed in R statistical programming language which contributes to the potential of the framework itself.