Statistical monitoring of heteroscedastic dose-response profiles from high-throughput screening

Abstract

In pharmaceutical drug discovery and agricultural crop product discovery, in vivo bioassay experiments are used to identify promising compounds for further research. The reproducibility and accuracy of the bioassay is crucial to be able to correctly distinguish between active and inactive compounds. In the case of agricultural product discovery, a replicated dose-response of commercial crop protection products is assayed and used to monitor test quality. The activity of these compounds on the test organisms, the weeds, insects, or fungi, is characterized by a dose-response curve measured from the bioassay. These curves are used to monitor the quality of the bioassays. If undesirable conditions in the bioassay arise, such as equipment failure or problems with the test organisms, then a bioassay monitoring procedure is needed to quickly detect such issues. In this paper we illustrate a proposed nonlinear profile monitoring method to monitor the variability of multiple assays, the adequacy of the dose-response model chosen, and the estimated dose-response curves for aberrant cases in the presence of heteroscedasticity. We illustrate these methods with in vivo bioassay data collected over one year from DuPont Crop Protection.

Statistical monitoring of nonlinear product and process quality profiles

“…multivariate normal random vectors with mean vector zero and covariance matrix σ 2 I. For an example of profile monitoring where the covariance matrix is allowed to take on a more general form, see Williams et al 4 . Jensen et al 9 proposed a control chart based on the F -distribution to monitor the k + 1 parameters (coefficients) from a multiple linear regression model for Phase II applications.…”

A Change-Point Approach for Phase-I Analysis in Multivariate Profile Monitoring and Diagnosis

“…See, for instance, Williams et al (2007) and the references therein. Letλ k andυ k (•) denote the corresponding eigenfunctions and eigenvalues ofĉ(u, u ), respectively.…”

“…Profile monitoring has been extensively studied in statistical process control (SPC) and several methods have been developed for monitoring linear and nonlinear profile data. Some examples include the use of multivariate control charts for monitoring linear and nonlinear regression coefficients (Kang and Albin 2000;Mahmoud and Woodall 2004;Zou et al 2007;Williams et al 2007), monitoring methods based on mixed-effect models (Jensen et al 2008;Paynabar et al 2012), wavelet methods (Jin and Shi 1999;Chicken et al 2009;Paynabar and Jin 2011), and nonparametric regression methods . Extensive discussion about various research problems on profile monitoring can be found in Woodall (2007), Noorossana et al (2011) and Qiu (2014, Chap 10).…”

Understanding the abnormal brain activity in epilepsy as a potential predictor of the onset of an epileptic seizure

“…Previous studies modelled the blood changes as a convolution of the eeg discharges with a canonical hemodynamic response function in the general linear model framework [89]. Also, fmri measurements can be modelled by a mathematical function in n dimensional space [90,91,92,81,93]. Here we model the change in blood oxygenation (measured by fmri) as a function of the eeg discharge.…”

“…For example, to estimate the dose-response curve of a manufactured drug, once a batch of the drug is produced, several doses of the drug are administered to patients and the responses are measured. The resultant dose-response curve summarises the quality of the particular batch of the drug, indicating the maximal effective response, minimal effective response, and the rate in which the response change between the two [81]. Another example of a process characterised by a profile is a semiconductor manufacturing quality control problem involving calibration in which the performance of the mass flow controller is monitored by a linear function [82].…”