Dataset Information

Data-driven multi-objective optimization via grid compatible simplex technique and desirability approach for challenging high throughput chromatography applications.

ABSTRACT: Recently, a grid compatible Simplex variant has been demonstrated to identify optima consistently and rapidly in challenging high throughput (HT) applications in early bioprocess development. Here, this method is extended by deploying it to multi-objective optimization problems. Three HT chromatography case studies are presented, each posing challenging early development situations and including three responses which were amalgamated by the adoption of the desirability approach. The suitability of a design of experiments (DoE) methodology per case study, using regression analysis in addition to the desirability approach, was evaluated for a large number of weights and in the presence of stringent and lenient performance requirements. Despite the adoption of high-order models, this approach had low success in identification of the optimal conditions. For the deployment of the Simplex approach, the deterministic specification of the weights of the merged responses was avoided by including them as inputs in the formulated multi-objective optimization problem, facilitating this way the decision making process. This, and the ability of the Simplex method to locate optima, rendered the presented approach highly successful in delivering rapidly operating conditions, which belonged to the Pareto set and offered a superior and balanced performance across all outputs compared to alternatives. Moreover, its performance was relatively independent of the starting conditions and required sub-minute computations despite its higher order mathematical functionality compared to DoE techniques. These evidences support the suitability of the grid compatible Simplex method for early bioprocess development studies involving complex data trends over multiple responses. © 2018 The Authors Biotechnology Progress published by Wiley Periodicals, Inc. on behalf of American Institute of Chemical Engineers Biotechnol. Prog., 34:1393-1406, 2018.

SUBMITTER: Konstantinidis S

PROVIDER: S-EPMC6585819 | biostudies-other | 2018 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Data-driven multi-objective optimization via grid compatible simplex technique and desirability approach for challenging high throughput chromatography applications.

Konstantinidis Spyridon S Welsh John P JP Titchener-Hooker Nigel J NJ Roush David J DJ Velayudhan Ajoy A

Biotechnology progress 20181009 6

Recently, a grid compatible Simplex variant has been demonstrated to identify optima consistently and rapidly in challenging high throughput (HT) applications in early bioprocess development. Here, this method is extended by deploying it to multi-objective optimization problems. Three HT chromatography case studies are presented, each posing challenging early development situations and including three responses which were amalgamated by the adoption of the desirability approach. The suitability ...[more]

PMID: 30294895

Similar Datasets

Project description:Objective.Deep brain stimulation (DBS) is an effective treatment for Parkinson's disease (PD) but its success depends on a time-consuming process of trial-and-error to identify the optimal stimulation settings for each individual patient. Data-driven optimization algorithms have been proposed to efficiently find the stimulation setting that maximizes a quantitative biomarker of symptom relief. However, these algorithms cannot efficiently take into account stimulation settings that may control symptoms but also cause side effects. Here we demonstrate how multi-objective data-driven optimization can be used to find the optimal trade-off between maximizing symptom relief and minimizing side effects.Approach.Cortical and motor evoked potential data collected from PD patients during intraoperative stimulation of the subthalamic nucleus were used to construct a framework for designing and prototyping data-driven multi-objective optimization algorithms. Using this framework, we explored how these techniques can be applied clinically, and characterized the design features critical for solving this optimization problem. Our two optimization objectives were to maximize cortical evoked potentials, a putative biomarker of therapeutic benefit, and to minimize motor potentials, a biomarker of motor side effects.Main Results.Using thisin silicodesign framework, we demonstrated how the optimal trade-off between two objectives can substantially reduce the stimulation parameter space by 61 ± 19%. The best algorithm for identifying the optimal trade-off between the two objectives was a Bayesian optimization approach with an area under the receiver operating characteristic curve of up to 0.94 ± 0.02, which was possible with the use of a surrogate model and a well-tuned acquisition function to efficiently select which stimulation settings to sample.Significance.These findings show that multi-objective optimization is a promising approach for identifying the optimal trade-off between symptom relief and side effects in DBS. Moreover, these approaches can be readily extended to newly discovered biomarkers, adapted to DBS for disorders beyond PD, and can scale with the development of more complex DBS devices.

Dataset Information

Data-driven multi-objective optimization via grid compatible simplex technique and desirability approach for challenging high throughput chromatography applications.

Publications

Data-driven multi-objective optimization via grid compatible simplex technique and desirability approach for challenging high throughput chromatography applications.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets