A general deep hybrid model for bioreactor systems: Combining first principles with deep neural networks

Pinto, José P.; Mestre, Mykaella; Ramos, João R. C.; Costa, Rafael S.; Striedner, Gerald; Oliveira, Rui

doi:10.1016/j.compchemeng.2022.107952

Cited by 30 publications

(55 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many different hybrid model architectures have been published. The vast majority of HANNs reviewed here are well-represented or are extensions of the general bioreactor hybrid model represented in Figure 1 [14][15][16][17][18][19] . This model is briefly reviewed for context.…”

Section: Hybrid Artificial Neural Network (Hann) Modelingmentioning

confidence: 99%

“…den layers. For further details, the reader is referred to Pinto et al, 2022 [19] . Lastly, the general bioreactor model (Eqs.1-2) may be easily adapted to a wide range of unit operations described by systems of ODEs.…”

Section: Hybrid Artificial Neural Network (Hann) Modelingmentioning

confidence: 99%

“…Another important point is that the hybrid model should not include "wrong" mechanisms or otherwise an off-set to the global optimum is observed. Recently, hybrid modeling of P. pastoris was revisited by Pinto et al ( 2022) using state-of-the-art deep learning methods [19] . FFNN networks with [33,34] .…”

Section: Microbial Culturementioning

confidence: 99%

“…Most of the hybrid modeling studies so far applied simple shallow neural networks. With a significant delay, hybrid modeling is now incorporating some of the advances in deep learning [19,64] . Pinto et al (2022) recently compared traditional shallow hybrid modeling (using the Levenberg-Marquardt training coupled with the indirect sensitivities, cross-validation and tanh activation function) with a novel hybrid deep modeling approach (using ADAM training, semidirect sensitivities, stochastic regularization, multiple hidden layers and ReLU activation functions) [19] .…”

Section: Research Gapmentioning

confidence: 99%

See 3 more Smart Citations

Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review

Agharafeie

Oliveira

Ramos

et al. 2023

Preprint

View full text Add to dashboard Cite

Due to the complexity of biological processes, developing model-based strategies for monitoring, optimization and control is nontrivial. Hybrid neural models, combining mechanistic modeling with artificial neural networks, have been reported as powerful tools for bioprocess applications. In this paper, a systematic literature review is presented focused on the application of hybrid neural models to bioprocesses by Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) over the last 30 years. This analysis showed that hybrid neural modeling has covered a wide range of microbial processes, animal cells, mixed microbial cultures, and enzyme biocatalysis. Hybrid neural models have been mainly applied for predictive modeling/process analysis, process monitoring/software sensors, open- and closed-loop control, batch-to-batch control, model predictive control, intensified design of experiments, process analytical technology, quality-by-design, and more recently, digital twins. Hybrid modeling experienced a decline in the number of publications after a peak in 2004 and is now surging again. A “model scale” research gap was identified, which will likely narrow by a better integration with deep learning and systems biology in the near future. The biopharma sector is currently a major driver but applications to biologics quality attributes (e.g. glycosylation), new modalities and downstream unit operations are significant research gaps.

show abstract

Section: Hybrid Artificial Neural Network (Hann) Modelingmentioning

confidence: 99%

Section: Hybrid Artificial Neural Network (Hann) Modelingmentioning

confidence: 99%

Section: Microbial Culturementioning

confidence: 99%

Section: Research Gapmentioning

confidence: 99%

See 2 more Smart Citations

Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review

Agharafeie

Oliveira

Ramos

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…They must be established from data during the training process. A typical example is the combination of material balance equations over biochemical species in the form of a system of ordinary differential equations (ODEs)—parametric function easily established from prior knowledge—with an artificial neural network (ANN) to model partially or completely the biologic kinetics—non-parametric function of a more complex part of the model lacking mechanistic understanding ( Pinto et al , 2019 , 2022 ).…”

Section: Introductionmentioning

confidence: 99%

SBML2HYB: a Python interface for SBML compatible hybrid modeling

et al. 2023

Self Cite

View full text Add to dashboard Cite

Summary Here we present sbml2hyb, an easy-to-use standalone Python tool that facilitates the conversion of existing mechanistic models of biological systems in Systems Biology Markup Language (SBML) into hybrid semiparametric models that combine mechanistic functions with machine learning (ML). The so-formed hybrid models can be trained and stored back in databases in SBML format. The tool supports a user-friendly export interface with an internal format validator. Two case studies illustrate the use of the sbml2hyb tool. Additionally, we describe HMOD, a new model format designed to support and facilitate hybrid models building. It aggregates the mechanistic model information with the ML information and follows as close as possible the SBML rules. We expect the sbml2hyb tool and HMOD to greatly facilitate the widespread usage of hybrid modeling techniques for biological systems analysis. Availability and implementation The Python interface, source code and the example models used for the case studies are accessible at: https://github.com/r-costa/sbml2hyb. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Noise aware parameter estimation in bioprocesses: Using neural network surrogate models with nonuniform data sampling

Weir,

Mathias,

Corbett

et al. 2024

AIChE Journal

View full text Add to dashboard Cite

This article demonstrates a parameter estimation technique for bioprocesses that utilizes measurement noise in experimental data to determine credible intervals on parameter estimates, with this information of potential use in prediction, robust control, and optimization. To determine these estimates, the work implements Bayesian inference using nested sampling, presenting an approach to develop neural network‐ (NN) based surrogate models. To address challenges associated with nonuniform sampling of experimental measurements, an NN structure is proposed. The resultant surrogate model is utilized within a Nested Sampling Algorithm that samples possible parameter values from the parameter space and uses the NN to calculate model output for use in the likelihood function based on the joint probability distribution of the noise of output variables. This method is illustrated against simulated data, then with experimental data from a Sartorius fed‐batch bioprocess. Results demonstrate the feasibility of the proposed technique to enable rapid parameter estimation for bioprocesses.

show abstract

A general deep hybrid model for bioreactor systems: Combining first principles with deep neural networks

Cited by 30 publications

References 34 publications

Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review

Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review

SBML2HYB: a Python interface for SBML compatible hybrid modeling

Noise aware parameter estimation in bioprocesses: Using neural network surrogate models with nonuniform data sampling

Contact Info

Product

Resources

About