SBML2HYB: a Python interface for SBML compatible hybrid modeling

Pinto, José P.; Costa, Rafael S.; Alexandre, Leonardo; Ramos, João R. C.; Oliveira, Rui

doi:10.1093/bioinformatics/btad044

Cited by 6 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SBML2HYB python package was adopted to read SBML models, redesign to hybrid models and to store in model databases [24]. This freely available python package converts existing systems biology models stored in databases in SBML format into hybrid models that combine mechanistic equations and deep neural networks (currently limited to FFNNs).…”

Section: Interfacing With Sbml Databases and Sbml Modeling Toolsmentioning

confidence: 99%

“…The resulting hybrid models in SBML format can be simulated, analyzed, trained with existing tools such as MATLAB and COPASI [29] or special purpose tools with training algorithms for hybrid models that are able to read SBML files. For further details the reader is referred to [24].…”

Section: Interfacing With Sbml Databases and Sbml Modeling Toolsmentioning

confidence: 99%

“…Here, we propose a hybrid modeling framework that is SBML compatible. A previously published python package, SBML2HYB, is used to convert existing systems biology models into hybrid models and vice-versa [24]. The so-formed hybrid models are trained with a deep learning algorithm based on ADAM, stochastic regularization and semidirect sensitivity equations [25].…”

Section: Introductionmentioning

confidence: 99%

“…Step 3: A feedforward neural network (FFNN) was inserted in the mechanistic model and converted to the HMOD format using the SBML2HYB python tool, freely available in Pinto et al [24]. The size of the FFNN and interface with the mechanistic model depended on the case study.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A General SBML Compatible Hybrid Modeling Framework: Combining Biochemical Mechanisms with Deep Neural Networks for Systems Biology Applications

Pinto¹,

Ramos²,

Costa³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper we propose a computational framework that merges mechanistic modeling with deep neural networks obeying the Systems Biology Markup Language (SBML) standard. Over the last 20 years, the systems biology community has developed a large number of mechanistic models in SBML that are currently stored in public databases. With the proposed framework, existing SBML mechanistic models may be upgraded to hybrid systems through the incorporation of deep neural networks into the model core, using a freely available python tool. The so-formed hybrid mechanistic/neural network models are trained with a deep learning algorithm based on the adaptive moment estimation method (ADAM), stochastic regularization and semidirect sensitivity equations. The trained hybrid models are encoded in SBML and stored back in model databases, where they can be further analyzed as regular SBML models. The application of this approach is illustrated with three well-known case studies: the threonine synthesis model in Escherichia coli, the P58IPK signal transduction model, and the Yeast glycolytic oscillations model. The proposed framework is expected to greatly facilitate the widespread use of hybrid modeling techniques for systems biology applications.

show abstract

Section: Interfacing With Sbml Databases and Sbml Modeling Toolsmentioning

confidence: 99%

Section: Interfacing With Sbml Databases and Sbml Modeling Toolsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A General SBML Compatible Hybrid Modeling Framework: Combining Biochemical Mechanisms with Deep Neural Networks for Systems Biology Applications

Pinto¹,

Ramos²,

Costa³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Here, we propose a hybrid modeling framework that combines both modeling approaches obeying to the SBML standard. A previously published python package, SBML2HYB, is used to convert existing systems biology models into hybrid models and vice versa [36]. The so-formed hybrid models are trained with a deep learning algorithm based on ADAM, stochastic regularization and semidirect sensitivity equations [37].…”

Section: Introductionmentioning

confidence: 99%

A General Hybrid Modeling Framework for Systems Biology Applications: Combining Mechanistic Knowledge with Deep Neural Networks under the SBML Standard

Pinto

Ramos

Costa

et al. 2023

Self Cite

View full text Add to dashboard Cite

In this paper, a computational framework is proposed that merges mechanistic modeling with deep neural networks obeying the Systems Biology Markup Language (SBML) standard. Over the last 20 years, the systems biology community has developed a large number of mechanistic models that are currently stored in public databases in SBML. With the proposed framework, existing SBML models may be redesigned into hybrid systems through the incorporation of deep neural networks into the model core, using a freely available python tool. The so-formed hybrid mechanistic/neural network models are trained with a deep learning algorithm based on the adaptive moment estimation method (ADAM), stochastic regularization and semidirect sensitivity equations. The trained hybrid models are encoded in SBML and uploaded in model databases, where they may be further analyzed as regular SBML models. This approach is illustrated with three well-known case studies: the Escherichia coli threonine synthesis model, the P58IPK signal transduction model, and the Yeast glycolytic oscillations model. The proposed framework is expected to greatly facilitate the widespread use of hybrid modeling techniques for systems biology applications.

show abstract