Metabolic pathway synthesis based on predicting compound transformable pairs by using neural classifiers with imbalanced data handling

Tongman, Sasiporn; Chanama, Suchart; Chanama, Manee; Plaimas, Kitiporn; Lursinsap, Chidchanok

doi:10.1016/j.eswa.2017.06.026

Cited by 6 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When used as a hybrid mechanism/data‐driven model, this tool ranked four different candidate pathways for pinocembrin production that matched closely with experimentally determined pinocembrin titers. To a similar end, a neural network model was recently constructed to identify whether or not a given reaction can occur in an E. coli host . This work validated a unique approach to a data imbalance problem (i.e., far more reactions are infeasible than feasible) through the generation of synthetic data at “borders” between positive‐ and negative‐labeled samples.…”

Section: Review Of Instances Of Data‐driven Me Effortsmentioning

confidence: 92%

Systems Metabolic Engineering Meets Machine Learning: A New Era for Data‐Driven Metabolic Engineering

Presnell

Alper

2019

Biotechnology Journal

View full text Add to dashboard Cite

The recent increase in high‐throughput capacity of ‘omics datasets combined with advances and interest in machine learning (ML) have created great opportunities for systems metabolic engineering. In this regard, data‐driven modeling methods have become increasingly valuable to metabolic strain design. In this review, the nature of ‘omics is discussed and a broad introduction to the ML algorithms combining these datasets into predictive models of metabolism and metabolic rewiring is provided. Next, this review highlights recent work in the literature that utilizes such data‐driven methods to inform various metabolic engineering efforts for different classes of application including product maximization, understanding and profiling phenotypes, de novo metabolic pathway design, and creation of robust system‐scale models for biotechnology. Overall, this review aims to highlight the potential and promise of using ML algorithms with metabolic engineering and systems biology related datasets.

show abstract

Section: Review Of Instances Of Data‐driven Me Effortsmentioning

confidence: 92%

Systems Metabolic Engineering Meets Machine Learning: A New Era for Data‐Driven Metabolic Engineering

Presnell

Alper

2019

Biotechnology Journal

View full text Add to dashboard Cite

show abstract

“…Other than starting from an end-product perspective, researchers may also be interested in determining the possibilities of metabolite pairs transforming into each other, and the pathway required to do so. In this regard, an ANN-based approach has been developed ( Tongman et al, 2017 ). Further reviews of ML applications for de novo pathway design are available elsewhere ( Jeffryes et al, 2018 ; Kotera and Goto, 2016 ).…”

Section: Modelling Approachesmentioning

confidence: 99%

Metabolomics and modelling approaches for systems metabolic engineering

Khanijou

Kulyk

Bergès

et al. 2022

Metabolic Engineering Communications

View full text Add to dashboard Cite

“…The information and parameters are focused on chemical structure, experimental and physicochemical data, and toxicity. The toxicity data can concern living tissues, metabolic pathways [1], DNA [2,3], RNA, [4,5], gut microbia [6], or mitochondrial toxicity [7]. Chemoinformatics is also essential for the development of new drugs [8][9][10][11] and for the assessment of their toxicity [12].…”

Section: Introductionmentioning

confidence: 99%

Model of an Artificial Blastula for Assessing Development Toxicity

Muzika¹,

Górecki²

2024

Biomedical Engineering

View full text Add to dashboard Cite

We are concerned with computer simulations of a ring of 20 coupled CSTRs with glycolytic oscillatory reaction. Each CSTR represents an artificial cell, and the ring can be regarded as an artificial blastula. The cells are coupled to two adjacent CSTRs via the mass exchange of reagents. The glycolytic oscillatory reaction is simulated using the two-variable core model. Our work is focused on the classification of stationary discrete nonuniform concentration patterns (discrete Turing patterns). The control parameters in simulations are autocatalytic and inhibition rate coefficients, as well as the transport rate coefficients. We performed the analysis of stability and bifurcations of stationary states to identify the stationary states. The inflow of reagents into each CSTR was used to initiate a particular pattern. We propose a method to assess the morphogenetic toxicity of any chemical from a database by switching between patterns or between patterns and oscillations. Moreover, we investigated nonuniform patterns that create discrete concentration waves inside the ring of 20 coupled cells, which can trigger gastrulation.

show abstract

Metabolic pathway synthesis based on predicting compound transformable pairs by using neural classifiers with imbalanced data handling

Cited by 6 publications

References 41 publications

Systems Metabolic Engineering Meets Machine Learning: A New Era for Data‐Driven Metabolic Engineering

Systems Metabolic Engineering Meets Machine Learning: A New Era for Data‐Driven Metabolic Engineering

Metabolomics and modelling approaches for systems metabolic engineering

Model of an Artificial Blastula for Assessing Development Toxicity

Contact Info

Product

Resources

About