Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling
Foam-related parameters are associated with beer quality and dependent, among others, on the protein content. This study aimed to develop a machine learning (ML) model to predict the pattern and presence of 54 proteins. Triplicates of 24 beer samples were analyzed through proteomics. Furthermore, sa...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Beverages |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5710/6/2/28 |
id |
doaj-3c15d4b7fc5240369166accb9517ecb8 |
---|---|
record_format |
Article |
spelling |
doaj-3c15d4b7fc5240369166accb9517ecb82020-11-25T02:40:34ZengMDPI AGBeverages2306-57102020-05-016282810.3390/beverages6020028Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning ModelingClaudia Gonzalez Viejo0Christopher H. Caboche1Edward D. Kerr2Cassandra L. Pegg3Benjamin L. Schulz4Kate Howell5Sigfredo Fuentes6School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Parkville, VIC 3010, AustraliaSchool of Chemistry and Molecular Biosciences, The University of Queensland, St. Lucia, QLD 4072, AustraliaSchool of Chemistry and Molecular Biosciences, The University of Queensland, St. Lucia, QLD 4072, AustraliaSchool of Chemistry and Molecular Biosciences, The University of Queensland, St. Lucia, QLD 4072, AustraliaSchool of Chemistry and Molecular Biosciences, The University of Queensland, St. Lucia, QLD 4072, AustraliaSchool of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Parkville, VIC 3010, AustraliaSchool of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Parkville, VIC 3010, AustraliaFoam-related parameters are associated with beer quality and dependent, among others, on the protein content. This study aimed to develop a machine learning (ML) model to predict the pattern and presence of 54 proteins. Triplicates of 24 beer samples were analyzed through proteomics. Furthermore, samples were analyzed using the RoboBEER to evaluate 15 physical parameters (color, foam, and bubbles), and a portable near-infrared (NIR) device. Proteins were grouped according to their molecular weight (MW), and a matrix was developed to assess only the significant correlations (<i>p</i> < 0.05) with the physical parameters. Two ML models were developed using the NIR (Model 1), and RoboBEER (Model 2) data as inputs to predict the relative quantification of 54 proteins. Proteins in the 0–20 kDa group were negatively correlated with the maximum volume of foam (MaxVol; r = −0.57) and total lifetime of foam (TLTF; r = −0.58), while those within 20–40 kDa had a positive correlation with MaxVol (r = 0.47) and TLTF (r = 0.47). Model 1 was not as accurate (testing r = 0.68; overall r = 0.89) as Model 2 (testing r = 0.90; overall r = 0.93), which may serve as a reliable and affordable method to incorporate the relative quantification of important proteins to explain beer quality.https://www.mdpi.com/2306-5710/6/2/28proteomicsartificial neural networksroboticsartificial intelligence |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Claudia Gonzalez Viejo Christopher H. Caboche Edward D. Kerr Cassandra L. Pegg Benjamin L. Schulz Kate Howell Sigfredo Fuentes |
spellingShingle |
Claudia Gonzalez Viejo Christopher H. Caboche Edward D. Kerr Cassandra L. Pegg Benjamin L. Schulz Kate Howell Sigfredo Fuentes Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling Beverages proteomics artificial neural networks robotics artificial intelligence |
author_facet |
Claudia Gonzalez Viejo Christopher H. Caboche Edward D. Kerr Cassandra L. Pegg Benjamin L. Schulz Kate Howell Sigfredo Fuentes |
author_sort |
Claudia Gonzalez Viejo |
title |
Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling |
title_short |
Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling |
title_full |
Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling |
title_fullStr |
Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling |
title_full_unstemmed |
Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling |
title_sort |
development of a rapid method to assess beer foamability based on relative protein content using robobeer and machine learning modeling |
publisher |
MDPI AG |
series |
Beverages |
issn |
2306-5710 |
publishDate |
2020-05-01 |
description |
Foam-related parameters are associated with beer quality and dependent, among others, on the protein content. This study aimed to develop a machine learning (ML) model to predict the pattern and presence of 54 proteins. Triplicates of 24 beer samples were analyzed through proteomics. Furthermore, samples were analyzed using the RoboBEER to evaluate 15 physical parameters (color, foam, and bubbles), and a portable near-infrared (NIR) device. Proteins were grouped according to their molecular weight (MW), and a matrix was developed to assess only the significant correlations (<i>p</i> < 0.05) with the physical parameters. Two ML models were developed using the NIR (Model 1), and RoboBEER (Model 2) data as inputs to predict the relative quantification of 54 proteins. Proteins in the 0–20 kDa group were negatively correlated with the maximum volume of foam (MaxVol; r = −0.57) and total lifetime of foam (TLTF; r = −0.58), while those within 20–40 kDa had a positive correlation with MaxVol (r = 0.47) and TLTF (r = 0.47). Model 1 was not as accurate (testing r = 0.68; overall r = 0.89) as Model 2 (testing r = 0.90; overall r = 0.93), which may serve as a reliable and affordable method to incorporate the relative quantification of important proteins to explain beer quality. |
topic |
proteomics artificial neural networks robotics artificial intelligence |
url |
https://www.mdpi.com/2306-5710/6/2/28 |
work_keys_str_mv |
AT claudiagonzalezviejo developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling AT christopherhcaboche developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling AT edwarddkerr developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling AT cassandralpegg developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling AT benjaminlschulz developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling AT katehowell developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling AT sigfredofuentes developmentofarapidmethodtoassessbeerfoamabilitybasedonrelativeproteincontentusingrobobeerandmachinelearningmodeling |
_version_ |
1724780746677157888 |