Improving lipid production by <i>Rhodotorula glutinis</i> for renewable fuel production based on machine learning

doi:10.1007/s11705-024-2410-8

Front. Chem. Sci. Eng.

2024, Vol. 18

Issue (5) : 51 https://doi.org/10.1007/s11705-024-2410-8

Improving lipid production by Rhodotorula glutinis for renewable fuel production based on machine learning

Lihe Zhang^1,², Changwei Zhang^1,², Xi Zhao^1,², Changliu He^1,², Xu Zhang^1,^2,³(

)

¹. National Energy R & D Center for Biorefinery, Beijing University of Chemical Technology, Beijing 100029, China
². Collage of Life Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
³. Beijing Key Laboratory of Bioprocess, Beijing University of Chemical Technology, Beijing 10029, China

Download: PDF(1322 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Microbial lipid fermentation encompasses intricate complex cell growth processes and heavily relies on expert experience for optimal production. Digital modeling of the fermentation process assists researchers in making intelligent decisions, employing logical reasoning and strategic planning to optimize lipid fermentation. It this study, the effects of medium components and concentrations on lipid fermentation were investigated, first. And then, leveraging the collated data, a variety of machine learning algorithms were used to model and optimize the lipid fermentation process. The models, based on artificial neural networks and support vector machines, achieved R² values all higher than 0.93, ensuring accurate predictions of the fermentation process. Multiple linear regression was used to evaluate the respective target parameter, which were affected by the medium components of lipid fermentation. Lastly, single and multi-objective optimization were conducted for lipid fermentation using the genetic algorithm. Experimental results demonstrated the maximum biomass of 50.3 g·L⁻¹ and maximum lipid concentration of 14.1 g·L⁻¹ with the error between the experimental and predicted values less than 5%. The results of the multi-objective optimization reveal the synergistic and competitive relationship between biomass, lipid concentration, and conversion rate, which lay a basis for in-depth optimization and amplification.

Keywords microbial lipid machine learning artificial neural network support vector machine genetic algorithm

Corresponding Author(s): Xu Zhang

Just Accepted Date: 12 January 2024 Issue Date: 12 April 2024

Cite this article:

Lihe Zhang,Changwei Zhang,Xi Zhao, et al. Improving lipid production by Rhodotorula glutinis for renewable fuel production based on machine learning[J]. Front. Chem. Sci. Eng., 2024, 18(5): 51.

URL:

https://academic.hep.com.cn/fcse/EN/10.1007/s11705-024-2410-8
https://academic.hep.com.cn/fcse/EN/Y2024/V18/I5/51

Tab.1 Effect of different medium component concentration on lipid fermentation

Tab.2 Effect of nitrogen source concentration on lipid fermentation

Fig.1 Data analysis among substrate concentration, biomass, lipid concentration, lipid content and percent conversion: (a) lipid content vs. precent conversion; (b) initial sugar vs. biomass; (c) initial sugar vs. lipid; (d) residual sugar vs. biomass; (e) residual sugar vs. lipid; (f) biomass vs. lipid; (g) initial sugar vs. precent conversion; (h) residual sugar vs. precent conversion; (i) initial sugar vs. lipid content; (j) residual sugar vs. lipid content; (k) biomass vs. lipid content; (l) biomass vs. precent conversion.

Fig.2 Data analysis of C/N with main output variables: (a) residual sugar; (b) fermentation time; (c) biomass; (d) lipid concentration; (e) lipid content; (f) percent conversion; (g) substrate consumption rate; (h) cell growth rate; (i) lipid synthesis rate.

Fig.3 Multiple linear analysis results of different objective parameters: (a) biomass; (b) lipid; (c) lipid content; (d) percent conversion.

Tab.3 Evaluation of the fermentation models based on BP-ANN and SVM

Fig.4 Comparison of the measured and predicted values of the BP-ANN and SVM models. The left three graphs are the prediction results of BP-ANN models: (a) glucose concentration, (b) biomass, and (c) lipid; the right three graphs are the prediction results of SVM models: (d) glucose concentration, (e) biomass, and (f) lipid.

Tab.4 The best fermentation medium for different target parameters obtained by SVM-GA

Fig.5 The predicted values of lipid fermentation vs. experimental values.

Fig.6 Two-objective Pareto optimal solution distribution curve based on GA: (a) lipid vs. biomass; (b) conversion rate vs. biomass; (c) lipid vs. conversion rate.

1	W Bao , Z Li , X Wang , R Gao , X Zhou , S Cheng , Y Men , L Zheng . Approaches to improve the lipid synthesis of oleaginous yeast Yarrowia lipolytica: a review. Renewable & Sustainable Energy Reviews, 2021, 149(6): 111386 https://doi.org/10.1016/j.rser.2021.111386
2	X Chen , S Sun . Color reversion of refined vegetable oils: a review. Molecules, 2023, 28(13): 5177 https://doi.org/10.3390/molecules28135177
3	C Economou , G Aggelis , S Pavlou , D V Vayenas . Modeling of single-cell oil production under nitrogen-limited and substrate inhibition conditions. Biotechnology and Bioengineering, 2011, 108(5): 1049–1055 https://doi.org/10.1002/bit.23026
4	B Gao , J Hong , J Chen , H Zhang , R Hu , C Zhang . The growth, lipid accumulation and adaptation mechanism in response to variation of temperature and nitrogen supply in psychrotrophic filamentous microalga Xanthonema hormidioides (Xanthophyceae). Biotechnology for Biofuels and Bioproducts, 2023, 16(1): 12 https://doi.org/10.1186/s13068-022-02249-0
5	G Gong , L Liu , X Zhang , T Tan . Comparative evaluation of different carbon sources supply on simultaneous production of lipid and carotene of Rhodotorula glutinis with irradiation and the assessment of key gene transcription. Bioresource Technology, 2019, 288(5): 121559 https://doi.org/10.1016/j.biortech.2019.121559
6	D Henriques , R Minebois , S N Mendoza , L G Macías , R Pérez-Torrado , E Barrio , B Teusink , A Querol , E Balsa-Canto . A multiphase multiobjective dynamic genome-scale model shows different redox balancing among yeast species of the Saccharomyces genus in fermentation. Msystems, 2021, 6(4): e00260–21 https://doi.org/10.1128/mSystems.00260-21
7	P Joe . Global edible vegetable oil market trends. Biomedical Journal of Scientific & Technical Research, 2018, 2(1): 2282–2291 https://doi.org/10.26717/BJSTR.2018.02.000680
8	W N A Kadir , M K Lam , Y Uemura , J W Lim , K T Lee . Harvesting and pre-treatment of microalgae cultivated in wastewater for biodiesel production: a review. Energy Conversion and Management, 2018, 171(5): 1416–1429 https://doi.org/10.1016/j.enconman.2018.06.074
9	M K Khaleghi , I S P Savizi , N E Lewis , S A Shojaosadati . Synergisms of machine learning and constraint-based modeling of metabolism for analysis and optimization of fermentation parameters. Biotechnology Journal, 2021, 16(11): 2100212 https://doi.org/10.1002/biot.202100212
10	G B Kim , W J Kim , H U Kim , S Y Lee . Machine learning applications in systems metabolic engineering. Current Opinion in Biotechnology, 2020, 64: 1–9 https://doi.org/10.1016/j.copbio.2019.08.010
11	I Kolouchová , O Maťátková , K Sigler , J Masák , T Řezanka . Lipid accumulation by oleaginous and non-oleaginous yeast strains in nitrogen and phosphate limitation. Folia Microbiologica, 2016, 61(5): 431–438 https://doi.org/10.1007/s12223-016-0454-y
12	A M Kot , S Błażejak , M Kieliszek , I Gientka , J Bryś , L Reczek , K Pobiega . Effect of exogenous stress factors on the biosynthesis of carotenoids and lipids by Rhodotorula yeast strains in media containing agro-industrial waste. World Journal of Microbiology & Biotechnology, 2019, 35(10): 157 https://doi.org/10.1007/s11274-019-2732-8
13	M Kumar , M Husain , N Upreti , D Gupta . Genetic algorithm: review and application. SSRN Electronic Journal, 2020, 2(2): 451–454
14	E Leca , B Zennaro , J Hamelin , H Carrère , C Sambusiti . Use of additives to improve collective biogas plant performances: a comprehensive review. Biotechnology Advances, 2023, 65: 108129 https://doi.org/10.1016/j.biotechadv.2023.108129
15	W H Leong , J W Lim , M K Lam , Y Uemura , Y C Ho . Third generation biofuels: a nutritional perspective in enhancing microbial lipid production. Renewable & Sustainable Energy Reviews, 2018, 91(4): 950–961 https://doi.org/10.1016/j.rser.2018.04.066
16	X Li , Y Dong , L Chang , L Chen , G Wang , Y Zhuang , X Yan . Dynamic hybrid modeling of fuel ethanol fermentation process by integrating biomass concentration XGBoost model and kinetic parameter artificial neural network model into mechanism model. Renewable Energy, 2023, 205: 574–582 https://doi.org/10.1016/j.renene.2023.01.113
17	Y Li , H Xu , Z Li , S Meng , H Song . Catalytic methanotreating of vegetable oil: a pathway to second-generation biodiesel. Fuel, 2022, 311(10): 122504 https://doi.org/10.1016/j.fuel.2021.122504
18	H Li , Y Zhong , Q Lu , X Zhang , Q Wang , H Liu , Z Diao , C Yao , H Liu . Co-cultivation of: Rhodotorula glutinis and Chlorella pyrenoidosa to improve nutrient removal and protein content by their synergistic relationship. RSC Advances, 2019, 9(25): 14331–14342 https://doi.org/10.1039/C9RA01884K
19	M Llamas , S Greses , J A Magdalena , C González-Fernández , E Tomás-Pejó . Microbial co-cultures for biochemicals production from lignocellulosic biomass: a review. Bioresource Technology, 2023, 386(10): 129499 https://doi.org/10.1016/j.biortech.2023.129499
20	H Lu , H Chen , X Tang , Q Yang , H Zhang , Y Q Chen , W Chen . Time-resolved multi-omics analysis reveals the role of nutrient stress-induced resource reallocation for TAG accumulation in oleaginous fungus Mortierella alpina. Biotechnology for Biofuels, 2020, 13(1): 116 https://doi.org/10.1186/s13068-020-01757-1
21	N Nosrati-Ghods , S T L Harrison , A J Isafiade , S Leng Tai . Mathematical modelling of bioethanol fermentation from glucose, xylose or their combination: a review. ChemBioEng Reviews, 2020, 7(3): 68–88 https://doi.org/10.1002/cben.201900024
22	S Papanikolaou , G Aggelis . Lipids of oleaginous yeasts. Part I: biochemistry of single cell oil production. European Journal of Lipid Science and Technology, 2011, 113(8): 1031–1051 https://doi.org/10.1002/ejlt.201100014
23	N Ramanauske , T Balezentis , D Streimikiene . Biomass use and its implications for bioeconomy development: a resource efficiency perspective for the European countries. Technological Forecasting and Social Change, 2023, 193: 122628 https://doi.org/10.1016/j.techfore.2023.122628
24	S Safarian , S M E Saryazdi , R Unnthorsson , C Richter . Artificial neural network modeling of bioethanol production via syngas fermentation. Biophysical Economics and Sustainability, 2021, 6(1): 1–13 https://doi.org/10.1007/s41247-020-00083-2
25	L H Sales de Menezes , L L Carneiro , I Maria de Carvalho Tavares , P H Santos , T Pereira das Chagas , A A Mendes , E G Paranhos da Silva , M Franco , J Rangel de Oliveira . Artificial neural network hybridized with a genetic algorithm for optimization of lipase production from Penicillium roqueforti ATCC 10110 in solid-state fermentation. Biocatalysis and Agricultural Biotechnology, 2021, 31: 101885 https://doi.org/10.1016/j.bcab.2020.101885
26	J D Silva , L H Martins , D K Moreira , L D Silva , P D Barbosa , A Komesu , N R Ferreira , J A Oliveira . Microbial lipid based biorefinery concepts: a review of status and prospects. Foods, 2023, 12(10): 2074 https://doi.org/10.3390/foods12102074
27	A Singh , S Wilson , O P Ward . Docosahexaenoic acid (DHA) production by Thraustochytrium sp. ATCC 20892. World Journal of Microbiology & Biotechnology, 1996, 12(1): 76–81 https://doi.org/10.1007/BF00327806
28	V Singh , S Haque , R Niwas , A Srivastava , M Pasupuleti , C K Tripathi . Strategies for fermentation medium optimization: an in-depth review. Frontiers in Microbiology, 2017, 7: 1–12 https://doi.org/10.3389/fmicb.2016.02087
29	S Song , X Xiong , X Wu , Z Xue . Modeling the SOFC by BP neural network algorithm. International Journal of Hydrogen Energy, 2021, 46(38): 20065–20077 https://doi.org/10.1016/j.ijhydene.2021.03.132
30	H Sun , Z Gao , L Zhang , X Wang , M Gao , Q Wang . A comprehensive review on microbial lipid production from wastes: research updates and tendencies. Environmental Science and Pollution Research International, 2023, 30(33): 79654–79675 https://doi.org/10.1007/s11356-023-28123-6
31	C Thon , B Finke , A Kwade , C Schilde . Artificial intelligence in process engineering. Advanced Intelligent Systems, 2021, 3(6): 200261
32	E Tomás-Pejó , S Morales-Palomo , C González-Fernández . Microbial lipids from organic wastes: outlook and challenges. Bioresource Technology, 2021, 323(3): 124612 https://doi.org/10.1016/j.biortech.2020.124612
33	M TranmerJ MurphyM ElliotM Pampaka. Multiple Linear Regression (2nd Edition). Manchester, UK: Cathie Marsh Institute, 2020
34	H Wang , X Peng , H Zhang , S Yang , H Li . Microorganisms-promoted biodiesel production from biomass: a review. Energy Conversion and Management: X, 2021, 12: 100137
35	J Wang , R Ledesma-Amaro , Y Wei , B Ji , X J Ji . Metabolic engineering for increased lipid accumulation in Yarrowia lipolytica: a review. Bioresource Technology, 2020, 313: 123707 https://doi.org/10.1016/j.biortech.2020.123707
36	K Wang , T Q Shi , J Wang , P Wei , R Ledesma-Amaro , X J Ji . Engineering the lipid and fatty acid metabolism in Yarrowia lipolytica for sustainable production of high oleic oils. ACS Synthetic Biology, 2022, 11(4): 1542–1554 https://doi.org/10.1021/acssynbio.1c00613
37	Q Wang , W Han , W Jin , S Gao , X Zhou . Docosahexaenoic acid production by Schizochytrium sp: review and prospect. Food Biotechnology, 2021, 35(2): 111–135 https://doi.org/10.1080/08905436.2021.1908900
38	W M Willis , R W Lencki , A G Marangoni . Lipid modification strategies in the production of nutritionally functional fats and oils. Critical Reviews in Food Science and Nutrition, 1998, 38(8): 639–674 https://doi.org/10.1080/10408699891274336
39	F Xue , B Gao , Y Zhu , X Zhang , W Feng , T Tan . Pilot-scale production of microbial lipid using starch wastewater as raw material. Bioresource Technology, 2010, 101(15): 6092–6095 https://doi.org/10.1016/j.biortech.2010.01.124
40	J Yang , Y Huang , H Xu , D Gu , F Xu , J Tang , C Fang , Y Yang . Optimization of fungi co-fermentation for improving anthraquinone contents and antioxidant activity using artificial neural networks. Food Chemistry, 2020, 313: 126138 https://doi.org/10.1016/j.foodchem.2019.126138
41	L Zhang , B Chao , X Zhang . Modeling and optimization of microbial lipid fermentation from cellulosic ethanol wastewater by Rhodotorula glutinis based on the support vector machine. Bioresource Technology, 2021, 301(11): 122781
42	L Zhang , J E Lee , Y Ok , Y Dai , Y Tong . Enhancing microbial lipids yield for biodiesel production by oleaginous yeast Lipomyces starkeyi fermentation: a review. Bioresource Technology, 2022, 344(1): 126294 https://doi.org/10.1016/j.biortech.2021.126294
43	L Zhang , Y Song , Q Wang , X Zhang . Culturing rhodotorula glutinis in fermentation-friendly deep eutectic solvent extraction liquor of lignin for producing microbial lipid. Bioresource Technology, 2021, 337(5): 125475 https://doi.org/10.1016/j.biortech.2021.125475
44	X Zhang , M Liu , X Zhang , T Tan . Microbial lipid production and organic matters removal from cellulosic ethanol wastewater through coupling oleaginous yeasts and activated sludge biological method. Bioresource Technology, 2018, 267(11): 395–400 https://doi.org/10.1016/j.biortech.2018.07.075
45	Z Y Zheng , G Xie , L Li , W L Liu . The joint effect of ultrasound and magnetic Fe3O4 nanoparticles on the yield of 2,6-dimethoxy-ρ-benzoquinone from fermented wheat germ: comparison of evolutionary algorithms and interactive analysis of paired-factors. Food Chemistry, 2020, 302: 125275 https://doi.org/10.1016/j.foodchem.2019.125275

[1]

FCE-23089-OF-ZL_suppl_1

Download

[1]	Xiaonan Wang, Jie Li, Yingzhe Zheng, Jiali Li. Smart systems engineering contributing to an intelligent carbon-neutral future: opportunities, challenges, and prospects[J]. Front. Chem. Sci. Eng., 2022, 16(6): 1023-1029.
[2]	Yiming Ma, Zhenguo Gao, Peng Shi, Mingyang Chen, Songgu Wu, Chao Yang, Jing-Kang Wang, Jingcai Cheng, Junbo Gong. Machine learning-based solubility prediction and methodology evaluation of active pharmaceutical ingredients in industrial crystallization[J]. Front. Chem. Sci. Eng., 2022, 16(4): 523-535.
[3]	Haoqin Fang, Jianzhao Zhou, Zhenyu Wang, Ziqi Qiu, Yihua Sun, Yue Lin, Ke Chen, Xiantai Zhou, Ming Pan. Hybrid method integrating machine learning and particle swarm optimization for smart chemical process operations[J]. Front. Chem. Sci. Eng., 2022, 16(2): 274-287.
[4]	Quirin Göttl, Dominik G. Grimm, Jakob Burger. Automated synthesis of steady-state continuous processes using reinforcement learning[J]. Front. Chem. Sci. Eng., 2022, 16(2): 288-302.
[5]	Ewan Chee, Wee Chin Wong, Xiaonan Wang. An integrated approach for machine-learning-based system identification of dynamical systems under control: application towards the model predictive control of a highly nonlinear reactor system[J]. Front. Chem. Sci. Eng., 2022, 16(2): 237-250.
[6]	Patrick Otto Ludl, Raoul Heese, Johannes Höller, Norbert Asprion, Michael Bortz. Using machine learning models to explore the solution space of large nonlinear systems underlying flowsheet simulations with constraints[J]. Front. Chem. Sci. Eng., 2022, 16(2): 183-197.
[7]	Yumei WANG, Wei LIU, Jie BAO. Repeated batch fermentation with water recycling and cell separation for microbial lipid production[J]. Front Chem Sci Eng, 2012, 6(4): 453-460.
[8]	Saravanan P, Muthuvelayudham R, Rajesh Kannan R, Viruthagiri T. Optimization of cellulase production using Trichoderma reesei by RSM and comparison with genetic algorithm[J]. Front Chem Sci Eng, 2012, 6(4): 443-452.
[9]	PAN Yong, JIANG Juncheng, WANG Zhirong. Prediction of the flash points of alkanes by group bond contribution method using artificial neural networks[J]. Front. Chem. Sci. Eng., 2007, 1(4): 390-394.

Viewed

Full text

Abstract

Cited

Shared

Discussed