Research article Special Issues

Managing extreme cryptocurrency volatility in algorithmic trading: EGARCH via genetic algorithms and neural networks

  • The blockchain ecosystem has seen a huge growth since 2009, with the introduction of Bitcoin, driven by conceptual and algorithmic innovations, along with the emergence of numerous new cryptocurrencies. While significant attention has been devoted to established cryptocurrencies like Bitcoin and Ethereum, the continuous introduction of new tokens requires a nuanced examination. In this article, we contribute a comparative analysis encompassing deep learning and quantum methods within neural networks and genetic algorithms, incorporating the innovative integration of EGARCH (Exponential Generalized Autoregressive Conditional Heteroscedasticity) into these methodologies. In this study, we evaluated how well Neural Networks and Genetic Algorithms predict "buy" or "sell" decisions for different cryptocurrencies, using F1 score, Precision, and Recall as key metrics. Our findings underscored the Adaptive Genetic Algorithm with Fuzzy Logic as the most accurate and precise within genetic algorithms. Furthermore, neural network methods, particularly the Quantum Neural Network, demonstrated noteworthy accuracy. Importantly, the X2Y2 cryptocurrency consistently attained the highest accuracy levels in both methodologies, emphasizing its predictive strength. Beyond aiding in the selection of optimal trading methodologies, we introduced the potential of EGARCH integration to enhance predictive capabilities, offering valuable insights for reducing risks associated with investing in nascent cryptocurrencies amidst limited historical market data. This research provides insights for investors, regulators, and developers in the cryptocurrency market. Investors can utilize accurate predictions to optimize investment decisions, regulators may consider implementing guidelines to ensure fairness, and developers play a pivotal role in refining neural network models for enhanced analysis.

    Citation: David Alaminos, M. Belén Salas, Ángela M. Callejón-Gil. Managing extreme cryptocurrency volatility in algorithmic trading: EGARCH via genetic algorithms and neural networks[J]. Quantitative Finance and Economics, 2024, 8(1): 153-209. doi: 10.3934/QFE.2024007

    Related Papers:

    [1] Flávia da Silva Fernandes, Luan Reis Honorato da Silva, Érica Simplício de Souza, Lívia Melo Carneiro, João Paulo Alves Silva, Steven Zelski, João Vicente Braga de Souza, Jacqueline da Silva Batista . Isolation, genetic identification of Amazonian yeasts and analysis of thermotolerance and alcohol tolerance of Saccharomyces cerevisiae from Theobroma grandiflorum and Eugenia stipitata. AIMS Bioengineering, 2024, 11(1): 24-43. doi: 10.3934/bioeng.2024003
    [2] Ana Paula Guedes Pinheiro, Augusto Bücker, Ana Cláudia Cortez, John Edward Hallsworth, João Vicente Braga de Souza, Érica Simplício de Souza . Vinegar production from Theobroma grandiflorum SCHUM (cupuassu). AIMS Bioengineering, 2021, 8(4): 257-266. doi: 10.3934/bioeng.2021022
    [3] Zongyuan Zhu, Rachael Simister, Susannah Bird, Simon J. McQueen-Mason, Leonardo D. Gomez, Duncan J. Macquarrie . Microwave assisted acid and alkali pretreatment of Miscanthus biomass for biorefineries. AIMS Bioengineering, 2015, 2(4): 449-468. doi: 10.3934/bioeng.2015.4.449
    [4] Khalil Essani, Anton Glieder, Martina Geier . Combinatorial pathway assembly in yeast. AIMS Bioengineering, 2015, 2(4): 423-436. doi: 10.3934/bioeng.2015.4.423
    [5] Frank R. Bengelsdorf, Christina Gabris, Lisa Michel, Manuel Zak, Marian Kazda . Syntrophic microbial communities on straw as biofilm carrier increase the methane yield of a biowaste-digesting biogas reactor. AIMS Bioengineering, 2015, 2(3): 264-276. doi: 10.3934/bioeng.2015.3.264
    [6] Nikolaos Giormezis, Konstantinos Papakonstantinou, Fevronia Kolonitsiou, Eleanna Drougka, Antigoni Foka, Styliani Sarrou, Evangelos D. Anastassiou, Efthimia Petinaki, Iris Spiliopoulou . Biofilm synthesis and its relationship with genetic characteristics in clinical methicillin-resistant staphylococci. AIMS Bioengineering, 2015, 2(4): 375-386. doi: 10.3934/bioeng.2015.4.375
    [7] Urooj Ainuddin, Maria Waqas . Finite state machine and Markovian equivalents of the lac Operon in E. coli bacterium. AIMS Bioengineering, 2022, 9(4): 400-419. doi: 10.3934/bioeng.2022029
    [8] Kevyn Melo Lotas, Raissa Sayumy Kataki Fonseca, Joice Camila Martins da Costa, Ana Claudia Alves Cortez, Francisca das Chagas do Amaral Souza, Márcio Rodrigues Barreto, Lívia Melo Carneiro, João Paulo Alves Silva, Eveleise Samira Martins Canto, Flávia da Silva Fernandes, João Vicente Braga de Souza, Érica Simplício de Souza . Optimization of laccase production by Pleurotus ostreatus (Jacq.) P. Kumm. using agro-industrial residues: a comparative study on peels of tucumã (Astrocaryum aculeatum G. Mey.) and pupunha (Bactris gasipaes Kunth) fruits. AIMS Bioengineering, 2024, 11(4): 561-573. doi: 10.3934/bioeng.2024025
    [9] Olga M. Tsivileva, Inna M. Uchaeva, Nikolay A. Yurasov . Biotesting of technologically important carboxy containing acridones with solid-state fungal culture. AIMS Bioengineering, 2021, 8(1): 1-13. doi: 10.3934/bioeng.2021001
    [10] Luan Reis Honorato da Silva, Flávia da Silva Fernandes, Jocélia Pinheiro Santos, Érica Simplício de Souza, Lívia Melo Carneiro, João Paulo Alves Silva, Jacqueline da Silva Batista, João Vicente Braga de Souza . Bioprospecting Saccharomyces cerevisiae in fruits from Amazonian region for beer brewing. AIMS Bioengineering, 2024, 11(2): 130-146. doi: 10.3934/bioeng.2024008
  • The blockchain ecosystem has seen a huge growth since 2009, with the introduction of Bitcoin, driven by conceptual and algorithmic innovations, along with the emergence of numerous new cryptocurrencies. While significant attention has been devoted to established cryptocurrencies like Bitcoin and Ethereum, the continuous introduction of new tokens requires a nuanced examination. In this article, we contribute a comparative analysis encompassing deep learning and quantum methods within neural networks and genetic algorithms, incorporating the innovative integration of EGARCH (Exponential Generalized Autoregressive Conditional Heteroscedasticity) into these methodologies. In this study, we evaluated how well Neural Networks and Genetic Algorithms predict "buy" or "sell" decisions for different cryptocurrencies, using F1 score, Precision, and Recall as key metrics. Our findings underscored the Adaptive Genetic Algorithm with Fuzzy Logic as the most accurate and precise within genetic algorithms. Furthermore, neural network methods, particularly the Quantum Neural Network, demonstrated noteworthy accuracy. Importantly, the X2Y2 cryptocurrency consistently attained the highest accuracy levels in both methodologies, emphasizing its predictive strength. Beyond aiding in the selection of optimal trading methodologies, we introduced the potential of EGARCH integration to enhance predictive capabilities, offering valuable insights for reducing risks associated with investing in nascent cryptocurrencies amidst limited historical market data. This research provides insights for investors, regulators, and developers in the cryptocurrency market. Investors can utilize accurate predictions to optimize investment decisions, regulators may consider implementing guidelines to ensure fairness, and developers play a pivotal role in refining neural network models for enhanced analysis.



    Industrial biotechnology represents more than hundred billion market in the US, and is the fastest growing sector in the last decade [1]. Microbial chemical production has been covered by a reduced number of model organisms, such as Escherichia coli, Aspergillus genus or Pichia pastoris, but Saccharomyces cerevisiae is one of the most widely utilized. This is partly because S. cerevisiae is classified as Generally Regarded as Safe (GRAS) organism, but also because it grows very well in environmental conditions normally associated to standard biotechnological processes, e.g. glucose fermentation during ethanol production [2].

    General examples of industrially produced chemicals by S. cerevisiae are bioethanol or a number of recombinant proteins, like human insulin [2],[3]. Aspergillus is well known for enzymes and citric acid production [4],[5], and E. coli for vitamins and fine chemicals manufacture [6],[7]. On the other hand, there are still important challenges regarding the production processes, sometimes due to limitations in the host organism used. Examples of this are S. cerevisiae and E. coli, which cannot tolerate certain environmental stresses. They normally have a better growth in moderate temperatures, and require a substantial microbial engineering effort in order to grow relatively well in such stressful conditions for them (e.g. to increase the ability to utilize carbon sources different to glucose or become thermotolerant) [8],[9]. Similarly, many problems are associated to the filamentous growth of Aspergillus in bioreactors or industrial tanks, making the process more fastidious and expensive. Furthermore, expensive feedstocks, high energy and water use, loss of productivity due to contamination and downstream separation costs can be added to the list of challenges to be addressed [10].

    The use of non-conventional microorganisms (the term “non-conventional” referring to any other microbe different from the classical aforementioned production workhorses) could easily overcome some of the challenges already mentioned. In fact, some of those microbes are already known for presenting a significant advantage compared to the model organisms. Some non-conventional microbes are able to withstand extreme environmental conditions, such as high temperature and osmotic pressure, while others show tolerance to inhibitors produced during different bioprocesses [10],[11]. Moreover, an increased availability of molecular tools and synthetic biology methods is being lately offered for their use in non-model organisms (Figure 1).

    Figure 1.  A comparative overview of the strategies from lab-scale to industrial scale of production hosts, and the dedicated engineering efforts in each case, as well as the expected outcome, based on the initial microbial choice. ALE: adaptive laboratory evolution.

    In this mini-review, we offer a fast and precise overview about the topic, which is already considered of great significance but will become more and more important in the coming years. We focus on yeasts as one of the most studied microbial group in nature and their consideration as a model for eukaryotic cell research. Therefore, in this manuscript, we present some of the most relevant non-conventional yeasts and their use as production platforms for sustainable fermentation based bio-manufacturing processes. Yarrowia lipolytica, Trichosporon oleaginosus, Kluyveromyces marxianus, Dekkera bruxellensis, Pichia kudriavzevii, Debaryomyces hansenii and Hansenula polymorpha, are reviewed for their use in biotechnology and/or their improved industrial potential for the near future.

    Genetic and metabolic engineering is commonly more challenging in non-conventional yeasts than in other model organisms, especially due to a more limited knowledge about their metabolism and genomics. Even though non-conventional yeasts already present interesting native phenotypes for industrial production purposes, some metabolic engineering will be needed at some point to enhance those phenotypes and increase e.g. yields or production rates [12].

    Gene expression methods are basically based on expression cassettes which can be expressed through episomal vectors or by integration in the host's genome. Some limitations are associated to gene expression through episomal vectors, e.g. lack of stable plasmids, low gene copy number or variable expression in the host's cells [13],[14]. On the other hand, homogenous expression levels, increased stability of the expression cassette or lack of need for selection markers, are advantages while using genome integration methods. These methods can be divided into two different types, and are performed by the native DNA repair pathways in the host organism [15]:

    1) Random integration via non-homologous end joining (NHEJ)

    2) Targeted integration via homologous recombination (HR)

    Although random integration via NHEJ is the preferred method to be used in non-conventional yeasts (HR is considered inefficient in this case), it can cause unwanted disruptions in genomic key elements or lead to variable expression levels across transformant cells [16],[17]. For that reason, it was of especial importance the development of clustered regularly interspaced short palindromic repeats (CRISPR) and CRISPR-associated 9 (CRISPR-Cas9) tools, for genome editing in non-conventional yeasts [18]. The use of these CRISPR tools allow to achieve a more efficient HR by the introduction of a genomic double strand break and a programmable endonuclease in the presence of a homologous repair template [12],[19].

    Yeast is one of the most studied microbial group in nature, as it has been associated e.g. with the production of fermented beverages and food for human consumption over thousands of years. They have provided an extensive scientific knowledge on basic and applied microbiology, and became model organisms for eukaryotic cell research [20]. A broad number of yeast genomes have been sequenced and uncountable molecular biology tools were described and are available for their genetic modification (some of which are reviewed along this manuscript). Besides, non-conventional yeasts are of great interest due to their unique characteristics and metabolism, which make them suitable for different biotechnological processes at an industrial level (Table 1), in comparison with traditional model organisms.

    Table 1.  Overview of non-conventional yeast species, their industrially-relevant phenotypes/products and genetic tools availability.
    Non-conventional yeast Valuable phenotype Product Recombinant protein Genetic tools CRISPR system
    Y. lipolytica Oleaginous yeast, growth on organic acids, polyalcohols and paraffins [21],[23] Lipids, citric acid, erythritol, α-ketoglutaric acid, lycopene, Omega-3 eicosapentaenoic acid [116],[117],[118],[119],[120], [121],[122] Selenomethionyl lipase, erythritol dehydrogenase [24],[25] Highly developed TEFintron promoter codon-optimized [31], UAS1B8-TEF promoter codon-optimized [32]
    T. oleaginosus Oleaginous yeast, metabolize recalcitrant feedstocks, tolerate by-products of lignocellulose pretreatments [33],[36],[37],[38] Lipids, modified fatty acids [36],[37],[39],[40] _ Need for improvement _
    K. marxianus Thermotolerance, fast growth characteristics, utilization of sugar cane or molasses, growth on a range of sugars [44],[45],[46] HTF-ethanol, 2-phenylethanol/2-phenyl ethyl acetate, hexanoic acid [46],[51],[123] Inulinase, β-galactosidase, pectidases [47],[48],[124],[125] Highly developed ScTEF1 promoter codon-optimized [61]
    D. bruxellensis Tolerance to ethanol and acetic acid, assimilation of nitrate, fermentation of cellobiose [63],[64],[66],[70] Ethanol [61] _ Need for improvement _
    P. kudriavzevii Thermotolerance, growth at low pH, growth on complex substrates, acetic acid, vanillin and furan derivative tolerance [75],[77],[78],[45],[80],[79] Ethanol, succinic acid [67],[74],[75] β-glucosidase [78] Need for improvement _
    D. hansenii Halophilic and oleaginous yeast, osmotolerance, xerotolerance, resistance to inhibitory compounds, consumption of broad range of substrates [33],[84],[90],[91] Xylitol, trehalose, flavonoids, fatty acids, killer toxins, essential fat-soluble vitamins [84],[90] _ Need for improvement _
    H. polymorpha Methylotrophic yeast, nitrate assimilation, thermotolerance [97],[104],[99] Ethanol [101],[102] Hepatitis B surface antigen, insulin, hexose oxidase, phytase [108],[109],[107],[106] Highly developed DH3 promoter human codon-optimized [115]

     | Show Table
    DownLoad: CSV

    Y. lipolytica is an oleaginous non-conventional yeast and very attractive from the industrial point of view, due to its uncommon physiological characteristics [21]. It is classified as GRAS, obligate aerobe microbe and it can switch between hyphal and yeast morphology depending on the environmental conditions [22]. Moreover, it shows high secretory rates, low glycosylation rates and high cell densities during fermentation [21]. Especially interesting is its capacity to metabolize organic acids, polyalcohols and paraffins as sole carbon source [23]. Also biomass-derived sugars and industrial wastes, which makes the bioprocesses more cost effective and highly productive [11]. Y. lipolytica is actually a better candidate for recombinant protein expression compared to S. cerevisiae or Kluyveromyces lactis, for production of selenomethionyl lipase and erythritol dehydrogenase [24],[25]. The best productivity level is obtained when Y. lipolytica is cultivated at 28–30 °C, pH 5.5–7.0 and dissolved oxygen levels at 20% of air saturation [22],[26].

    The genome of Y. lipolytica was sequenced and is available for researchers [27]. There are some examples of engineering methods already published for this yeast, being the ectopic integration of homology cassettes the preferred one [28][30]. Besides, CRISPR-Cas9 system has been successfully used [31],[32]. On the other hand, homologous recombination is still a weakness that needs to be improved.

    T. oleaginosus is an oleaginous yeast with a lipid accumulation capacity between 20–60% of its biomass [33]. The optimal growth conditions for T. oleaginosus are within the range of 28–30 °C and pH 5.4–5.8, and it is able to utilize a broad range of carbon and nitrogen sources, being glucose the preferred substrate [34],[35]. Moreover, it can metabolize a wide variety of recalcitrant feedstocks [33] and tolerate several by-products of lignocellulose pretreatments, like acetic acid, furfural and ammonia [36][38]. Due to its natural ability for lipid accumulation, T. oleaginosus has been mainly studied for its lipid production capability under different dissolved oxygen concentration or diverse substrates utilization [36],[37],[39],[40]. Furthermore, its ability to tolerate and metabolize lignin-derived aromatic compounds, while remaining oleaginous, has been well described [41].

    There are a couple of studies about genetic modification in T. oleaginosus, which was also successfully transformed by genomic integration for the production of modified fatty acids, although transformation efficiencies are not reported [42],[43]. Nevertheless, an increased knowledge and development on molecular biology tools and genetic engineering are still needed for this yeast.

    K. marxianus is a hemiascomycetous non-conventional yeast, isolated mostly from cheese and other dairy products and with a respirofermentative metabolism (Crabtree negative yeast). It is considered an extreme thermotolerant microbe that can grow in temperatures up to 52 °C. Moreover, it shows acid tolerance (pH 3.8). K. marxianus is an interesting option for industrial bioprocesses, also because it presents high growth rates and it is able to utilize a number of industrially relevant substrates, such as sugar cane or molasses [44],[45]. Those characteristics make K. marxianus a very good candidate for its use in biotechnology, presenting some advantages when compared to S. cerevisiae. For instance, it utilizes a broad range of different carbon sources in contrast to the model yeast: xylose, xylitol, cellobiose, lactose and arabinose. Additionally, it shows similar ethanol yield and glucose consumption as S. cerevisiae at 30 °C, although K. marxianus can also achieve glucose fermentation between 30–45 °C [46].

    Currently, K. marxianus is used in several industrial bioprocesses, e.g. to produce recombinant proteins and enzymes (inulinase and β-galactosidase) [47],[48], to perform high-temperature fermentation of ethanol [49] or, due to its GRAS classification, to produce food-related compounds like aroma compounds and bioingredients [50],[51].

    As its genome was completely sequenced in 2012 [52], there are several tools already described for K. marxianus' genetic manipulation including transformation with linear DNA and simultaneous multiple integration [46],[53]. Besides, genomics and transcriptomics analysis have been performed for this yeast [54][56], as well as genome-scale metabolic models [57][59]. The CRISPR system has been successfully applied in K. marxianus and used to characterize e.g. functional genes in biosynthesis pathway of ethyl acetate [60][62].

    D. bruxellensis is a non-conventional yeast with an extremely complex genome, which cannot be defined as haploid or diploid, due to its genetic polymorphism. Similarly to S. cerevisiae, it has been isolated from beer, wine (spoilage yeast) and cider, and classified as facultative anaerobic and Crabtree positive [45]. D. bruxellensis is able to produce and accumulate ethanol, being one of its main characteristic its tolerance to ethanol (10–16%) [63]. Similar ethanol yields to S. cerevisiae are obtained during glucose fermentation, although D. bruxellensis presents lower growth rates compared to the model yeast [64]. Positively, it can grow in acidic environments [65], produces low amount of glycerol [64], which leads to a more energy efficient process, and assimilates nitrate during industrial fermentation [66]. The yeast also shows a complex pattern of substrate consumption and metabolite production [67], and it is tolerant and able to accumulate acetic acid [64]. On the other hand, D. bruxellensis is thermosensitive already at 35 °C, being 30 °C its optimal growth temperature [68],[69].

    Its biotechnological potential mainly resides in its capability of fermenting cellobiose, which makes this yeast a good candidate for fermentation of lignocellulose to ethanol processes, and due to its utilization of nitrate as sole nitrogen source, for ethanol processes based on sugar cane [70].

    As we mentioned before, D. bruxellensis has an important genome complexity that makes difficult its genetic modification even though its genome is fully sequenced [71],[72]. Molecular tools are underdeveloped for this yeast and just one transformation method has been described so far, based on non-homologous DNA integration, and with an efficiency of only 0.6–20 transformants/µg [73]. Together with basic identification/manipulation molecular tools, transcriptomic analysis has been more recently carried out in D. bruxellensis in glucose and oxygen-limited cultures [74].

    P. kudriavzevii has been isolated from several niches, including sourdough, cocoa bean fermentation, cereal-based beverages, sugar cane juice or rice straw. That gives an idea of its great ability to grow on complex substrates [45]. Carbon sources assimilated by P. kudriavzevii are glucose, sucrose, fructose, mannose and weakly galactose, but it is not able to utilize maltose, xylose, arabinose, cellobiose, raffinose and trehalose [75]. The yeast is classified as Crabtree negative [76], thermotolerant [75] and able to grow at low pH (lower than pH 2) [77],[78].

    P. kudriavzevii shows furan derivative tolerance, which makes this yeast very interesting in industrial bioprocesses. It tolerates up to 3 g/L of furfural, 5 g/L of 5-HMF, 8–10 g/L of acetic acid, 2 g/L of formic acid and 1.8–2 g/L of vanillin [75],[79],[80]. It is more efficient than S. cerevisiae in ethanol production at temperatures higher than 35 °C and can ferment at up to 45 °C. The same study also identified the salt and sugar tolerance of P. kudriavzevii, which can tolerate 5% (w/v) of NaCl (0.85 M) and 40% (w/v) of glucose [75].

    The genome of P. kudriavzevii is also sequenced [81], but the molecular tools available for its genetic manipulation are still very limited. A first attempt to engineering the yeast was performed in 2010, in which study the authors successfully developed a β-glucosidase expression system for conversion of cellobiose to ethanol [78]. Besides, a metabolic engineered strain was generated for industrial scale production of succinic acid. While P. kudriavzevii is not a natural producer, its engineered version was able to produce and tolerate succinic acid [82],[83].

    D. hansenii is a halophilic, xerotolerant and oleaginous non-conventional yeast that was originally isolated from seawater and commonly found in high osmotic and saline environments, such as cured meats and cheeses. This yeast is able to grow in a broad range of temperatures (20–35 °C) and pHs (3–10), and up to 25% of NaCl (4M). Besides, it respires a broad number of carbon sources [33],[84]. Several studies have demonstrated that sodium protects D. hansenii against oxidative stress and other abiotic stresses [85][87]. Moreover, glycerol is produced and accumulated as a compatible solute under osmotic pressure [88],[89].

    D. hansenii is used in biotechnology for production of fine chemicals, such as xylitol and flavonoids, killer toxins and others [84],[90]. Furthermore, this yeast shows resistance to a variety of inhibitory compounds including chlorine dioxide, penconazole, benomyl, and cycloheximide [90],[91]. Apart from its great biotechnological potential, which mostly resides in its improved performance under very harsh conditions (high salinity, osmotic pressure, media acidification or nutrient scarcity), the use of pure water sources will not be necessary when industrially growing D. hansenii. That could lead to a decrease in production costs whilst the production yields are increased. Furthermore, when growing in high salt concentration media, the risk of contamination is also highly reduced.

    The only limitation when working with D. hansenii, whose genome was sequenced in 2004 [27], is the lack of molecular tools for engineering this yeast. Although some methods for transformation and heterologous gene expression have been published, there is still low transformation efficiency and low reproducibility between labs [92][96].

    H. polymorpha is a thermotolerant methylotrophic yeast used for production of traditional fermented wine in Asia [97]. It optimally grows at 37 °C, although it has been described as able to grow up to 48–50 °C [98],[99]. H. polymorpha is capable to metabolize a range of different carbon sources such as glycerol, C5 and C6 sugar monomers and C12 disaccharides [100]. Moreover, it ferments glucose, xylose, cellobiose and other lignocellulose sugars to ethanol, at high temperature [101]. The yeast also shows resistance to several growth inhibitors and can utilize lignocellulosic as crude substrate streams [102].

    H. polymorpha was first studied as model organism for peroxisome function and biosynthesis, as well as nitrate metabolism and assimilation [103],[104]. Its ability to grow on methanol promotes peroxisome proliferation, which was used for penicillin production, partially located in this organelle [105]. From an industrial point of view, H. polymorpha is considered a powerful production platform for heterologous protein biosynthesis, based on a strong inducible expression system coupled with effective protein secretion and glycosylation. Actually, it is less prone to toxic hyperglycosylation (compared to S. cerevisiae), as it does not produce alpha-1,3-linked residues which triggers immunogenicity in humans [106]. Biopharmaceutical examples, industrially produced by H. polymorpha, are insulin [106],[107] and proteins for hepatitis B vaccine [108],[109].

    The H. polymorpha genome was sequenced in 2003 [110]. Several engineering tools have been described for this yeast, being random integration and homologous recombination into telomeric regions the most successful ones. On the other hand, non-homologous end-joining mechanism makes it hard to disrupt genes in this yeast [12]. Expression cassettes used in H. polymorpha are commonly constructed using inducible methanol oxidase promoter and terminator (pMOX, MOXt) [111],[112], although other endogenous promoters has also been used [113]. H. polymorpha plasmids containing autonomously replicating sequence (ARS) elements have been isolated and demonstrated to have highly transformation efficiency and episomal replication [114]. CRISPR-Cas9 system has also been successfully used in H. polymorpha, obtaining gene disruption rates up to 71% [115].

    One of the biggest challenges in industrial biotechnology is coping with the host limitations normally found for a specific production process. Dealing with high osmotic stress, high salt or sugar concentrations, high temperature processes or product inhibition are the most common problems found among the sector [45]. As we mentioned before, model organisms such as S. cerevisiae or E. coli are very well-studied, both physiologically and genetically, and have been highly genetically modified for an improved performance under certain stress conditions. Still, they have their limitations regarding metabolic engineering to mitigate some of those detrimental effects. In that sense, non-conventional organisms (yeast) represent a better natural choice to overcome the problems related to stress tolerance during industrial bioprocesses.

    In this review, we have presented some of the best examples of non-conventional yeasts with a strong potential in biotechnology, and able to naturally deal with the biggest problems mentioned above. E.g. T. oleaginosus tolerates several by-products like acetic acid, furfural and ammonia, K. marxianus is thermotolerant, D. bruxellensis tolerates up to 16% of ethanol, P. kudriavzevii shows furan derivative and vanillin tolerance, D. hansenii is a halophilic yeast, and H. polymorpha is a methylotrophic yeast. Besides, their genomes are sequenced and several genetic tools are already available to the scientific community. Nevertheless, there is still room for improvement when industrially using these microbes or any other non-conventional yeast in general, especially related to the development of new molecular biology methods and the investigation of the molecular mechanisms underlying their tolerance, which can lead to their maximum fermentative capacity and/or best optimal behavior.

    In this respect, some of the biggest challenges that need to be addressed in the future are the following:

    1) Development, and improvement, of new genetic tools for non-conventional microorganisms.

    2) Investigation of the molecular mechanisms underlying their natural tolerance.

    3) Implementation of CRISPR-Cas systems for highly efficient genome editing, which allows getting the most desired phenotypes for industrial bioprocesses.

    4) Improvement of random integration engineering of non-conventional yeast for stable genetic modifications by disrupting/repressing competing DNA repair through non-homologous end-joining (NHEJ).

    5) Design of Genome Scale Models (GSMs) based on experimental data-sets relevant to metabolic engineering and synthetic biology, and specifically developed during industrial performances.

    6) Development of metabolic models based on genomic and transcriptomic information, which allows designing genomes for improved productivity.

    Industrial biotechnology is a field in exponential expansion, and fermentation-based manufacturing of bio-based chemicals has attracted a considerable attention within the last decade. Given the current global situation, there is an increasing need of novel green technologies to mitigate CO2 emissions, exploring sustainable ways of production that favor a competitive shift from oil-based technologies towards biosustainable alternatives. The concept of circular economy and the waste revalorization into high-value products strategy, demand better large-scale production strategies. A new generation of microbial production hosts may tackle the challenge and replace the classical production workhorses, as they lack of the capacity of withstanding large-scale production setups and require substantial engineering efforts.

    In this review we suggest a series of alternative yeast hosts, that could serve as a better starting point for bio-based production processes of chemicals or other molecules of interest (industrial enzymes, peptide based biotherapeutics, food ingredients, etc). Because of i) their inherent and evolutionary acquired higher tolerance in hostile environments, ii) their higher tolerance to fermentation inhibitors normally produced as by-products from biomass hydrolysates, or iii) their ability to consume a wide range of different carbon sources, they certainly show in all aspects greater advantages than the current available options.

    With the recent advances in microbial engineering technologies, such as the implementation of CRISPR-based technologies, and the fast (and cheaper than ever) capacity of genome sequencing and annotation of novel microbial isolates, it has become easier to engineer these microbes for increasing production yields instead of modifying the classical hosts to increase their tolerance. Overall, using one of these non-conventional microbes from the start will significantly decrease the initial engineering efforts, therefore speeding up the initial design and test process and the transition from lab to industrial scale of novel production hosts.



    [1] Abakah EJA, Gil-Alana LA, Madigu G, et al. (2020) Volatility persistence in cryptocurrency markets under structural breaks. Int Rev Econ Financ 69: 680–691. https://doi.org/10.1016/j.iref.2020.06.035. doi: 10.1016/j.iref.2020.06.035
    [2] Abdallah A, Maarof MA, Zainal A (2016) Fraud detection system: A survey. J Netw Comput Appl 68: 90–113. https://doi.org/10.1016/j.jnca.2016.04.007 doi: 10.1016/j.jnca.2016.04.007
    [3] Adcock R, Gradojevic N (2019) Non-fundamental, non-parametric Bitcoin forecasting. Physica A 531: 121727. https://doi.org/10.1016/j.physa.2019.121727 doi: 10.1016/j.physa.2019.121727
    [4] Akyildirim E, Goncu A, Sensoy A (2021) Prediction of cryptocurrency returns using machine learning. Ann Oper Res 297: 3–36. https://doi.org/10.1007/s10479-020-03575-y doi: 10.1007/s10479-020-03575-y
    [5] Alameer Z, Elaziz MA, Ewees AA, et al. (2019) Forecasting copper prices using hybrid adaptive neuro-fuzzy inference system and genetic algorithms. Nat Resour Res 28: 1385–1401. https://doi.org/10.1007/s11053-019-09473-w doi: 10.1007/s11053-019-09473-w
    [6] Alaminos D, Esteban I, Salas MB (2023) Neural networks for estimating Macro Asset Pricing model in football clubs. Intell Syst Account Financ Manage 30: 57–75. https://doi.org/10.1002/isaf.1532 doi: 10.1002/isaf.1532
    [7] Alaminos D, Esteban I, Salas MB, et al. (2020) Quantum Neural Networks for Forecasting Inflation Dynamics. J Sci Ind Res 79: 103–106. https://doi.org/10.56042/jsir.v79i2.68439 doi: 10.56042/jsir.v79i2.68439
    [8] Alaminos D, Salas MB, Fernandez-Gámez MA (2022) Forecasting Stock Market Crashes via Real-Time Recession Probabilities: A Quantum Computing Approach. Fractals 30: 1–16. https://doi.org/10.1142/S0218348X22401624 doi: 10.1142/S0218348X22401624
    [9] Alonso-Monsalve S, Suárez-Cetrulo AL, Cervantes A, et al. (2020) Convolution on neural networks for high-frequency trend prediction of cryptocurrency exchange rates using technical indicators. Expert Syst Appl 149: 113250. https://doi.org/10.1016/j.eswa.2020.113250 doi: 10.1016/j.eswa.2020.113250
    [10] Aloud ME, Alkhamees N (2021) Intelligent Algorithmic Trading Strategy Using Reinforcement Learning and Directional Change. IEEE Access 9: 114659–114671. https://doi.org/10.1109/ACCESS.2021.3105259 doi: 10.1109/ACCESS.2021.3105259
    [11] Appel G (2005) Technical analysis: power tools for active investors, FT Press.
    [12] Arévalo A, Niño J, Hernández G, et al. (2016) High-frequency trading strategy based on deep neural networks. In International conference on intelligent computing, 424–436. Springer, Cham. https://doi.org/10.1007/978-3-319-42297-8_40
    [13] Atsalakis GS, Atsalaki IG, Pasiouras F, et al. (2019) Bitcoin price forecasting with neuro-fuzzy techniques. Eur J Oper Res 276: 770–780. https://doi.org/10.1016/j.ejor.2019.01.040 doi: 10.1016/j.ejor.2019.01.040
    [14] Bhattacharyya S, Jha S, Tharakunnel K, et al. (2011) Data mining for credit card fraud: A comparative study. Decis support syst 50: 602–613. https://doi.org/10.1016/j.dss.2010.08.008 doi: 10.1016/j.dss.2010.08.008
    [15] Bianchi D, Babiak M, Dickerson A (2022) Trading volume and liquidity provision in cryptocurrency markets. J Bank Financ 142: 106547. https://doi.org/10.1016/j.jbankfin.2022.106547 doi: 10.1016/j.jbankfin.2022.106547
    [16] Binns R (2018) Fairness in machine learning: Lessons from political philosophy. In Conference on Fairness, Accountability and Transparency, 149–159. PMLR.
    [17] Bishop CM (1995) Neural networks for pattern recognition, Oxford university press. https://doi.org/10.1093/oso/9780198538493.001.0001
    [18] Borovkova S, Tsiamas I (2019) An ensemble of LSTM neural networks for high-frequency stock market classification. J Forecasting 38: 600–619. https://doi.org/10.1002/for.2585 doi: 10.1002/for.2585
    [19] Bouri E, Gupta R, Roubaud D (2019) Herding behaviour in cryptocurrencies. Financ Res Lett 29: 216–221. https://doi.org/10.1016/j.frl.2018.07.008. doi: 10.1016/j.frl.2018.07.008
    [20] Bouri E, Lau CKM, Lucey BM, et al. (2019) Trading volume and the predictability of return and volatility in the cryptocurrency market. Financ Res Lett 29: 340–346. https://doi.org/10.1016/j.frl.2018.08.015 doi: 10.1016/j.frl.2018.08.015
    [21] Bouri E, Lucey B, Roubaud D (2020) The volatility surprise of leading cryptocurrencies: Transitory and permanent linkages. Financ Res Lett 33: 101188. https://doi.org/10.1016/j.frl.2019.05.006 doi: 10.1016/j.frl.2019.05.006
    [22] Bouri E, Shahzad S, Roubaud D (2019) Co-explosivity in the cryptocurrency market. Financ Res Lett 29: 178–183. https://doi.org/10.1016/j.frl.2018.07.005 doi: 10.1016/j.frl.2018.07.005
    [23] Briola A, Turiel J, Marcaccioli R, et al. (2021) Deep reinforcement learning for active high frequency trading.
    [24] Bustos O, Pomares-Quimbaya A (2020) Stock market movement forecast: A systematic review. Expert Syst Appl 156: 113464. https://doi.org/10.1016/j.eswa.2020.113464 doi: 10.1016/j.eswa.2020.113464
    [25] Cao M, Shang F (2010) Double chains quantum genetic algorithm with application in training of process neural networks. In 2010 Second International Workshop on Education Technology and Computer Science, 19–22, IEEE. https://doi.org/10.1109/ETCS.2010.88
    [26] Cheng Y, Zheng Z, Wang J, et al. (2019) Attribute reduction based on genetic algorithm for the coevolution of meteorological data in the industrial internet of things. Wirel Commun Mob Com 2019: 1–8. https://doi.org/10.1155/2019/3525347 doi: 10.1155/2019/3525347
    [27] Chih-Hung W, Gwo-Hshiung T, Rong-Ho L (2009) A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression. Expert Syst Appl 36: 4725–4735. https://doi.org/10.1016/j.eswa.2008.06.046 doi: 10.1016/j.eswa.2008.06.046
    [28] Corbet S, Eraslan V, Lucey B, et al. (2019) The effectiveness of technical trading rules in cryptocurrency markets. Financ Res Lett 31: 32–37. https://doi.org/10.1016/j.frl.2019.04.027 doi: 10.1016/j.frl.2019.04.027
    [29] Corbet S, Katsiampa P (2018). Asymmetric mean reversion of Bitcoin price returns. Int Rev Financ Anal. https://doi.org/10.1016/j.irfa.2018.10.004. doi: 10.1016/j.irfa.2018.10.004
    [30] Corbet S, Larkin CJ, Lucey BM, et al. (2020) Kodakcoin: a blockchain revolution or exploiting a potential cryptocurrency bubble? Appl Econ Lett 27: 518–524. https://doi.org/10.1080/13504851.2019.1637512 doi: 10.1080/13504851.2019.1637512
    [31] Demir E, Gozgor G, Lau CKM, et al. (2018) Does economic policy uncertainty predict the Bitcoin returns? An empirical investigation. Financ Res Lett 26: 145–149. https://doi.org/10.1016/j.frl.2018.01.005 doi: 10.1016/j.frl.2018.01.005
    [32] Demir S, Mincev K, Kok K, et al. (2019) Introducing technical indicators to electricity price forecasting: A feature engineering study for linear, ensemble, and deep machine learning models. Appl Sci 10: 255. https://doi.org/10.3390/app10010255 doi: 10.3390/app10010255
    [33] Drachal K, Pawłowski M (2021) A review of the applications of genetic algorithms to forecasting prices of commodities. Economies 9: 6. https://doi.org/10.3390/economies9010006 doi: 10.3390/economies9010006
    [34] Drezner Z, Misevičius A (2013) Enhancing the performance of hybrid genetic algorithms by differential improvement. Com Oper Res 40: 1038–1046. https://doi.org/10.1016/j.cor.2012.10.014 doi: 10.1016/j.cor.2012.10.014
    [35] Egger DJ, Gambella C, Marecek J, et al. (2020) Quantum computing for finance: State-of-the-art and future prospects. IEEE Trans Quantum Eng 1: 1–24. https://doi.org/10.1109/TQE.2020.3030314 doi: 10.1109/TQE.2020.3030314
    [36] Fang F, Ventre C, Basios M, et al. (2022) Cryptocurrency trading: a comprehensive survey. Financial Innovation 8: 1–59. https://doi.org/10.1186/s40854-021-00321-6 doi: 10.1186/s40854-021-00321-6
    [37] Feng W, Wang Y, Zhang Z (2018) Informed trading in the Bitcoin market. Financ Res Lett 26: 63–70. https://doi.org/10.1016/j.frl.2017.11.009. doi: 10.1016/j.frl.2017.11.009
    [38] Fernández-Blanco P, Bodas-Sagi DJ, Soltero FJ, et al. (2008) Technical market indicators optimization using evolutionary algorithms. In Proceedings of the 10th annual conference companion on Genetic and evolutionary computation. 1851–1858. https://doi.org/10.1145/1388969.1388989
    [39] Frino A, Garcia M, Zhou Z (2020) Impact of algorithmic trading on speed of adjustment to new information: Evidence from interest rate derivatives. J Futures Mark 40: 749–760. https://doi.org/10.1002/fut.22104 doi: 10.1002/fut.22104
    [40] Gandal N, Hamrick J, Moore T, et al. (2018) Price manipulation in the Bitcoin ecosystem. J Monetary Econ 95: 86–96. https://doi.org/10.1016/j.jmoneco.2017.12.004 doi: 10.1016/j.jmoneco.2017.12.004
    [41] Gao X, Li X, Zhao B, et al. (2019) Short-term electricity load forecasting model based on EMD-GRU with feature selection. Energies 12: 1140. https://doi.org/10.3390/en12061140 doi: 10.3390/en12061140
    [42] García EAC (2004) An Application of Gibbons-Ross-Shanken'S Test of The Efficiency of A Given Portfolio. Revista Mexicana de Economía y Finanzas Nueva Época REMEF (Mexican J Econ Financ) 3. https://doi.org/10.21919/remef.v3i1.161
    [43] Gerritsen DF, Bouri E, Ramezanifar E, et al. (2020) The profitability of technical trading rules in the bitcoin market. Financ Res Lett 34: 101263. https://doi.org/10.1016/j.frl.2019.08.011 doi: 10.1016/j.frl.2019.08.011
    [44] Giudici P, Abu-Hashish I (2019). What determines Bitcoin exchange prices? a network var approach. Financ Res Lett 28: 309–318. https://doi.org/10.1016/j.frl.2018.05.013. doi: 10.1016/j.frl.2018.05.013
    [45] Goldberg DE (1990) A note on Boltzmann tournament selection for genetic algorithms and populationoriented simulated annealing. Complex Syst 4: 44
    [46] Goldblum M, Schwarzschild A, Patel A, et al. (2021) Adversarial attacks on machine learning systems for high-frequency trading. In Proceedings of the Second ACM International Conference on AI in Finance, 1–9. https://doi.org/10.1145/3490354.3494367
    [47] Gonçalves DSCP (2019) Quantum neural machine learning: Theory and experiments. Machine Learning in Medicine and Biology, 95–115. IntechOpen. https://doi.org/10.5772/intechopen.84149 doi: 10.5772/intechopen.84149
    [48] Goodell JW, Kumar S, Lim WM, et al. (2021) Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis. J Behav Expl Financ 32: 100577. https://doi.org/10.1016/j.jbef.2021.100577 doi: 10.1016/j.jbef.2021.100577
    [49] Gradojevic N, Kukolj D, Adcock R, et al. (2023) Forecasting Bitcoin with technical analysis: A not-so-random forest? Int J Forecast 39: 1–17. https://doi.org/10.1016/j.ijforecast.2021.08.001 doi: 10.1016/j.ijforecast.2021.08.001
    [50] Granville JE (1976). Granville's new strategy of daily stock market timing for maximum profit. Prentice-Hall. Hoboken, New Jersey, U.S.
    [51] Greaves A, Au B (2015) Using the Bitcoin Transaction graph to predict the price of bitcoin. Available from: htpp://snap.standord.edu/class/cs224w-2015/projects_2015/.
    [52] Griffin JM, Shams A (2018) Is Bitcoin really un-tethered? SSRN. Available from: https://ssrn.com/abstract=3195066.
    [53] Grobys K, Sapkota N (2020) Predicting cryptocurrency defaults. Appl Econ 52: 5060–5076. https://doi.org/10.1080/00036846.2020.1752903 doi: 10.1080/00036846.2020.1752903
    [54] Grover LK (2005) Fixed-point quantum search. Phys Rev Lett 95: 150501. https://doi.org/10.1103/PhysRevLett.113.210501 doi: 10.1103/PhysRevLett.113.210501
    [55] Guerreschi GG (2019) Repeat-until-success circuits with fixed-point oblivious amplitude amplification. Phys Rev A 99: 022306. https://doi.org/10.1103/PhysRevA.99.022306 doi: 10.1103/PhysRevA.99.022306
    [56] Guidi B, Michienzi A (2022) Social games and blockchain: exploring the metaverse of decentraland. In 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops, 199–204. https://doi.org/10.1109/ICDCSW56584.2022.00045
    [57] Gupta N, Jalal AS (2020) Integration of textual cues for fine-grained image captioning using deep CNN and LSTM. Neural Comput Appl 32: 17899–17908. https://doi.org/10.1007/s00521-019-04515-z doi: 10.1007/s00521-019-04515-z
    [58] Hasan M, Naeem MA, Arif M, et al. (2022) Liquidity connectedness in cryptocurrency market. Financial Innovation 8: 1–25. https://doi.org/10.1186/s40854-021-00308-3 doi: 10.1186/s40854-021-00308-3
    [59] Hassan MK, Hudaefi FA, Caraka RE (2022) Mining netizen's opinion on cryptocurrency: sentiment analysis of Twitter data. Stud Econ Financ 39: 365–385. https://doi.org/ 10.1108/SEF-06-2021-0237 doi: 10.1108/SEF-06-2021-0237
    [60] Hendershott T, Jones CM, Menkveld AJ (2011) Does algorithmic trading improve liquidity? J Financ 66: 1–33. https://doi.org/10.1111/j.1540-6261.2010.01624.x doi: 10.1111/j.1540-6261.2010.01624.x
    [61] Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9: 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 doi: 10.1162/neco.1997.9.8.1735
    [62] Huang B, Huan Y, Xu LD, et al. (2019) Automated trading systems statistical and machine learning methods and hardware implementation: a survey. Enterp Inf Syst 13: 132–144. https://doi.org/10.1080/17517575.2018.1493145 doi: 10.1080/17517575.2018.1493145
    [63] Huang CW, Narayanan SS (2017) Deep convolutional recurrent neural network with attention mechanism for robust speech emotion recognition. In 2017 IEEE international conference on multimedia and expo (ICME), 583–588. IEEE. https://doi.org/10.1109/ICME.2017.8019296
    [64] Huang JZ, Huang W, Ni J (2019). Predicting Bitcoin returns using high-dimensional technical indicators. J Financ Data Sci 5:140–155. https://doi.org/10.1016/j.jfds.2018.10.001 doi: 10.1016/j.jfds.2018.10.001
    [65] Jia WU, Chen WANG, Xiong L, et al. (2019) Quantitative trading on stock market based on deep reinforcement learning. In 2019 International Joint Conference on Neural Networks (IJCNN), 1–8. IEEE. https://doi.org/10.1109/IJCNN.2019.8851831 doi: 10.1109/IJCNN.2019.8851831
    [66] Katoch S, Chauhan SS, Kumar V (2021) A review on genetic algorithm: past, present, and future. Multimedia Tools Appl 80: 8091–8126. https://doi.org/10.1007/s11042-020-10139-6 doi: 10.1007/s11042-020-10139-6
    [67] Katsiampa P, Corbet S, Lucey B (2019). Volatility spillover effects in leading cryptocurrencies: a BEKK-MGARCH analysis. Financ Res Lett 29: 68–74. https://doi.org/10.1016/j.frl.2019.03.009. doi: 10.1016/j.frl.2019.03.009
    [68] Kim BS, Kim TG (2019). Cooperation of simulation and data model for performance analysis of complex systems. Int J Simulation Model 18: 608–619. https://doi.org/10.2507/IJSIMM18(4)491 doi: 10.2507/IJSIMM18(4)491
    [69] King T, Koutmos D (2021) Herding and feedback trading in cryptocurrency markets. Ann Oper Res 300: 79–96. https://doi.org/10.1007/s10479-020-03874-4 doi: 10.1007/s10479-020-03874-4
    [70] Kirkpatrick S, Gelatt CDJ, Vecchi MP (1983) Optimization by simulated annealing. Science 220: 671–680. https://doi.org/10.1126/science.220.4598.671 doi: 10.1126/science.220.4598.671
    [71] Klaus T, Elzweig B (2017) The market impact of high-frequency trading systems and potential regulation. Law Financ Mark Rev 11: 13–19. https://doi.org/10.1080/17521440.2017.1336397 doi: 10.1080/17521440.2017.1336397
    [72] Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI'95) 2: 1137–1143.
    [73] Kristoufek L (2015) What are the main drivers of the Bitcoin price? Evidence from wavelet coherence analysis. PLoS One 10: e0123923. https://doi.org/10.1371/journal.pone.0123923 doi: 10.1371/journal.pone.0123923
    [74] Lahmiri S, Bekiros S (2019) Cryptocurrency forecasting with deep learning chaotic neural networks. Chaos Soliton Fract 118: 35–40. https://doi.org/10.1016/j.chaos.2018.11.014 doi: 10.1016/j.chaos.2018.11.014
    [75] Lane GC (1984) Lane's stochastics. Tech Anal Stocks Commodities 2: 80.
    [76] LeCun Y, Bottou L, Bengio Y, et al. (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86: 2278–2324. https://doi.org/10.1109/5.726791 doi: 10.1109/5.726791
    [77] Lewis J, Hart E, Ritchie G (1998) A comparison of dominance mechanisms and simple mutation on non-stationary problems. Parallel Problem Solving from Nature (PPSN V) 1498: 139–148. https://doi.org/10.1007/BFb0056857 doi: 10.1007/BFb0056857
    [78] Livieris IE, Pintelas E, Stavroyiannis S, et al. (2020) Ensemble deep learning models for forecasting cryptocurrency time-series. Algorithms 13: 121. https://doi.org/10.3390/a13050121 doi: 10.3390/a13050121
    [79] Lu W, Li J, Li Y, et al. (2020) A CNN-LSTM-based model to forecast stock prices. Complexity https://doi.org/10.1155/2020/6622927 doi: 10.1155/2020/6622927
    [80] Ma M, Mao Z (2019) Deep recurrent convolutional neural network for remaining useful life prediction. In 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), 1–4. IEEE. https://doi.org/10.1109/ICPHM.2019.8819440
    [81] Madan I, Saluja S, Zhao A (2015) Automated Bitcoin trading via machine learning algorithms. Available from: http://cs229.stanford.edu/projects2014.html.
    [82] Maghsoodi AI (2023) Cryptocurrency portfolio allocation using a novel hybrid and predictive big data decision support system. Omega 115: 102787. https://doi.org/10.1016/j.omega.2022.102787 doi: 10.1016/j.omega.2022.102787
    [83] Mahajan RP (2011) Hybrid quantum inspired neural model for commodity price prediction. In 13th International Conference on Advanced Communication Technology (ICACT2011), 1353–1357. IEEE.
    [84] Makarov I, Schoar A (2022) Cryptocurrencies and Decentralized Finance (DeFi). Brookings Pap Econ Ac 2022: 141–215. https://doi.org/10.1353/eca.2022.0014 doi: 10.1353/eca.2022.0014
    [85] Makrichoriti P, Moratis G (2016) BitCoin's roller coaster: systemic risk and market sentiment. http://dx.doi.org/10.2139/ssrn.2808096.
    [86] Makridis CA, Fröwis M, Sridhar K, et al. (2023) The rise of decentralized cryptocurrency exchanges: evaluating the role of airdrops and governance tokens. J Corp Financ 79: 102358. https://doi.org/10.1016/j.jcorpfin.2023.102358 doi: 10.1016/j.jcorpfin.2023.102358
    [87] Marzo GD, Pandolfelli F, Servedio VD (2022) Modeling innovation in the cryptocurrency ecosystem. Sci Reports 12: 1–12. https://doi.org/10.1038/s4159802216924-7 doi: 10.1038/s4159802216924-7
    [88] McNally S, Roche J, Caton S (2018) Predicting the price of bitcoin using machine learning. In 2018 26th euromicro international conference on parallel, distributed and network-based processing (PDP). IEEE, 339–343. https://doi.org/10.1109/PDP2018.2018.00060
    [89] Mensi W, Al-Yahyaee K, Kang S (2019) Structural breaks and double long memory of cryptocurrency prices: a comparative analysis from Bitcoin and ethereum. Financ Res Lett 29: 222–230. https://doi.org/10.1016/j.frl.2018.07.011. doi: 10.1016/j.frl.2018.07.011
    [90] Mensi W, Lee YJ, Al-Yahyaee KH, et al. (2019). Intraday downward/upward multifractality and long memory in Bitcoin and ethereum markets: an asymmetric multifractal detrended fluctuation analysis. Financ Res Lett. https://doi.org/10.1016/j.frl.2019.03.029. doi: 10.1016/j.frl.2019.03.029
    [91] Milana C, Ashta A (2021) Artificial intelligence techniques in finance and financial markets: a survey of the literature. Strat Change 30: 189–209. https://doi.org/10.1002/jsc.2403 doi: 10.1002/jsc.2403
    [92] Mirkamol S, Mansur E (2023) Cryptocurrencies as the Money of the Future, In: Koucheryavy, Y., Aziz, A. (eds) Internet of Things, Smart Spaces, and Next Generation Networks and Systems, NEW2AN 2022, Lecture Notes in Computer Science, 13772. https://doi.org/10.1007/978-3-031-30258-9_21
    [93] Murray-Rust D, Elsden C, Nissen B, et al. (2023) Blockchain and Beyond: Understanding Blockchains through Prototypes and Public Engagement. ACM T Comput Hum Int 29: 1–73. https://doi.org/10.1145/3503462 doi: 10.1145/3503462
    [94] Murphy JJ (1999) Technical analysis of the financial markets: A comprehensive guide to trading methods and application, Penguin. London, U.K.
    [95] Nakano M, Takahashi A, Takahashi S (2018) Bitcoin technical trading with artificial neural network. Physica A 510: 587–609. https://doi.org/10.1016/j.physa.2018.07.017 doi: 10.1016/j.physa.2018.07.017
    [96] Nica O, Piotrowska K, Schenk-Hoppé KR (2022) Cryptocurrencies: Concept and Current Market Structure. In Cryptofinance: A New Currency for a New Economy, 1–28. https://doi.org/10.1007/978-3-031-30258-9_21
    [97] Nielsen MA, Chuang IL (2001) Quantum computation and quantum information. Phys Today 54: 60. https://doi.org/10.1063/1.1428442 doi: 10.1063/1.1428442
    [98] Ortu M, Uras N, Conversano C, et al. (2022) On technical trading and social media indicators for cryptocurrency price classification through deep learning. Expert Syst Appl 198: 116804. https://doi.org/10.1016/j.eswa.2022.116804 doi: 10.1016/j.eswa.2022.116804
    [99] Othman AHA, Kassim S, Rosman RB, et al. (2020) Prediction accuracy improvement for Bitcoin market prices based on symmetric volatility information using artificial neural network approach. J Revenue Pricing Ma 19: 314–330. https://doi.org/10.1057/s41272-020-00229-3 doi: 10.1057/s41272-020-00229-3
    [100] Panagiotidis T, Stengos T, Vravosinos O (2018) On the determinants of Bitcoin returns: a lasso approach. Financ Res Lett 27: 235–240. https://doi.org/10.1016/j.frl.2018.03.016. doi: 10.1016/j.frl.2018.03.016
    [101] Patel MM, Tanwar S, Gupta R, et al. (2020) A deep learning-based cryptocurrency price prediction scheme for financial institutions. J Inf Security Appl 55: 102583. https://doi.org/10.1016/j.jisa.2020.102583 doi: 10.1016/j.jisa.2020.102583
    [102] Paule-Vianez J, Prado-Román C, Gómez-Martínez R (2020) Economic policy uncertainty and Bitcoin. Is Bitcoin a safe-haven asset? European Journal of Management and Business Economics 29 (3): 347-363. https://doi.org/10.1108/EJMBE-07-2019-0116 doi: 10.1108/EJMBE-07-2019-0116
    [103] Petukhina AA, Reule RC, Härdle WK (2021) Rise of the machines? Intraday high-frequency trading patterns of cryptocurrencies. Eur J Financ 27: 8–30. https://doi.org/10.1080/1351847X.2020.1789684 doi: 10.1080/1351847X.2020.1789684
    [104] Ping-Feng P, Chih-Shen L, Wei-Chiang H, et al. (2006) A hybrid support vector machine regression for exchange rate prediction. Int J Inf Manage Sci 17: 19–32.
    [105] Polasik M, Piotrowska AI, Wisniewski TP, et al. (2015) Price fluctuations and the use of Bitcoin: An empirical inquiry. International J Electron Comm 20: 9–49. https://doi.org/10.1080/10864415.2016.1061413 doi: 10.1080/10864415.2016.1061413
    [106] Qin L, Yu N, Zhao D (2018) Applying the convolutional neural network deep learning technology to behavioural recognition in intelligent video. Tehnički vjesnik 25: 528–535. https://doi.org/10.17559/TV-20171229024444 doi: 10.17559/TV-20171229024444
    [107] Refaeilzadeh P, Tang L, Liu H (2009) Cross-validation. Encyclopedia Database Syst, 532–538. https://doi.org/10.1007/978-0-387-39940-9_565. doi: 10.1007/978-0-387-39940-9_565
    [108] Ren YS, Ma CQ, Kong XL, et al. (2022) Past, present, and future of the application of machine learning in cryptocurrency research. Res Int Bus Financ 63: 101799. https://doi.org/10.1016/j.ribaf.2022.101799 doi: 10.1016/j.ribaf.2022.101799
    [109] Saad M, Choi J, Nyang D, et al. (2019) Toward characterizing blockchain-based cryptocurrencies for highly accurate predictions. IEEE Syst J 14: 321–332. https://doi.org/10.1109/INFCOMW.2018.8406859 doi: 10.1109/INFCOMW.2018.8406859
    [110] Sensoy A (2018) The inefficiency of Bitcoin revisited: a high-frequency analysis with alternative currencies. Finance Res Lett. https://doi.org/10.1016/j.frl.2018.04.002. doi: 10.1016/j.frl.2018.04.002
    [111] Sezer OB, Gudelek MU, Ozbayoglu AM (2020) Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Appl Soft Comput 90: 106181. https://doi.org/10.1016/j.asoc.2020.106181 doi: 10.1016/j.asoc.2020.106181
    [112] Sinha D (2022) https://www.analyticsinsight.net/top-10-new-cryptocurrencies-of-2022-to-buy-for-good-returns/.
    [113] Ta VD, Liu CM, Tadesse DA (2020) Portfolio optimization-based stock prediction using long-short term memory network in quantitative trading. Appl Sci 10: 437. https://doi.org/10.3390/app10020437 doi: 10.3390/app10020437
    [114] Tacchino F, Macchiavello C, Gerace D, et al. (2019) An artificial neuron implemented on an actual quantum processor. npj Quantum Inf 5: 1–8. https://doi.org/10.1038/s41534-019-0140-4 doi: 10.1038/s41534-019-0140-4
    [115] Trimborn S, Li M, Härdle WK (2020) Investing with cryptocurrencies—A liquidity constrained investment approach. J Financ Econometrics 18: 280–306. https://doi.org/10.1093/jjfinec/nbz016 doi: 10.1093/jjfinec/nbz016
    [116] Tsang WW H, Chong TTL (2009) Profitability of the on-balance volume indicator. Econ Bull 29: 2424–2431.
    [117] Vargas MR, Dos Anjos CE, Bichara GL, et al. (2018) Deep leaming for stock market prediction using technical indicators and financial news articles. In 2018 international joint conference on neural networks (IJCNN), 1–8. IEEE. https://doi.org/10.1109/IJCNN.2018.8489208
    [118] Vidal-Tomas D, Ibanez A, Farinos J (2018) Herding in the cryptocurrency market: cssd and csad approaches. Financ Res Lett. https://doi.org/10.1016/j.frl.2018.09.008 doi: 10.1016/j.frl.2018.09.008
    [119] Vidal-Tomás D (2022) Which cryptocurrency data sources should scholars use? Int Rev Financ Anal 81: 102061. https://doi.org/10.1016/j.irfa.2022.102061 doi: 10.1016/j.irfa.2022.102061
    [120] Vo A, Yost-Bremm C (2020) A high-frequency algorithmic trading strategy for cryptocurrency. J Comput Inf Syst 60: 555–568. https://doi.org/10.1080/08874417.2018.1552090 doi: 10.1080/08874417.2018.1552090
    [121] Wan KH, Dahlsten O, Kristjánsson H, et al. (2017) Quantum generalisation of feedforward neural networks. npj Quantum Inf 3: 1–8. https://doi.org/10.1038/s41534-017-0032-4 doi: 10.1038/s41534-017-0032-4
    [122] Wang J, Gao L, Zhang H, et al. (2011) Adaboost with SVM-based classifier for the classification of brain motor imagery tasks. In International Conference on Universal Access in Human-Computer Interaction, 629–634, Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21663-3_68
    [123] Wang J, Ma F, Bouri E, et al. (2023) Which factors drive Bitcoin volatility: Macroeconomic, technical, or both? J Forecast 42: 970–988. https://doi.org/10.1002/for.2930 doi: 10.1002/for.2930
    [124] Weng F, Hou M, Zhang T, et al. (2018) Application of regularized extreme learning machine based on BIC criterion and genetic algorithm in iron ore price forecasting. In 2018 3rd International Conference on Modelling, Simulation and Applied Mathematics (MSAM 2018), 212–217. Atlantis Press. https://doi.org/10.2991/msam-18.2018.45
    [125] Westland JC (2023) Determinants of liquidity in cryptocurrency markets. Digital Financ 5: 261–293. https://doi.org/10.1007/s42521-022-00073-7 doi: 10.1007/s42521-022-00073-7
    [126] Wilder JW (1978) New concepts in technical trading systems, Bloomington, IN: Trend Research.
    [127] Yang B, Sun Y, Wang S (2020) A novel two-stage approach for cryptocurrency analysis. Int Rev Financ Anal. https://doi.org/10.1016/j.irfa.2020.101567. doi: 10.1016/j.irfa.2020.101567
    [128] Zhengyang W, Xingzhou L, Jinjin R, et al. (2019) Prediction of cryptocurrency price dynamics with multiple machine learning techniques. In Proceedings of the 2019 4th International Conference on Machine Learning Technologies, 15–19. https://doi.org/10.1145/3340997.3341008
    [129] Zhu Y, Dickinson D, Li J (2017) Analysis on the influence factors of Bitcoin's price based on VEC model. Financial Innovation 3: 3. https://doi.org/10.1186/s40854-017-0054-0. doi: 10.1186/s40854-017-0054-0
  • This article has been cited by:

    1. Clara Navarrete, August T. Frost, Laura Ramos‐Moreno, Mette R. Krum, José L. Martínez, A physiological characterization in controlled bioreactors reveals a novel survival strategy for Debaryomyces hansenii at high salinity , 2021, 0749-503X, 10.1002/yea.3544
    2. Lucrezia Gatti, Federica Troiano, Violetta Vacchini, Francesca Cappitelli, Annalisa Balloi, An In Vitro Evaluation of the Biocidal Effect of Oregano and Cloves’ Volatile Compounds against Microorganisms Colonizing an Oil Painting—A Pioneer Study, 2020, 11, 2076-3417, 78, 10.3390/app11010078
    3. Alexander Zwirzitz, Lauren Alteio, Daniel Sulzenbacher, Michael Atanasoff, Manuel Selg, Ethanol Production from Wheat Straw Hydrolysate by Issatchenkia Orientalis Isolated from Waste Cooking Oil, 2021, 7, 2309-608X, 121, 10.3390/jof7020121
    4. Claudia Segal-Kischinevzky, Lucero Romero-Aguilar, Luis D. Alcaraz, Geovani López-Ortiz, Blanca Martínez-Castillo, Nayeli Torres-Ramírez, Georgina Sandoval, James González, Yeasts Inhabiting Extreme Environments and Their Biotechnological Applications, 2022, 10, 2076-2607, 794, 10.3390/microorganisms10040794
    5. Clara Navarrete, Mònica Estrada, José L. Martínez, Debaryomyces hansenii: an old acquaintance for a fresh start in the era of the green biotechnology, 2022, 38, 0959-3993, 10.1007/s11274-022-03280-x
    6. Katarína Šuchová, Csaba Fehér, Jonas L. Ravn, Soma Bedő, Peter Biely, Cecilia Geijer, Cellulose- and xylan-degrading yeasts: Enzymes, applications and biotechnological potential, 2022, 59, 07349750, 107981, 10.1016/j.biotechadv.2022.107981
    7. Clarisse Manishimwe, Yifan Feng, Jingxiang Sun, Runze Pan, Yujia Jiang, Wankui Jiang, Wenming Zhang, Fengxue Xin, Min Jiang, Biological production of xylitol by using nonconventional microbial strains, 2022, 38, 0959-3993, 10.1007/s11274-022-03437-8
    8. Hongzhong Lu, Eduard J. Kerkhoven, Jens Nielsen, A Pan-Draft Metabolic Model Reflects Evolutionary Diversity across 332 Yeast Species, 2022, 12, 2218-273X, 1632, 10.3390/biom12111632
    9. Marie-José Ayoub, Pamela Bechara, Mariana Habchi, Rachelle Hosry, Mohamad Akl, Sandy Haj Hassan, Pierre Abi Nakhoul, Raw goat's milk fermented Anbaris from Lebanon: insights into the microbial dynamics and chemical changes occurring during artisanal production, with a focus on yeasts, 2022, 89, 0022-0299, 440, 10.1017/S002202992200067X
    10. Renato L Binati, Elisa Salvetti, Anna Bzducha-Wróbel, Loreta Bašinskienė, Dalia Čižeikienė, David Bolzonella, Giovanna E Felis, Non-conventional yeasts for food and additives production in a circular economy perspective, 2021, 21, 1567-1364, 10.1093/femsyr/foab052
    11. Tomas Strucko, Niklas L Andersen, Mikkel R Mahler, José L Martínez, Uffe H Mortensen, A CRISPR/Cas9 method facilitates efficient oligo-mediated gene editing in Debaryomyces hansenii, 2021, 6, 2397-7000, 10.1093/synbio/ysab031
    12. Renato L. Binati, Ilaria Larini, Elisa Salvetti, Sandra Torriani, Glutathione production by non-Saccharomyces yeasts and its impact on winemaking: A review, 2022, 156, 09639969, 111333, 10.1016/j.foodres.2022.111333
    13. Pongsanat Pongcharoen, Wittaya Tawong, Wanwarang Pathaichindachote, Weerawan Rod–in, Physiological responses contributing to multiple stress tolerance in Pichia kudriavzevii with potential enhancement for ethanol fermentation, 2024, 138, 13891723, 314, 10.1016/j.jbiosc.2024.07.012
    14. Djamel Drider, Vanessa Demey, Giuseppe Spano, Françoise Coucheney, Frédérique Chaucheyras-Durand, Mathieu Castex, Potential of Non-Saccharomyces Yeasts as Probiotics and Alternatives to Antibiotics in Animal Production, 2024, 1535-3141, 10.1089/fpd.2023.0175
    15. Kyle R. Pomraning, Shuang Deng, Rylan D. Duong, Jeffrey J. Czajka, Pavlo Bohutskyi, Identification of Yarrowia lipolytica as a platform for designed consortia that incorporate in situ nitrogen fixation to enable ammonia-free bioconversion, 2024, 2, 2813-7809, 10.3389/finmi.2024.1473316
    16. Eléonore Pourcelot, Cleo Conacher, Thérèse Marlin, Florian Bauer, Virginie Galeote, Thibault Nidelet, Comparing the hierarchy of inter- and intra-species interactions with population dynamics of wine yeast cocultures, 2023, 23, 1567-1364, 10.1093/femsyr/foad039
    17. Karolina Drężek, Maria Krystyna Sobczyk, Zoltán Kállai, Anna Detman, Paula Bardadyn, Jolanta Mierzejewska, Valorisation of Whey Permeate in Sequential Bioprocesses towards Value-Added Products–Optimisation of Biphasic and Classical Batch Cultures of Kluyveromyces marxianus, 2023, 24, 1422-0067, 7560, 10.3390/ijms24087560
    18. Eduardo Luís Menezes de Almeida, Eduard J. Kerkhoven, Wendel Batista da Silveira, Reconstruction of genome-scale metabolic models of non-conventional yeasts: current state, challenges, and perspectives, 2024, 29, 1226-8372, 35, 10.1007/s12257-024-00009-5
    19. Fengyuan Li, Y. Shen, X. Luo, Z. Liu, Applications of Genome Editing in Yeast with an Example of Tup1 Mutants Construction, 2023, 72, 2117-4458, 01012, 10.1051/bioconf/20237201012
    20. Anita Ejiro Nwaefuna, Mar Garcia-Aloy, Daniel Loeto, Thembekile Ncube, Andreas K. Gombert, Teun Boekhout, Saleh Alwasel, Nerve Zhou, Dung beetle-associated yeasts display multiple stress tolerance: a desirable trait of potential industrial strains, 2023, 23, 1471-2180, 10.1186/s12866-023-03044-z
    21. Anna Glushakova, Aleksey Kachalkin, Diversity of Culturable Yeasts in the Feces of Mew Gulls Breeding in Natural and Urban Habitats, with Insights into the Antifungal Susceptibility of the Observed Pathogens, 2024, 5, 2673-6004, 543, 10.3390/birds5030036
    22. Abhishek Gupta, Kalisa Kang, Ruchi Pathania, Lisa Saxton, Barbara Saucedo, Ashleyn Malik, Yasin Torres-Tiji, Crisandra J. Diaz, João Vitor Dutra Molino, Stephen P. Mayfield, Harnessing genetic engineering to drive economic bioproduct production in algae, 2024, 12, 2296-4185, 10.3389/fbioe.2024.1350722
    23. H. P. Shruthi Prakash, K. R. Sangeetha Gowda, Sunil S. More, 2025, 9781394287857, 107, 10.1002/9781394287888.ch5
    24. Mª Lourdes Martínez-Cartas, Manuel Cuevas-Aranda, Sebastián Sánchez, Harnessing of Sunflower Stalks by Hydrolysis and Fermentation with Hansenula polymorpha to Produce Biofuels, 2024, 16, 2073-4360, 3548, 10.3390/polym16243548
  • Reader Comments
  • © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(2461) PDF downloads(187) Cited by(2)

Figures and Tables

Figures(1)  /  Tables(4)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog