Prerpints.org logo
Preprint
Article

A Bibliometric Study of Machine Learning in Biofilm

Altmetrics

Downloads

290

Views

157

Comments

0

This version is not peer-reviewed

Submitted:

04 April 2023

Posted:

04 April 2023

You are already at the latest version

Alerts
Abstract
Biofilm is a complex community of microorganisms that are attached to surfaces and encased in a self-produced extracellular matrix. Machine learning (ML) techniques have been applied to various aspects of biofilm research, such as predicting biofilm formation, identifying key genes, and designing new therapeutic strategies. In this study, we conducted a bibliometric analysis of machine learning in biofilm research to provide a comprehensive overview of the current state of the field. We searched the Web of Science database for articles published included "machine learning biofilm". A total of 126 articles were identified and analysed. Our results showed that the number of publications on machine learning in biofilm has been increasing rapidly over the past decade, indicating a growing interest in the application of ML techniques to biofilm research. The analysis also revealed that the most common research topics in this area were related to biofilm formation, prediction, and control. Furthermore, the most frequently used ML techniques in biofilm research were artificial neural networks and support vector machines. Overall, our study provides valuable insights into the current trends and future directions of machine learning in biofilm research. It also highlights the importance of interdisciplinary collaboration between biofilm researchers and ML experts to drive innovation in this field.
Keywords: 
Subject: Biology and Life Sciences  -   Immunology and Microbiology

1. Introduction

Biofilm is a fascinating and complex community of microorganisms that adhere to surfaces and secrete a self-produced extracellular matrix, known as a biofilm matrix [1]. This matrix acts as a protective barrier, making the biofilm resilient to antibiotics, immune system responses, and other environmental factors [2]. Biofilms are widely distributed in nature and can colonize various surfaces, including medical implants, water distribution systems, and food processing equipment [3]. Biofilms are associated with a range of problems, including infections, biofouling, and corrosion, making them a significant area of interest in scientific research [4].
Over the past decade, there has been a growing interest in the application of machine learning (ML) techniques in biofilm research [5,6,7,8]. ML is a subfield of artificial intelligence that enables computer systems to learn and improve from experience without being explicitly programmed [9]. By using ML algorithms, large and complex datasets generated from biofilm research, such as genomics, proteomics, and metabolomics data, can be analyzed to identify key genes, proteins, and metabolites that are involved in biofilm formation and function [10].
The objective of this study is to conduct a comprehensive bibliometric analysis of the use of ML in biofilm research to gain insights into the current state of the field [11]. Bibliometrics is a quantitative analysis of scientific publications that provides valuable insights into the structure, dynamics, and trends of a particular research area [12,13]. A bibliometric analysis of ML in biofilm research can identify the most influential publications, authors, and institutions in the field, as well as the most common research topics and trends [14].
This analysis can also reveal how researchers have used ML to advance our understanding of biofilm formation, growth, and function. The integration of ML and biofilm research has enabled researchers to analyse large and complex datasets to identify key factors that influence biofilm formation, growth, and function, such as environmental factors, genetic makeup, and metabolic processes. Furthermore, ML can also be used to develop new approaches to biofilm detection, prevention, and control, making it a valuable tool in the fight against biofilm-associated problems.
In this study, we will conduct a thorough search of relevant databases for articles published with "machine learning biofilm". By focusing on this relatively recent time, we can gain insights into the most current research trends in this area. We will then use bibliometric analysis tools, such as VOSviewer, to analyze the identified articles and generate bibliometric networks that can reveal important information about the structure and dynamics of the field. Our analysis will include co-authorship analysis, keyword co-occurrence analysis, and citation analysis, among others, to identify the most influential authors, institutions, and publications, as well as the most common research topics and trends.
Overall, this study will provide a comprehensive overview of the current state of the field of ML in biofilm research. By identifying key research themes, trends, and influential institutions in the field, we can better understand the challenges and opportunities associated with the integration of ML and biofilm research. Moreover, this analysis can guide future research efforts, helping to advance our understanding of the complex biological processes involved in biofilm formation, growth, and function.

2. Material and methods

To gain a better understanding of the current state of research on the application of ML in the context of biofilm, we conducted a thorough search of the Web of Science, ensuring that our analysis is up-to-date and relevant. Searching "machine learning biofilm," we identified a total of 126 articles that met our inclusion criteria [15,16,17]. To gain insights into the key themes and trends in this body of literature, we employed VOSviewer, a powerful software tool for constructing and visualizing bibliometric networks [18,19,20]. Specifically, we performed a range of bibliometric analyses, including co-occurrence analysis, country/region analysis, and institution analysis [21].
In our co-authorship analysis, we examined the most influential authors in the field of ML and biofilm [22]. This analysis revealed several highly productive authors who have made significant contributions to the field. In our co-occurrence analysis, we identified the most common research topics and themes within the body of literature [23]. Our analysis revealed that several key themes emerged, including biofilm formation, biofilm detection, and the use of ML to identify and predict bacterial growth patterns [24]. Additionally, we identified several subtopics within these broader themes, such as the role of different environmental factors in biofilm formation, and the development of ML algorithms to accurately predict bacterial growth [25].
Finally, our citation analysis revealed the most influential publications in this field, as well as the most highly cited articles [26]. We found that several articles have received many citations, indicating that they have had a significant impact on the field. Notably, many of these highly cited articles focused on the use of ML to predict biofilm formation, and the development of new algorithms to better understand bacterial growth patterns.
Our bibliometric analysis provides valuable insights into the current state of research on the application of ML in the context of biofilm [11]. By identifying the most influential authors, institutions, and publications, as well as the most common research themes and trends, we are better equipped to understand the challenges and opportunities associated with this exciting field of study [27,28]. Furthermore, our findings may inform future research efforts, helping to advance our understanding of the complex biological processes involved in biofilm formation and growth [29,30].

3. Results

Our analysis showed that the number of publications on ML in biofilm has been increasing rapidly over the past decade, indicating a growing interest in the application of ML techniques to biofilm research. The analysis also revealed that the most common research topics in this area were related to biofilm formation, prediction, and control. Furthermore, the most frequently used ML techniques in biofilm research were artificial neural networks [31,32,33] and support vector machines [34,35,36].
In terms of authorship, the most influential authors were from a diverse range of institutions, including academic and research institutions, as well as industrial and commercial organizations. The most influential institutions were also diverse and included universities, research centres, and hospitals. The most highly cited publications were focused on the development of ML algorithms for predicting biofilm formation and identifying key genes involved in biofilm formation.
The central portion of Figure 1 depicts the two most significant words in the field, namely "machine learning" and "biofilm formation". Additionally, the figure highlights several other important words related to biofilm formation, such as "Pseudomonas aeruginosa", "expression", "adaptation", "evolution", "virulence", "growth", "dynamics", "mechanism", and "resistance". These words provide insights into the most critical bacteria (P. aeruginosa), processes (adaptation, expression, and growth), and study targets (dynamics, mechanism, and resistance) in biofilm formation research. The words related to machine learning, such as "prediction", "performance", and "system", are linked to the most significant target for ML in biofilm research. This analysis emphasizes the importance of machine learning, particularly in predicting the biofilm formation. Overall, Figure 1 provides a clear overview of the most important words in the field and their interrelationships.
As depicted in Figure 2, there is a global interest in research activities pertaining to the field under investigation, and this has resulted in numerous collaborations between different countries and regions. The visualization highlights the prominent roles of the United States and China in this area, with both countries demonstrating a high level of engagement and contributing significantly to the body of knowledge. However, other countries such as Canada, the United Kingdom, Japan, India, Spain, Germany, Switzerland, Italy, Sweden, Denmark, and South Korea have also been actively involved in this field and have made noteworthy contributions to the advancement of research. The contributions of these countries have enhanced the diversity of research perspectives and approaches, making the field richer and more comprehensive. It is evident that global collaborations and exchange of ideas have played a crucial role in driving progress in this area, and it is expected that this trend will continue in the future.
According to Figure 3, the most important institutions in this research area are Stanford University, the University of Illinois, the University of California at Irvine and San Diego, Sapienza University, the Agricultural University of Athens, Oregon State University, the University of Toronto, the Chinese Academy of Sciences, the Memorial Sloan Kettering Cancer Center, the Jožef Stefan Institute, and the Max Planck Society.

4. Discussion

4.1. Recent and significant papers

In the pursuit of developing effective strategies for managing bacterial biofilms, scientists have continued to explore the potential applications of ML techniques. Upon examining Table 1, which outlines recent and significant papers in the field, it is apparent that ML techniques have been widely employed in the study of biofilms. In fact, one notable study conducted by a group of researchers utilized an ML model to predict the presence of biofilm inhibitory molecules [37]. This investigation incorporated a combination of descriptor, fingerprint, and hybrid models, and the accuracy of these models was found to be impressive, achieving 93%, 88%, and 90%, respectively. Additionally, the software created by this study, Molib, has become a widely utilized tool for predicting small molecules with biofilm inhibitory properties. The implications of this software's success are particularly promising, as it presents an opportunity for therapeutic intervention against bacteria that can form biofilms.
One such investigation involved the use of P. aeruginosa, a commonly studied model organism, to examine the chemical components of essential oils and their potential impact on biofilm formation [5,6]. In this study, the researchers utilized eleven different classification models (F1-F11) to analyse the data and assess the accuracy of the ML predictions. The results showed that the models achieved prediction accuracies ranging from 69% to 98%, demonstrating the effectiveness of ML in identifying essential oil chemical components that may impact biofilm formation. Through their analysis, the authors were able to identify specific essential oil chemical components that were likely responsible for modulating bacterial biofilm formation in both positive and negative ways. This information is invaluable for scientists who are working to develop interventions that can effectively manage biofilms and prevent their potentially harmful effects.
Another article discussed the challenges in treating biofilm-associated infections caused by Staphylococcus aureus and Staphylococcus epidermidis [7]. It explored the potential of essential oils (EOs) as a treatment option and analyzed the ability of 89 EOs to modulate biofilm production in different strains of the bacteria. ML algorithms were applied to the chemical compositions of the EOs to determine their anti-biofilm potencies and identify the chemical components responsible for biofilm production, inhibition, or stimulation for each strain.
In another study, EOs are investigated as natural alternatives to chemotherapeutic drugs for inhibiting biofilm in chronic S. aureus infections [8]. 61 EOs were tested for biofilm modulation and antibacterial activity. Chemical composition was analysed by GC/MS and ML algorithms correlated potency with active components. Select EOs inhibited biofilm growth at 1.00% concentration and were characterized for their ability to alter biofilm organization through scanning electron microscope (SEM) studies.
Another paper presented a novel computational methodology that combines meta-analysis and ML to identify important genes and pathways in biofilm-forming bacteria [38]. This approach was used to analyse gene expression profiles in different strains of S. aureus and identify a set of 36 candidate genes, 11 of which are reported for the first time. These genes are predicted to be important in biofilm formation and can be considered as a signature target list to develop anti-biofilm therapeutics. The study highlights the potential of combining meta-analysis and ML to gain deeper insights into biofilm mechanisms and develop effective therapeutic strategies.
Another study developed a machine-learning-aided cocktail assay for prompt and reliable biofilm detection [39]. Lanthanide nanoparticles with different properties were formulated into the cocktail kits, and the physicochemical heterogeneities of biofilms were transformed into luminescence intensity. The random forest algorithm was used to identify unknown biofilms with an overall accuracy of over 80%. Antibiotic-loaded cocktail nanoprobes efficiently eradicated biofilms, and the technique can serve as a reliable diagnostic tool for biofilm infections. It can also provide instructions for the design of assays for detecting biochemical compounds beyond biofilms.

4.2. Bibliometric analysis on the machine learning in biofilm research

Our bibliometric analysis provides a comprehensive overview of the current state of ML in biofilm research. The analysis highlights the growing interest in the application of ML techniques to biofilm research and the importance of interdisciplinary collaboration between biofilm researchers and ML experts to drive innovation in this field [25].
The most common research topics in this area were related to biofilm formation, prediction, and control, which reflects the urgent need for new strategies for controlling biofilm-related problems [40]. The most frequently used ML techniques in biofilm research were artificial neural networks [31,32,33] and support vector machines [34,35,36], which suggests that these techniques are well-suited for analysing complex biofilm-related data.
In terms of authorship and institutions, our analysis showed that the most influential authors and institutions were from a diverse range of fields, which highlights the interdisciplinary nature of biofilm research. This diversity is important for driving innovation.

4.3. Future recommendation of using ML in bacterial and biofilm studies

The application of big data and ML techniques has become increasingly prevalent in various fields, such as species distribution [41,42], education [43,44], and cancer prediction [45,46]. Based on machine learning, the policymakers can adjust the policy and help the people [41,43,47]. However, despite the numerous studies on bacteria and biofilm, the use of ML in this area remains limited, as highlighted in previous paragraphs.
Bacteria and biofilm are subjects of extensive research in different environmental and industrial settings, including pollutant removal [48,49,50], electricity generation [51,52,53], concrete enhancement [54,55,56], and multi-functional building [57,58,59]. To enhance or weaken biological processes, scientists have devised methods to genetically modify bacterial genes [48], resulting in stronger or weaker biofilms. Despite these advances, the underlying mechanisms of these biological processes remain uncertain [60].
Given the wide-ranging applications and importance of bacteria and biofilm research, it is imperative to explore the potential benefits of integrating ML techniques in this area [61]. By leveraging the vast amounts of data generated through research, ML can help unravel the complex interactions and mechanisms involved in bacterial processes and provide novel insights and predictions [62]. Furthermore, the development of new ML algorithms specifically tailored to the unique challenges posed by bacterial data can potentially yield more accurate and efficient results [63,64].
Overall, the integration of ML in bacteria and biofilm research has the potential to advance our understanding of these important biological processes and may lead to new discoveries and applications in various fields.

References

  1. Flemming, H.-C.; Wingender, J. The biofilm matrix. Nature reviews microbiology 2010, 8, 623–633. [Google Scholar] [CrossRef]
  2. Dufour, D.; Leung, V.; Lévesque, C.M. Bacterial biofilm: structure, function, and antimicrobial resistance. Endod. Top. 2010, 22, 2–16. [Google Scholar] [CrossRef]
  3. Galié, S.; García-Gutiérrez, C.; Miguélez, E.M.; Villar, C.J.; Lombó, F. Biofilms in the Food Industry: Health Aspects and Control Methods. Front. Microbiol. 2018, 9, 898. [Google Scholar] [CrossRef] [PubMed]
  4. Wang, H.; Christiansen, D.E.; Mehraeen, S.; Cheng, G. Winning the fight against biofilms: the first six-month study showing no biofilm formation on zwitterionic polyurethanes. Chem. Sci. 2020, 11, 4709–4721. [Google Scholar] [CrossRef] [PubMed]
  5. Artini, M.; Papa, R.; Sapienza, F.; Božović, M.; Vrenna, G.; Tuccio Guarna Assanti, V.; Sabatino, M.; Garzoli, S.; Fiscarelli, E.V.; Ragno, R. Essential Oils Biofilm Modulation Activity and Machine Learning Analysis on Pseudomonas aeruginosa Isolates from Cystic Fibrosis Patients. Microorganisms 2022, 10, 887. [Google Scholar] [CrossRef] [PubMed]
  6. Artini, M.; Patsilinakos, A.; Papa, R.; Božović, M.; Sabatino, M.; Garzoli, S.; Vrenna, G.; Tilotta, M.; Pepi, F.; Ragno, R. Antimicrobial and antibiofilm activity and machine learning classification analysis of essential oils from different Mediterranean plants against Pseudomonas aeruginosa. Molecules 2018, 23, 482. [Google Scholar] [CrossRef] [PubMed]
  7. Patsilinakos, A.; Artini, M.; Papa, R.; Sabatino, M.; Božović, M.; Garzoli, S.; Vrenna, G.; Buzzi, R.; Manfredini, S.; Selan, L. Machine learning analyses on data including essential oil chemical composition and in vitro experimental antibiofilm activities against Staphylococcus species. Molecules 2019, 24, 890. [Google Scholar] [CrossRef]
  8. Papa, R.; Garzoli, S.; Vrenna, G.; Sabatino, M.; Sapienza, F.; Relucenti, M.; Donfrancesco, O.; Fiscarelli, E.V.; Artini, M.; Selan, L. Essential oils biofilm modulation activity, chemical and machine learning analysis—Application on Staphylococcus aureus isolates from cystic fibrosis patients. International Journal of Molecular Sciences 2020, 21, 9258. [Google Scholar] [CrossRef]
  9. Lavallin, A.; Downs, J.A. Machine learning in geography–Past, present, and future. Geography Compass 2021, 15, e12563. [Google Scholar] [CrossRef]
  10. Johnson, C.H.; Ivanisevic, J.; Siuzdak, G. Metabolomics: beyond biomarkers and towards mechanisms. Nat. Rev. Mol. Cell Biol. 2016, 17, 451–459. [Google Scholar] [CrossRef]
  11. Li, P.; Tong, X.; Wang, T.; Wang, X.; Zhang, W.; Qian, L.; Liao, J.; Diao, W.; Zhou, J.; Wu, W. Biofilms in wound healing: A bibliometric and visualised study. Int. Wound J. 2022, 20, 313–327. [Google Scholar] [CrossRef] [PubMed]
  12. Talafidaryani, M.; Jalali, S.M.J.; Moro, S. Tracing the evolution of digitalisation research in business and management fields: Bibliometric analysis, topic modelling and deep learning trend forecasting. J. Inf. Sci. 2023. [Google Scholar] [CrossRef]
  13. Anwar, M.A.; Zhang, Q.; Asmi, F.; Hussain, N.; Plantinga, A.; Zafar, M.W.; Sinha, A. Global perspectives on environmental kuznets curve: A bibliometric review. Gondwana Res. 2021, 103, 135–145. [Google Scholar] [CrossRef]
  14. Zhang, S.; Mao, G.; Crittenden, J.; Liu, X.; Du, H. Groundwater remediation from the past to the future: A bibliometric analysis. Water Res. 2017, 119, 114–125. [Google Scholar] [CrossRef] [PubMed]
  15. AlRyalat, S.A.S.; Malkawi, L.W.; Momani, S.M. Comparing bibliometric analysis using PubMed, Scopus, and Web of Science databases. JoVE (Journal of Visualized Experiments) 2019, e58494.
  16. Archambault. ; Campbell, D.; Gingras, Y.; Larivière, V. Comparing bibliometric statistics obtained from the Web of Science and Scopus. J. Am. Soc. Inf. Sci. Technol. 2009, 60, 1320–1326. [Google Scholar] [CrossRef]
  17. Gorraiz, J.; Schloegl, C. A bibliometric analysis of pharmacology and pharmacy journals: Scopus versus Web of Science. J. Inf. Sci. 2008, 34, 715–725. [Google Scholar] [CrossRef]
  18. Shah, S.H.H.; Lei, S.; Ali, M.; Doronin, D.; Hussain, S.T. Prosumption: bibliometric analysis using HistCite and VOSviewer. Kybernetes, 1020. [Google Scholar] [CrossRef]
  19. Ji, B.; Zhao, Y.; Vymazal, J.; Mander. ; Lust, R.; Tang, C. Mapping the field of constructed wetland-microbial fuel cell: A review and bibliometric analysis. Chemosphere 2020, 262, 128366. [Google Scholar] [CrossRef]
  20. Ramírez-Malule, H.; Quiñones-Murillo, D.H.; Manotas-Duque, D. Emerging contaminants as global environmental hazards. A bibliometric analysis. Emerg. Contam. 2020, 6, 179–193. [Google Scholar] [CrossRef]
  21. Zhu, Y.; Li, J.J.; Reng, J.; Wang, S.; Zhang, R.; Wang, B. Global trends of Pseudomonas aeruginosa biofilm research in the past two decades: A bibliometric study. Microbiologyopen 2020, 9, 1102–1112. [Google Scholar] [CrossRef]
  22. Liu, P.; Xia, H. Structure and evolution of co-authorship network in an interdisciplinary research field. Scientometrics 2015, 103, 101–134. [Google Scholar] [CrossRef]
  23. Xue, J.; Reniers, G.; Li, J.; Yang, M.; Wu, C.; van Gelder, P. A Bibliometric and Visualized Overview for the Evolution of Process Safety and Environmental Protection. Int. J. Environ. Res. Public Heal. 2021, 18, 5985. [Google Scholar] [CrossRef] [PubMed]
  24. Ju, Y.; Zhang, F.; Yu, P.; Zhang, Y.; Zhao, P.; Xu, P.; Sun, L.; Bao, Y.; Long, H. A Bibliometric Analysis of Research on Bacterial Persisters. BioMed Res. Int. 2023, 2023, 1–15. [Google Scholar] [CrossRef]
  25. Hashemi, S.J.; Bak, N.; Khan, F.; Hawboldt, K.; Lefsrud, L.; Wolodko, J. Bibliometric Analysis of Microbiologically Influenced Corrosion (MIC) of Oil and Gas Engineering Systems. Corrosion 2017, 74, 468–486. [Google Scholar] [CrossRef] [PubMed]
  26. Rickert, C.A.; Hayta, E.N.; Selle, D.M.; Kouroudis, I.; Harth, M.; Gagliardi, A.; Lieleg, O. Machine Learning Approach to Analyze the Surface Properties of Biological Materials. ACS Biomater. Sci. Eng. 2021, 7, 4614–4625. [Google Scholar] [CrossRef]
  27. Qi, Y.; Chen, X.; Hu, Z.; Song, C.; Cui, Y. Bibliometric Analysis of Algal-Bacterial Symbiosis in Wastewater Treatment. Int. J. Environ. Res. Public Heal. 2019, 16, 1077. [Google Scholar] [CrossRef] [PubMed]
  28. Zhang, T.; Yin, X.; Yang, X.; Man, J.; He, Q.; Wu, Q.; Lu, M. Research trends on the relationship between Microbiota and Gastric Cancer: A Bibliometric Analysis from 2000 to 2019. J. Cancer 2020, 11, 4823–4831. [Google Scholar] [CrossRef]
  29. Moura, L.K.B.; Tapety, F.I.; Mobim, M.; Lago, E.C.; de LobÃ, E.S.; Leal, C.M.d.C.L.; Santos, T.C.; Monte, T.L. Bacterial association and oral biofilm formation: A bibliometric analysis. African Journal of Microbiology Research 2016, 10, 1654–1661. [Google Scholar]
  30. Colares, G.S.; Dell'Osbel, N.; Wiesel, P.G.; Oliveira, G.A.; Lemos, P.H.Z.; da Silva, F.P.; Lutterbeck, C.A.; Kist, L.T.; Machado. L. Floating treatment wetlands: A review and bibliometric analysis. Sci. Total. Environ. 2020, 714, 136776. [Google Scholar] [CrossRef]
  31. Lesnik, K.L.; Liu, H. Predicting Microbial Fuel Cell Biofilm Communities and Bioreactor Performance using Artificial Neural Networks. Environ. Sci. Technol. 2017, 51, 10881–10892. [Google Scholar] [CrossRef]
  32. Lahiri, D.; Nag, M.; Sarkar, T.; Dutta, B.; Ray, R.R. Antibiofilm Activity of α-Amylase from Bacillus subtilis and Prediction of the Optimized Conditions for Biofilm Removal by Response Surface Methodology (RSM) and Artificial Neural Network (ANN). Appl. Biochem. Biotechnol. 2021, 193, 1853–1872. [Google Scholar] [CrossRef]
  33. de Ramón-Fernández, A.; Salar-García, M.; Fernández, D.R.; Greenman, J.; Ieropoulos, I. Evaluation of artificial neural network algorithms for predicting the effect of the urine flow rate on the power performance of microbial fuel cells. Energy 2020, 213, 118806. [Google Scholar] [CrossRef] [PubMed]
  34. Shengxian, C.; Yanhui, Z.; Jing, Z.; Dayu, Y. Experimental Study on Dynamic Simulation for Biofouling Resistance Prediction by Least Squares Support Vector Machine. Energy Procedia 2012, 17, 74–78. [Google Scholar] [CrossRef]
  35. Modak, S.; Lahorkar, A.; Valadi, J. Recent Advances in Applications of Support Vector Machines in Fungal Biology. Laboratory Protocols in Fungal Biology: Current Methods in Fungal Biology 2022, 117-136.
  36. Li, X.; Chen, S.; Zhang, J.; Yu, L.; Chen, W.; Zhang, Y. Optimization of Ultrasonic-Assisted Extraction of Active Components and Antioxidant Activity from Polygala tenuifolia: A Comparative Study of the Response Surface Methodology and Least Squares Support Vector Machine. Molecules 2022, 27, 3069. [Google Scholar] [CrossRef] [PubMed]
  37. Srivastava, G.N.; Malwe, A.S.; Sharma, A.K.; Shastri, V.; Hibare, K.; Sharma, V.K. Molib: A machine learning based classification tool for the prediction of biofilm inhibitory molecules. Genomics 2020, 112, 2823–2832. [Google Scholar] [CrossRef] [PubMed]
  38. Subramanian, D.; Natarajan, J. Integrated meta-analysis and machine learning approach identifies acyl-CoA thioesterase with other novel genes responsible for biofilm development in Staphylococcus aureus. Infection, Genetics and Evolution 2021, 88, 104702. [Google Scholar] [CrossRef] [PubMed]
  39. Wang, J.; Jiang, Z.; Wei, Y.; Wang, W.; Wang, F.; Yang, Y.; Song, H.; Yuan, Q. Multiplexed Identification of Bacterial Biofilm Infections Based on Machine-Learning-Aided Lanthanide Encoding. ACS Nano 2022, 16, 3300–3310. [Google Scholar] [CrossRef] [PubMed]
  40. Mdarhri, H.A.; Benmessaoud, R.; Yacoubi, H.; Seffar, L.; Assimi, H.G.; Hamam, M.; Boussettine, R.; Filali-Ansari, N.; Lahlou, F.A.; Diawara, I.; et al. Alternatives Therapeutic Approaches to Conventional Antibiotics: Advantages, Limitations and Potential Application in Medicine. Antibiotics 2022, 11, 1826. [Google Scholar] [CrossRef]
  41. Chen, S.; Ding, Y. Machine Learning and Its Applications in Studying the Geographical Distribution of Ants. Diversity 2022, 14, 706. [Google Scholar] [CrossRef]
  42. Gobeyn, S.; Mouton, A.M.; Cord, A.F.; Kaim, A.; Volk, M.; Goethals, P.L. Evolutionary algorithms for species distribution modelling: A review in the context of machine learning. Ecol. Model. 2019, 392, 179–195. [Google Scholar] [CrossRef]
  43. Chen, S.; Ding, Y. A Machine Learning Approach to Predicting Academic Performance in Pennsylvania’s Schools. Soc. Sci. 2023, 12, 118. [Google Scholar] [CrossRef]
  44. Chen, S.; Ding, Y.; Liu, X. Development of the growth mindset scale: evidence of structural validity, measurement model, direct and indirect effects in Chinese samples. Curr. Psychol. 2021, 42, 1712–1726. [Google Scholar] [CrossRef]
  45. Cammarota, G.; Ianiro, G.; Ahern, A.; Carbone, C.; Temko, A.; Claesson, M.J.; Gasbarrini, A.; Tortora, G. Gut microbiome, big data and machine learning to promote precision medicine for cancer. Nat. Rev. Gastroenterol. Hepatol. 2020, 17, 635–648. [Google Scholar] [CrossRef] [PubMed]
  46. Chen, S.; Ding, Y. A Feasibility Study of Machine Learning Models for Cancer Rate Prediction. Preprints.org 2023, 2023030491. [Google Scholar]
  47. Ding, Y. Heavy metal pollution and transboundary issues in ASEAN countries. Water Policy 2019, 21, 1096–1106. [Google Scholar] [CrossRef]
  48. Ding, Y.; Peng, N.; Du, Y.; Ji, L.; Cao, B. Disruption of Putrescine Biosynthesis in Shewanella oneidensis Enhances Biofilm Cohesiveness and Performance in Cr(VI) Immobilization. Appl. Environ. Microbiol. 2014, 80, 1498–1506. [Google Scholar] [CrossRef] [PubMed]
  49. Ding, Y.; Zhou, Y.; Yao, J.; Szymanski, C.; Fredrickson, J.; Shi, L.; Cao, B.; Zhu, Z.; Yu, X.-Y. In Situ Molecular Imaging of the Biofilm and Its Matrix. Anal. Chem. 2016, 88, 11244–11252. [Google Scholar] [CrossRef]
  50. Ding, Y.; Zhou, Y.; Yao, J.; Xiong, Y.; Zhu, Z.; Yu, X.-Y. Molecular evidence of a toxic effect on a biofilm and its matrix. Anal. 2019, 144, 2498–2503. [Google Scholar] [CrossRef]
  51. Zhao, C.-E.; Wu, J.; Ding, Y.; Wang, V.B.; Zhang, Y.; Kjelleberg, S.; Loo, J.S.C.; Cao, B.; Zhang, Q. Hybrid Conducting Biofilm with Built-in Bacteria for High-Performance Microbial Fuel Cells. ChemElectroChem 2015, 2, 619–619. [Google Scholar] [CrossRef]
  52. Yang, Y.; Ding, Y.; Hu, Y.; Cao, B.; Rice, S.A.; Kjelleberg, S.; Song, H. Enhancing Bidirectional Electron Transfer of Shewanella oneidensis by a Synthetic Flavin Pathway. ACS Synth. Biol. 2015, 4, 815–823. [Google Scholar] [CrossRef]
  53. Zhao, C.-E.; Chen, J.; Ding, Y.; Wang, V.B.; Bao, B.; Kjelleberg, S.; Cao, B.; Loo, S.C.J.; Wang, L.; Huang, W.; et al. Chemically Functionalized Conjugated Oligoelectrolyte Nanoparticles for Enhancement of Current Generation in Microbial Fuel Cells. ACS Appl. Mater. Interfaces 2015, 7, 14501–14505. [Google Scholar] [CrossRef]
  54. Zhang, Z.; Liu, D.; Ding, Y.; Wang, S. Mechanical performance of strain-hardening cementitious composites (SHCC) with bacterial addition. J. Infrastruct. Preserv. Resil. 2022, 3, 1–11. [Google Scholar] [CrossRef]
  55. Zhang, Z.; Ding, Y.; Qian, S. Influence of bacterial incorporation on mechanical properties of engineered cementitious composites (ECC). Constr. Build. Mater. 2019, 196, 195–203. [Google Scholar] [CrossRef]
  56. Zhang, Z.; Weng, Y.; Ding, Y.; Qian, S. Use of Genetically Modified Bacteria to Repair Cracks in Concrete. Materials 2019, 12, 3912. [Google Scholar] [CrossRef]
  57. Hamdany, A.H.; Ding, Y.; Qian, S. Visible light antibacterial potential of graphene-TiO2 cementitious composites for self-sterilization surface. Journal of Sustainable Cement-Based Materials 2022, 1-11.
  58. Hamdany, A.H.; Ding, Y.; Qian, S. Cementitious Composite Materials for Self-Sterilization Surfaces. ACI Mater. J. 2022, 119, 197–210. [Google Scholar] [CrossRef]
  59. Hamdany, A.H.; Ding, Y.; Qian, S. Mechanical and Antibacterial Behavior of Photocatalytic Lightweight Engineered Cementitious Composites. J. Mater. Civ. Eng. 2021, 33, 04021262. [Google Scholar] [CrossRef]
  60. Tribedi, P.; Das Gupta, A.; Sil, A.K. Adaptation of Pseudomonas sp. AKS2 in biofilm on low-density polyethylene surface: an effective strategy for efficient survival and polymer degradation. Bioresour. Bioprocess. 2015, 2, 14. [Google Scholar] [CrossRef]
  61. Sadeghi, M.; Panahi, B.; Mazlumi, A.; Hejazi, M.A.; Komi, D.E.A.; Nami, Y. Screening of potential probiotic lactic acid bacteria with antimicrobial properties and selection of superior bacteria for application as biocontrol using machine learning models. LWT 2022, 162. [Google Scholar] [CrossRef]
  62. Long, F.; Fan, J.; Xu, W.; Liu, H. Predicting the performance of medium-chain carboxylic acid (MCCA) production using machine learning algorithms and microbial community data. J. Clean. Prod. 2022, 377. [Google Scholar] [CrossRef]
  63. Cordier, T.; Lanzén, A.; Apothéloz-Perret-Gentil, L.; Stoeck, T.; Pawlowski, J. Embracing Environmental Genomics and Machine Learning for Routine Biomonitoring. Trends Microbiol. 2019, 27, 387–397. [Google Scholar] [CrossRef]
  64. Long, F.; Wang, L.; Cai, W.; Lesnik, K.; Liu, H. Predicting the performance of anaerobic digestion using machine learning algorithms and genomic data. Water Res. 2021, 199, 117182. [Google Scholar] [CrossRef]
Preprints 70517 g001
Figure 1. Most important words in this research field and their connection by VOSviewer.
Figure 1. Most important words in this research field and their connection by VOSviewer.
Preprints 70517 g001
Preprints 70517 g002
Figure 2. Scientific collaboration network from different countries by VOSviewer.
Figure 2. Scientific collaboration network from different countries by VOSviewer.
Preprints 70517 g002
Preprints 70517 g003
Figure 3. Most important institutions in the field by VOSviewer.
Figure 3. Most important institutions in the field by VOSviewer.
Preprints 70517 g003
Table 1. Summary for recent and important biofilm machine learning studies.
Table 1. Summary for recent and important biofilm machine learning studies.
Model organism Target/Biofilm process ML models ML accuracy Main contributions Year Reference
NA Biofilm inhibitory molecules Classification 88% - 93% ML to predict biofilm inhibitory molecules 2020 [37]
Pseudomonas aeruginosa Essential oil chemical components Binary Classification 69% - 98% ML to identify chemical components responsible for bacterial biofilm formation 2018-2022 [5,6]
Staphylococcus aureus and Staphylococcus epidermidis Essential oil chemical components Binary Classification 68.7% - 90.6% ML to identify chemical component that modulate biofilm production [7]
S. aureus Essential oil chemical components Binary Classification NA ML to predict essential oils modulate biofilm production and inhibit biofilm 2019 [8]
S. aureus acyl-CoA thioesterase Classification 59.46 - 94.59% Identification of 36 candidate genes including an acyl-CoA thioesterase enzyme and
ten hypothetical proteins		 2021 [38]
S. aureus, P. aeruginosa, Acinetobacter baumannii, Stenotrophomonas maltophilia, Escherichia coli Biofilm infection Random forest 95.0% - 100% Using lanthanide nanoparticles detects pathogenic biofilms based on random forest 2022 [39]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

facebook logotwitter logolinkedin logo
MDPI Initiatives
Important Links
Subscribe

Disclaimer

Terms of Use

Privacy Policy

© 2024 MDPI (Basel, Switzerland) unless otherwise stated