UNIVERSITY OF PORT HARCOURT
FACULTY OF SCIENCE
DEPARTMENT OF MICROBIOLOGY
A SEMINAR PRESENTATION
ON
MACHINE LEARNING APPLICATIONS AND TOOLS EMPLOYED IN ENVIRONMENTAL
MICROBIOLOGY
BY
IHEANYI, FAITH
U2020/5555184
COURSE CODE: MCB 409.2
COURSE TITLE: SEMINAR IN MICROBIOLOGY AND
BIOTECHNOLOGY COURSE COORDINATOR: DR. J. N OMORODION
1
PROJECT SUPERVISOR: : PROF C .B CHIKERE
OUTLINE
• Introduction
• Application of Machine Learning
• Main Parts of Machine Language
• Types of Machine Learning
• Tools of Machine Learning in Environmental Microbiology
• Challenges
• Conclusion
2
• References
INTRODUCTION
• Environmental microbiology studies the interactions between microorganisms
and their natural or human-made environments (Singh et al., 2021).
• It examines how microbes contribute to ecological processes such as nutrient
cycling, biodegradation, and climate regulation, as well as their overall impact
on Earth's systems.
3
Singh, B. K., Trivedi, P., Egidi, E., Macdonald, C. A., & Delgado-Baquerizo, M. (2021). Microbial contributions to climate change through
carbon cycle feedbacks. ISME Journal, 15, 782–788. https://doi.org/10.1038/s41396-020-00880-y
Fig. 1: Environmental microbiology interfaces with many other fields of microbiology.
Reproduced from: Maier et al., (2009)
4
Maier, R. M., Pepper, I. L., & Gerba, C. P. (2009). Introduction to Environmental Microbiology. Environmental Microbiology, 3–7.
https://doi.org/10.1016/B978-0-12-370519-8.00001-8
INTRODUCTION CONT’D
• Machine learning (ML) is a subset of artificial intelligence that focuses on
building systems capable of learning from data, identifying patterns, and making
decisions without being explicitly programmed (Zhang et al., 2022).
• It enables computers to improve their performance on tasks over time through
experience and data-driven insights (Abiodun et al., 2021).
• Machine learning (ML) has become an indispensable tool in microbial studies,
the microbial world encompasses diverse species and interactions, many of which
are challenging to decipher using traditional methods alone.
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2021). Comprehensive review
of artificial neural network applications to pattern recognition. IEEE Access, 7, 158820–158846.
https://doi.org/10.1109/ACCESS.2019.2945545 5
Zhang, Y., Ren, S., Liu, Y., & Si, S. (2022). Machine learning and deep learning for smart manufacturing: Challenges
and opportunities. Journal of Manufacturing Systems, 62, 837–857. https://doi.org/10.1016/j.jmsy.2022.01.011
APPLICATION OF MACHINE LEARNING
1. Disease detection and medical imaging analysis (Esteva et al., 2019).
2. Personalized healthcare and treatment recommendation (Esteva et al., 2019).
3. Crop yield prediction and pest detection in agriculture
4. Soil quality and irrigation management
5. Environmental monitoring and pollution prediction (Willcock et al., 2018).
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., ... & Dean, J. (2019). A guide to deep
6
learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-0316-z
Willcock, S., Martínez-López, J., Hooftman, D. A. P., Bagstad, K. J., Balbi, S., Marzo, A., ... & Bullock, J. M. (2018).
Machine learning for ecosystem services. Ecosystem Services, 33, 165–174.
MAIN PARTS OF MACHINE LEARNING SYSTEM
University of California, Berkeley breaks out the learning system of a machine
learning algorithm into three main parts.
3. A Model
1. Decision 2. An Error
Optimization
Process Function
Process
7
TYPES OF MACHINE LEARNING
1. Supervised Learning: Supervised learning (Stoter et al., 2019) requires that
the model be trained using a training set.
2. Unsupervised learning,
3. Reinforcement Learning (RL)
8
Stoter, J., de Koning, D., & van Wijk, M. (2019). Supervised machine learning in land use classification: A
review of current applications and future directions. Remote Sensing, 11(14), 1643.
https://doi.org/10.3390/rs11141643
Fig. 2: Construction and analysis of metagenomic libraries.
Reproduced from: Fuller (2008)
9
Fuller, N. R. (2008). Construction and analysis of metagenomic libraries [Illustration]. In National Science Foundation,
U.S. Department of Energy Genomics Program. Retrieved from https://genomics.energy.gov
APPLICATIONS OF MACHINE LEARNING IN ENVIRONMENTAL
MICROBIOLOGY
1. Microbial Community Analysis and Metagenomics -It involves extracting
DNA directly from an environmental sample e.g. seawater, soil, the human gut–
and then studying the DNA sample.
10
APPLICATIONS OF MACHINE LEARNING IN ENVIRONMENTAL
MICROBIOLOGY CONT’D
2. Prediction of Microbial Interactions and Functions
3. Antibiotic Resistance Gene Detection
11
MACHINE LEARNING TOOLS IN ENVIRONMENTAL MICROBIOLOGY
1. Bioinformatics and Data Processing Tools
2. Machine Learning Platforms
3. Data Visualization and Statistical Analysis Tools
4. Cloud Computing and Big Data Platforms
12
CHALLENGES
• Limited availability of high-quality labeled data
• Complexity and diversity of environmental microbial communities
• High computational requirements for large datasets
• Difficulty in interpreting machine learning model outputs
13
CONCLUSION
• Machine learning has emerged as a powerful tool in environmental
microbiology offering various capabilities yet limited. Through
interdisciplinary collaboration, standardized protocols, and continuous
technological development the power of machine learning for environmental
sustainability and microbial research can be fully harnessed.
14
REFERENCES
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2021).
Comprehensive review of artificial neural network applications to pattern recognition. IEEE Access,
7, 158820–158846. https://doi.org/10.1109/ACCESS.2019.2945545.
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., ... & Dean, J. (2019). A guide
to deep learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-
0316-z
Fuller, N. R. (2008). Construction and analysis of metagenomic libraries [Illustration]. In National Science
Foundation, U.S. Department of Energy Genomics Program. Retrieved from
https://genomics.energy.gov
Singh, B. K., Trivedi, P., Egidi, E., Macdonald, C. A., & Delgado-Baquerizo, M. (2021). Microbial
contributions to climate change through carbon cycle feedbacks. ISME Journal, 15, 782–788.
https://doi.org/10.1038/s41396-020-00880-y
Stoter, J., de Koning, D., & van Wijk, M. (2019). Supervised machine learning in land use classification: A
review of current applications and future directions. Remote Sensing, 11(14), 1643.
https://doi.org/10.3390/rs11141643
Zhang, Y., Ren, S., Liu, Y., & Si, S. (2022). Machine learning and deep learning for smart manufacturing:
Challenges and opportunities. Journal of Manufacturing Systems, 62, 837–857.
https://doi.org/10.1016/j.jmsy.2022.01.011.
15
THANK YOU
FOR
LISTENING
16
