The pathogenic microbiome is the community of microorganisms that live in humans or animals and cause disease. These microorganisms include bacteria, viruses, fungi, protozoa, etc. They usually live in the host's skin, mouth, intestinal tract, genitourinary tract, etc. Normally, there is a state of equilibrium between the host and these microorganisms, but when this equilibrium is disturbed, these microorganisms become the pathogenic microbiome and cause disease. To advance the field of microbiome research, artificial intelligence methods, especially machine learning and deep learning, have recently been used as important tools due to their powerful predictive and informative potential.
Classical machine learning algorithms such as linear regression, random forests, support vector machines, etc. perform well on microbiome data. However, as algorithms have been iteratively updated, these models have long been relegated to the basics. Linear regression models are now more often used to interpret these models more intuitively by using the output of other models as input. Deep learning is a branch of machine learning that involves a large number of neural network structures. Deep learning relies on neurons whose role is to transform the input and propagate it forward to the next neuron. Deep learning is currently being used with spectacular success in areas such as image recognition, text processing and automatic translation. As a result, a growing number of researchers are attempting to apply deep learning techniques to biomedical data analysis. Although there are still challenges in practical applications, such as model interpretability, data availability, model evaluation and selection, machine learning and deep learning are very promising tools in pathogenic microbiome research.
This Research Topic, therefore, aims to contribute to the latest advances in machine learning, especially deep learning, and to explore new applications of related techniques in pathogenic microbiome research, trying to find relationships between microbiome and human health as well as the environment by studying high-throughput sequencing data of microbes, laying the foundation for further applications for subsequent treatment or forensic identification.
We welcome submissions of Original Research, Brief Research Report, Review, Mini-Review, Methods, Perspective and Opinion articles that focus on, but are not limited to, the utilization of machine learning and deep learning to address the following subtopics.
1. Classification and identification of pathogenic microorganisms
2. Virulence prediction of pathogenic microorganisms
3. Antimicrobial resistance prediction of pathogenic microorganisms
4. Population structure and epidemiology of pathogenic microorganisms-related diseases
5. Immunological studies of pathogenic microorganisms
6. Drug target prediction for pathogenic microorganisms-related diseases
The pathogenic microbiome is the community of microorganisms that live in humans or animals and cause disease. These microorganisms include bacteria, viruses, fungi, protozoa, etc. They usually live in the host's skin, mouth, intestinal tract, genitourinary tract, etc. Normally, there is a state of equilibrium between the host and these microorganisms, but when this equilibrium is disturbed, these microorganisms become the pathogenic microbiome and cause disease. To advance the field of microbiome research, artificial intelligence methods, especially machine learning and deep learning, have recently been used as important tools due to their powerful predictive and informative potential.
Classical machine learning algorithms such as linear regression, random forests, support vector machines, etc. perform well on microbiome data. However, as algorithms have been iteratively updated, these models have long been relegated to the basics. Linear regression models are now more often used to interpret these models more intuitively by using the output of other models as input. Deep learning is a branch of machine learning that involves a large number of neural network structures. Deep learning relies on neurons whose role is to transform the input and propagate it forward to the next neuron. Deep learning is currently being used with spectacular success in areas such as image recognition, text processing and automatic translation. As a result, a growing number of researchers are attempting to apply deep learning techniques to biomedical data analysis. Although there are still challenges in practical applications, such as model interpretability, data availability, model evaluation and selection, machine learning and deep learning are very promising tools in pathogenic microbiome research.
This Research Topic, therefore, aims to contribute to the latest advances in machine learning, especially deep learning, and to explore new applications of related techniques in pathogenic microbiome research, trying to find relationships between microbiome and human health as well as the environment by studying high-throughput sequencing data of microbes, laying the foundation for further applications for subsequent treatment or forensic identification.
We welcome submissions of Original Research, Brief Research Report, Review, Mini-Review, Methods, Perspective and Opinion articles that focus on, but are not limited to, the utilization of machine learning and deep learning to address the following subtopics.
1. Classification and identification of pathogenic microorganisms
2. Virulence prediction of pathogenic microorganisms
3. Antimicrobial resistance prediction of pathogenic microorganisms
4. Population structure and epidemiology of pathogenic microorganisms-related diseases
5. Immunological studies of pathogenic microorganisms
6. Drug target prediction for pathogenic microorganisms-related diseases
