Applications of Artificial Intelligence in Microbiome Analysis and Probiotic Interventions—An Overview and Perspective Based on the Current State of the Art

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The manuscritp provides an interesting overview abour AI approaches for microbiome analysis and their utilization in clinical research. However, you need to address some observations for manuscript improving.

 

Lines 47-49: Include citation or references to recent studies.

Table 1, point 4. It is preferable to specify the differences between genomics and metagenomics, as well as between microbiota (microbial composition) and microbiome (functional description of microbiota genes).

Lines 163-165 and Lines 197-199: The sentences are very similar and redundant.

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Reviewer 1.

Comments 1: The manuscript provides an interesting overview about AI approaches for microbiome analysis and their utilization in clinical research.

However, you need to address some observations for manuscript improving. Lines 47-49: Include citation or references to recent studies. Table 1, point 4. It is preferable to specify the differences between genomics and metagenomics, as well as between microbiota (microbial composition) and microbiome (functional description of microbiota genes). Lines 163-165 and Lines 197-199: The sentences are very similar and redundant.

Comments 1: We thank the reviewer for his appreciation. We have, accordingly, done all the changes suggested by the reviewer.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The manuscript presented herein aims to review the applications of artificial intelligence in microbiome analysis and probiotic intervention. However, it reads more like a future perspective to the reviewer since few established cases/studies was discussed or reviewed here. The manuscript discussed more of what AI could possibly do rather than any progress in this field.

Besides, some portion of the manuscript is redundant. For example, Line 194 to 199 is a copy of line 160 to 165.

Author Response

Reviewer 2

The manuscript presented herein aims to review the applications of artificial intelligence in microbiome analysis and probiotic intervention. However, it reads more like a future perspective to the reviewer since few established cases/studies was discussed or reviewed here. The manuscript discussed more of what AI could possibly do rather than any progress in this field.

Besides, some portion of the manuscript is redundant. For example, Line 194 to 199 is a copy of line 160 to 165.

 

Comments 2: Thank you for your insightful feedback. We would like to clarify that the manuscript is intended to be a perspective, as stated, rather than a traditional review. The aim is to offer a forward-looking view on the potential applications of artificial intelligence in microbiome analysis and probiotic intervention, highlighting future directions rather than focusing solely on established cases.

We appreciate your note regarding the redundancy between lines 160-165 and 194-199. We will revise the manuscript to remove this duplication and improve its clarity."

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

General concept comments

The article discussed the importance of intestinal microbiota to human health and the application of artificial intelligence (AI) in this field. The intestinal microbiota is a complex microbial ecosystem that closely interacts with the host's immune and metabolic system and plays an important role in the regulation of digestion, vitamin production, and immune response. In recent years, the progress of AI has provided a new way to study these complex functions, especially in chronic inflammatory diseases and probiotic interventions. AI, especially ML and DL, shows their advantages in processing high-dimensional and heterogeneous data. The specific methods mentioned in the article, such as random forest, support vector machine, convolutional neural network, etc., show the wide application and future development potential of AI in microbiome data analysis.

Specific comments

1. If possible, add some specific data or charts(such as abstract figures) to show the performance of AI technology (such as DeepMicro) in practical applications.

2. The detailed description of AI and ML technologies should be clearer. For example, explain the working principle of "high-throughput sequencing data" and "deep learning model" to help readers better understand the technology behind it

3. Introduce more case studies of practical applications to illustrate the actual performance and effect of AI technology in different environments.

4. Please carefully check the references to ensure their accuracy and necessity.

5. Line 18-19, “ artificial intelligence(AI)” should be changed into “AI”. The author should pay attention to use the abbreviations.

7. From Introduction. Ensure that the use of terms is consistent. For example, when talking about "chronic inflammatory disease", consider using "chronic inflammatory disease" as a consistent expression and remain consistent in the full text.

8. I suggest that including more details on the AI methodologies and their comparative advantages would provide a more comprehensive view of their application in microbiome analysis.

9. Consider adding a brief description of the types of machine learning models used and how they are specifically applied in clustering techniques in Metabolomics.

10. 10. Providing examples of specific machine learning algorithms used for protein interaction analysis could improve understanding.

Comments on the Quality of English Language

English language needs to be modified.

Author Response

Reviewer 3

General concept comments

The article discussed the importance of intestinal microbiota to human health and the application of artificial intelligence (AI) in this field. The intestinal microbiota is a complex microbial ecosystem that closely interacts with the host's immune and metabolic system and plays an important role in the regulation of digestion, vitamin production, and immune response. In recent years, the progress of AI has provided a new way to study these complex functions, especially in chronic inflammatory diseases and probiotic interventions. AI, especially ML and DL, shows their advantages in processing high-dimensional and heterogeneous data. The specific methods mentioned in the article, such as random forest, support vector machine, convolutional neural network, etc., show the wide application and future development potential of AI in microbiome data analysis.

 

 

Specific comments

1. If possible, add some specific data or charts(such as abstract figures) to show the performance of AI technology (such as DeepMicro) in practical applications.
2. The detailed description of AI and ML technologies should be clearer. For example, explain the working principle of "high-throughput sequencing data" and "deep learning model" to help readers better understand the technology behind it
3. Introduce more case studies of practical applications to illustrate the actual performance and effect of AI technology in different environments.
4. Please carefully check the references to ensure their accuracy and necessity.
5. Line 18-19, “ artificial intelligence(AI)” should be changed into “AI”. The author should pay attention to use the abbreviations.
6. From Introduction. Ensure that the use of terms is consistent. For example, when talking about "chronic inflammatory disease", consider using "chronic inflammatory disease" as a consistent expression and remain consistent in the full text.
7. I suggest that including more details on the AI methodologies and their comparative advantages would provide a more comprehensive view of their application in microbiome analysis.
8. Consider adding a brief description of the types of machine learning models used and how they are specifically applied in clustering techniques in Metabolomics.
9. Providing examples of specific machine learning algorithms used for protein interaction analysis could improve understanding.

 

Comments 3:

Thank you for your valuable and specific comments. Your feedback has greatly contributed to improving the manuscript, and we appreciate the opportunity to refine our work based on your suggestions. Please find the point-by-point detailed responses to comments and suggestions:

 

For points 1-3:

2.2. Machine Learning (ML) and deep learning approaches for microbiome data analysis

 

High-throughput sequencing data is particularly useful in microbiome research because it provides a detailed snapshot of microbial diversity. AI models, like DeepMicro, can process these huge datasets to detect patterns, classify microbes, and predict disease associations. Without AI, it would be extremely difficult to analyze the large volumes of data produced by high-throughput sequencing.

Deep learning is a subset of ML, which is itself a branch of AI. Deep learning models use multiple layers of artificial neurons, similar to how the human brain works, to process and analyze complex data. These models are particularly useful when dealing with unstructured data like images, text, or, in this case, microbiome sequencing data. At the core of deep learning are neural networks. These are computational models made up of interconnected layers of artificial neurons. Each neuron takes input, performs a computation (usually a mathematical function), and produces an output, which is passed to the next layer of neurons.

A deep learning model, such as DeepMicro, can be trained on microbiome sequencing data. After training, it can predict whether a specific microbial composition is associated with conditions like IBD or other CIDs. The model can learn patterns that link the presence or absence of certain microbial species to health outcomes, making it a powerful tool in precision medicine [12].

 

 

5. Conclusions and Future Perspective

High-throughput sequencing generates vast amounts of microbiome data, capturing the diversity and complexity of microbial communities. Deep learning models, like DeepMicro, are powerful AI tools that can analyze this data, extract patterns, and make predictions about health outcomes, such as identifying potential disease markers or predicting the success of probiotic interventions. These technologies together enable a much deeper understanding of the microbiome and its impact on human health, providing the foundation for the development of AI-driven solutions in microbiome-based therapies.

Points 4-6. Done

Points 7-10. The figure 1 was entirely redone to respond to the reviewer's requests

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The manuscript presented herein reviewed machine learning methods for microbiome data analysis and offered a perspective on the applications of artificial intelligence in microbiome analysis and probiotic intervention. It could serve as a good guidance for AI scientists as it provides clinical scenarios where AI could be of great help.

Reviewer 3 Report

Comments and Suggestions for Authors

This manuscript might be accepted for publication.

Comments on the Quality of English Language

Much better.