An Alternative Analysis of Computational Learning within Behavioral Neuropharmacology in an Experimental Anxiety Model Investigation

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

 

The use of Bayesian networks/regression trees  and other methods found in the report allows for a sophisticated analysis of behavioral data, revealing   interpretable insights and conclusions.  Clearly, the potential for neuropharmacological endeavors is enhanced via the use of these methodologies as found in the report.  The report “An alternative analysis, computational learning within behavioral neuropharmacology” contains all the noted successful method details and interpretation of the data found in conclusion.  The report is interesting and should be considered as significant in contributing to the field. There are no major concerns. 

 

Minor points:

The text should be gone over to make certain statements more accurate.  For example, in the Discussion section it is stated the study “aimed to”.  This should be the study determined.  Further, the introduction and results section can be shortened by briefly defining the terms/methodologies because experts are reading the document, unless the authors feel the explanations are truly novel.  

The internal labelling/writing in the figures is really small and difficult to read- can this be increased in size?

Comments on the Quality of English Language

See review above

Author Response

Comments 1:

• The text should be gone over to make certain statements more accurate. For example, in the Discussion section it is stated the study “aimed to”.  This should be the study determined.  

Response 1:

Thank you for pointing this out. It was modified (that part of the discussion), and the writing was revised to be more precise and direct. (line 262-265)

 

Comments 2:

• Further, the introduction and results section can be shortened by briefly defining the terms/methodologies because experts are reading the document unless the authors feel the explanations are truly novel.

 Response 2:

 Based on your comment, we have revised and adjusted some of the definitions provided in the document.

 

Comments 3:

• The internal labelling/writing in the figures is really small and difficult to read- can this be increased in size?

Response 3:

Thank you very much for your point. We try to make the images larger; however, this is how the software delivers them to us. We improve the quality of the images for better visualization.

Reviewer 2 Report

Comments and Suggestions for Authors

See the attachment.

Comments for author File: Comments.pdf

Author Response

Comments 1:

• The title is very general and needs more keywords to reflect the authors’ investigations. It can be turn into “An alternative analysis, computational learning within behavioral neuropharmacology on an animal model investigation”. The authors can rephrase it on their own but some keywords should be added.

 Response 1:

We consider the reviewer's points and agree to modify the article's title to "An Alternative Analysis, Computational Learning within Behavioral Neuropharmacology on an Experimental Anxiety Model Investigation."

 

Comments 2:

• In Discussion section, the authors can add more human studies similar to their work (specifically utilized the Machine Learning algorithms) and discuss about the potentialities and weaknesses between human studies and animal studies, then they can suggest more progressions in animal studies and the discussion part will be improved.

Response 2:

Following your comment, we have added a paragraph that discusses some of the work related to the algorithms used and the benefits and weaknesses of using animal and human models. (Line 331-350)

 

Comments 3:

• Additionally, this paper has no tables which is not a good point and by adding one or two tables, the complexities of the text will be decreased and more readers will benefit from this paper. I recommend a general table representing sample characteristics and all of groups and another comprehensive table showing the most important findings of each ML algorithms.

Response 3:

Thank you for pointing this out. We have added the requested tables.