Prediction of Intrinsically Disordered Proteins Using Machine Learning Algorithms Based on Fuzzy Entropy Feature
Round 1
Reviewer 1 Report
This study proposed a predictor for intrinsically disordered proteins using machine learning algorithms based on fuzzy entropy features. It is a resubmitted manuscript, the authors have addressed some previous comments. However, there are some comments that need room for improvement:
1. Did the authors remove similar sequences before training? What was the similarity cut-off level?
2. Some machine learning algorithms are simple and well-known, thus the authors don't need to re-describe them in every detail.
3. Since there are a lot of machine learning algorithms, what is the idea behind the use of SVM, LDA, and BP rather than the others?
4. PSSM is a 2D matrix, how did the authors fit it into machine learning models?
5. When comparing different models/methods, it is suggested to have some statistical tests to see the significant differences. p-value also needs to be shown.
6. The authors should have more discussions on the biological insights of their models/findings.
7. For this kind of problem, it is mandatory to provide a web server to support users to use the prediction models.
8. "Data preprocessing" could be moved to "Methods".
9. The authors should combine Tables 5-6-7 into one.
10. Source codes should be provided for replicating the methods.
Author Response
Dear reviewer
Thank you for your efforts in the review of our manuscript.
Please see the attachment.
Best regards
Author Response File: 
Author Response.docx
Reviewer 2 Report
Thanks, authors for developing the paper considerably. All required modifications are applied and the paper can be published.
Author Response
Dear reviewer
Thank you very much for your recognition of our work!
Please see the attachment.
Best regards
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
My previous comments have been addressed well.
Reviewer 2 Report
Thanks authors to apply all required modifications.
