All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
The paper was well improved and both reviewers accepted the paper.
[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]
No comments
No comments
No comments
No comments
The authors must respond more detailed to the second reviewer!
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
The authors have substantially improved the manuscript and it can be accepted for publication.
no comment
no comment
For my first comment, the authors responded, "Exploration of diversified methods for analysis of data is truly required as per the suggestions. As the current focus and this work are mainly focused on the detection of the abiotic stress with the snareproteins, the authors can consider this and carry out as a further work. "
This is a very poor response and the authors should at least discuss the methods in the introduction or discussion section.
The authors used a method called MDA to create feature visualization without referring to the paper or the code repository.
no comment
no comment
no comment
The article must be improved according to all suggestions from reviewers!
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors agree that they are relevant and useful.
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** PeerJ staff have identified that the English language needs to be improved. When you prepare your next revision, please either (i) have a colleague who is proficient in English and familiar with the subject matter review your manuscript, or (ii) contact a professional editing service to review your manuscript. PeerJ can provide language editing services - you can contact us at [email protected] for pricing (be sure to provide your manuscript number and title). – PeerJ Staff
The authors have used some old references in related work and the introduction section. Please go through some recent state-of-the-art published work related to the field and update it accordingly.
• The related work lacks coherence. To address this, consider presenting the information in a tabular format, allowing for a comparison of methods based on criteria such as technique, dataset, novelty, etc.
Can you provide more details regarding the concept of "early detection" mentioned in the manuscript's title? Does it pertain to the identification of abiotic or biotic stressors before their visible symptoms become apparent? If this is the case, kindly elaborate further on the process of early detection.
•
• Does Processing the protein information in 20X20 dimension can cause loss of data? Is their any way to process it in 1D form?
• Please mention the train test and validation split in Figure 4.
• Additionally, include details about the hyperparameters utilized during the model training process.
mentioned above
No comments
Further benchmarking is necessary with state-of-the-art tabular data analysis techniques such as DeepInsight [1] and Genomap [2].
[1] Sharma, A., Vans, E., Shigemizu, D. et al. DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture. Sci Rep 9, 11399 (2019).
[2] Islam, M.T., Xing, L. Cartography of Genomic Interactions Enables Deep Analysis of Single-Cell Expression Data. Nat Commun 14, 679 (2023).
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors agree that they are relevant and useful.
To better validate the findings and improve the interpretability, visualization of the deep learning feature space is necessary. I would suggest the authors use deep learning feature space analysis tools such as MDA (https://github.com/xinglab-ai/mda, published in Nature Communications) to show the distribution of the data in the feature space. The authors should show a) the distribution in at least 4 intermediate layers to show how their network is performing prediction, b) the distribution of data at one layer (preferably one of the final layers) with change in epoch to better understand the feature extraction process by their network. c) add some Gaussian noise to testing data and then show the feature distribution using MDA to visualize the robustness of their network. The authors can choose any other network such as GoogleNet/DenseNet to show side-by-side comparisons of the MDA visualizations of the feature space with their network.
The paper is overall well-written. However, the figure resolution should be improved. The captions of the figures should be more descriptive.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.