Reviewer name and names of any other individual's who aided in reviewer	Guanjing Hu and Cong Sun
Do you understand and agree to our policy of having open and named reviews, and having your review included with the published manuscript. (If no, please inform the editor that you cannot review this manuscript.)	Yes
Is the language of sufficient quality?	Yes
Please add additional comments on language quality to clarify if needed
Is there a clear statement of need explaining what problems the software is designed to solve and who the target audience is?	Yes
Additional Comments
Is the source code available, and has an appropriate Open Source Initiative license <a href="https://opensource.org/licenses" target="_blank">(https://opensource.org/licenses)</a> been assigned to the code?	Yes
Additional Comments
As Open Source Software are there guidelines on how to contribute, report issues or seek support on the code?	Yes
Additional Comments
Is the code executable?	Unable to test
Additional Comments
Is installation/deployment sufficiently outlined in the paper and documentation, and does it proceed as outlined?	Yes
Additional Comments
Is the documentation provided clear and user friendly?	Yes
Additional Comments
Additional Comments
Is there a clearly-stated list of dependencies, and is the core functionality of the software documented to a satisfactory level?	Yes
Additional Comments
Have any claims of performance been sufficiently tested and compared to other commonly-used packages?	No
Additional Comments
Additional Comments
Are there (ideally real world) examples demonstrating use of the software?	Yes
Additional Comments
Additional Comments
Any Additional Overall Comments to the Author	The authors presented Poly Pipeline as a standardized downstream analysis workflow for spatial transcriptomics (ST) data. Built around BGI's Stereopy package, it wraps the downstream analysis into a single packaged pipeline, including a proprietary-format converter (h5ad/GEM to GEF), several clustering methods (Louvain, Leiden, Spatial Leiden, and a custom "anchoring" step), highly variable and marker gene detection, and hdWGCNA-based co-expression network analysis, with benchmarking on wheat, rice, Arabidopsis, and mouse. Relative to Stereopy itself, the added value of Poly Pipeline lies in packaging the full downstream analysis and in its ease of use, rather than in algorithmic innovation. Nevertheless, because it provides a standardized and reproducible ST downstream pipeline, I recommend the paper for publication after the following revisions. Major comment: The title, abstract, and introduction all position "overcoming polyploid complexity" as the primary innovation, but the manuscript does not engage with the core question it raises: what, specifically, does this pipeline do to address polyploid complexity that a standard diploid-oriented pipeline does not? Polyploid genomes present well-defined analytical challenges, including homeologous gene copies that share high sequence similarity, subgenome-specific expression biases, dosage effects from multiple gene copies, and the potential for read multi-mapping ambiguity. These are distinct from the data sparsity problem, which is shared across all ST platforms and organisms. The pipeline's methods rely on Stereopy's Louvain/Leiden clustering (a generic graph-based approach with no homoeolog-aware logic), hdWGCNA's metacell KNN bagging (engineered to mitigate zero-inflated expression matrices, a universal ST issue), and format conversion and standard QC (platform-compatibility benefits, not polyploid-specific). None of these components introduces allele-level or subgenome-level resolution. The pipeline does not, for instance, triage reads by subgenome, assign expression to A/B/D homeologs in wheat, or employ dosage-normalized differential expression. The Discussion's most compelling biological example, PEPC gene subgenome retention and spatial localization in wheat endosperm, is drawn from Millsteed et al. (2025)'s published biological analysis, not from a pipeline-enabled discovery. Framing it as a validation that the pipeline recapitulates known biology is fine; leaving it ambiguous implies an analytical capability the pipeline does not actually provide. Overall, the pipeline has clear value, but it does not target the key polyploid-specific methodology challenges, and the manuscript should not claim otherwise without new analysis to support it. So my recommendation for the authors is either (a) incorporate and demonstrate concrete polyploid-aware analytical modules (e.g., homoeolog-resolved expression quantification, subgenome-aware clustering, or dosage-corrected network construction), or (b) significantly downplay the polyploid-specific claim throughout the manuscript, retitle, revise the abstract, and recast the innovation as "a unified ST workflow validated on diverse organisms including polyploid plants." Minor comments: 1. Verify whether the hdWGCNA package is genuinely used in the scripts. The manuscript's wording regarding hdWGCNA should be consistent with what the code actually runs. 2. The pipeline itself does not demonstrate any improvement in the quality of the raw data. I suggest revising phrases such as "mitigate sparsity and resolve duplicated gene functions" in the abstract, and "solving the sparsity" and "considerably reducing dropouts" in the discussion, to more cautious wording, or supporting them with quantitative evidence. 3. All four benchmark datasets are BGI Stereo-seq, and the main workflow is built on the Stereopy package. I suggest adding at least one complete worked example on 10x Visium or another spatial transcriptomics platform, or restricting the stated "universality" to "universality within the Stereo-seq/Stereopy ecosystem." 4. Further improve the language and the accuracy of the technical terminology. For example: (i) the resolution unit is described as a "nanopore radius," but Stereo-seq is based on DNA nanoball (DNB) patterned arrays, not nanopores; (ii) The statement "1 bin unit representing 10–14 microns" is inaccurate because the bin size is not specified. DNA nanoball diameter is much smaller than 10-14 microns; and (iii) "Giotto se" should be "Giotto."
Recommendation	Minor Revisions