- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The author of this paper introduce a simple and interpretable geometric framework for learning depth coordinate of tissue from spatial transcritomics data. The idea of the paper is follow. First, identifies dominant direction of expression change at each spot, second assign the sign to these axis through spectral synchronization so the directions points consistently across the tissue and finally using Hodge projection integrate direction field into a scaler depth. The authors also provide a clean theoretical analysis when the layer structure is identifiable, and the order of layer can be recovered. On both synthetic data and Visium data outperforms the baselines.
Critical strengths
-
The central idea of the paper is clean and clear, and they break down the problem into distinct steps make it very easy to understand and follow.
-
I found the theoretical analysis the paper strong and substantial, especially analysis where the method can fail.
-
Depth ordering results is very convincing ( correlation improves from 0.690 (GASTON) to 0.885, and adjacent layer AUC from 0.834 to 0.901 )
Critical weaknesses
-
Biological scope and validation is very narrow: The experimental data is used in this study is strongly layered (cortical tissue) and its matches strongly with the assumption of the model. It's unclear how the method works on tissues with branches, niches or other competing spatial patterns.
-
The paper lack clean and well controlled ablation to attribute the clustering gain to the depth.
-
Limited sensitivity analysis of the hyper parameters
Questions for authors
- Could you please show results on a non layered tissue?
2.Could you please run every baseline through the same downstream decoder to estimate the contribution of the depth?
- How the results changes w.r.t the neighborhood size k and other hyper parameters?
3 comments
Evaluation on non-layered cancer tissues
1. Evaluation on non-layered cancer tissues
To assess whether HodgeDepth is useful beyond layered cortex, we evaluated it on spatial transcriptomics data from two cancers whose pathology annotations lack a clear laminar organization.
- Colorectal cancer. We analyzed two sections,
SN123_A798015_Rep1andSN124_A798015_Rep2, each with 12 valid pathology categories, from Valdeolivas et al. (2024). - Breast cancer. We analyzed spatial transcriptomics data with HE images with seven annotated pathology categories in Wu et al. (2021).
ARI values are relatively low across all methods on both datasets, consistent with the difficulty of recovering fragmented pathology regions in which spots from different categories are spatially intermingled. HodgeDepth achieves the highest ARI on both datasets. Its ARI is 0.2635 in colorectal cancer, compared with 0.1651 for the strongest baseline, SpatialPCA, and 0.3913 in breast cancer, compared with 0.2136 for the strongest baseline, SpaGCN-noHE. These results suggest that the learned depth representation can aid pathology-domain recovery even in tissues without a clear layered structure.
In addition to the colorectal and breast cancer studies, we evaluated HodgeDepth on a lung adenocarcinoma section and reported the results in our response to Point 3.2 above. HodgeDepth achieved the highest ARI in all three cancer studies, providing evidence that its utility for spatial domain recovery extends beyond layered tissues.
1.1. Colorectal cancer
| Method | ARI rank | ARI ↑ | NMI ↑ | AMI ↑ | Matched accuracy ↑ | Completeness ↑ | V-measure ↑ | FMI ↑ |
|---|---|---|---|---|---|---|---|---|
| HodgeDepth | 1 | 0.2635 | 0.4185 | 0.4064 | 0.4228 | 0.4669 | 0.4185 | 0.4458 |
| GraphST | 9 | 0.1293 | 0.3344 | 0.3227 | 0.2935 | 0.3207 | 0.3344 | 0.2667 |
| GASTON | 8 | 0.1373 | 0.3383 | 0.3259 | 0.3309 | 0.3185 | 0.3383 | 0.2663 |
| STAGATE | 6 | 0.1449 | 0.3747 | 0.3630 | 0.3150 | 0.3505 | 0.3747 | 0.2705 |
| SEDR | 7 | 0.1445 | 0.3797 | 0.3682 | 0.3131 | 0.3503 | 0.3797 | 0.2668 |
| SpaceFlow | 10 | 0.1289 | 0.3473 | 0.3354 | 0.2739 | 0.3168 | 0.3473 | 0.2489 |
| SpaGCN-noHE | 4 | 0.1516 | 0.3760 | 0.3645 | 0.3150 | 0.3463 | 0.3760 | 0.2721 |
| SpatialPCA | 2 | 0.1651 | 0.3534 | 0.3412 | 0.3309 | 0.3319 | 0.3534 | 0.2930 |
| BayesSpace | 5 | 0.1502 | 0.3727 | 0.3611 | 0.3419 | 0.3472 | 0.3727 | 0.2740 |
| BASS | 3 | 0.1544 | 0.3708 | 0.3589 | 0.3346 | 0.3489 | 0.3708 | 0.2825 |
1.2. Breast cancer
| Method | ARI rank | ARI ↑ | NMI ↑ | AMI ↑ | Matched accuracy ↑ | Completeness ↑ | V-measure ↑ | FMI ↑ |
|---|---|---|---|---|---|---|---|---|
| HodgeDepth | 1 | 0.3913 | 0.3396 | 0.3376 | 0.6393 | 0.2999 | 0.3396 | 0.6479 |
| GraphST | 8 | 0.1303 | 0.3080 | 0.3061 | 0.3576 | 0.2450 | 0.3080 | 0.4169 |
| GASTON | 3 | 0.1968 | 0.2674 | 0.2653 | 0.4088 | 0.2091 | 0.2674 | 0.4619 |
| STAGATE | 9 | 0.1265 | 0.3002 | 0.2982 | 0.3700 | 0.2353 | 0.3002 | 0.4103 |
| SEDR | 10 | 0.1008 | 0.2667 | 0.2647 | 0.2631 | 0.2053 | 0.2667 | 0.3669 |
| SpaceFlow | 6 | 0.1547 | 0.3079 | 0.3060 | 0.3442 | 0.2376 | 0.3079 | 0.4140 |
| SpaGCN-noHE | 2 | 0.2136 | 0.3239 | 0.3220 | 0.4127 | 0.2538 | 0.3239 | 0.4712 |
| SpatialPCA | 7 | 0.1435 | 0.2708 | 0.2688 | 0.3846 | 0.2095 | 0.2708 | 0.4098 |
| BayesSpace | 4 | 0.1903 | 0.3348 | 0.3430 | 0.3890 | 0.2659 | 0.3448 | 0.4483 |
| BASS | 5 | 0.1790 | 0.3016 | 0.2997 | 0.3252 | 0.2313 | 0.3016 | 0.4345 |
Response to Authors’ Rebuttal and Updated Assessment
Thanks to authors for addressing my all three concerns and conducting experiments for my question 1 about non layered tissue and 3 about neighbourhood size k/hyperparameters. I suggest including these results in the main paper/ supplementary material. For question 2 of downstream decoder, the authors provided an explanation of not applying the joint expression depth decoder of HodgeDepth to all baselines but I still recommend to mention this in benchmark tables and annotate that which methods were evaluated using exactly the same downstream decoder and spatial voting as HodgeDepth and which methods were evaluated using their native clustering pipelines. This will help the readers to clearly understand the implementation details of all benchmarks including the HodgeDepth. Based on the author response I am happy to raise my rating to weak acceptance.
Shared-Decoder Comparisons and Hyperparameter Sensitivity
We greatly appreciate your thoughtful comments and thank you for these suggestions. The original ablations left open how much of the clustering improvement came from the learned depth coordinate under a shared decoder. Following your and other reviewers’ comments, we conducted additional ablation experiments, sensitivity analyses, and applications to non-layered tissue data. To avoid redundancy, we attach the results in the responses to the first reviewer's questions above
2. Shared-decoder comparison and other ablations.
In Point 4 of our response to Reviewer 1, we use a shared GMM to compare expression alone; expression combined with HodgeDepth or GASTON depth (the alternative single-index representation); and HodgeDepth alone, each with and without spatial voting. Adding HodgeDepth improves mean ARI over expression alone by 0.170 before voting and 0.115 after voting. Compared with expression plus GASTON depth, the corresponding gains are 0.106 and 0.117.
In our benchmark, GraphST and SpaGCN already use the same clustering decoder and spatial voting as HodgeDepth. The remaining baselines retain their native clustering pipelines. Most already incorporate gene expression and neighborhood-based smoothing or voting at intermediate stages, so applying our joint expression–depth decoder is not straightforward for those approaches.
We also ablate projector smoothing, neighborhood-asymmetry correction, eigen-contrast, and confidence weighting, including stage-specific confidence removals (Point 5). Ablating projector smoothing, neighborhood-asymmetry correction, eigen-contrast, or confidence weighting, including one stage at a time, has little effect on layer ordering on the original counts.
3. Sensitivity to neighborhood size and other hyperparameters
Point 6 reports sweeps over local regression neighborhood size k, the number of expression PCs, smoothing strength, depth-feature weight, voting neighborhood size, and the number of voting passes. Mean absolute Spearman correlation stays between 0.887 and 0.892 for the tested settings with k≥48 and at least eight PCs. At 14 PCs, it falls to 0.843 at k=24 and 0.467 at k=12. It is stable for the tested smoothing coefficients from 0 to 1 and falls to 0.849 at λP=10. In the clustering sweeps, mean ARI ranges from 0.618 to 0.619 for depth-feature weights from 0.5 to 8, and from 0.614 to 0.619 for voting neighborhoods of 25 to 150 spots. These results indicate that HodgeDepth's strong performance is robust to hyperparameter choices.