- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces Zoom ST, a framework to learn spatial-transcriptomic representations from gene expression and coordinates (spatial component) using nested neighborhoods and neural ODE to predict representations at intermediate sizes not seen during training. It tackles a relevant problem with impact for the community; how spatial transcriptomic representations change as tissue context expands. The authors performed the evaluation on held-out mouse and human tissue sections showing promissing results; The novelty of this work consists of providing an axis for analyzing tissue-context dependence, for that they treat the spatial granularities as a lernable component of spatial transcriptomics pre-training.
Critical strengths
• The paper tackles a relevant problem for the scientific community by modeling and proposing a framework to understand how spatial transcriptomic representations changes as tissue context expands, instead of treating each scale independently. This gives an axis for analyzing tissue-context dependence.
• Using a neural ODE, to query intermediate neighborhood sizes is interesting and potentially useful, however I would expect stronger validation against a simple interpolation using conventional methods.
• The evaluation protocol regarding data broad and coverage is reasonable well-defined, the use of mouse and human samples gives a stronger support in terms of generalizability.
• The method (ZoomST) is conceptually coherent, and the paper is technically detailed and reproducible. The supplementary material provides detailed descriptions to support paper reproducibility.
Critical weaknesses
• The method has some limitations in terms of comparability across sections and sampling densities. Since granularity is not a precise state the neighborhoods are defined by 8, 32 and 128 nearest observations (p.3, lines 156 - 161), which depends on tissue sampling.
• The neural ODE as far as I understood is supervised at only three granularities, which leaves many possible trajectories between the observed scales. Comparisons with classical approaches like linear interpolation approaches are missing.
• The fact that the intermediate states are evaluated using the same encoder demonstrates internal consistency but l it would be great to see Molecular and Spatial encoders using different approaches.
• The context sensitivity metrics is weakly validated since the score measures the latent representation displacement and not a directly observed biological quantity. The majority of biological examples come from the training sections, and the correlation with tissue composition change is low, as measured by the whole-section Spearman correlation.
• The generalization claim should be more conservative, the experiments demonstrate within-atlas generalization to held-out sections, not cross-atlas transfer. Moreover, the same improvements are marginal, (e.g. On MOSTA mean ARI is 0.345 for ZoomST, compared with 0.343 for STAGATE and 0.342 for BANKSY - Table C2).
Questions for authors
-
The benefit of the neural ODE over simpler interpolation remains unclear, does it outperform simpler alternatives? Baselines are missing, compare against linear interpolation or splines, using the same encoder and evaluation protocol (training splits).
-
The biological relevance of the intermediate representationsis is only partially established. It would be great to see the impact on an independent task, such as tissue annotation or boundary detection, or any other relevant task.
-
Neighbor count may not represent a comparable spatial scale across tissues. Is granularity comparable across tissues? It would be great to see the physical radius covered by each neighbor count, and a comparison between count-based and fixed-radius neighborhoods. This can give us more details about the dependecy on how densely the tissue was sampled.
-
What is the practical advantage of querying an intermediate scale instead of directly encoding the corresponding neighborhood? Would be useful a comparison of computational cost and downstream performance to clarify whether the ZoomST provides practical value beyond interpolation, also to understand the tradeoff.
10 comments
Response to 9oUc (2/4): Q2, Q4 & W5 - Intermediate-scale utility and generalization
Intermediate-scale utility and generalization — Questions 2 and 4; Weakness 5
Summary of concerns. (1) scope of generalization and interpretation of comparative performance; (2) downstream usefulness and computational cost of intermediate-scale predictions.
Response
Thank you for these thoughtful questions and constructive suggestions. We agree that our experiments support within-atlas generalization to held-out sections and that the MOSTA ARI results should be described as comparable to STAGATE and BANKSY. We will revise the corresponding claims accordingly.
Following your suggestions, we have further evaluated the downstream usefulness and computational efficiency of intermediate-scale predictions. The additional results provide evidence for their practical value in the following two aspects.
1. Predicted intermediate-scale representations support tissue annotation.
We evaluated ODE-predicted representations at six intermediate granularities not used during training, using the same seven held-out HESTA sections, coarse anatomical labels, and evaluation protocol as Table 2. Mean AMI ranged from 0.5295 to 0.5346, exceeding the comparator means reported in Table R7.1. These results support the usefulness of intermediate-scale predictions for an independent anatomical task.
Table R7.1. Tissue-annotation performance of ZoomST at intermediate granularities on HESTA.
AMI (higher is better) on the same seven held-out HESTA sections and coarse anatomical labels as Table 2. ZoomST uses molecular representations predicted from r = 8 by its frozen neural ODE. Other methods retain their Table 2 values. Entries average clustering seeds 42, 43, and 44; Mean weights sections equally. Bold indicates the best score in each column.
| Method | CS12-13 | CS14-15 | CS17 | CS18 | CS19 | CS20 | CS23 | Mean |
|---|---|---|---|---|---|---|---|---|
| ZoomST (intermediate r = 12) | 0.5168 | 0.5238 | 0.4997 | 0.5431 | 0.5324 | 0.5601 | 0.5374 | 0.5305 |
| ZoomST (intermediate r = 16) | 0.5364 | 0.5373 | 0.5025 | 0.5385 | 0.5272 | 0.5653 | 0.5353 | 0.5346 |
| ZoomST (intermediate r = 24) | 0.5300 | 0.5336 | 0.4992 | 0.5488 | 0.5180 | 0.5656 | 0.5467 | 0.5345 |
| ZoomST (intermediate r = 48) | 0.5190 | 0.5305 | 0.4941 | 0.5351 | 0.5356 | 0.5614 | 0.5375 | 0.5305 |
| ZoomST (intermediate r = 64) | 0.5306 | 0.5292 | 0.4915 | 0.5443 | 0.5216 | 0.5600 | 0.5327 | 0.5300 |
| ZoomST (intermediate r = 96) | 0.5180 | 0.5292 | 0.4947 | 0.5393 | 0.5246 | 0.5616 | 0.5390 | 0.5295 |
| Novae | 0.3383 | 0.3307 | 0.3762 | 0.2828 | 0.3817 | 0.4192 | 0.4230 | 0.3646 |
| SToFM | 0.1705 | 0.2052 | 0.2703 | 0.1749 | 0.2890 | 0.2573 | 0.3198 | 0.2410 |
| scGPT-spatial | 0.3422 | 0.3841 | 0.4164 | 0.3656 | 0.4473 | 0.4383 | 0.4900 | 0.4120 |
| TERRA Cell | 0.2282 | 0.2789 | 0.3583 | 0.2673 | 0.3823 | 0.3376 | 0.3927 | 0.3208 |
| TERRA Nbh. | 0.3268 | 0.4103 | 0.4169 | 0.3892 | 0.4639 | 0.4378 | 0.4777 | 0.4175 |
| TERRA S-cell | 0.3178 | 0.4160 | 0.4165 | 0.4108 | 0.4712 | 0.4572 | 0.4860 | 0.4251 |
| CellWorld | 0.2847 | 0.2276 | 0.3225 | 0.2521 | 0.2893 | 0.3214 | 0.3764 | 0.2963 |
| DECIPHER Ctr. | 0.4022 | 0.4159 | 0.4759 | 0.3306 | 0.4831 | 0.4647 | 0.4687 | 0.4344 |
| DECIPHER Ctx. | 0.4749 | 0.5233 | 0.4135 | 0.4551 | 0.3434 | 0.4236 | 0.4215 | 0.4365 |
2. Additional scales can be queried efficiently.
ZoomST applies its pretrained model directly to held-out sections, avoiding the section-specific training used by methods such as GraphST and STAGATE. Once the representations are cached, the frozen ODE queries additional scales without repeated neighborhood construction and encoding.
Averaged over the seven held-out HESTA sections and the same six intermediate granularities, querying required 0.092 seconds per scale per section, compared with 77.49 seconds for direct neighborhood construction and encoding (Table R7.2). This low incremental cost supports repeated multiscale analysis as spatial atlases grow.
Table R7.2. Runtime summary on held-out HESTA sections.
| Method | Mean time (s) |
|---|---|
| ZoomST(query scales) | 0.092 |
| Pretrain model | |
| ZoomST direct encoding | 77.49 |
| Novae | 872.83 |
| SToFM | 1,405.61 |
| TERRA | 2,642.63 |
| scGPT-spatial | 603.52 |
| CellWorld | 30.85 |
| Target-fitted models | |
| GraphST | 684.53 |
| STAGATE | 265.12 |
| DECIPHER | 314.28 |
| BANKSY | 199.02 |
Legend. Values are mean times across seven equally weighted held-out HESTA sections (n = 7). Bold indicates the lowest mean runtime. ZoomST(query scales) queries from e8 which need not encoding new neighborhoods. Shared raw-input preparation is excluded. ZoomST direct encoding includes neighborhood pooling, tokenization and encoding. Pretrained-model timings include input encoding and inference; GraphST, STAGATE and DECIPHER timings include fitting and inference. GPU runs primarily used NVIDIA L20 48GB; BANKSY measures CPU feature construction. Following L20 memory limitations, STAGATE (1 section) and DECIPHER (4 sections) used NVIDIA A800 80GB
Added evidence: Revised manuscript, Introduction, p. 2 (generalization scope); Appendix H.7, p. 50 (Tables R7.1–R7.2).
Response to 9oUc (3/4): W4 - Biological interpretation of context sensitivity
Biological interpretation of context sensitivity — Weakness 4
Summary of concerns. Biological interpretation of context-sensitivity scores and validation on held-out tissue.
Response
We appreciate your suggestion to strengthen the biological validation of context sensitivity. The score measures how strongly a location’s representation changes as the surrounding tissue context expands, and we assess its biological relevance through correspondence with anatomical organization.
The original whole-section comparison combines responses averaged over 8–128 with composition changes based on coarse tissue-region labels (Fig. 5b–c). These summaries can obscure differences among finer structures and between scale intervals. Following your suggestion, we therefore examined a held-out HESTA section using finer anatomical annotations from the original atlas (Fig. R6.1A–B), separating responses over 8–32 and 32–128.
1. Responses distinguish local anatomical compartments.
Over 8–32, the choroid plexus epithelium and its surroundings are distinguished in both the spatial response map and the compartment-specific density curves (Figs. R6.1C and R6.2A). Epithelial responses are lower and more concentrated, whereas surrounding responses are higher and more broadly distributed, with clearly separated density peaks. This contrast corresponds to the annotated spatial organization: epithelial spots cluster together, whereas erythrocyte-labelled spots are interspersed among other tissue components in the surrounding compartment (Fig. R6.1B).
2. The response contrast depends on the scale interval.
Over 32–128, responses in both compartments are lower and more concentrated, and their density peaks are less clearly separated (Figs. R6.1D and R6.2B). The weaker separation indicates that 8–32 is more informative for resolving this local anatomical contrast. Examining responses over separate intervals therefore helps identify the observation ranges in which local tissue organization is most apparent, illustrating the value of following representation changes across scales.
Added evidence: Appendix H.6, p. 49 (Figures R6.1–R6.2).
Response to 9oUc (1/4): W2, W3 & Q1 - Intermediate-state validation and interpolation comparisons
Intermediate-state validation and interpolation comparisons — Weaknesses 2–3 and Question 1
Summary of concerns. (1) encoder design and validation beyond encoder-derived targets; (2) comparison with conventional interpolation under matched conditions.
Response
We sincerely thank the reviewer for their thoughtful assessment and constructive suggestions, and for recognizing the value of studying how representations change as tissue context expands. Following these suggestions, we have clarified the roles of the molecular and spatial encoders and expanded the developmental-age evaluation to compare the neural ODE with conventional interpolation methods under matched conditions.
1. Dual-view design and downstream validation (Weakness 3).
The molecular view encodes explicitly aggregated neighborhood expression, providing a direct basis for learning cross-granularity transformations. The spatial view combines spot-level expression and relative spatial information to capture granularity-specific tissue structure. Both views are jointly learned through within-granularity VICReg alignment and expression reconstruction.
To assess the usefulness of intermediate representations beyond agreement with encoder-derived targets, we evaluated developmental-age prediction on held-out MOSTA sections using observed embryonic ages as labels.
2. Comparison with conventional interpolation (Weakness 2 and Question 1).
Using the same encoder and training/evaluation splits, we compared the neural ODE with linear interpolation, quadratic spline interpolation, and natural cubic spline interpolation. The interpolation methods used representations at the trained granularities (r=8,32,128) as anchors. All methods were evaluated at the same six unseen intermediate granularities using separately fitted ridge readouts, with matched training samples, regression settings, and held-out evaluation locations.
The neural ODE achieved lower developmental-age prediction MAE than all three interpolation methods at every unseen granularity. Compared with linear interpolation, which had the lowest mean MAE among the interpolation baselines, the ODE reduced mean MAE from 0.9165 to 0.8565 days, a 6.5% reduction (Table R8.5).
Developmental-age prediction at unseen granularities.
This table reproduces the interpolation comparisons from Table R8.5 (Appendix H.8, p. 53).
Values are MAE in embryonic days; lower is better. Each method and target granularity uses a separately fitted ridge readout. Interpolation uses the same log-granularity coordinate as the ODE, u(r)=log2(r/8)/4.