- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes Boundary-aware Multi-level Relational Learning for spatially resolved transcriptomics. The method estimates continuous boundary scores by combining local expression differences with global semantic information derived from optimal-transport assignments to prototypes. These scores guide different learning constraints: boundary-related spots receive stronger relational consistency supervision, while interior spots receive stronger spatial smoothing and local consistency constraints. The framework further incorporates region-level prototype relations, slice-level consistency, prototype supervision, and cross-slice similarity scaling.
Critical strengths
Heterogeneous neighborhoods near tissue interfaces can make uniform spatial smoothing inappropriate. Combining local expression variation with broader semantic information provides a reasonable basis for adapting the learning constraints. The continuous weighting scheme also avoids requiring a hard boundary classification during training.
Critical weaknesses
-
The contribution beyond the closest existing framework is insufficiently isolated. Spotscape already introduces global cross-view relation consistency, multi-granularity prototype contrastive learning, and intra-/inter-slice similarity scaling. The unweighted form of Eq. (10) corresponds to its relation-consistency objective, while Eqs. (17) and (19) closely follow its prototype and scaling mechanisms. These relationships should be explained explicitly when positioning the new contributions. Although Spotscape is included in the multi-slice experiments, it is absent from the single-slice main comparison, where its global relational modeling is particularly relevant. This omission makes it difficult to determine how much of the reported improvement comes specifically from boundary adaptation and the newly added consistency terms.
-
The central boundary-aware mechanism is not directly validated sufficiently. Figure 1 provides a qualitative comparison with annotation-derived boundaries, but the paper does not report quantitative boundary-estimation accuracy or clustering performance separately for boundary and interior spots.
Questions for authors
-
Methodological distinction and comparison. Could you explicitly identify the differences between BMRL and Spotscape in the relational, prototype, and similarity-scaling objectives? Please include Spotscape in the single-slice comparison and, if possible, compare it with a variant that adds only the proposed boundary adaptation.
-
Boundary-mechanism validation. Can you quantify the agreement between the estimated boundary scores and annotation-derived boundaries, using annotations only for evaluation? Please also report clustering performance separately for boundary and interior spots, together with a control that removes boundary dependence from all applicable losses.
-
Optimization and reproducibility. What is the complete training objective for single-slice and multi-slice experiments, including all coefficients? Please specify the rank-fusion rule, prototype counts and granularities, Sinkhorn regularization, temperature, boundary enhancement coefficient, and prototype-update schedule.
-
Evaluation fairness. Were the baseline results rerun under the same preprocessing, graph construction, and downstream clustering protocol, or adopted from previous publications? How were hyperparameters and cluster numbers selected, and were evaluation annotations used in that process?
-
Preservation of biological differences. The cross-slice scaling loss encourages similar within-slice and between-slice similarity levels. How does the method handle tissue domains or biological states present in only one slice?
7 comments
Weakness 2 and Question 2: Insufficient Quantitative Validation of Boundary Awareness.
Answer: Thank you for encouraging us to clarify this point.
To address this issue, we conducted additional quantitative experiments on boundary localization accuracy and clustering performance in different spatial regions.
-
To further evaluate boundary localization performance, we calculated the Euclidean distance from each reference boundary spot to its nearest predicted boundary spot. We then normalized these distances by the typical spacing between adjacent spots. The results show an average distance of 2.5112 spot spacings.
Previous studies (e.g., (a) and (b)) have used spatial distances to measure the proximity of spots to tissue boundaries. They also pointed out that annotations near spatial domain boundaries may contain some uncertainty. Therefore, strict spot-level matching may not fully reflect the spatial correspondence between predicted and reference boundaries.
In addition, BMRL uses a multi-layer GNN to aggregate local spatial neighborhood information. Some spatial offsets may exist between the predicted and reference boundaries. However, the model may still capture structural information near tissue boundaries. More importantly, BMRL does not require precise localization of every boundary spot. Instead, it uses continuous boundary scores to capture tissue boundary patterns and adaptively adjust relation learning constraints at different spatial locations.
-
We further divided the nodes into boundary and interior nodes based on the reference tissue annotations. We then calculated CA, ARI, and NMI for these two types of nodes separately. The results are shown in the following table.
Table. Clustering performance of boundary and interior nodes. Results are reported as mean (standard deviation).
Metric Boundary Nodes Interior Nodes Overall CA 0.54 (0.02) 0.91 (0.03) 0.87 (0.03) ARI 0.29 (0.01) 0.86 (0.04) 0.80 (0.03) NMI 0.48 (0.01) 0.82 (0.03) 0.76 (0.02) The experimental results show that boundary nodes have much lower clustering performance than interior nodes. This indicates that clustering boundary regions is more challenging. These findings also support the need to distinguish different spatial regions during representation learning.
-
We further removed boundary dependence from all applicable loss functions while keeping the other learning constraints unchanged. The results are presented in the following table.
Table. Effect of removing all boundary-adaptive weights.
Method ARI NMI CA BMRL (Full) 0.777 0.775 0.871 w/o Boundary Weighting 0.753 0.770 0.840 After removing all boundary-adaptive weights, ARI, NMI, and CA decrease by 0.024, 0.005, and 0.031, respectively. These results show that the boundary-aware mechanism provides additional performance improvements.
References
(a) Daniel C. Jones, Patrick Danaher, Youngmi Kim, Joseph M. Beechem, Raphael Gottardo, and Evan W. Newell. An information theoretic approach to detecting spatially varying genes. Cell Reports Methods, 3(6), 2023.
(b) Yunhak Oh, Junseok Lee, Yeongmin Kim, Sangwoo Seo, Namkyeong Lee, and Chanyoung Park. Global context-aware representation learning for spatially resolved transcriptomics. arXiv preprint arXiv:2506.15698, 2025.
Question 3: Optimization and Reproducibility
Answer: Thank you for your helpful suggestion.
(1) BMRL uses different training objectives for single-slice and multi-slice experiments.
Single-slice Training Objective. As shown in the following equation,
Multi-slice Training Objective. As shown in the following equation,
Here, denotes the current training epoch, and denotes the number of warm-up epochs. The Multi-scale Prototype Contrastive Loss is only used in multi-slice experiments and is activated after the warm-up stage.
The results are shown in the following table.
Table. Ranges of loss coefficients and warm-up epochs used in BMRL.
| Parameter | Value Range |
|---|---|
| 0.1–0.3 | |
| 0.65–1.5 | |
| – | |
| 0.02–0.06 | |
| 0.07 (fixed) | |
| 0.001–0.1 | |
| 0.1–1.0 (multi-slice only) | |
| 0.01–0.05 (multi-slice only) | |
| 100–500 epochs |
(2) In Eqs. (3)–(8), we compute the local and global boundary scores, respectively. We then use percentile-rank fusion to obtain the final continuous boundary score, as defined in the following equation:
where denotes the normalized rank transformation. We rank the scores in ascending order and divide each rank by the total number of spots . The fusion weight ranges from 0.2 to 0.9 across different experiments.
(3) Prototype-update schedule.
As shown in Eqs. (13)–(14), we perform multi-granularity K-means on the second augmented view to generate shared region prototypes. These prototypes are used to maintain consistent semantic relations between the two augmented views and the region prototypes. is optimized from the beginning of training. The region prototypes are recomputed at each parameter update.
As shown in Eqs. (16)–(17), we use the stop-gradient representations of the second augmented view to generate prototype pseudo-labels. These labels supervise the prototype predictions of the first augmented view. uses the same shared region prototypes. It is only used in multi-slice experiments and is activated after a warm-up period of 100–500 epochs.
(4) Other hyperparameter settings are summarized in the following table, including prototype counts and granularities, Sinkhorn regularization, temperature, and boundary enhancement coefficients.
Table. Other hyperparameter settings of BMRL.
| Parameter | Value |
|---|---|
| OT prototype count | |
| Prototype granularities | or |
| Sinkhorn regularization | |
| Maximum Sinkhorn iterations | 100 |
| Sinkhorn stopping tolerance | |
| PCL temperature | 0.75–1.0 |
| Boundary enhancement coefficient | 0.35–1.0 |
Here, denotes the base number of clusters, and denotes the OT cost matrix defined in Eq. (4).
We thank the reviewer for carefully reading our paper and appendix and for the valuable comments and constructive suggestions. We provide our responses to the questions below.
Weakness 1 and Question 1: Distinction from Spotscape and Contribution of New Modules
Answer: We sincerely appreciate your detailed assessment.
Spotscape learns spot representations through cross-view relation consistency. However, it does not explicitly consider the differences in spatial neighborhood structures between interior and boundary spots. Interior spots usually have relatively homogeneous neighborhoods. In contrast, boundary spots are more likely to be affected by the propagation of heterogeneous information from different tissue regions. Applying the same relation learning constraints to both types of spots may lead to over-smoothing near tissue boundaries. This can weaken the distinctions between different tissue regions.
Unlike Spotscape, BMRL combines local expression differences with global semantic information derived from optimal transport. It estimates a continuous boundary score for each spot and incorporates these scores into the relation learning process.
To further evaluate the effectiveness of BMRL compared with Spotscape, we conducted additional comparative experiments on single-slice spatial domain identification.
In addition, we tried to adjust the downstream clustering configuration of Spotscape to match that of BMRL. Spotscape achieved lower clustering performance under this setting than under the configuration used in its original paper. Therefore, we retained the results reported in the original Spotscape paper to avoid underestimating the baseline performance due to differences in clustering settings. We will clearly explain the sources of these results and the differences in evaluation settings in the revised manuscript. The results are shown in the following table.
Table. Comparison of Spotscape and BMRL on different datasets. Results are reported as mean (standard deviation). Spotscape results are taken from the original paper. Bold values indicate that BMRL outperforms Spotscape, while underlined values indicate equal performance.
The experimental results show that BMRL outperforms Spotscape on 15 of the 16 cases in both ARI and NMI. For CA, BMRL also achieves better performance in 15 cases. These findings demonstrate the effectiveness of BMRL and suggest that boundary-adaptive representation learning and multi-level relation modeling help improve model performance.