- Rating
- 1
- Confidence
- 4(+1)
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The authors present DRIFT, a framework for aligning unpaired spatial transcriptomic snapshots across developmental time by incorporating directed developmental geometry. Using a paired single-cell reference, DRIFT builds a velocity-informed absorbing Markov chain to estimate cell-type developmental reachability, converts it into a cell-type cost, and lifts it to heterogeneous spatial spots through composition-aware entropic optimal transport, giving a spot-to-spot developmental distance. This distance is added to the expression cost of an entropic fused Gromov-Wasserstein objective that also preserves within-slice spatial geometry, yielding cross-time spot couplings. Empirical results on four human datasets (fetal pancreas, intestine, embryonic limb, and skin wound healing) suggest correspondences more consistent with reference lineage graphs and lower developmental deviation than OT, FGW-OT, PASTE, PASTE2, and DeST-OT, as well as improved held-out stage reconstruction with linear transport and flow matching in interpolation and extrapolation settings.
Critical strengths
The visuals are truly curated and intuitive. I really appreciated the overall polish, both in the figures and the text. In general, I think the paper's quality is satisfying. I also commend the authors for presenting applications across multiple datasets to showcase its versatility. Reported results are promising, overall.
Critical weaknesses
- L152: Minor, define .
- A lot of the paper is based on spots, but the future of spatial transcriptomics technology seems to be leading towards higher resolution, single-cell measurements. I feel this slightly undermines the relevance of the method.
- I feel the first part is quite similar to CellRank (Lange et al., 2022), if not in all the technical details, at least in spirit. I currently do not see a lot of novelty in the methodology. The velocity-cosine kernel on a kNN graph (Eqs. 5–6) mirrors CellRank's velocity kernel, and the absorption probabilities (Eqs. 7–8) are CellRank's fate probabilities. The main differences are the Gaussian distance factor, the pseudotime-based endpoint selection (App. B.2.2), and the "stay" probability (App. B.2.1). I wonder why one should use this method rather than CellRank. The latter is also quite flexible, as it identifies terminal states by itself, without for them to be supplied from the outside.
- Connected to the above, I think the paper does make some unique choices, like the choice of the cost, but it does not seem like a significant-enough contribution for ICLR. As said, part 1 is very similar to CellRank, part 3 (4.3) is a standard FGW OT framework (and I think it would be more transparent for the paper to address it this way). The novelty boils down to lifting the cost at a cell type level, but this feels a bit A+B as a contribution and dies out as soon as one moves to more granular datasets, unannotated or unreliably annotated settings. Or even settings where lineage mapping is not the core question (e.g., spatiotemporal brain datasets).
- I am a bit critical of the interpolation experiment overall. Why would a model with no intermediate supervision be able to predict biological meaningful interpolations, and why would a different coupling help? This is even more significant for extrapolation.
- I know space is slim, but metrics are not introduced. It would be great to at least categorize the metrics to understand what they measure. For now they are mostly acronyms. Moreover, is not defined before introducing it in the main.
- Limitations should be added to the discussion.
Questions for authors
- Is the neighborhood in Eq. 5 symmetrized?
- Why isn't MOSCOT compared with the other methods?
- Why are all the shapes of Fig. 5 the same for different methods? Also, what makes DRIFT better performing than Ordinary OT qualitatively? Or how exactly are intermediate overlays obtained?
- Since I am skeptical regarding qualitative extrapolations, I wonder if you could provide some overlays for it as well, similar to interpolation. It would be useful to see whether such a difficult task can still preserve target morphology and composition.
- Looking at Fig. 3, I feel the biggest advantage of method is that it is directly cell type informed, while the counterparts are not. Am I missing something? Are there other advantage beyond that? I believe it would be more fair to compare to standard OT with some sort of mask for inadmissible transitions. That would be a much more convincing counterpart.
5 comments
(4) Weakness 4: We acknowledge that DRIFT uses established Markov modeling and FGW-OT. Our motivation is a concrete gap in all existing methods: expression-similar spatial observations can still represent biologically implausible developmental transitions. Existing methods model expression, geometry, population dynamics, or differentiation potential, but do not explicitly place cell-type developmental reachability into the cross-time spatial alignment cost (Table 3).
Table 3. Comparison of representative spatial and spatiotemporal alignment methods.
| Method | Main Modeling Strategy | Directed Reachability | Composition-Aware Cost |
|---|---|---|---|
| Ordinary OT | Transcriptomic similarity | No | No |
| FGW-OT | Expression and spatial geometry | No | No |
| PASTE / PASTE2 | Spatial and expression alignment | No | No |
| MOSCOT | Multimodal and spatiotemporal OT | No | No |
| DeST-OT | Population growth and developmental transport | No | No |
| STORIES | Spatially informed differentiation potential | No | No |
| stVCR | Differentiation, proliferation, and migration | No | No |
| SOCS | Spatially coherent trajectory inference | No | No |
| DRIFT (Ours) | Velocity-guided developmental geometry | Yes | Yes |
Our contribution is therefore not a new Markov-chain method or FGW solver: we construct directed cell-type reachability, translate it into a developmental cost between heterogeneous spatial observations, and integrate it with expression and geometry. Consequently, similarly expressed spots can receive different alignment costs according to their underlying developmental compatibility—something expression or spatial similarity alone cannot capture. As noted above, the cost naturally reduces to a cell-type transition cost at single-cell resolution. We have also clarified the FGW connection in Section 4.3 and refined our positioning in the Introduction and Related Work.
(5) Weakness 5: Thank you for this question. About what can be reconstructed without intermediate supervision and why coupling matters. First, observed spatial snapshots constrain the endpoints, while the single-cell reference informs plausible cell-type transitions. Multiple paths may fit these observations, so we evaluate population-level agreement with a measured held-out stage, rather than claiming to recover individual cell trajectories. Held-out interpolation is also used in CellBRIDGE (Estévez et al., 2026), Waddington-OT (Schiebinger et al., 2019), TrajectoryNet (Tong et al., 2020), PRESCIENT (Yeo et al., 2021), and ContextFlow (Rathod et al., 2025); stVCR and STORIES also evaluate interpolation/extrapolation on spatial omics data.
Second, coupling controls which source–target pairs drive the prediction. Under linear interpolation, for a coupled pair , where contains expression and coordinates; different couplings therefore produce different intermediate distributions. In flow matching, these pairs also determine the displacements used to train the velocity field.
And we isolate this effect by keeping the predictor fixed across methods and evaluating predictions against measured held-out slices using expression, spatial, and composition metrics. The new figures in response to Questions 3–4 display predicted slices by each methods, hope they can give you a more clear view.
(6) Weakness 6: Thank you for your advice. We will revise Section 5.1 to group the metrics into alignment (LCR, MLDD, CWLD, LSC) and reconstruction/prediction (MMD, cell-type JS divergence, Moran's I error), and defined at first use as the spatial-geometry weight.
(7) Weakness 7: Thank you for your advice. We will expand the Discussion to acknowledge reliance on single-cell reference availability and quality, RNA-velocity estimates, cell-type annotations, and deconvolution; inferred correspondences are probabilistic associations rather than experimentally validated cell trajectories, especially for extrapolation.
(8) Question 1: They are not symmetrized. contains the nearest neighbors of cell in joint PCA space, without symmetrization; need not imply .
(9) Question 2: We have added moscot to the alignment benchmarks (Table 4).
Table 4. Lineage alignment quality across developmental spatial datasets.
| Method | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ |
|---|---|---|---|---|---|---|---|---|
| Pancreas | Intestine | |||||||
| Ordi. OT | 0.539 | 0.449 | 0.557 | 0.270 | 0.354 | 0.593 | 0.611 | 0.267 |
| FGW OT | 0.432 | 0.555 | 0.657 | 0.217 | 0.358 | 0.583 | 0.642 | 0.263 |
| PASTE | 0.239 | 0.748 | 0.749 | 0.112 | 0.220 | 0.711 | 0.708 | 0.168 |
| PASTE2 | 0.268 | 0.719 | 0.722 | 0.078 | 0.243 | 0.687 | 0.675 | 0.101 |
| DeST-OT | 0.586 | 0.406 | 0.458 | 0.300 | 0.386 | 0.560 | 0.575 | 0.295 |
| DRIFT | 0.845 | 0.152 | 0.284 | 0.485 | 0.573 | 0.384 | 0.599 | 0.433 |
| moscot | 0.454 | 0.535 | 0.607 | 0.222 | 0.338 | 0.606 | 0.622 | 0.254 |
| Method | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ |
|---|---|---|---|---|---|---|---|---|
| Limb | Skin Wound | |||||||
| Ordi. OT | 0.877 | 0.116 | 0.202 | 0.070 | 0.623 | 0.375 | 0.446 | 0.175 |
| FGW OT | 0.843 | 0.147 | 0.276 | 0.067 | 0.561 | 0.435 | 0.532 | 0.158 |
| PASTE | 0.425 | 0.572 | 0.573 | 0.015 | 0.332 | 0.666 | 0.671 | 0.089 |
| PASTE2 | 0.393 | 0.603 | 0.593 | 0.009 | 0.268 | 0.729 | 0.727 | 0.047 |
| DeST-OT | 0.839 | 0.155 | 0.158 | 0.063 | 0.653 | 0.343 | 0.387 | 0.185 |
| DRIFT | 0.888 | 0.092 | 0.161 | 0.076 | 0.682 | 0.316 | 0.357 | 0.237 |
| moscot | 0.829 | 0.168 | 0.216 | 0.063 | 0.680 | 0.319 | 0.355 | 0.173 |
(10) Question 3: Dear reviewer you may refer to Fig.4. We apologize that Figure 4 made morphology difficult to compare: the original panels shared the measured slice's outline because we displayed expression similarity scores on that same reference slice. Each method first predicted the intermediate slice using its own coupling; we then used FGW-OT to match its predicted spots to the held-out slice and visualized matched expression similarities on the reference outline. The held-out slice was used only after prediction, for visualization.
The new figure instead displays each method's actual predicted slice. Ordinary OT fills much of the gap between the two measured tissue regions, producing an almost continuous band, whereas DRIFT retains a clearer separation.
Interpolation prediction results: https://hackmd.io/_uploads/rkmz-sHAfe.png
(11) Question 4: We agree that extrapolation is difficult. Here it serves as a downstream test of alignment quality under fixed observed stages and predictor, assessed against a measured future slice; similar evaluations appear in ContextFlow (Rathod et al., 2025), scNODE (Zhang et al., 2024), PI-SDE (Jiang and Wan, 2024), stVCR (Peng et al., 2026), and STORIES (Huizing et al., 2026).
The new figure below shows the actual forecasts slices with the held-out slice. The measured tissue has two separated regions; Ordinary OT produces a largely continuous band, while DRIFT better preserves the observed separation and spatial organization.
Extrapolation prediction results: https://hackmd.io/_uploads/Sy6iHjrAze.png
(12) Question 5: We agree that leveraging biological information is an intended contribution of DRIFT—not an accidental advantage.
Following the reviewer's suggestion, we add a standard OT baseline with a binary mask defined by biological lineage rules: a source–target spot pair is allowed only if at least one cell-type pair present in the two spots has an allowed developmental transition; otherwise we impose . Table 5 compares this baseline with DRIFT.
Table 5. DRIFT versus standard OT with a developmental mask. Higher LCR and LSC and lower MLDD and CWLD indicate better alignment performance.
| Dataset | Method | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ |
|---|---|---|---|---|---|
| Pancreas | Ordinary OT | 0.539 | 0.449 | 0.557 | 0.270 |
| OT + developmental mask | 0.515 | 0.428 | 0.518 | 0.258 | |
| Full DRIFT | 0.845 | 0.152 | 0.284 | 0.485 | |
| Intestine | Ordinary OT | 0.354 | 0.593 | 0.611 | 0.267 |
| OT + developmental mask | 0.345 | 0.600 | 0.611 | 0.259 | |
| Full DRIFT | 0.573 | 0.384 | 0.599 | 0.433 | |
| Limb | Ordinary OT | 0.877 | 0.116 | 0.202 | 0.070 |
| OT + developmental mask | 0.876 | 0.118 | 0.174 | 0.069 | |
| Full DRIFT | 0.888 | 0.092 | 0.161 | 0.076 | |
| Skin Wound | Ordinary OT | 0.623 | 0.375 | 0.446 | 0.175 |
| OT + developmental mask | 0.672 | 0.325 | 0.366 | 0.212 | |
| Full DRIFT | 0.682 | 0.316 | 0.357 | 0.237 |
From Table 5, DRIFT outperforms masked OT on all four metrics in Pancreas, Intestine, Limb and Skin Wound. Masked OT performs better in MLDD, and CWLD comparing to standard OT. Thus, a binary lineage constraint can be effective, but does not consistently reproduce the benefits.
We thank the reviewer for the detailed feedback. Your advices help us a lot to revise our work. Below we clarify the methodological contribution, address limitations, and provide additional controlled comparisons and qualitative results.
(1) Weakness 1: We will define nm as the number of spatial transcriptomic spots at stage tm in Section 3.
(2) Weakness 2: We agree that spatial transcriptomics is moving toward single-cell resolution. Importantly, DRIFT can naturally extend to single-cell-resolution data without modifying its formulation, as single-cell observations are a special case of our composition-aware framework.
The developmental distance is defined as
+\tau\mathrm{KL}\left(\gamma \Big\|\ \theta_i\theta_j^\top\right)\}.$$ For single-cell observations, the compositions become one-hot vectors, $\theta_i=e_{a_i}$ and $\theta_j=e_{a_j}$, and the distance **naturally reduces to $D_{ij}^{\mathrm{single}}=C_{a_i a_j}^{\mathrm{dev}}$**. Thus, the same developmental alignment framework applies at both spot and single-cell resolutions, with no additional modeling components required. **To empirically examine this simplified representation**, we evaluate the Dominant variant, which approximates each mixed spot by a single cell type and therefore uses the same one-hot developmental cost as the single-cell case. Although this is not a direct single-cell-resolution benchmark, it assesses whether DRIFT remains effective when full cell-type mixtures are replaced by single-type representations. **Table 1. Comparison of Full DRIFT and Dominant across four spatiotemporal datasets.** Higher LCR and LSC and lower MLDD and CWLD indicate better alignment performance. | Dataset | Method | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ | |---|---|---|---|---|---| | Pancreas | Full DRIFT | 0.845 | 0.152 | 0.284 | 0.485 | | | Dominant | 0.8643 | 0.1348 | 0.2783 | 0.4181 | | Intestine | Full DRIFT | 0.573 | 0.384 | 0.599 | 0.433 | | | Dominant | 0.6194 | 0.3527 | 0.5874 | 0.4488 | | Limb | Full DRIFT | 0.888 | 0.092 | 0.161 | 0.076 | | | Dominant | 0.8393 | 0.1304 | 0.2425 | 0.0825 | | Skin Wound | Full DRIFT | 0.682 | 0.316 | 0.357 | 0.237 | | | Dominant | 0.6438 | 0.3551 | 0.4361 | 0.1779 | **DRIFT provides a unified formulation across spatial resolutions, naturally reducing to cell-type-level developmental alignment at single-cell resolution**. We will clarifiy this applicability in the revised manuscript. **(3) Weakness 3:** We agree that velocity-informed Markov kernels and absorbing probabilities are established techniques, and **we do not claim them as independent innovations**. Our aim is to use biologically directed reachability as a criterion for **cross-time spatial alignment**, rather than terminal-fate inference. CellRank typically estimates the probability of eventually reaching terminal populations, which may cover only a subset of annotated types. By contrast, DRIFT needs a stage-dependent $K\times K$ reachability matrix over the cell-type vocabulary used for spatial alignmen. We therefore specify absorbing populations according to that context. It is true that CellRank can also implement this with a **user-defined absorbing state**, as we also explored in developing DRIFT. Under matched references, graphs, annotations, and absorbing states, the two kernels produce comparable alignment performance (Table 2), without a consistent winner. Table 2. Comparison of CellRank-based and DRIFT-based developmental transition modeling across four datasets. All variants use the same single-cell references, neighborhood graphs, cell-type annotations, absorbing endpoints. Higher LCR and LSC and lower MLDD and CWLD indicate better performance. | Dataset | Transition modeling | LCR ↑ | MLDD ↓ | CWLD ↓ | LSC ↑ | |---|---|---:|---:|---:|---:| | Pancreas | CellRank kernel | 0.8472 | 0.1503 | 0.3057 | 0.4821 | | | Drift kernel | 0.845 | 0.152 | 0.284 | 0.485 | | Intestine | CellRank kernel | 0.5589 | 0.3981 | 0.6016 | 0.4237 | | | Drift kernel | 0.573 | 0.384 | 0.599 | 0.433 | | Limb | CellRank kernel | 0.9048 | 0.0840 | 0.1594 | 0.0767 | | | Drift kernel | 0.888 | 0.092 | 0.161 | 0.076 | | Skin Wound | CellRank kernel | 0.6847 | 0.3135 | 0.3553 | 0.2410 | | | Drift kernel | 0.682 | 0.316 | 0.357 | 0.237 | We chose our own implementation mainly for **flexibility and computational simplicity**, not to replace CellRank; its distance-aware kernel is a task-specific choice, **not our central contribution**. DRIFT instead aggregates cell-level hitting probabilities into directed cell-type reachability and lifts this geometry to heterogeneous spatial spots via composition-aware OT, directly informing cross-time spatial correspondence.