- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
PerturbBridge predicts single-cell perturbation responses from unpaired populations using a negative-binomial-difference reference process. The reference jointly defines endpoint coupling and integer bridge generation, with separate controls for displacement scale and shape. Experiments cover genetic and cytokine perturbations, including transfer to unseen cellular contexts.
Critical strengths
The method is Well motivated. It addresses state-dependent response heterogeneity and provides targeted analysis, component ablations, and evaluation across multiple perturbation settings.
Critical weaknesses
Limited conceptual novelty. NB-difference processes, Schrödinger bridge decompositions, and integer count-bridge generation have established precedents. The contribution is primarily a reference-design extension, with a useful but restricted two-state analysis, rather than a substantially new theoretical framework.
Incomplete attribution of improvements. The closest Poisson-reference comparison is limited to a PBMC subset, and key component ablations use single training runs. A direct conditional generator using the same NB coupling is also missing, leaving the additional value of bridge generation insufficiently isolated.
Questions for authors
Appendix K fixes (\delta=1), giving (H_1(r)=|r|-1/2) for every nonzero integer residual. Why was this threshold chosen? Does the NB advantage persist when the Huber threshold and entropy temperature are selected using the same validation protocol, allowing curvature to extend across moderate count differences?
The authors select reference parameters using validation Sinkhorn-(W_2), whereas Table 7 shows different rankings for count transport error and response recovery. Could you report the validation scores and selected reference parameters for each main task, and clarify how the highlighted NB configuration and its Poisson comparator were chosen under this criterion?
6 comments
Response to Reviewer iLZU 2/4
Q2. Attribution to the reference, bridge training, and generation (Weakness 2)
Incomplete attribution of improvements. The closest Poisson-reference comparison is limited to a PBMC subset, and key component ablations use single training runs. A direct conditional generator using the same NB coupling is also missing, leaving the additional value of bridge generation insufficiently isolated.
A. We agree that the reference, training path, and inference steps should be assessed separately. We independently train a direct conditional predictor with the same NB coupling, condition inputs, backbone capacity, training budget, ZINB endpoint likelihood, and validation-based checkpoint selection rule. It predicts a count distribution from a control cell and is a probabilistic model, not deterministic regression. It is trained at the control endpoint t=1, whereas NB is trained on bridge states across times. Direct prediction and one-step NB each use one network call, testing the training construction; NB 1/5/20/100-step inference reuses one checkpoint to test the inference procedure.
The table reports all path and step comparisons on the same 1,080 unseen-cell-type groups. Direct prediction and interpolation use one inference step; both Gaussian bridges use 100 steps with their respective Gaussian updates. All four NB step settings reuse the same checkpoint.
| Method | W2 ↓ | MMD² ↓ | Pearson ↑ | Spearman ↑ | PDS ↑ | ES ↑ |
|---|---|---|---|---|---|---|
| Direct conditional predictor | 96.8359 | 0.0171 | 0.2530 | 0.4021 | 0.6762 | 0.4921 |
| Interpolation | 96.2610 | 0.0192 | 0.1990 | 0.3040 | 0.6182 | 0.3061 |
| Conditional-moment Gaussian | 96.4419 | 0.0121 | 0.3075 | 0.4672 | 0.7194 | 0.5738 |
| Fixed-scale Gaussian | 95.2165 | 0.0129 | 0.2762 | 0.4222 | 0.6823 | 0.5343 |
| NB 1 step | 97.1703 | 0.0122 | 0.3205 | 0.4746 | 0.7236 | 0.5335 |
| NB 5 steps | 94.2152 | 0.0104 | 0.3393 | 0.4968 | 0.7175 | 0.5552 |
| NB 20 steps | 89.2246 | 0.0082 | 0.3990 | 0.5471 | 0.7925 | 0.5795 |
| NB 100 steps | 89.1649 | 0.0094 | 0.3949 | 0.5525 | 0.7834 | 0.6231 |
One-step NB improves five of the six metrics, including MMD², Pearson, Spearman, PDS, and ES. With the checkpoint fixed, 20 steps further improve all six. Learning the same endpoint relation from multiple intermediate states couples overall response prediction with local response reconstruction; iterative sampling then applies this learned recovery along the matching path. Interpolation and Gaussian controls further distinguish the effects of the intermediate-state distribution. Matching the conditional variance improves all four response-oriented metrics over a fixed Gaussian scale, indicating that endpoint-dependent uncertainty contributes to learning useful response structure. The exact NB bridge combines this state-dependent uncertainty with a matching count-valued path and achieves the strongest overall performance among the 100-step variants.
Poisson, CellOT, and PerturbDiff now enter the main benchmark and its task-level ranks. PerturbBridge ranks first on all three PBMC tasks; on unseen types its mean rank is 1.6125, compared with 3.7625 for Poisson. The appendix table reports W2, MMD², Pearson, Spearman, PDS, and ES alongside the main figure’s ranks. We also independently trained the selected NB (κ,h)=(8,0.5) configuration with three additional seeds on the same subset. Their complete six-metric results are below; the mean and sample SD are calculated over these three additional runs.
| Training seed | W2 ↓ | MMD² ↓ | Pearson ↑ | Spearman ↑ | PDS ↑ | ES ↑ |
|---|---|---|---|---|---|---|
| 88 | 88.1753 | 0.0094 | 0.3966 | 0.5509 | 0.7869 | 0.6732 |
| 2024 | 88.2168 | 0.0094 | 0.4021 | 0.5613 | 0.7971 | 0.6504 |
| 3407 | 88.4891 | 0.0098 | 0.3880 | 0.5428 | 0.7815 | 0.6097 |
| Mean | 88.2937 | 0.0095 | 0.3956 | 0.5517 | 0.7885 | 0.6444 |
| Sample SD | 0.1705 | 0.0003 | 0.0071 | 0.0092 | 0.0079 | 0.0322 |
Pearson remains within 0.3880–0.4021 and PDS within 0.7815–0.7971 across these runs, supporting the repeatability of response recovery for the selected configuration. Figure 5 also shows the range over the original run and these three additional runs. Section 4.3 and Appendix N.3, Tables 38–39 report the added path and seed experiments; Appendix N.6 gives all four-space results.
Response to Reviewer iLZU 3/4
Q3. Huber threshold and entropy-temperature selection (Question 1)
Appendix K fixes (\delta=1), giving (H_1(r)=|r|-1/2) for every nonzero integer residual. Why was this threshold chosen? Does the NB advantage persist when the Huber threshold and entropy temperature are selected using the same validation protocol, allowing curvature to extend across moderate count differences?
A. We agree with your observation that delta=1 places all nonzero integer residuals in the linear regime, so the original setting serves as a linear-tail control. The expanded comparison tests curvature across moderate count differences. We added thresholds {1,2,5,10,20} at tau=1, temperatures {10,30,100,300} at delta=1, and the crossed candidate (5,100). The same validation criterion selects (5,100), with score 95.0279. The ten candidates cover threshold changes, temperature changes, and a crossed setting.
The table compares the validation-selected Huber configuration with NB on the same subset. All Huber candidates retain the NB (8,0.5) bridge. Appendix N.4, Table 40 reports the validation scores and six key test metrics for all ten candidates; Appendix N.6, Tables 44, 47, 50 and 53 gives their complete metrics in the four expression spaces.
| Method | Validation score ↓ | W2 ↓ | MMD² ↓ | Pearson ↑ | Spearman ↑ | PDS ↑ | ES ↑ |
|---|---|---|---|---|---|---|---|
| Huber delta=5 tau=100 | 95.0279 | 89.4185 | 0.0140 | 0.2999 | 0.4341 | 0.6930 | 0.5362 |
| NB (8,0.5) | 89.1725 | 89.1649 | 0.0094 | 0.3949 | 0.5525 | 0.7834 | 0.6231 |
The threshold sigma in the experiment files is the Huber delta, which controls where the residual penalty changes from quadratic to linear. Tau controls the softness of the transport plan through exp(-cost/tau). They affect different aspects of supervision: delta changes which residual magnitudes are distinguished by curvature, while tau changes how strongly the resulting preferences concentrate transport mass. At tau=1, increasing delta from 1 to 5 raises Pearson/PDS from 0.2199/0.5865 to 0.3028/0.7006. At delta=1, tau=100 gives 0.2165/0.5912. This pattern identifies preserving moderate-residual geometry as a useful ingredient. The joint candidate (5,100) is selected by its lower validation score, 95.0279 versus 95.1946 for (5,1), and gives 0.2999/0.6930. NB achieves MMD²/Pearson/PDS of 0.0094/0.3949/0.7834. Its compact scale–shape family controls displacement variance and marginal penalties together; the known-state studies further verify the correspondence benefit of that geometry. The expanded Huber comparison is discussed in Section 4.3 and reported in Appendix N.4, Table 40.
Response to Reviewer iLZU 1/4
Thank you for the specific questions about attribution, robust-cost tuning, and validation selection. They helped make the methodological contribution and the actual model-selection procedure more precise.
Q1. Methodological contribution and established components (Weakness 1)
A. We agree that the established mathematical components should be distinguished from the design capability introduced here. We build on established integer processes and the Schrödinger decomposition, with explicit attribution. The new design capability is to adjust the pairing geometry's shape at fixed displacement variance while retaining a tractable matching integer bridge throughout the family. A robust static cost alone specifies a coupling but does not supply the matching conditional path law. A fixed Poisson reference supplies a path law but ties its shape to its scale. Our construction connects these two choices through one family, and the correspondence analysis identifies why its bounded marginal penalties can protect state information from large legitimate responses. The controlled tests below assess this design capability directly.