- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper presents a flow matching technique for interpolating between unbalanced experimental snapshots. The method is based on the unbalanced optimal transport problem, defining the log mass of the snapshots as an additional variable over which to learn the flow. The method is benchmarked on existing synthetic and single-cell datasets.
Critical strengths
- Simple methodology that retains the simulation-free training benefit of flow matching.
- Addresses an interesting problem of inferring cellular trajectories.
Critical weaknesses
Unfortunately, I have significant concerns regarding the novelty and significance of the methodology as well as the presentation.
Soundness
- Fundamentally, the problem of inferring “cell growth” is ill-defined for two reasons:
- The # of cells measured by scRNA-seq in a single sample is almost entirely a function of the # of samples, sample size, and sequencing setup. Thus, rather than learning actual population growth, such a method is likely only learning technical artifacts.
- As far as I understand, this method is inferring trajectories per individual cell state, whereas cell growth / death clearly represents multiple (or zero) cell states. To accurately model such a phenomenon implies a need to model at a population-level rather single-cell level.
- The prescribed linear interpolation in log mass is a highly restrictive and simplistic assumption.
- Some existing works on trajectory inference are missing in the benchmarking: [1-3] in particular all have stronger performance than ESFM on CITE 50D [3] (the only experimental setup that is directly comparable).
- Overall, ESFM does not demonstrate any significant improvement over prior workk.
- One key benefit of a simulation-free training objective is efficient training, but no timing benchmarking is provided.
[1] OT-MFM 2024 https://arxiv.org/abs/2405.14780
[2] WLF-UOT 2024 https://arxiv.org/abs/2310.10649
[3] OTP-FM 2026 https://arxiv.org/abs/2606.05327
Presentation and informativeness
- Section 4 describing the method is hard to follow. It reads like a series of equations without clear motivations and explanations of the significance and intuition behind each equation.
- Thms. 4.1 and 4.3 in particular appear to be presented without context - their motivation, significance, and intuition should be better explained.
- Because of this, technical differences with respect to similar methods such as VGFM and WFR-FM are also not clear. VGFM in particular appears to have an identical training objective.
- Minor comments:
- Some sloppy notation, e.g. Unclear in what sense \rho^\hat is a probability distribution, presumably you mean \rho^\hat(\dot, y) is a valid prob. distribution of x for each y?
Questions for authors
- How can you disentangle technical measurements artifacts in the dataset from true cell growth?
- What evidence supports the prescribed linear interpolation in log mass?
- Can you incorporate the prior work mentioned above and others in this space?
- Can you provide a training time comparison with other simulation-free methods?
- Can you describe the methodology clearly and explain the novelty with respect to prior work?
7 comments
Response to Q2–Q4: Growth Prior, Additional Baselines, and Efficiency (2/4)
Q2/W3: Justification for Linear Log-Mass Interpolation
The linear log-mass path has a population-growth interpretation through the Malthusian model. This model assumes approximately constant per-capita proliferation and death rates, and , over an interval, as may be reasonable when resources are sufficient and the environment is stable. The expected total proliferation and death rates are then proportional to the current population, giving
Thus, the relative growth rate is constant, physical mass changes exponentially, and log mass changes linearly.
The same assumption of constant conditional relative growth is also used in VGFM [4] and USB [5]. Over short time intervals, we consider monotone conditional mass evolution a more biologically plausible prior than the transient mass decrease followed by regrowth permitted by WFR geodesics. Further discussion is provided in our response to Reviewer qGy6, Q1.
Linear interpolation in log mass is one illustrative choice within ESFM. As discussed in Appendix D and our response to Reviewer qGy6, Q2, the framework also accommodates other actions and geodesics. Appendices D.2–D.3 derive the construction for paths linear in physical mass, and Appendix D.4 recovers the standard static WFR semi-coupling formulation from the microscopic WFR action.
Q3/W4: Additional Baselines: OT-MFM, WLF-UOT, and OTP-FM
Thank you for pointing out these relevant works. We have added comparisons with OT-MFM, WLF-UOT, and OTP-FM to Tables 2 and 3 of the revised manuscript. For convenience, we reproduce the results for these three baselines and ESFM below.
Results on synthetic datasets, reproduced from Table 2 of the revised manuscript.
| Method | Gene W1 | Gene RME | Dyngen W1 | Dyngen RME | Gaussian W1 | Gaussian RME |
|---|---|---|---|---|---|---|
| OT-MFM | 0.311 | --- | 1.767 | --- | 3.794 | --- |
| WLF-UOT | 0.618 | --- | 2.056 | --- | 4.101 | --- |
| OTP-FM | 0.433 | --- | 1.142 | --- | 2.139 | --- |
| ESFM (ours) | 0.017 | 0.0005 | 0.111 | 0.003 | 2.428 | 0.0001 |
Bold values mark the lowest W1 among the four methods shown.
W1 results on real datasets, reproduced from Table 3 of the revised manuscript.
| Method | EMT | EB | CITE | Mouse |
|---|---|---|---|---|
| OT-MFM | 0.314 | 10.726 | 36.217 | 7.753 |
| WLF-UOT | 0.314 | 11.616 | 36.990 | 9.040 |
| OTP-FM | 0.315 | 10.953 | 37.160 | 8.286 |
| ESFM (ours) | 0.295 | 10.134 | 37.147 | 6.714 |
Bold values mark the lowest W1 among the four methods shown.
The additional comparisons show that ESFM achieves the lowest W1 among the four methods on five of the seven datasets: Gene, Dyngen, EMT, EB, and Mouse. We acknowledge that OT-MFM and WLF-UOT obtain lower errors on CITE 50D, while OTP-FM performs better on the 1000D Gaussian benchmark. Nevertheless, these results demonstrate the competitive performance of ESFM across diverse synthetic and real-world datasets, rather than uniform superiority.
We appreciate the reviewer's suggestions and have taken care to acknowledge and cite the relevant prior work more comprehensively in the revised manuscript. We will also cite these works in our future research where relevant.
Q4/W5: Training Time and Memory Comparison
To address both Q4 and W5, we reproduce the computational-efficiency benchmark on the 100-dimensional EB dataset directly in Table 3. These are the results shown in Figure 13 of the revised manuscript (Appendix B.5). All results were obtained using a single NVIDIA A100 GPU.
Computational efficiency on the 100D EB dataset.
| Method | Training time (s) | Memory (GB) |
|---|---|---|
| ESFM (ours) | 42 | 0.4 |
| USB | 73 | 0.7 |
| SF2M | 89 | 0.7 |
| MMFM | 98 | 0.6 |
| WFR-FM | 128 | 0.9 |
| Metric FM | 136 | 4.2 |
| UOT-FM | 149 | 0.6 |
| VGFM | 285 | 0.6 |
| MIOFlow | 378 | 0.7 |
| TIGON | 453 | 0.7 |
| DeepRUOT | 617 | 10.1 |
| Var-RUOT | 920 | 20.0 |
Bold values mark the lowest reported value in each metric.
ESFM requires 42 seconds and 0.4 GB of memory, giving the shortest reported runtime and lowest reported memory usage among the compared methods. The ESFM runtime includes coupling computation, endpoint-pair presampling, and network training.
Response to Q5: Methodology and Intuition Behind the Main Theorems (3/4)
Q5/W6: Methodology and Theorem Intuition
We agree that Section 4 does not explain our method clearly enough. Below, we first clarify the methodology and then explain its novelty relative to prior work.
Clarifying the methodology.
Our starting point is to incorporate assumptions about how cell states and population mass evolve into the construction of an unbalanced flow-matching model. We express these assumptions through prescribed conditional paths and construct a compatible transport action, from which the endpoint coupling and training targets are derived.
In Section 4.1, we introduce the dynamics in the extended space, together with the density, boundary conditions, and continuity equation. In the physical state space, the mass density evolves according to the unbalanced continuity equation
\partial_t\rho_t(\boldsymbol{x}) +\nabla\cdot\left(\rho_t(\boldsymbol{x})\boldsymbol{u}_t(\boldsymbol{x})\right) =\rho_t(\boldsymbol{x})g_t(\boldsymbol{x}), \tag{3.3}
which includes a source term accounting for growth and death. By introducing log mass as an additional coordinate, we represent mass changes as transport along this coordinate, leading to the conservative continuity equation in the extended space:
\partial_t\hat\rho_t +\nabla_{\boldsymbol{x}}\cdot(\hat\rho_t\hat{\boldsymbol{u}}_t) +\partial_y(\hat\rho_t\hat g_t)=0. \tag{4.2}
Theorem 4.1 establishes the consistency between these two descriptions: under a vanishing weighted-flux condition as , the mass-weighted projection of (4.2) recovers (3.3), with the corresponding projected velocity and growth fields. Intuitively, transport along the log-mass coordinate becomes growth or death when viewed in the physical state space. This shows that the extended-space formulation is consistent with the dynamics in the original state space, providing a mathematical justification for modeling transport and growth in the extended space.
Building on this extended-space formulation, our framework proceeds through four steps, as illustrated in the revised Figure 1. First, we prescribe linear state interpolation and exponential mass interpolation between the endpoints:
Equivalently, log mass evolves linearly as , where . These paths have constant conditional state velocity and constant conditional relative growth rate, .
Second, we construct a microscopic action for which these prescribed paths are minimizers. These two steps are presented in Section 4.2. Third, we lift the microscopic action to a population-level dynamic OT problem and derive its equivalent static formulation in the extended space (Section 4.3).
We next ask how this extended-space static OT problem can be formulated in the original state space. This motivates Theorem 4.3 in Section 4.4: with the source log mass fixed at and the terminal log mass bounded by , where , the extended static problem is equivalent to an optimization over semi-couplings in the original state space. This allows the coupling to be computed without explicitly discretizing the additional mass coordinate. The objective in (4.8) is
\iint\left[\\|\boldsymbol{x}_1-\boldsymbol{x}_0\\|^2 +\delta^2\Phi_M\\!\left(R(\boldsymbol{x}_0,\boldsymbol{x}_1)\right)\right]\\,\mathrm d\gamma_0. \tag{4.8}
Here, and represent the initial and final mass assigned to each state pair, and is the local growth ratio.
In this reduced formulation, state transport retains the squared Euclidean cost , while mass change is penalized through , where is the local growth ratio. The explicit form of is given in Theorem 4.3.
Finally, we sample from the resulting coupling and train the velocity and growth networks by regressing against the conditional fields determined by the prescribed paths (Section 4.5). The central idea is that the coupling and the regression targets are constructed from the same underlying paths and action, ensuring consistency between the transport problem and flow-matching training.
Response to Q1/W1 and W2: Growth Interpretation and Population-Level Modeling (1/4)
Q1/W1: Technical Measurement Effects versus Biological Growth
Our objective is to reconstruct population dynamics from observed single-cell snapshots, conditional on the population abundance information provided by the data. Unbalanced OT has been used to model cell differentiation and population growth [1,2,3]. In particular, TIGON [2] and stVCR [3] employ population-level transport equations with growth terms, closely related to the dynamics considered in ESFM.
We agree that observed cell abundance can be influenced by technical factors, including sampling efficiency and sequencing protocols. In such cases, the inferred growth rate should be interpreted as an effective growth rate, potentially reflecting both biological proliferation/apoptosis and technical measurement effects. ESFM does not claim to disentangle these contributions from unpaired snapshots alone, as doing so generally requires additional information about the observation process. When the underlying technical measurement mechanism is known, the ESFM framework can accommodate an explicit observation model to account for such effects in the inference of biological population dynamics.
Accordingly, our synthetic experiments with known ground-truth growth rates validate the recovery of biological growth dynamics, whereas the real-data experiments demonstrate the reconstruction of observed population distributions and abundance changes. We will clarify this distinction and the associated limitations in the revised manuscript.
W2: Population-Level Dynamics and Cell Division/Death
We clarify that ESFM primarily models population-level dynamics rather than explicitly reconstructing individual cell lineages.
(1) Population-level dynamics. As established in Theorem 4.1, ESFM describes a conservative particle distribution ρt(x,y) in the extended space, where y=lnm. The physical population density is recovered through the mass-weighted projection
ρt(x)=∫Reyρt(x,y),dy.
Importantly, this projected density satisfies the unbalanced continuity equation
∂tρt+∇x⋅(ρtut)=ρtgt.
Thus, ESFM describes both state transport and state-dependent population growth or decay. In particular, the total population mass Mt=∫ρt(x),dx evolves according to
dtdMt=∫Rdρt(x)gt(x),dx.
(2) Stochastic realization of cell division and death. Furthermore, following stVCR and USB [3,5], the learned extended-space dynamics can be used to construct a stochastic birth–death process.
Each particle evolves directly under the learned extended-space fields:
\frac{\mathrm{d}\mathbf{x}_t}{\mathrm{d}t} = v_\theta(\mathbf{x}_t,y_t,t), \qquad \frac{\mathrm{d}y_t}{\mathrm{d}t} = g_\phi(\mathbf{x}_t,y_t,t). \tag{1}
The predicted relative growth rate gϕ(x,y,t) determines the net balance between proliferation and apoptosis. We construct nonnegative division and death rates as
βt(x,y)=[gϕ(x,y,t)]+,dt(x,y)=[−gϕ(x,y,t)]+,
such that gϕ=βt−dt. Over a sufficiently small time interval Δt, the probabilities of division and apoptosis are
\begin{aligned} P(\mathrm{division}\mid \mathbf{x}_t=\mathbf{x},y_t=y) &= [g_\phi(\mathbf{x},y,t)]_+ \Delta t+o(\Delta t),\\\\ P(\mathrm{apoptosis}\mid \mathbf{x}_t=\mathbf{x},y_t=y) &= [-g_\phi(\mathbf{x},y,t)]_+ \Delta t+o(\Delta t). \end{aligned} \tag{2}
In practice, we draw U∼Uniform(0,1) at each time step. A cell divides into two if gϕ(xt,yt,t)>0 and U<gϕ(xt,yt,t)Δt, or undergoes apoptosis if gϕ(xt,yt,t)<0 and U<−gϕ(xt,yt,t)Δt. Otherwise, the cell survives without division. Upon division, the parent particle is replaced by two daughter particles initialized at (xt±ξ,yt), where ξ is a small random perturbation. Both daughters subsequently evolve under the same learned extended-space fields.
As illustrated in Figure 7 of Appendix B.3 in the revised manuscript, this stochastic realization produces explicit division and apoptosis events on the Dyngen dataset, complementing the continuous population-level representation. It provides one possible realization of the inferred net growth dynamics, rather than uniquely identifying biological division and death rates or actual individual cell lineages.