Organizations: School of Mathematical Sciences, Peking University, Beijing, China · Beijing International Center for Mathematical Research, Peking University, Beijing, China · Center for Quantitative Biology, Peking University, Beijing, China · Center for Quantitative Biology, Center for Machine Learning Research, National Engineering Laboratory for Big Data Analysis and Applications, AI for Science Institute, Peking University, Beijing, China. · School of Mathematical Sciences, Beijing International Center for Mathematical Research, Center for Quantitative Biology, Center for Machine Learning Research, Institute for Artificial Intelligence, Peking University, Beijing 100871, China
Lineage tracing links cell states through clonal ancestry, but does not generally identify unique source-descendant pairings. Learning from such data therefore requires a model of conditional outcomes, rather than only the terminal population distribution. We introduce LIFT, a latent flow framework for probabilistic cell-state generation from lineage-informed couplings. Variational inference encodes alternative outcomes in a latent space, while a conditional prior enables sampling from the initial state alone. A Mean Flow decoder predicts future cell state directly, requiring one decoder evaluation per sampling, which makes it convenient to predict cell fate through large scale Monte-Carlo sampling. This construction combines a representation of one-to-many relationships with efficient sampling and an analysis of conditional prediction error. Experiments on synthetic and real datasets demonstrate LIFT's ability to recover both population distribution and cell fate probabilities.
Figures & tables
α=0.5
α=1
α=2
Method
W2
PE
W2
PE
W2
PE
CFM
0.238
1.370
0.275
2.678
0.305
5.002
Mean Flow
0.470
1.370
1.011
2.678
1.101
5.002
SM
0.463
0.282
0.478
1.500
0.460
3.580
LIFT
0.266
0.121
0.268
0.457
0.280
0.809
Table 1: Results on the synthetic branching benchmark. Lower values are better. PE is the sum in ( 54 ).
Figure 1: Conditional reconstruction in the branching system. (a) Source and terminal populations. (b) Predicted branch probabilities along the query segment. (c) Generated endpoint distributions at a fixed initial state as α varies.
α=0.5
α=1
α=2
Method
NFE
Time (ms)
W2
PE
W2
PE
W2
PE
CFM
1,000
401.09
0.238
1.370
0.275
2.678
0.305
5.002
100
40.26
0.238
1.370
0.282
2.678
0.305
5.002
10
3.87
0.270
1.370
0.367
2.678
0.369
5.002
SM
1,000
855.93
0.463
0.282
0.478
1.500
0.460
3.580
100
86.74
0.531
0.382
0.548
1.556
0.558
3.619
Table 2: Effect of NFE on the synthetic branching benchmark. Inference times are averaged over 100 timing measurements. Lower values are better for W2 , PE, and inference time. The best values in each metric column are highlighted in bold.
Hematopoiesis
Reprogramming
Method
W2
MeanPE
r
W2
MeanPE
r
CFM–Geo
0.301
0.336
0.657
1.013
0.288
0.729
CFM–Lin
0.539
0.366
0.728
3.393
0.268
0.729
MF–Geo
0.370
0.343
0.643
1.846
0.261
0.746
MF–Lin
0.549
0.349
0.689
3.946
0.363
0.701
SM
0.190
0.296
0.735
1.191
0.213
0.763
Table 3: Results on the two lineage-traced datasets. Geo and Lin indicate geometric and lineage-informed coupling variants, respectively. Here SM relies on entropic optimal transport coupling as [ 19 ] , so SM does not have different couplings. Lower W2 and MeanPE and higher Pearson correlation r are better. The best value in each column is highlighted in bold.
Figure 2: Representative fate prediction in mouse hematopoiesis. (a) Lineage-derived reference fate information. (b) Hard fate assignments. (c) Mo fate probabilities predicted by LIFT. The highlighted region contains mixed Mo and Neu clonal outcomes with a bias toward Mo. LIFT represents this region through intermediate fate probabilities rather than exclusively binary assignments.
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
Dataset
Time interval
Source cells
Target cells
Synthetic branching
0→1
1,000
5,000
Hematopoiesis
Day 2 → Day 6
1144
6477
Reprogramming
Day 15 → Day 28
1897
5945
Appendix
Table 1: Experimental datasets. Here we use low dimension representation of real datasets deduced from standard SPRING [ 23 ] method.
Parameter
Synthetic
Real data
Encoder widths
32,64,32
32,128,128,32
Prior widths
32,64,32
32,128,128,32
Decoder widths
32,64,32
32,64,128,64,32
Latent dimension dz
2
2
Regularization weight β
10
2
Reconstruction weight C
1
10
Appendix
Table 2: LIFT architecture and training parameters. Widths specify hidden layers in order. The real-data column applies to both lineage-traced scRNA-seq applications. ReLU activations and Adam optimization are used throughout.
α=0.5
α=1
α=2
Parameter
Value
W2
PE
W2
PE
W2
PE
Latent dimension dz
1
0.417
0.135
0.288
0.577
0.302
1.212
2
0.266
0.121
0.268
0.457
0.280
0.809
4
0.277
0.122
0.306
0.334
0.379
1.095
Reconstruction weight C
0.5
0.250
0.179
0.279
0.537
0.261
0.936
1
0.266
0.121
0.268
0.457
0.280
0.809
Appendix
Table 3: Hyperparameter sensitivity on the synthetic branching benchmark. The default setting is (dz,C,β)=(2,1,10) . Lower values are better for W2 and PE.
α=0.5
α=1
α=2
Decoder
Time
W2
PE
W2
PE
W2
PE
Latent FM
43.16
0.201
0.928
0.234
0.805
0.267
1.714
Latent MLP
0.8516
0.280
0.350
0.413
0.813
0.379
1.325
Latent Mean Flow
0.9607
0.259
0.198
0.268
0.457
0.280
0.809
Appendix
Table 4: Latent-decoder ablation. FM uses 100 Euler steps. Times are milliseconds per batch of 1,000 points on the reported CPU, averaged over 100 timing measurements. All three variants retain latent conditioning.
Figure 1: Vector fields derived by standard conditional flow matching (a-c) and mean vector fields derived by standard mean flow (d-f).
Figure 2: Vector fields derived by LIFT with different latent variable z .
Figure 3: Latent representations in the hematopoietic experiment. (a) Posterior means mϕ(x,y) , which use both endpoints. (b) Conditional-prior means mη(x) , which use the initial state only. Colors indicate the Mo and Neu fate annotations associated with the displayed observations.
Figure 4: Visualization of cell fate probabilities for other baseline methods on the hematopoiesis dataset. Colors match the main text.
Single-cell snapshot data can resolve a continuum of cellular states but do not uniquely determine the dynamics governing transitions between them. However, additional dynamical information can often be encoded in a cell-cell Markov transition kernel. Existing generative approaches for single cell trajectory inference either infer transport only from population marginals, impose a symmetric geometry on the state space, or incorporate directionality through a single velocity vector at each observed state. We introduce Finsler Flow Matching (FFM), a framework for learning continuous stochastic dynamics from discrete Markov transition graphs. We use the first and second local moments to construct a Finsler structure motivated by the Freidlin--Wentzell action, where the second moment determines anisotropic accessibility and the first moment introduces a preferred direction of motion. We learn neural approximations of the resulting directed geodesics, use their Finsler cost to construct source-target couplings, and define geometry-aware stochastic conditional paths that can be distilled into a continuous generative process through simulation-free score and flow matching. Across synthetic and single-cell trajectory inference benchmarks, FFM improves recovery of withheld intermediate populations, particularly when the transition dynamics are strongly directional or anisotropic. Our results provide a principled route from discrete transition probabilities to continuous generative dynamics while retaining both directional and diffusive structure.
Niklas Canova, Jonas Simon Fleck
Institute of Human Biology (IHB), Roche, Basel, Switzerland
Single-cell trajectory inference maps transcriptomic measurements onto developmental continua, yet configurations that fit the data equally well can assign conflicting cell fates. FateMultiplicity is a label-free framework that constructs a statistically admissible model set, or Rashomon set, without lineage labels, by evaluating model discrepancy on cross-fitted held-out genes under non-inferiority testing calibrated against random-seed variation. Multiplicity is large and depends more on the diversity of the model space than its size: twelve configurations of a second algorithm expose 20.0% of cells where twenty-four of the first expose 3.8%. Whether the per-cell certified fate margin FM yields more reliable assignments than the fitted model already provides is then tested, and it does not. On simulation ground truth, on the same cells, FM discriminates misassignment at AUC 0.682, against 0.965 for the baseline configuration's own decision margin (p = 0.003) and 0.854 for a seed-dispersion baseline. Informativeness is governed by the breadth of the admitted set, not its cardinality: at cardinality four, seed refits give 0.933 and hyperparameter-perturbed sets 0.701. Relaxing the infimum to a q-quantile recovers discrimination but converges toward the single model's own confidence; the supremum reaches 0.973 because theta*'s membership bounds it from below, while the infimum is unanchored. Multiplicity in trajectory inference is worth measuring and reporting, but per-cell certification over a label-free Rashomon set is not a route to more reliable fate calls. Two constructions survive: a margin-erosion ratio separates real from spurious branch points in simulation (AUC 0.890, untested on real data), and against clonally observed fate, uncertified cells disagree with their clone's outcome 16.4 percentage points more often than certified cells (p < 0.001).
A central goal of biology is to predict the dynamics of multicellular systems. Lineage context (the states of a cell's sisters, cousins, etc.) could inform these predictions, but how best to leverage it remains unclear. Here we introduce lineage inpainting, a generative modeling approach that uses lineage context with tree-structured transformers and stochastic interpolants to model cell state dynamics across lineage trees. Applied to a lineage-traced transcriptional atlas of mouse embryogenesis, it recovers dynamics not resolved by gene expression alone, including multiple transcriptional convergence events where distinct lineages are drawn to a common state. Despite being fit on unperturbed development, lineage inpainting can generate hypotheses about perturbation responses by simulating counterfactuals. These simulations agree in many cases with observed developmental phenotypes, including a single-cell measurement of the Tbx5 knockout response. Our results show that lineage information provides a rich source of context for learning multicellular dynamics.
Gokul Gowri, Nic Fishman, William N. Colgan +10
Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA · Whitehead Institute for Biomedical Research, Cambridge, MA, 02142, USA · Howard Hughes Medical Institute, Chevy Chase, MD, 20815, USA +11