scChronos: hierarchical temporal context learning for missing snapshot prediction in single-cell time series
Abstract
Motivation: Single-cell time-series atlases provide discrete cross-sectional snapshots of continuous developmental processes, making missing-snapshot prediction essential for reconstructing trajectories and dynamic programs. However, destructive scRNA-seq profiling prevents tracking the same cells across time, yielding unpaired population snapshots and making missing-snapshot prediction challenging. Existing methods typically rely on explicit dynamical propagation or transport-based coupling between snapshots, which may ignore the statistical constraints of the overall population distribution and be sensitive to sampling noise and cell-to-cell variability.
Results: We introduce scChronos, a hierarchical temporal context learning framework that formulates missing-snapshot prediction as target-conditioned population distribution prediction rather than individual-cell propagation. Unlike cell-centric propagation approaches, scChronos explicitly captures dual-level dynamics: (i) within each observed snapshot, scChronos compresses cell populations into cluster-representative cell representations with a transcriptomic encoder, preserving population information while reducing noise and (ii) across reference snapshots, the dual-branch temporal context integration module fuses information from all available and nearby time points into a temporal representation, which is then decoded with learnable cell-generation seeds to predict the target distribution. Extensive experiments demonstrate that scChronos improves both interpolation-style recovery and extrapolation-style forecasting compared with state-of-the-art methods. Beyond reducing distributional discrepancy, scChronos better preserves developmental topology and maintains cell-type-specific marker and pathway programs.
Availability: The code and data are available at https://github.com/yjs193/scChronos and https://doi.org/10.5281/zenodo.20933283.
Related
- An extensible deep learning framework for multi-type chromatin interaction prediction through hierarchical adaptation strategies
- Metaheuristic Optimization of Temporal Surrogates for Early Prediction of Protein Conformational Stability from Short Molecular-Dynamics Trajectories
- Mutation-resolved ABL1 inhibitor resistance prediction under mutation-disjoint and temporal cross-study validation
- BRIDGE-KO: auditable transfer learning with bridged knockoffs improves cross-cohort microbiome prediction of immunotherapy response
- Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
BibTeX
@article{yao2026scchronos,
title = {{scChronos: hierarchical temporal context learning for missing snapshot prediction in single-cell time series}},
author = {Jiongsen Yao and Yunfei Zhang and Yong Xu and Jinjin Ma and Si Wu},
journal = {Bioinformatics},
year = {2026},
month = oct,
doi = {10.1093/bioinformatics/btag772},
url = {https://doi.org/10.1093/bioinformatics/btag772},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - scChronos: hierarchical temporal context learning for missing snapshot prediction in single-cell time series
AU - Jiongsen Yao
AU - Yunfei Zhang
AU - Yong Xu
AU - Jinjin Ma
AU - Si Wu
PY - 2026
DA - 2026/10/14
JO - Bioinformatics
DO - 10.1093/bioinformatics/btag772
UR - https://doi.org/10.1093/bioinformatics/btag772
AB - Motivation: Single-cell time-series atlases provide discrete cross-sectional snapshots of continuous developmental processes, making missing-snapshot prediction essential for reconstructing trajectories and dynamic programs. However, destructive scRNA-seq profiling prevents tracking the same cells across time, yielding unpaired population snapshots and making missing-snapshot prediction challenging. Existing methods typically rely on explicit dynamical propagation or transport-based coupling between snapshots, which may ignore the statistical constraints of the overall population distribution and be sensitive to sampling noise and cell-to-cell variability. Results: We introduce scChronos, a hierarchical temporal context learning framework that formulates missing-snapshot prediction as target-conditioned population distribution prediction rather than individual-cell propagation. Unlike cell-centric propagation approaches, scChronos explicitly captures dual-level dynamics: (i) within each observed snapshot, scChronos compresses cell populations into cluster-representative cell representations with a transcriptomic encoder, preserving population information while reducing noise and (ii) across reference snapshots, the dual-branch temporal context integration module fuses information from all available and nearby time points into a temporal representation, which is then decoded with learnable cell-generation seeds to predict the target distribution. Extensive experiments demonstrate that scChronos improves both interpolation-style recovery and extrapolation-style forecasting compared with state-of-the-art methods. Beyond reducing distributional discrepancy, scChronos better preserves developmental topology and maintains cell-type-specific marker and pathway programs. Availability: The code and data are available at https://github.com/yjs193/scChronos and https://doi.org/10.5281/zenodo.20933283.
SN - 1367-4803
SN - 1367-4811
ER -