Lineage context improves predictions of cell development dynamics
Learning developmental dynamics from lineage context
Machine Learning
Summary
Predicting how groups of cells develop and change is important in biology. The authors introduced a new method called lineage inpainting that uses family tree information of cells to better understand their changes over time. This approach helps find patterns that gene activity alone misses and can even suggest how cells might react to changes, like gene knockouts. Their method matches real experimental observations, showing that knowing cell family relationships gives extra clues about development.
What this means in practice
- •For developmental biology labs: Model and predict how cell lineages develop and respond to genetic changes using lineage-aware dynamic simulations.
- •For biotechnology companies: Simulate cell development under genetic perturbations to generate hypotheses for designing targeted therapies and interventions.
Authors
Gokul Gowri, Nic Fishman, William N. Colgan, Minming Wang, Yusuke Kijima, Sachin A. Kumar, Aleksandr Zimin, Luke W. Koblan, Marinka Zitnik, Zachary D. Smith, Stephen Bates, Philippe Rigollet, Jonathan S. Weissman
Abstract
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.