.png){kind=icon}
.png){kind=icon}
Return
Inferring single-cell transcriptomic dynamics with structured latent gene expression dynamics
.png){kind=icon}
OA
AI
DOI：10.1016/j.crmeth.2023.100581.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Gene expression dynamics provide directional information for trajectory inference from single-cell RNA sequencing data. Traditional approaches compute RNA velocity using strict modeling assumptions about transcription and splicing of RNA. This can fail in scenarios where multiple lineages have distinct gene dy-namics or where rates of transcription and splicing are time dependent. We present LatentVelo,an approach to compute a low-dimensional representation of gene dynamics with deep learning. LatentVelo embeds cells into a latent space with a variational autoencoder and models differentiation dynamics on this dynamics-basedlatent space with neural ordinary differential equations. LatentVelo infers a latent reg-ulatory state that controls the dynamics of an individual cell to model multiple lineages. LatentVelo can pre-dict latent trajectories, describing the inferred developmental path for individual cells rather than just local RNA velocity vectors. The dynamics-based embedding batch corrects cell states and velocities, outperform-ing comparable autoencoder batch correction methods that do not consider gene expression dynamics.
Keywords:
INFERENCE
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.5
Papers:
930
Citations:
2.0K