scLTNN: an innovative tool for automatically visualizing single-cell trajectories.

Motivation: Cellular state identification and trajectory inference enable the computational simulation of cell fate dynamics using single-cell RNA sequencing data. However, existing methods for constructing cell fate trajectories demand substantial computational resources or prior knowledge of the developmental process. Results: Here, based on the discovery of the consistent expression distribution of highly variable genes, we create a new tool named scRNA-seq latent time neural network (scLTNN) by combining an artificial neural network with a distribution model. This innovative tool is pre-trained and capable of automatically inferring the origin and terminal state of cells, and accurately illustrating the developmental trajectory of cells with minimal use of computational resources and time. We implement scLTNN on human bone marrow cells, mouse pancreatic endocrine lineage, and axial mesoderm lineage of zebrafish embryo, accurately reconstructing their cell fate trajectories, respectively. Our scLTNN tool provides a straightforward and efficient method for illustrating cell fate trajectories, applicable across various species without the need for prior knowledge of the biological process. Availability and implementation: https://github.com/Starlitnightly/scLTNN.