Predicting Future States with Spatial Point Processes in Single Molecule Resolution Spatial Transcriptomics

TL;DR

This paper presents a machine learning pipeline using XGBoost and spatial point processes to predict future gene expression states in embryonic development at single-cell resolution.

Contribution

It introduces a novel approach combining spatial point processes with machine learning to forecast cellular gene expression distributions in spatial transcriptomics.

Findings

Achieved accurate predictions of future active cell distributions.

Integrated Ripley's K-function with cell states for improved modeling.

Provided a new tool analogous to RNA Velocity for spatial data.

Abstract

In this paper, we introduce a pipeline based on XGboost to predict the future distribution of cells that are expressed by the Sog-D gene (active cells) in both the Anterior to posterior (AP) and the Dorsal to Ventral (DV) axis of the Drosophila in embryogenesis process. This method provides insights about how cells and living organisms control gene expression in super resolution whole embryo spatial transcriptomics imaging at sub cellular, single molecule resolution. An XGboost model was used to predict the next stage active distribution based on the previous one. To achieve this goal, we leveraged temporally resolved, spatial point processes by including Ripley's K-function in conjunction with the cell's state in each stage of embryogenesis, and found average predictive accuracy of active cell distribution. This tool is analogous to RNA Velocity for spatially resolved developmental biology, from one data point we can predict future spatially resolved gene expression using features from the spatial point processes.