Graduation Semester and Year
Spring 2024
Language
English
Document Type
Thesis
Degree Name
Master of Science in Computer Science
Department
Computer Science and Engineering
First Advisor
Jacob Luber
Second Advisor
Ming Li
Third Advisor
Rémi A. Chou
Abstract
In this thesis, we present an innovative framework centered around the application of Random Forest Regression to forecast the prospective distribution of cells expressing the Sog-D gene (active cells) during the embryogenesis process in Drosophila. Our methodology specifically targets the Anterior-to-posterior (AP) and Dorsal-to-Ventral (DV) axes, unraveling the intricacies of gene expression control in living organisms at super-resolution, single-molecule resolution through whole embryo spatial transcriptomics imaging. The Random Forest Regression model serves as a pivotal tool in predicting the succeeding stage’s active cell distribution, capitalizing on the insights obtained from the preceding stage. We integrate temporally resolved, spatial point processes into our analysis, incorporating Ripley’s K-function alongside the cell’s state at each embryogenesis stage. Our approach yields an average predictive accuracy for active cell distribution, providing a valuable tool akin to RNA Velocity for spatially resolved developmental biology. This framework empowers researchers to extrapolate future spatially resolved gene expression from a singular data point, leveraging features derived from spatial point processes. Through this thesis, we contribute to advancing the understanding of developmental biology, offering a robust methodology for predicting gene expression dynamics at sub-cellular resolutions.
Keywords
Random Forest, Regression, Dorpsophila, Sog-D, Ripley’s K-function, Transcriptomics, Embryogenesis
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Rout, Biraaj, "PREDICTING FUTURE STATES WITH SPATIAL POINT PROCESSES IN SINGLE MOLECULE RESOLUTION SPATIAL TRANSCRIPTOMICS" (2024). Computer Science and Engineering Theses. 365.
https://mavmatrix.uta.edu/cse_theses/365