Farag et al., Developmental Cell 2024
We have developed a code for learning decision tree classifiers, predicting manually-annotated endodermal morphotypes at 96 hrs, from morphological features (derived from brightfield images) and marker expression features (derived from fluorescence GFP and RFP images).
The code and data are deposited on both GitHub and Zenodo, and available from the following links:
https://github.com/ChenSchiff/Dev_Cell_paper
https://doi.org/10.5281/zenodo.11181735
https://zenodo.org/records/13928014
The code learns 500 decision trees from the input data set (using a bootstrap train/test split approach). It then visualizes the statistics of one-parameter (top tree node) and three-parameter (first and second tree levels) frequencies, as either bar graph or heatmap, respectively. In computing these frequencies, only learned trees with test-set accuracy above a set threshold are taken into consideration.
The code is at the basis of the machine learning section of our publication Farag et. al., Coordination between endoderm progression and mouse gastruloid elongation controls endodermal morphotype choice (Developmental Cell, 2024):
https://www.cell.com/developmental-cell/fulltext/S1534-5807(24)00335-6
With the preprint available open access at:
https://www.biorxiv.org/content/10.1101/2023.02.07.527329v1
The morphological and expression features used by the code were manually curated from the time series dataset.
Villaronga-Luque, Savill et al., Cell Stem Cell 2025
The data and code for Villaronga-Luque, Savill et al., Integrated molecular-phenotypic profiling reveals metabolic control of morphological variation in a stem-cell-based embryo model (Cell Stem Cell, in press) is available here:
Single-cell RNA-sequencing data are accessible at the National Center for Biotechnology Information BioProjects Gene Expression Omnibus (GEO) under accession number GSE250136.
All code is available at https://github.com/Team-Stembryo/Integrated_Molecular-Phenotypic_Profiling_of_Stembryos. Imaging processing and analysis requires the library https://github.com/Cryaaa/organoid_prediction_python developed for this project.
Imaging datasets from the molecular-phenotypic profiling are available at: