AI-based approach to dissect the variability of mouse stem cell-derived embryo models

Abstract

Copyright and License

© The Author(s) 2025.

This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Acknowledgement

We thank Wenqi Hu for the annotation of the dataset. This work was supported by the MZG.PIONEER.1.NIHP (HD104575A to M.Z.-G.), NOMIS Foundation (12540449 to M.Z.-G.), the Wellcome Trust (207415/Z/17/Z to M.Z.-G.), the Open Philanthropy Project (to M.Z.-G.), the Helmholtz Association under the joint research school “HIDSS4Health” – Helmholtz Information and Data Science School for Health to L.D., and the Helmholtz program NACIP to R.M. and L.D. This work is supported by the Helmholtz Association Initiative and Networking Fund on the HAICORE@KIT partition.

Funding

This work was supported by the MZG.PIONEER.1.NIHP (HD104575A to M.Z.-G.), NOMIS Foundation (12540449 to M.Z.-G.), the Wellcome Trust (207415/Z/17/Z to M.Z.-G.), the Open Philanthropy Project (to M.Z.-G.), the Helmholtz Association under the joint research school “HIDSS4Health” – Helmholtz Information and Data Science School for Health to L.D., and the Helmholtz program NACIP to R.M. and L.D. This work is supported by the Helmholtz Association Initiative and Networking Fund on the HAICORE@KIT partition.

Data Availability

The data generated in this study have been deposited in the Zenodo database available at https://doi.org/10.5281/zenodo.14605093³⁵. Source data are provided with this paper.

Code Availability

The custom code developed for this study is publicly accessible on GitHub at https://github.com/deiluca/StembryoNet and co-deposited on Zenodo at https://doi.org/10.5281/zenodo.14605177³⁶.

Contributions

These authors contributed equally: Paolo Caldarelli, Luca Deininger.

The project was originally conceptualized by P.C. and M.Z.-G and developed by P.C., M.Z.-G, L.D., R.M., C.Y. and P.C. designed and performed experiments with help from P.P. and L.D. developed the deep learning model with help from S.Z., P.C. and L.D. analyzed the data. P.C., L.D., and M.Z.-G. wrote the manuscript with comments from the other co-authors. M.Z.-G., R.M., and C.Y. supervised the project and acquired funding.

Conflict of Interest

The authors declare no competing interests.

Supplemental Material