Skip to content
/ speos Public

A positive-unlabeled ensemble learning framework for disease gene prioritization.

License

Notifications You must be signed in to change notification settings

fratajcz/speos

Repository files navigation

SPEOS Header

Identification of core genes from Biological Networks, GWAS and gene expression.

Speos, pronounced almost like "space", is a machine learning framework to merge deep learning and the omnigenic model. Its goal is to predict core genes for several diseases which allow subsequent research to allocate resources to the most promising candidates.

For the installation instructions please see the documentation.

Documentation

https://speos.readthedocs.io/en/latest/index.html

Publication

Speos has now been published in Nature Communications! https://www.nature.com/articles/s41467-023-42975-z

Citation

If you use Speos in your work, please cite the paper above. You can use the following information:

@article{ratajczak_speos_2023,
	title = {Speos: an ensemble graph representation learning framework to predict core gene candidates for complex diseases},
  	author = {Ratajczak, Florin and Joblin, Mitchell and Hildebrandt, Marcel and Ringsquandl, Martin and Falter-Braun, Pascal and Heinig, Matthias},
	journal = {Nature Communications},
	volume = {14},
	url = {https://www.nature.com/articles/s41467-023-42975-z},
	doi = {10.1038/s41467-023-42975-z},
	year = {2023},
	pages = {7206}
}

About

A positive-unlabeled ensemble learning framework for disease gene prioritization.

Resources

License

Stars

Watchers

Forks

Packages

No packages published