Skip to content

A cell-type annotation method for single cell transcriptomics data using semi-supervised learning

License

Notifications You must be signed in to change notification settings

deeplearner87/CASSL

Repository files navigation

CASSL

Dibyendu Bikash Seal, Vivek Das, Rajat K. De, "A cell-type annotation method for single cell transcriptomics data using semi-supervised learning. This project aims at learning cell annotations for missing cell labels via NMF and recursive k-Means clustering"

Citation

Seal, D.B., Das, V. & De, R.K. CASSL: A cell-type annotation method for single cell transcriptomics data using semi-supervised learning. Appl Intell (2022). https://doi.org/10.1007/s10489-022-03440-4

Authors' Information

Dibyendu Bikash Seal

A. K. Choudhury School of Information Technology, University of Calcutta, JD - II, Sector III, Salt Lake City, Kolkata 700106, India

E-mail: [email protected]

Vivek Das

Novo Nordisk A/S, Novo Nordisk Park 1, 2760 M ̊aløv, Denmark

E-mail: [email protected]

Rajat K. De

Machine Intelligence Unit, Indian Statistical Institute, 203 Barrackpore Trunk Road, Kolkata 700108, India

E-mail: [email protected]

Instructions

To test CASSL on datasets with missing annotations, run CASSL.ipynb.

To validate CASSL on datasets with no missing annotations, run CASSL_Validation.ipynb. Go to "Remove p% labels" sub-section and set the percentage of cells to be used for training.

Dataset source

https://doi.org/10.5281/zenodo.5681184

Graphical abstract

CASSL_Workflow

About

A cell-type annotation method for single cell transcriptomics data using semi-supervised learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published