LamineTourelab / OmiVAE

End-to-end deep learning model for low dimensional latent space extraction and multi-class classification on multi-omics datasets.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OmiVAE

Integrated Multi-omics Analysis Using Variational Autoencoders. An end-to-end deep learning model for low dimensional latent space extraction and multi-class classification on multi-omics datasets. This is modified architecture of the original paper. Instead of using mathylation data zith chromosome listing, I change the architecture to take into account only one entry like expression data.

Model architecture

image

Example of results

https://deepai.org/publication/integrated-multi-omics-analysis-using-variational-autoencoders-application-to-pan-cancer-classification

image

About

End-to-end deep learning model for low dimensional latent space extraction and multi-class classification on multi-omics datasets.

License:MIT License


Languages

Language:Python 100.0%