VASC – Variational Autoencoder for Single Cell RNA-seq datasets

VASC

:: DESCRIPTION

VASC (deep Variational Autoencoder for SCRNA-seq data) is a deep multi-layer generative model, for the dimension reduction and visualization. It can do nonlinear hierarchical feature representations and model the dropout events of scRNA-seq data. Tested on more than twenty datasets, VASC show better performances in most cases and higher stability compared with several dimension reduction methods. VASC successfully re-establishes the embryo pre-implantation cell lineage and its associated genes based on the 2D representation of a large-scale scRNA-seq from human embryos.

::DEVELOPER

Bioinformatics & Intelligent Information Processing Research Group

:: SCREENSHOTS

N/A

:: REQUIREMENTS

  • Linux
  • Python 3.5+
  • numpy 1.12.1
  • h5py 2.7.0
  • sklearn 0.18.1
  • tensorflow 1.1.0
  • keras 2.0.6

:: DOWNLOAD

VASC

:: MORE INFORMATION

Citation

VASC: dimension reduction and visualization of single cell RNA sequencing data by deep variational autoencoder.
Genomics, Proteomics & Bioinformatics 2018, 16(5):320-331.
Dongfang Wang, Jin Gu

Leave a Reply

Your email address will not be published. Required fields are marked *

 

This site uses Akismet to reduce spam. Learn how your comment data is processed.