GSR: Simulator - MichiGAN

Basic Package Attributes
AttributeValue
Title MichiGAN
Short Description MichiGAN: sampling from disentangled representations of single-cell data using generative adversarial networks
Long Description MichiGAN is a novel neural network that combines the strengths of VAEs and GANs to sample from disentangled representations without sacrificing data generation quality. MichiGAN allows us to manipulate semantically distinct aspects of cellular identity and predict single-cell gene expression response to drug treatment.
Keywords Cellular identity, Disentangled representations, Generative adversarial networks, Representation learning, Single-cell genomics
Version 1.0
Project Started 2021
Last Release 4 years, 3 months ago
Homepagehttps://github.com/welch-lab/MichiGAN
Citations Yu H, Welch JD, MichiGAN: sampling from disentangled representations of single-cell data using generative adversarial networks., Genome Biol, May 20, 2021 [ Abstract, cited in PMC ]
GSR Certification

Accessibility
Documentation
Application
Support

Last evaluatedSept. 28, 2022 (934 days ago)
Author verificationThe basic description provided was derived from a website or publications by the GSR team and has not yet been verified by the simulation author. To modify this entry or add more information, propose changes to this simulator.
Detailed Attributes
Attribute CategoryAttribute
Target
Type of Simulated DataRNA, Gene Expression, Single-Cell Sequencing,
Variations
Simulation MethodNeural network,
Input
Data Type
File format
Output
Data Type
Sequencing Reads
File Format
Sample Type
Phenotype
Trait Type
Determinants
Evolutionary Features
Demographic
Population Size Changes
Gene Flow
Spatiality
Life Cycle
Mating System
Fecundity
Natural Selection
Determinant
Models
Recombination
Mutation Models
Events Allowed
Other
InterfaceWeb-based,
Development
Tested Platforms
LanguagePython,
LicenseGNU Public License,
GSR CertificationDocumentation, Support,

Number of Primary Citations: 1

Number of Non-Primary Citations: 1

The following 1 publications are selected examples of applications that used MichiGAN.

2022

Hazra D, Kim MR, Byun YC, Generative Adversarial Networks for Creating Synthetic Nucleic Acid Sequences of Cat Genome., Int J Mol Sci, March 28, 2022 [Abstract]


Propose changes to this simulator