Try Boost
Accelerate your research with up to 20 hours of computing
Contact Us
scVI-Tools |

LDVAE

1
2
Omics
    More
Step 1: Upload your data

Single Cell RNA-Seq Data

Drag your file(s) or upload
  • Your file can be in the following formats:csv, h5ad, h5
    • Data should be in .h5, .h5ad, .csv format
or
Don’t have a file?
Use our demo data to run
Use Demo Data
View example data
Step 2: Set Parameters
1
10
20
1000
1500
10000
50
300
1000
8
128
512
1
1
3
0.10
0.50
Step 3: Complete run profile

LDVAE (Linearly-decoded Variational Auto-encoder, also called Linear scVI) is a flavor of scVI with a linear decoder.

The advantages of LDVAE are: (i) Can be used to interpret latent dimensions with factor loading matrix. (ii) Scalable to very large datasets (>1 million cells).

The limitations of LDVAE include: (i) Less capacity than scVI differential expression or scANVI for annotation, which use a neural network decoder. (ii) Less capable of integrating data with complex batch effects. 

Citation:
Valentine Svensson, Adam Gayoso, Nir Yosef, and Lior Pachter. Interpretable factor models of single-cell RNA-seq via variational autoencoders. Bioinformatics, 36(11):3418–3421, March 2020. doi:10.1093/bioinformatics/btaa169.
Released:
Nov-28-2022
Previous Job Parameters
Your previous job parameters will show up here
so you can keep track of your jobs
Results
Parameters