The scDHA software package can perform cell segregation through unsupervised learning, dimension reduction and visualization, cell classification, and time-trajectory inference on single-cell RNA sequencing data.
devtools::install_github('duct317/scDHA')Or, install with manual and vignette:
devtools::install_github('duct317/scDHA', build_manual = T, build_vignettes = T)
libtorchcan be installed using:
data('Goolam'); data <- t(Goolam$data); label <- as.character(Goolam$label)
data <- log2(data + 1)
result <- scDHA(data, seed = 1)
cluster <- result$cluster
To use our package for new data, the package includes these functions: - scDHA: main function, doing dimension reuction and clustering. The input is a matrix with rows as samples and columns as genes. - scDHA.w: plot the normalized weight variances to select suitable cutoff for gene filtering (optional). - scDHA.vis: visualization. The input is demension reduction output. - scDHA.pt: generating pseudotime. The input is demension reduction output. - scDHA.class: classification new data using available one. The inputs consist of train data matrix, train data label and new data matrix. - The result is reproducible by setting seed for these functions. - More detail about parameters for each function could be found in the manual.
Duc Tran, Hung Nguyen, Bang Tran, Carlo La Vecchia, Hung N. Luu, Tin Nguyen (2021). Fast and precise single-cell data analysis using a hierarchical autoencoder. Nature Communications, 12, 1029. doi: 10.1038/s41467-021-21312-2 (link)
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.