scPOEM (version 0.1.3)

pg_embedding: Co-embeddings of Peaks and Genes.

Description

Learn the low-dimensional representations for peaks and genes with a meta-path based method.

Usage

pg_embedding(
  gg_net,
  pp_net,
  pg_net_list,
  dirpath = tempdir(),
  relearn_pg_embedding = TRUE,
  save_file = TRUE,
  d = 100,
  numwalks = 5,
  walklength = 3,
  epochs = 100,
  neg_sample = 5,
  batch_size = 32,
  weighted = TRUE,
  exclude_pos = FALSE,
  seed = NULL,
  python_env = "scPOEM_env"
)

Value

A list containing the following:

E

Low-dimensional representations of peaks and genes

peak_node

Peak ids that are associated with other peaks or genes.

gene_node

Gene ids that are associated with other peaks or genes.

Arguments

gg_net

The gene-gene network.

pp_net

The peak-peak network.

pg_net_list

A list of peak-gene networks, constructed via different methods.

dirpath

The folder path to read or write file.

relearn_pg_embedding

Logical. Whether to relearn the low-dimensional representations for peaks and genes from scratch. If FALSE, the function will attempt to read from
node_embeddings.mtx, node_used_peak.csv, node_used_gene.csv
under dirpath/embedding in single mode or
dirpath/state_name/embedding in compare mode.

save_file

Logical, whether to save the output to a file.

d

Dimension of the latent space. Default is 100.

numwalks

Number of random walks per node. Default is 5.

walklength

Length of walk depth. Default is 3.

epochs

Number of training epochs. Default is 100.

neg_sample

Number of negative samples per positive sample. Default is 5.

batch_size

Batch size for training. Default is 32.

weighted

Whether the sampling network is weighted. Default is TRUE.

exclude_pos

Whether to exclude positive samples from negative sampling. Default is FALSE.

seed

An integer specifying the random seed to ensure reproducible results.

python_env

Name or path of the Python environment to be used.

Examples

# \donttest{
library(scPOEM)
library(monocle)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
gg_net <- GGN(example_data_single$Y,
              file.path(dirpath, "single"),
              save_file=FALSE)
pp_net <- PPN(example_data_single$X, example_data_single$peak_data,
              example_data_single$cell_data, example_data_single$genome,
              file.path(dirpath, "single"), save_file=FALSE)
net_Lasso <- PGN_Lasso(example_data_single$X, example_data_single$Y,
                       example_data_single$gene_data, example_data_single$neibor_peak,
                       file.path(dirpath, "single"), save_file=FALSE)
net_RF <- PGN_RF(example_data_single$X, example_data_single$Y,
                 example_data_single$gene_data, example_data_single$neibor_peak,
                 file.path(dirpath, "single"), save_file=FALSE)
net_XGB <- PGN_XGBoost(example_data_single$X, example_data_single$Y,
                       example_data_single$gene_data, example_data_single$neibor_peak,
                       file.path(dirpath, "single"), save_file=FALSE)
E_result <- pg_embedding(gg_net, pp_net, list(net_Lasso, net_RF, net_XGB),
                         file.path(dirpath, "single"), save_file=FALSE)
# }