Package 'scPOEM' reference manual

Title:	Single-Cell Meta-Path Based Omic Embedding
Description:	Provide a workflow to jointly embed chromatin accessibility peaks and expressed genes into a shared low-dimensional space using paired single-cell 'ATAC-seq' ('scATAC-seq') and single-cell 'RNA-seq' ('scRNA-seq') data. It integrates regulatory relationships among peak-peak interactions (via 'Cicero'), peak-gene interactions (via Lasso, random forest, and 'XGBoost'), and gene-gene interactions (via principal component regression). With the input of paired 'scATAC-seq' and 'scRNA-seq' data matrices, 'scPOEM' assigns a low-dimensional feature vector to each gene and peak. Additionally, it supports the reconstruction of gene-gene network with low-dimensional projections (via 'epsilon-NN') and then the comparison of the networks of two conditions through manifold alignment implemented in 'scTenifoldNet'.
Authors:	Yuntong Hou [aut, cre] (https://orcid.org/0009-0005-0587-4692), Yan Zhong [aut, ctb] (https://orcid.org/0000-0003-2412-043X), Yongjian Yang [ctb] (https://orcid.org/0000-0002-4135-5014), Xinyue Zheng [ctb], James Cai [ctb] (https://orcid.org/0000-0002-8081-6725)
Maintainer:	Yuntong Hou <[email protected]>
License:	GPL (>= 2)
Version:	0.1.2
Built:	2026-05-28 14:53:09 UTC
Source:	https://github.com/houyt23/scpoem

Gene Network Reconstruction and Alignment

Description

Reconstruct gene networks via epsilon-NN and compare conditions using manifold alignment implemented in scTenifoldNet."

Usage

align_embedding(
  gene_data1,
  gene_node1,
  E1,
  gene_data2,
  gene_node2,
  E2,
  dirpath,
  d = 100
)
align_embedding(
  gene_data1,
  gene_node1,
  E1,
  gene_data2,
  gene_node2,
  E2,
  dirpath,
  d = 100
)

Arguments

gene_data1

The information for genes in state1, must have a col names 'gene_name'.

gene_node1

Gene ids that are associated with other peaks or genes in state1.

E1

Embedding representations of peaks and genes in state1.

gene_data2

The information for genes in state2, must have a col names 'gene_name'.

gene_node2

Gene ids that are associated with other peaks or genes in state2.

E2

Embedding representations of peaks and genes in state2.

dirpath

The folder path to read or write file

d

The dimension of latent space.

Value

A list containing the following

E_g2: Embedding representations of genes in two conditions.
diffRegulation: A list of differential regulation informmation for each gene.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download compare mode example data
data(example_data_compare)
data_S1 <- example_data_compare$S1
data_S2 <- example_data_compare$S2
gg_net1 <- GGN(data_S1$Y, file.path(dirpath, "compare/S1"))
pp_net1 <- PPN(data_S1$X, data_S1$peak_data, data_S1$cell_data,
               data_S1$genome, file.path(dirpath, "compare/S1"))
net_Lasso1 <- PGN_Lasso(data_S1$X, data_S1$Y,
                        data_S1$gene_data, data_S1$neibor_peak,
                        file.path(dirpath, "compare/S1"))
net_RF1 <- PGN_RF(data_S1$X, data_S1$Y, data_S1$gene_data,
                  data_S1$neibor_peak, file.path(dirpath, "compare/S1"))
net_XGB1 <- PGN_XGBoost(data_S1$X, data_S1$Y,
                        data_S1$gene_data, data_S1$neibor_peak,
                        file.path(dirpath, "compare/S1"))
E_result_S1 <- pg_embedding(gg_net1, pp_net1, net_lasso1, net_RF1,
                            net_XGB1, file.path(dirpath, "compare/S1"))

gg_net2 <- GGN(data_S2$Y, file.path(dirpath, "compare/S2"))
pp_net2 <- PPN(data_S2$X, data_S2$peak_data,
               data_S2$cell_data, data_S2$genome,
               file.path(dirpath, "compare/S2"))
net_Lasso2 <- PGN_Lasso(data_S2$X, data_S2$Y,
                        data_S2$gene_data, data_S2$neibor_peak,
                        file.path(dirpath, "compare/S2"))
net_RF2 <- PGN_RF(data_S2$X, data_S2$Y, data_S2$gene_data,
                  data_S2$neibor_peak, file.path(dirpath, "compare/S2"))
net_XGB2 <- PGN_XGBoost(data_S2$X, data_S2$Y,
                        data_S2$gene_data, data_S2$neibor_peak,
                        file.path(dirpath, "compare/S2"))
E_result_S2 <- pg_embedding(gg_net2, pp_net2, net_lasso2, net_RF2,
                            net_XGB2, file.path(dirpath, "compare/S2"))

compare_result <- align_embedding(data_S1$gene_data,
                                  E_result_S1$gene_node,
                                  E_result_S1$E,
                                  data_S2$gene_data,
                                  E_result_S2$gene_node,
                                  E_result_S2$E,
                                  file.path(dirpath, "compare/compare"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download compare mode example data
data(example_data_compare)
data_S1 <- example_data_compare$S1
data_S2 <- example_data_compare$S2
gg_net1 <- GGN(data_S1$Y, file.path(dirpath, "compare/S1"))
pp_net1 <- PPN(data_S1$X, data_S1$peak_data, data_S1$cell_data,
               data_S1$genome, file.path(dirpath, "compare/S1"))
net_Lasso1 <- PGN_Lasso(data_S1$X, data_S1$Y,
                        data_S1$gene_data, data_S1$neibor_peak,
                        file.path(dirpath, "compare/S1"))
net_RF1 <- PGN_RF(data_S1$X, data_S1$Y, data_S1$gene_data,
                  data_S1$neibor_peak, file.path(dirpath, "compare/S1"))
net_XGB1 <- PGN_XGBoost(data_S1$X, data_S1$Y,
                        data_S1$gene_data, data_S1$neibor_peak,
                        file.path(dirpath, "compare/S1"))
E_result_S1 <- pg_embedding(gg_net1, pp_net1, net_lasso1, net_RF1,
                            net_XGB1, file.path(dirpath, "compare/S1"))

gg_net2 <- GGN(data_S2$Y, file.path(dirpath, "compare/S2"))
pp_net2 <- PPN(data_S2$X, data_S2$peak_data,
               data_S2$cell_data, data_S2$genome,
               file.path(dirpath, "compare/S2"))
net_Lasso2 <- PGN_Lasso(data_S2$X, data_S2$Y,
                        data_S2$gene_data, data_S2$neibor_peak,
                        file.path(dirpath, "compare/S2"))
net_RF2 <- PGN_RF(data_S2$X, data_S2$Y, data_S2$gene_data,
                  data_S2$neibor_peak, file.path(dirpath, "compare/S2"))
net_XGB2 <- PGN_XGBoost(data_S2$X, data_S2$Y,
                        data_S2$gene_data, data_S2$neibor_peak,
                        file.path(dirpath, "compare/S2"))
E_result_S2 <- pg_embedding(gg_net2, pp_net2, net_lasso2, net_RF2,
                            net_XGB2, file.path(dirpath, "compare/S2"))

compare_result <- align_embedding(data_S1$gene_data,
                                  E_result_S1$gene_node,
                                  E_result_S1$E,
                                  data_S2$gene_data,
                                  E_result_S2$gene_node,
                                  E_result_S2$E,
                                  file.path(dirpath, "compare/compare"))

## End(Not run)

Network Reconstruction via epsilon-NN

Description

Reconstruction of gene-gene network via low-dimentional projections (via epsilon-NN).

Usage

eNN(E_g)
eNN(E_g)

Arguments

E_g

Embedding representations of genes.

Value

The epsilon-NN network.

Example Input Data for Compare Mode Analysis

Description

A list containing example single-cell multi-omics data used in "compare" mode of the scPOEM package.

Usage

data(example_data_compare)
data(example_data_compare)

Format

A named list of length 2. Each element is itself a named list with the following components:

X: The scATAC-seq data, sparse matrix.
Y: The scRNA-seq data, sparse matrix.
peak_data: A data.frame containing peak information.
gene_data: A data.frame containing gene information (must contain column "gene_name").
cell_data: A data.frame containing cell metadata.
neibor_peak: The peak IDs within a certain range of each gene, must have cols c("gene_name", "start_use", "end_use"). The id numbers in "start_use" and "end_use" are start from 0.
genome: The genome length for the species.

Examples

data(example_data_compare)

data(example_data_compare)

Example Input Data for Single Mode Analysis

Description

A list containing example single-cell multi-omics data used in "single" mode of the scPOEM package.

Usage

data(example_data_single)
data(example_data_single)

Format

A named list with 7 elements:

X: The scATAC-seq data, sparse matrix.
Y: The scRNA-seq data, sparse matrix.
peak_data: A data.frame containing peak information.
gene_data: A data.frame containing gene information (must contain column "gene_name").
cell_data: A data.frame containing cell metadata.
neibor_peak: The peak IDs within a certain range of each gene, must have cols c("gene_name", "start_use", "end_use"). The id numbers in "start_use" and "end_use" are start from 0.
genome: The genome length for the species.

Examples

data(example_data_single)

data(example_data_single)

Construct Gene-Gene Network

Description

Construct the gene-gene network via principle component regression.

Usage

GGN(
  Y,
  dirpath,
  count_device = 1,
  nComp = 5,
  rebuild_GGN = T,
  python_env = "scPOEM_env"
)
GGN(
  Y,
  dirpath,
  count_device = 1,
  nComp = 5,
  rebuild_GGN = T,
  python_env = "scPOEM_env"
)

Arguments

Y

The scRNA-seq data, sparse matrix.

dirpath

The folder path to read or write file.

count_device

The number of cpus used to train the Lasso model.

nComp

The number of PCs used for regression

rebuild_GGN

Logical. Whether to rebuild the gene-gene network (GGN) from scratch. If FALSE, the function will attempt to read from 'GGN.mtx' under dirpath/test in single mode or dirpath/state_name/test in compare mode.

python_env

Name or path of the Python environment to be used.

Value

The GGN network.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct GGN net.
gg_net <- GGN(example_data_single$Y, file.path(dirpath, "single"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct GGN net.
gg_net <- GGN(example_data_single$Y, file.path(dirpath, "single"))

## End(Not run)

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,
  relearn_pg_embedding = T,
  d = 100,
  numwalks = 5,
  walklength = 3,
  epochs = 100,
  neg_sample = 5,
  batch_size = 32,
  weighted = TRUE,
  exclude_pos = FALSE,
  seed = 0,
  python_env = "scPOEM_env"
)
pg_embedding(
  gg_net,
  pp_net,
  pg_net_list,
  dirpath,
  relearn_pg_embedding = T,
  d = 100,
  numwalks = 5,
  walklength = 3,
  epochs = 100,
  neg_sample = 5,
  batch_size = 32,
  weighted = TRUE,
  exclude_pos = FALSE,
  seed = 0,
  python_env = "scPOEM_env"
)

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.

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.

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.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
library(data.table)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
gg_net <- GGN(example_data_single$Y, file.path(dirpath, "single"), 1, 5, T)
pp_net <- PPN(example_data_single$X, example_data_single$peak_data,
              example_data_single$cell_data, example_data_single$genome,
              file.path(dirpath, "single"))
net_Lasso <- PGN_Lasso(example_data_single$X, example_data_single$Y,
                       example_data_single$gene_data, example_data_single$neibor_peak,
                       file.path(dirpath, "single"))
net_RF <- PGN_RF(example_data_single$X, example_data_single$Y,
                 example_data_single$gene_data, example_data_single$neibor_peak,
                 file.path(dirpath, "single"))
net_XGB <- PGN_XGBoost(example_data_single$X, example_data_single$Y,
                       example_data_single$gene_data, example_data_single$neibor_peak,
                       file.path(dirpath, "single"))
E_result <- pg_embedding(gg_net, pp_net, list(net_Lasso, net_RF, net_XGB),
                         file.path(dirpath, "single"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
library(data.table)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
gg_net <- GGN(example_data_single$Y, file.path(dirpath, "single"), 1, 5, T)
pp_net <- PPN(example_data_single$X, example_data_single$peak_data,
              example_data_single$cell_data, example_data_single$genome,
              file.path(dirpath, "single"))
net_Lasso <- PGN_Lasso(example_data_single$X, example_data_single$Y,
                       example_data_single$gene_data, example_data_single$neibor_peak,
                       file.path(dirpath, "single"))
net_RF <- PGN_RF(example_data_single$X, example_data_single$Y,
                 example_data_single$gene_data, example_data_single$neibor_peak,
                 file.path(dirpath, "single"))
net_XGB <- PGN_XGBoost(example_data_single$X, example_data_single$Y,
                       example_data_single$gene_data, example_data_single$neibor_peak,
                       file.path(dirpath, "single"))
E_result <- pg_embedding(gg_net, pp_net, list(net_Lasso, net_RF, net_XGB),
                         file.path(dirpath, "single"))

## End(Not run)

Peak-Gene Network via Lasso

Description

Construct the peak-gene network via Lasso.

Usage

PGN_Lasso(
  X,
  Y,
  gene_data,
  neibor_peak,
  dirpath,
  count_device = 1,
  rebuild_PGN_Lasso = T
)
PGN_Lasso(
  X,
  Y,
  gene_data,
  neibor_peak,
  dirpath,
  count_device = 1,
  rebuild_PGN_Lasso = T
)

Arguments

X

The scATAC-seq data, sparse matrix.

Y

The scRNA-seq data, sparse matrix.

gene_data

The information for genes, must have a col names 'gene_name'.

neibor_peak

The peak IDs within a certain range of each gene, must have cols c("gene_name", "start_use", "end_use"). The id numbers in "start_use" and "end_use" are start from 0.

dirpath

The folder path to read or write file.

count_device

The number of cpus used to train the Lasso model.

rebuild_PGN_Lasso

Logical. Whether to rebuild the peak-gene network via Lasso from scratch. If FALSE, the function will attempt to read from 'PGN_Lasso.mtx' under
dirpath/test in single mode or dirpath/state_name/test in compare mode.

Value

The PGN_Lasso network.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PGN net via Lasso.
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"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PGN net via Lasso.
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"))

## End(Not run)

Peak-Gene Network via Random Forest

Description

Construct the peak-gene network via random forest.

Usage

PGN_RF(
  X,
  Y,
  gene_data,
  neibor_peak,
  dirpath,
  count_device = 1,
  rebuild_PGN_RF = T,
  seed = 0,
  python_env = "scPOEM_env"
)
PGN_RF(
  X,
  Y,
  gene_data,
  neibor_peak,
  dirpath,
  count_device = 1,
  rebuild_PGN_RF = T,
  seed = 0,
  python_env = "scPOEM_env"
)

Arguments

X

The scATAC-seq data, sparse matrix.

Y

The scRNA-seq data, sparse matrix.

gene_data

The information for genes, must have a col names 'gene_name'.

neibor_peak

The peak IDs within a certain range of each gene, must have cols c("gene_name", "start_use", "end_use"). The id numbers in "start_use" and "end_use" are start from 0.

dirpath

The folder path to read or write file.

count_device

The number of cpus used to train the Lasso model.

rebuild_PGN_RF

Logical. Whether to rebuild the peak-gene network via random forest from scratch. If FALSE, the function will attempt to read from 'PGN_RF.mtx' under dirpath/test in single mode or dirpath/state_name/test in compare mode.

seed

An integer specifying the random seed to ensure reproducible results.

python_env

Name or path of the Python environment to be used.

Value

The PGN_RF network.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PGN net via random forest (RF).
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"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PGN net via random forest (RF).
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"))

## End(Not run)

Peak-Gene Network via XGBoost

Description

Construct the peak-gene network via XGBoost.

Usage

PGN_XGBoost(
  X,
  Y,
  gene_data,
  neibor_peak,
  dirpath,
  count_device = 1,
  rebuild_PGN_XGB = T
)
PGN_XGBoost(
  X,
  Y,
  gene_data,
  neibor_peak,
  dirpath,
  count_device = 1,
  rebuild_PGN_XGB = T
)

Arguments

X

The scATAC-seq data, sparse matrix.

Y

The scRNA-seq data, sparse matrix.

gene_data

The information for genes, must have a col names 'gene_name'.

neibor_peak

The peak IDs within a certain range of each gene, must have cols c("gene_name", "start_use", "end_use"). The id numbers in "start_use" and "end_use" are start from 0.

dirpath

The folder path to read or write file.

count_device

The number of cpus used to train the Lasso model.

rebuild_PGN_XGB

Logical. Whether to rebuild the peak-gene network via XGBoost from scratch. If FALSE, the function will attempt to read from 'PGN_XGB.mtx' under
dirpath/test in single mode or dirpath/state_name/test in compare mode.

Value

The PGN_XGBoost network.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PGN net via XGBoost.
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"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PGN net via XGBoost.
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"))

## End(Not run)

Construct Peak-Peak Network

Description

Construct peak-peak network.

Usage

PPN(X, peak_data, cell_data, genome, dirpath, rebuild_PPN = T, seed = 0)
PPN(X, peak_data, cell_data, genome, dirpath, rebuild_PPN = T, seed = 0)

Arguments

X

The scATAC-seq data, sparse matrix.

peak_data

The information for peaks, must have a col names 'peak_name'.

cell_data

The information for cells, must have a col names 'cell_name'.

genome

The genome length for the species.

dirpath

The folder path to read or write file.

rebuild_PPN

Logical. Whether to rebuild the peak-peak network (PPN) from scratch. If FALSE, the function will attempt to read from 'PPN.mtx' under dirpath/test in single mode or dirpath/state_name/test in compare mode.

seed

An integer specifying the random seed to ensure reproducible results.

Value

The PPN network.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
library(data.table)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PPN net.
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"))

## End(Not run)

## Not run: 
library(scPOEM)
library(Matrix)
library(data.table)
dirpath <- "./example_data"
# Download single mode example data
data(example_data_single)
# Construct PPN net.
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"))

## End(Not run)

Main Function.

Description

This function takes paired single-cell ATAC-seq (scATAC-seq) and RNA-seq (scRNA-seq) data to embed peaks and genes into a shared low-dimensional space. It integrates regulatory relationships from peak-peak interactions (via Cicero), peak-gene interactions (via Lasso, random forest, and XGBoost), and gene-gene interactions (via principal component regression). Additionally, it supports gene-gene network reconstruction using epsilon-NN projections and compares networks across conditions through manifold alignment (scTenifoldNet).

Usage

scPOEM(
  mode = c("single", "compare"),
  input_data,
  dirpath,
  count_device = 1,
  nComp = 5,
  seed = 0,
  numwalks = 5,
  walklength = 3,
  epochs = 100,
  neg_sample = 5,
  batch_size = 32,
  weighted = TRUE,
  exclude_pos = FALSE,
  d = 100,
  rebuild_GGN = T,
  rebuild_PPN = T,
  rebuild_PGN_Lasso = T,
  rebuild_PGN_RF = T,
  rebuild_PGN_XGB = T,
  relearn_pg_embedding = T,
  pg_method = c("Lasso", "RF", "XGBoost"),
  python_env = "scPOEM_env"
)
scPOEM(
  mode = c("single", "compare"),
  input_data,
  dirpath,
  count_device = 1,
  nComp = 5,
  seed = 0,
  numwalks = 5,
  walklength = 3,
  epochs = 100,
  neg_sample = 5,
  batch_size = 32,
  weighted = TRUE,
  exclude_pos = FALSE,
  d = 100,
  rebuild_GGN = T,
  rebuild_PPN = T,
  rebuild_PGN_Lasso = T,
  rebuild_PGN_RF = T,
  rebuild_PGN_XGB = T,
  relearn_pg_embedding = T,
  pg_method = c("Lasso", "RF", "XGBoost"),
  python_env = "scPOEM_env"
)

Arguments

mode

The mode indicating whether to analyze data from a single condition or to compare two conditions.

input_data

A list of input data.

If mode = "single", input_data must be a list containing the following seven objects:

X: The scATAC-seq data, sparse matrix.
Y: The scRNA-seq data, sparse matrix.
peak_data: A data.frame containing peak information.
gene_data: A data.frame containing gene information (must contain column "gene_name").
cell_data: A data.frame containing cell metadata.
neibor_peak: The peak IDs within a certain range of each gene, must have cols c("gene_name", "start_use", "end_use"). The id numbers in "start_use" and "end_use" are start from 0.
genome: The genome length for the species.

If mode = "compare", input_data must be a named list of two elements, with names corresponding to two state names (e.g., "S1" and "S2"). Each element must itself be a list containing the same seven components as described above for mode = "single".

dirpath

The folder path to read or write file.

count_device

The number of cpus used to train models.

nComp

The number of PCs used for regression in constructing GGN.

seed

An integer specifying the random seed to ensure reproducible results.

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.

d

The dimension of latent space. Default is 100.

rebuild_GGN

Logical. Whether to rebuild the gene-gene network from scratch. If FALSE, the function will attempt to read from 'GGN.mtx' under dirpath/test in single mode or dirpath/state_name/test in compare mode.

rebuild_PPN

Logical. Whether to rebuild the peak-peak network from scratch. If FALSE, the function will attempt to read from 'PPN.mtx' under dirpath/test in single mode or dirpath/state_name/test in compare mode.

rebuild_PGN_Lasso

rebuild_PGN_RF

rebuild_PGN_XGB

relearn_pg_embedding

pg_method

The vector of methods used to construct peak-gene net. Default is c("Lasso", "RF", "XGBoost").

python_env

Name or path of the Python environment to be used.

Value

The scPOEM result.

Examples

## Not run: 
library(scPOEM)
library(Matrix)
library(data.table)
dirpath <- "./example_data"
# An example for analysing a single dataset.
# Download and read data.
data(example_data_single)
single_result <- scPOEM(mode = "single",
                        input_data=example_data_single,
                        dirpath=file.path(dirpath, "single"))

# An example for analysing and comparing datasets from two conditions.
# Download compare mode example data
data(example_data_compare)
compare_result <- scPOEM(mode = "compare",
                         input_data=example_data_compare,
                         dirpath=file.path(dirpath, "compare"))


## End(Not run)
## Not run: 
library(scPOEM)
library(Matrix)
library(data.table)
dirpath <- "./example_data"
# An example for analysing a single dataset.
# Download and read data.
data(example_data_single)
single_result <- scPOEM(mode = "single",
                        input_data=example_data_single,
                        dirpath=file.path(dirpath, "single"))

# An example for analysing and comparing datasets from two conditions.
# Download compare mode example data
data(example_data_compare)
compare_result <- scPOEM(mode = "compare",
                         input_data=example_data_compare,
                         dirpath=file.path(dirpath, "compare"))


## End(Not run)

Package 'scPOEM'

Help Index

Gene Network Reconstruction and Alignment

Description

Usage

Arguments

Value

Examples

Network Reconstruction via epsilon-NN

Description

Usage

Arguments

Value

Example Input Data for Compare Mode Analysis

Description

Usage

Format

Examples

Example Input Data for Single Mode Analysis

Description

Usage

Format

Examples

Construct Gene-Gene Network

Description

Usage

Arguments

Value

Examples

Co-embeddings of peaks and genes.

Description

Usage

Arguments

Value

Examples

Peak-Gene Network via Lasso

Description

Usage

Arguments

Value

Examples

Peak-Gene Network via Random Forest

Description

Usage

Arguments

Value

Examples

Peak-Gene Network via XGBoost

Description

Usage

Arguments

Value

Examples

Construct Peak-Peak Network

Description

Usage

Arguments

Value

Examples

Main Function.

Description

Usage

Arguments

Value

Examples