Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

Arguments

Value

The result of calling 'rhs(lhs)'.

Datasets geneList entrez gene list with decreasing fold change value

Description

Datasets geneList entrez gene list with decreasing fold change value

Datasets Differential expression analysis result of GSE42872

Datasets msig_species contains msigdb species information

Datasets msig_category contains msigdb category information

Datasets biocOrg_name contains organism name of bioconductor

Datasets keggOrg_name contains organism name of KEGG https://www.genome.jp/kegg/catalog/org_list.html

Datasets ensOrg_name contains organism name of ensembl

Datasets hsapiens_probe_platform contains human probe platforms

Modify dataframe for enrichment plot

Description

To make sure colname contains Description, Count, FoldEnrich/GeneRatio, pvalue/qvalue/p.adjust

Usage

as.enrichdat(enrich_df)

Arguments

Value

'data.frame'

Export list of data sets into different 'Excel' sheets

Description

Export list of data sets into different 'Excel' sheets

Usage

expoSheet(
  data_list,
  data_name,
  filename = NULL,
  dir = tempdir(),
  overwrite = TRUE
)

Arguments

Value

An Excel file.

Examples

library(openxlsx)
expoSheet(
  data_list = list(mtcars, ToothGrowth),
  data_name = c("mtcars", "tooth"),
  filename = "test.xlsx", dir = tempfile()
)

Gene Set Enrichment Analysis

Description

Gene Set Enrichment Analysis

Usage

genGSEA(
  genelist,
  geneset,
  padj_method = "BH",
  p_cutoff = 0.05,
  q_cutoff = 0.05,
  min_gset_size = 10,
  max_gset_size = 500,
  set_seed = FALSE
)

Arguments

Value

A 'data.frame'.

Examples

if(requireNamespace("geneset",quietly = TRUE)){
# only gene ids
data(geneList, package = "genekitr")
gs <- geneset::getGO(org = "human",ont = "mf",data_dir = tempdir())
gse <- genGSEA(genelist = geneList, geneset = gs)
  }

Get gene related information

Description

Get gene related information

Usage

genInfo(
  id = NULL,
  org = "hs",
  unique = FALSE,
  keepNA = TRUE,
  hgVersion = c("v38", "v19")
)

Arguments

Value

A 'data.frame'.

Examples

# example1: input list with fake id and one-to-many mapping id
x <- genInfo(id = c(
  "MCM10", "CDC20", "S100A9", "MMP1", "BCC7",
  "FAKEID", "TP53", "HBD", "NUDT10"
))

# example2: statistics of human gene biotypes
genInfo(org = "hs") %>%
  {
    table(.$gene_biotype)
  }

# example3: use hg19 data
x <- genInfo(id = c("TP53","BCC7"), hgVersion = "v19")

# example4: search genes with case-insensitive
x <- genInfo(id = c("tp53","nc886","FAke","EZh2"), org = "hs", unique = TRUE)

Gene Over-Representation Enrichment Analysis

Description

Gene Over-Representation Enrichment Analysis

Usage

genORA(
  id,
  geneset,
  group_list = NULL,
  padj_method = "BH",
  p_cutoff = 0.05,
  q_cutoff = 0.15,
  min_gset_size = 10,
  max_gset_size = 500,
  universe
)

Arguments

Value

A 'data.frame'.

Examples

# only gene ids
data(geneList, package = "genekitr")
id <- names(geneList)[abs(geneList) > 1]
gs <- geneset::getGO(org = "human",ont = "mf",data_dir = tempdir())
ora <- genORA(id, geneset = gs)

# gene id with groups
id <- c(head(names(geneList), 50), tail(names(geneList), 50))
group <- list(
  group1 = c(rep("up", 50), rep("down", 50)),
  group2 = c(rep("A", 20), rep("B", 30))
)
gora <- genORA(id, geneset = gs, group_list = group)

Get 'PubMed' paper records by searching abstract

Description

PubMed<https://pubmed.ncbi.nlm.nih.gov/> is a free search engine accessing primarily the database of references and abstracts on life ciences and biomedical topics.

Usage

getPubmed(term, add_term = NULL, num = 100)

Arguments

Value

A list of 'tibble' for pubmed records

Examples

term <- c("Tp53", "Brca1", "Tet2")
add_term <- c("stem cell", "mouse")
l <- getPubmed(term, add_term, num = 30)
# very easy to output
expoSheet(l, data_name = term, filename = "test.xlsx", dir = tempfile())

Import 'clusterProfiler' result

Description

Import 'clusterProfiler' result

Usage

importCP(object, type = c("go", "gsea", "other"))

Arguments

Value

'data.frame'

Import 'Panther' web result

Description

Import 'Panther' web result

Usage

importPanther(panther_file)

Arguments

Value

'data.frame'

Import 'shinyGO' web result

Description

Import 'shinyGO' web result

Usage

importShinygo(shinygo_file)

Arguments

Value

'data.frame'

Plot for gene enrichment analysis of ORA method

Description

Over-representation analysis (ORA) is a simple method for objectively deciding whether a set of variables of known or suspected biological relevance, such as a gene set or pathway, is more prevalent in a set of variables of interest than we expect by chance.

Usage

plotEnrich(
  enrich_df,
  fold_change = NULL,
  plot_type = c("bar", "wego", "dot", "bubble", "lollipop", "geneheat", "genechord",
    "network", "gomap", "goheat", "gotangram", "wordcloud", "upset"),
  term_metric = c("FoldEnrich", "GeneRatio", "Count", "RichFactor"),
  stats_metric = c("p.adjust", "pvalue", "qvalue"),
  sim_method = c("Resnik", "Lin", "Rel", "Jiang", "Wang", "JC"),
  up_color = "#E31A1C",
  down_color = "#1F78B4",
  show_gene = "all",
  xlim_left = 0,
  xlim_right = NA,
  wrap_length = NULL,
  org = NULL,
  ont = NULL,
  scale_ratio,
  layout,
  n_term,
  ...
)

Arguments

Value

A ggplot object

Examples

## example data
## More examples please refer to https://www.genekitr.fun/plot-ora-1.html
library(ggplot2)
data(geneList, package = "genekitr")
id <- names(geneList)[abs(geneList) > 1.5]
logfc <- geneList[id]

gs <- geneset::getGO(org = "human",ont = "bp",data_dir = tempdir())
ego <- genORA(id, geneset = gs)
ego <- ego[1:10, ]

## example plots
plotEnrich(ego, plot_type = "dot")

#plotEnrich(ego, plot_type = "bubble", scale_ratio = 0.4)

#plotEnrich(ego, plot_type = "bar")

Advanced Plot for gene enrichment analysis of ORA method

Description

Over-representation analysis (ORA) is a simple method for objectively deciding whether a set of variables of known or suspected biological relevance, such as a gene set or pathway, is more prevalent in a set of variables of interest than we expect by chance.

Usage

plotEnrichAdv(
  up_enrich_df,
  down_enrich_df,
  plot_type = c("one", "two"),
  term_metric = c("FoldEnrich", "GeneRatio", "Count", "RichFactor"),
  stats_metric = c("p.adjust", "pvalue", "qvalue"),
  wrap_length = NULL,
  xlim_left = NULL,
  xlim_right = NULL,
  color,
  ...
)

Arguments

Details

Both up and down regulated pathways could be plotted in one figure as two-side barplot

Value

A ggplot object

Plot for gene enrichment analysis of GSEA method

Description

Gene Set Enrichment Analysis (GSEA) is a computational method that determines whether an a priori defined set of genes shows statistically significant, concordant differences between two biological states (e.g. phenotypes).

Usage

plotGSEA(
  gsea_list,
  plot_type = c("volcano", "classic", "fgsea", "ridge", "bar"),
  stats_metric = c("p.adjust", "pvalue", "qvalue"),
  show_pathway = NULL,
  show_gene = NULL,
  colour = NULL,
  wrap_length = NULL,
  label_by = c("id", "description"),
  ...
)

Arguments

Value

A ggplot object

Examples

k1 = requireNamespace("cowplot",quietly = TRUE)
k2 = requireNamespace("fgsea",quietly = TRUE)
k3 = requireNamespace("ggplotify",quietly = TRUE)
k4 = requireNamespace("ggridges",quietly = TRUE)
if(k1&k2&k3&k4){
library(ggplot2)
## get GSEA result
data(geneList, package = "genekitr")
gs <- geneset::getMsigdb(org = "human",category = "H")
gse <- genGSEA(genelist = geneList, geneset = gs)

## volcano plot
# get top3 of up and down pathways
plotGSEA(gse, plot_type = "volcano", show_pathway = 3)
# choose pathway by character
pathways <- c('HALLMARK_KRAS_SIGNALING_UP','HALLMARK_P53_PATHWAY','HALLMARK_GLYCOLYSIS')
plotGSEA(gse, plot_type = "volcano", show_pathway = pathways)

## classic pathway plot
genes <- c('ENG','TP53','MET')
plotGSEA(gse, plot_type = "classic", show_pathway = pathways, show_gene = genes)

## fgsea table plot
plotGSEA(gse, plot_type = "fgsea", show_pathway = 3)

## ridgeplot
plotGSEA(gse,
  plot_type = "ridge",
  show_pathway = 10, stats_metric = "p.adjust"
)

## two-side barplot
plotGSEA(gse,
  plot_type = "bar", main_text_size = 8,
  colour = c("navyblue", "orange")
)
}

Venn plot for groups of genes

Description

If gene group over 4, plot will be visulized using UpSet plot.

Usage

plotVenn(
  venn_list,
  use_venn = TRUE,
  color = NULL,
  alpha_degree = 0.3,
  venn_percent = FALSE,
  ...
)

Arguments

Value

A ggplot object

Examples

k1 = requireNamespace("ComplexUpset",quietly = TRUE)
k2 = requireNamespace("futile.logger",quietly = TRUE)
k3 = requireNamespace("ggsci",quietly = TRUE)
k4 = requireNamespace("RColorBrewer",quietly = TRUE)
if(k1&k2&k3&k4){
library(ggplot2)
set1 <- paste0(rep("gene", 30), sample(1:1000, 30))
set2 <- paste0(rep("gene", 40), sample(1:1000, 40))
set3 <- paste0(rep("gene", 50), sample(1:1000, 50))
set4 <- paste0(rep("gene", 60), sample(1:1000, 60))
set5 <- paste0(rep("gene", 70), sample(1:1000, 70))
sm_gene_list <- list(gset1 = set1, gset2 = set2, gset3 = set3)
la_gene_list <- list(
  gset1 = set1, gset2 = set2, gset3 = set3,
  gset4 = set4, gset5 = set5
)
plotVenn(sm_gene_list,
  use_venn = TRUE,
  alpha_degree = 0.5,
  main_text_size = 3,
  border_thick = 0,
  venn_percent = TRUE
)
plotVenn(la_gene_list,
  use_venn = FALSE,
  main_text_size = 15,
  legend_text_size = 8,
  legend_position = 'left'
)
}

Volcano plot for differential expression analysis

Description

Volcano plot for differential expression analysis

Usage

plotVolcano(
  deg_df,
  stat_metric = c("p.adjust", "pvalue"),
  stat_cutoff = 0.05,
  logFC_cutoff = 1,
  up_color = "#E31A1C",
  down_color = "#1F78B4",
  show_gene = NULL,
  dot_size = 1.75,
  ...
)

Arguments

Value

A ggplot object

Examples

if(requireNamespace("ggrepel",quietly = T)){
library(ggplot2)
data(deg, package = "genekitr")
plotVolcano(deg, "p.adjust", remove_legend = TRUE, dot_size = 3)

# show some genes
plotVolcano(deg, "p.adjust",
  remove_legend = TRUE,
  show_gene = c("CD36", "DUSP6", "IER3","CDH7")
)
}

Themes for all plots

Description

Change ggplot text, font, legend and border

Usage

plot_theme(
  main_text_size = 8,
  legend_text_size = 6,
  font_type = "sans",
  border_thick = 1.5,
  remove_grid = TRUE,
  remove_border = FALSE,
  remove_main_text = FALSE,
  remove_legend_text = FALSE,
  remove_legend = FALSE
)

Arguments

Value

ggplot theme

Examples

library(ggplot2)
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point() +
  plot_theme(font_type = "Times", border_thick = 2)

Simplify GO enrichment result

Description

The Gene Ontology (GO) is a major bioinformatics initiative to unify the representation of gene and gene product attributes across all species.

Usage

simGO(
  enrich_df,
  sim_method = c("Resnik", "Lin", "Rel", "Jiang", "Wang"),
  org = NULL,
  ont = NULL
)

Arguments

Value

A 'data.frame' contains simplified GO terms.

Transform id among symbol, entrezid, ensembl and uniprot.

Description

Transform id among symbol, entrezid, ensembl and uniprot.

Usage

transId(
  id,
  transTo,
  org = "hs",
  unique = FALSE,
  keepNA = FALSE,
  hgVersion = c("v38", "v19")
)

Arguments

Value

data frame, first column is input id and others are converted id.

Examples

# example1:
transId(
  id = c("Cyp2c23", "Fhit", "Gal3st2b", "Trp53", "Tp53"),
  transTo = "ensembl", org = "mouse", keepNA = FALSE
)

## example2: input id with one-to-many mapping and fake one
transId(
  id = c("MMD2", "HBD", "RNR1", "TEC", "BCC7", "FAKEID", "TP53"),
  transTo = c("entrez", "ensembl"), keepNA = TRUE
)

# example3: auto-recognize ensembl version number
transId("ENSG00000141510.11", "symbol")

# example4: search genes with case-insensitive
transId(c('nc886','ezh2','TP53'),transTo = "ensembl",org = 'hs',unique = TRUE)

Transform probe id to symbol, entrezid, ensembl or uniprot.

Description

Transform probe id to symbol, entrezid, ensembl or uniprot.

Usage

transProbe(id, transTo, org = "human", platform = NULL)

Arguments

Value

data frame, first column is probe id and others are converted id.