## Validating gene lists..## 1 / 3 gene lists are valid.## Background already exists at: /github/home/.cache/R/MultiEWCE/bg-human-human-gprofiler.rds
+## Use `overwrite=TRUE` to overwrite.## + Version: 2023-11-07## Computing gene counts.## Done in: 3.3 seconds.## Done in: 5.9 seconds.##
-## Saving results ==> /tmp/RtmpnaSTmh/gen_results.rdsVisualise the results
@@ -331,7 +334,7 @@ Visualise the resultsJust as an example, we will create a plot showing the number of
significant enrichments per phenotype in the all_results data.frame. We
will use q <= 0.05 as the significance threshold.
-
+
library(ggplot2)
library(data.table)
#### Aggregate results ####
@@ -343,7 +346,7 @@ Visualise the results geom_col() +
labs(x="Phenotype",y="Enrichments (n)") +
theme_bw()
-
+
methods::show(plot1)
@@ -360,7 +363,7 @@ merge_results
+
all_results_2 <- MultiEWCE::merge_results(save_dir = save_dir_tmp)
## 1 results files found.
@@ -369,14 +372,14 @@ get_gene_list
+
phenotypes <- c("Scoliosis")
gene_set <- HPOExplorer::get_gene_lists(phenotypes = phenotypes,
phenotype_to_genes = gene_data)
## Translating all phenotypes to HPO IDs.
## ℹ All local files already up-to-date!
## + Returning a vector of phenotypes (same order as input).
-
+
cat(paste(length(unique(gene_set$gene_symbol)),
"genes associated with",shQuote(phenotypes),":",
paste(unique(gene_set$gene_symbol)[seq(5)],collapse = ", ")))
@@ -387,7 +390,7 @@ get_unfinished_list_names
This function is used to find which gene lists you have not yet
analysed
-
+
all_phenotypes <- unique(gene_data$hpo_name)
unfinished <- MultiEWCE::get_unfinished_list_names(list_names = all_phenotypes,
save_dir_tmp = save_dir_tmp)
@@ -403,30 +406,31 @@ Run disease-level enrichment testsSo far, we’ve iterated over gene list grouped by phenotypes. But we
can also do this at the level of diseases (which are composed of
combinations of phenotypes).
-
+
gene_data <- HPOExplorer::load_phenotype_to_genes("genes_to_phenotype.txt")
## Reading cached RDS file: genes_to_phenotype.txt
## + Version: v2023-10-09
-
+
#### Filter only to those with >=4 genes ####
gene_counts <- gene_data[,list(genes=length(unique(gene_symbol))),
by="disease_id"][genes>=4]
list_names <- unique(gene_counts$disease_id)[seq(5)]
-
+
all_results <- MultiEWCE::gen_results(ctd = ctd,
gene_data = gene_data,
list_name_column = "disease_id",
list_names = list_names,
annotLevel = 1,
reps = 10)
-## Results already exist at: /tmp/RtmpnaSTmh/gen_results.rds Use `force_new=TRUE` to overwrite.
+## Results already exist at: /tmp/RtmpVHxLis/gen_results.rds
+## Use `force_new=TRUE` to overwrite.
Full analysis
Run the following code the replicate the main analysis in the study
described here.
-
+
gene_data <- HPOExplorer::load_phenotype_to_genes()
gene_data[,n_gene:=length(unique(gene_symbol)),by="hpo_id"]
gene_data <- gene_data[n_gene>=4,]
@@ -441,7 +445,7 @@ Full analysis
Session info
-
+
utils::sessionInfo()
## R Under development (unstable) (2023-11-02 r85465)
## Platform: x86_64-pc-linux-gnu
@@ -466,7 +470,7 @@ Session info## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
-## [1] data.table_1.14.8 ggplot2_3.4.4 MultiEWCE_0.1.8 BiocStyle_2.31.0
+## [1] data.table_1.14.8 ggplot2_3.4.4 MultiEWCE_0.1.9 BiocStyle_2.31.0
##
## loaded via a namespace (and not attached):
## [1] later_1.3.1 bitops_1.0-7
diff --git a/articles/MultiEWCE_files/figure-html/display-1.png b/articles/MultiEWCE_files/figure-html/display-1.png
index 828b0ae..e9c02ae 100644
Binary files a/articles/MultiEWCE_files/figure-html/display-1.png and b/articles/MultiEWCE_files/figure-html/display-1.png differ
diff --git a/articles/docker.html b/articles/docker.html
index 7341726..d7ea012 100644
--- a/articles/docker.html
+++ b/articles/docker.html
@@ -33,7 +33,7 @@
@@ -188,7 +188,7 @@ Session Info## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
-## [1] MultiEWCE_0.1.8 BiocStyle_2.31.0
+## [1] MultiEWCE_0.1.9 BiocStyle_2.31.0
##
## loaded via a namespace (and not attached):
## [1] later_1.3.1 bitops_1.0-7
diff --git a/articles/index.html b/articles/index.html
index 939c555..f3d2efa 100644
--- a/articles/index.html
+++ b/articles/index.html
@@ -17,7 +17,7 @@
diff --git a/authors.html b/authors.html
index a166cda..58bbeeb 100644
--- a/authors.html
+++ b/authors.html
@@ -17,7 +17,7 @@
diff --git a/index.html b/index.html
index e429a5d..bd03861 100644
--- a/index.html
+++ b/index.html
@@ -40,7 +40,7 @@
@@ -90,7 +90,7 @@
-
+
Authors: Robert Gordon-Smith, Brian Schilder, Nathan Skene
diff --git a/news/index.html b/news/index.html
index fc4d07a..fdbd8f9 100644
--- a/news/index.html
+++ b/news/index.html
@@ -17,7 +17,7 @@
@@ -60,6 +60,24 @@ Changelog
Source: NEWS.md
+
MultiEWCE 0.1.8
diff --git a/pkgdown.yml b/pkgdown.yml
index 11e489c..69c450f 100644
--- a/pkgdown.yml
+++ b/pkgdown.yml
@@ -4,5 +4,5 @@ pkgdown_sha: ~
articles:
MultiEWCE: MultiEWCE.html
docker: docker.html
-last_built: 2023-11-07T16:30Z
+last_built: 2023-11-07T20:25Z
diff --git a/reference/add_ctd.html b/reference/add_ctd.html
index 9842199..3da1ca6 100644
--- a/reference/add_ctd.html
+++ b/reference/add_ctd.html
@@ -24,7 +24,7 @@
diff --git a/reference/agg_results.html b/reference/agg_results.html
index 6409696..3260359 100644
--- a/reference/agg_results.html
+++ b/reference/agg_results.html
@@ -18,7 +18,7 @@
diff --git a/reference/correlation_heatmap.html b/reference/correlation_heatmap.html
index bf4f7cc..32cd983 100644
--- a/reference/correlation_heatmap.html
+++ b/reference/correlation_heatmap.html
@@ -17,7 +17,7 @@
diff --git a/reference/create_dt.html b/reference/create_dt.html
index c90cc77..1818df3 100644
--- a/reference/create_dt.html
+++ b/reference/create_dt.html
@@ -17,7 +17,7 @@
diff --git a/reference/ewce_para.html b/reference/ewce_para.html
index fd433e1..899a0ca 100644
--- a/reference/ewce_para.html
+++ b/reference/ewce_para.html
@@ -17,7 +17,7 @@
@@ -72,13 +72,13 @@ EWCE parallel
list_name_column = "hpo_id",
gene_column = "gene_symbol",
list_names = unique(gene_data[[list_name_column]]),
- bg = unique(gene_data[[gene_column]]),
reps = 100,
annotLevel = 1,
+ force_new = FALSE,
genelistSpecies = "human",
sctSpecies = "human",
+ bg = get_bg(species1 = genelistSpecies, species2 = sctSpecies, overwrite = force_new),
save_dir_tmp = tempdir(),
- force_new = FALSE,
parallel_boot = FALSE,
cores = 1,
verbose = FALSE
@@ -110,12 +110,6 @@ Arguments
character vector of gene list names.
bg
-List of gene symbols containing the background gene list
-(including hit genes). If bg=NULL,
- an appropriate gene background will be created automatically.
reps
Number of random gene lists to generate (Default: 100,
but should be >=10,000 for publication-quality results).
Arguments
analyse (Default: 1).
+force_new
+Overwrite previous results
+in the save_dir_tmp.
genelistSpecies
Species that hits genes came from
(no longer limited to just "mouse" and "human").
@@ -138,16 +137,17 @@
Arguments
See list_species for all available species.bg
+List of gene symbols containing the background gene list
+(including hit genes). If bg=NULL,
+ an appropriate gene background will be created automatically.
save_dir_tmp
Folder to save intermediate results files to
(one file per gene list). Set to NULL to skip saving temporary files.
force_new
-Overwrite previous results
-in the save_dir_tmp.
parallel_boot
Parallelise at the level of bootstrap iterations,
rather than across gene lists.
Examples
gene_data = gene_data,
list_names = list_names,
reps = 10)
+#> Background already exists at: /github/home/.cache/R/MultiEWCE/bg-human-human-gprofiler.rds
+#> Use `overwrite=TRUE` to overwrite.
+#> + Version: 2023-11-07
#> Computing gene counts.
+-library(ggplot2) library(data.table) #### Aggregate results #### @@ -343,7 +346,7 @@Visualise the results geom_col() + labs(x="Phenotype",y="Enrichments (n)") + theme_bw()
@@ -360,7 +363,7 @@+methods::show(plot1)
merge_results
+all_results_2 <- MultiEWCE::merge_results(save_dir = save_dir_tmp)## 1 results files found.
get_gene_list
+
phenotypes <- c("Scoliosis")
gene_set <- HPOExplorer::get_gene_lists(phenotypes = phenotypes,
phenotype_to_genes = gene_data)
## Translating all phenotypes to HPO IDs.
## ℹ All local files already up-to-date!
## + Returning a vector of phenotypes (same order as input).
-
+
cat(paste(length(unique(gene_set$gene_symbol)),
"genes associated with",shQuote(phenotypes),":",
paste(unique(gene_set$gene_symbol)[seq(5)],collapse = ", ")))
@@ -387,7 +390,7 @@ get_unfinished_list_names
This function is used to find which gene lists you have not yet
analysed
-
+
all_phenotypes <- unique(gene_data$hpo_name)
unfinished <- MultiEWCE::get_unfinished_list_names(list_names = all_phenotypes,
save_dir_tmp = save_dir_tmp)
@@ -403,30 +406,31 @@ Run disease-level enrichment testsSo far, we’ve iterated over gene list grouped by phenotypes. But we
can also do this at the level of diseases (which are composed of
combinations of phenotypes).
-
+
gene_data <- HPOExplorer::load_phenotype_to_genes("genes_to_phenotype.txt")
## Reading cached RDS file: genes_to_phenotype.txt
## + Version: v2023-10-09
-
+
#### Filter only to those with >=4 genes ####
gene_counts <- gene_data[,list(genes=length(unique(gene_symbol))),
by="disease_id"][genes>=4]
list_names <- unique(gene_counts$disease_id)[seq(5)]
-
+
all_results <- MultiEWCE::gen_results(ctd = ctd,
gene_data = gene_data,
list_name_column = "disease_id",
list_names = list_names,
annotLevel = 1,
reps = 10)
-## Results already exist at: /tmp/RtmpnaSTmh/gen_results.rds Use `force_new=TRUE` to overwrite.
+## Results already exist at: /tmp/RtmpVHxLis/gen_results.rds
+## Use `force_new=TRUE` to overwrite.
Full analysis
Run the following code the replicate the main analysis in the study
described here.
-
+
gene_data <- HPOExplorer::load_phenotype_to_genes()
gene_data[,n_gene:=length(unique(gene_symbol)),by="hpo_id"]
gene_data <- gene_data[n_gene>=4,]
@@ -441,7 +445,7 @@ Full analysis
Session info
-
+
utils::sessionInfo()
## R Under development (unstable) (2023-11-02 r85465)
## Platform: x86_64-pc-linux-gnu
@@ -466,7 +470,7 @@ Session info## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
-## [1] data.table_1.14.8 ggplot2_3.4.4 MultiEWCE_0.1.8 BiocStyle_2.31.0
+## [1] data.table_1.14.8 ggplot2_3.4.4 MultiEWCE_0.1.9 BiocStyle_2.31.0
##
## loaded via a namespace (and not attached):
## [1] later_1.3.1 bitops_1.0-7
diff --git a/articles/MultiEWCE_files/figure-html/display-1.png b/articles/MultiEWCE_files/figure-html/display-1.png
index 828b0ae..e9c02ae 100644
Binary files a/articles/MultiEWCE_files/figure-html/display-1.png and b/articles/MultiEWCE_files/figure-html/display-1.png differ
diff --git a/articles/docker.html b/articles/docker.html
index 7341726..d7ea012 100644
--- a/articles/docker.html
+++ b/articles/docker.html
@@ -33,7 +33,7 @@
@@ -188,7 +188,7 @@ Session Info## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
-## [1] MultiEWCE_0.1.8 BiocStyle_2.31.0
+## [1] MultiEWCE_0.1.9 BiocStyle_2.31.0
##
## loaded via a namespace (and not attached):
## [1] later_1.3.1 bitops_1.0-7
diff --git a/articles/index.html b/articles/index.html
index 939c555..f3d2efa 100644
--- a/articles/index.html
+++ b/articles/index.html
@@ -17,7 +17,7 @@
diff --git a/authors.html b/authors.html
index a166cda..58bbeeb 100644
--- a/authors.html
+++ b/authors.html
@@ -17,7 +17,7 @@
diff --git a/index.html b/index.html
index e429a5d..bd03861 100644
--- a/index.html
+++ b/index.html
@@ -40,7 +40,7 @@
@@ -90,7 +90,7 @@
-
+
Authors: Robert Gordon-Smith, Brian Schilder, Nathan Skene
diff --git a/news/index.html b/news/index.html
index fc4d07a..fdbd8f9 100644
--- a/news/index.html
+++ b/news/index.html
@@ -17,7 +17,7 @@
@@ -60,6 +60,24 @@ Changelog
Source: NEWS.md
+
MultiEWCE 0.1.8
diff --git a/pkgdown.yml b/pkgdown.yml
index 11e489c..69c450f 100644
--- a/pkgdown.yml
+++ b/pkgdown.yml
@@ -4,5 +4,5 @@ pkgdown_sha: ~
articles:
MultiEWCE: MultiEWCE.html
docker: docker.html
-last_built: 2023-11-07T16:30Z
+last_built: 2023-11-07T20:25Z
diff --git a/reference/add_ctd.html b/reference/add_ctd.html
index 9842199..3da1ca6 100644
--- a/reference/add_ctd.html
+++ b/reference/add_ctd.html
@@ -24,7 +24,7 @@
diff --git a/reference/agg_results.html b/reference/agg_results.html
index 6409696..3260359 100644
--- a/reference/agg_results.html
+++ b/reference/agg_results.html
@@ -18,7 +18,7 @@
diff --git a/reference/correlation_heatmap.html b/reference/correlation_heatmap.html
index bf4f7cc..32cd983 100644
--- a/reference/correlation_heatmap.html
+++ b/reference/correlation_heatmap.html
@@ -17,7 +17,7 @@
diff --git a/reference/create_dt.html b/reference/create_dt.html
index c90cc77..1818df3 100644
--- a/reference/create_dt.html
+++ b/reference/create_dt.html
@@ -17,7 +17,7 @@
diff --git a/reference/ewce_para.html b/reference/ewce_para.html
index fd433e1..899a0ca 100644
--- a/reference/ewce_para.html
+++ b/reference/ewce_para.html
@@ -17,7 +17,7 @@
@@ -72,13 +72,13 @@ EWCE parallel
list_name_column = "hpo_id",
gene_column = "gene_symbol",
list_names = unique(gene_data[[list_name_column]]),
- bg = unique(gene_data[[gene_column]]),
reps = 100,
annotLevel = 1,
+ force_new = FALSE,
genelistSpecies = "human",
sctSpecies = "human",
+ bg = get_bg(species1 = genelistSpecies, species2 = sctSpecies, overwrite = force_new),
save_dir_tmp = tempdir(),
- force_new = FALSE,
parallel_boot = FALSE,
cores = 1,
verbose = FALSE
@@ -110,12 +110,6 @@ Arguments
character vector of gene list names.
bg
-List of gene symbols containing the background gene list
-(including hit genes). If bg=NULL,
- an appropriate gene background will be created automatically.
reps
Number of random gene lists to generate (Default: 100,
but should be >=10,000 for publication-quality results).
Arguments
analyse (Default: 1).
+force_new
+Overwrite previous results
+in the save_dir_tmp.
genelistSpecies
Species that hits genes came from
(no longer limited to just "mouse" and "human").
@@ -138,16 +137,17 @@
Arguments
See list_species for all available species.bg
+List of gene symbols containing the background gene list
+(including hit genes). If bg=NULL,
+ an appropriate gene background will be created automatically.
save_dir_tmp
Folder to save intermediate results files to
(one file per gene list). Set to NULL to skip saving temporary files.
force_new
-Overwrite previous results
-in the save_dir_tmp.
parallel_boot
Parallelise at the level of bootstrap iterations,
rather than across gene lists.
Examples
gene_data = gene_data,
list_names = list_names,
reps = 10)
+#> Background already exists at: /github/home/.cache/R/MultiEWCE/bg-human-human-gprofiler.rds
+#> Use `overwrite=TRUE` to overwrite.
+#> + Version: 2023-11-07
#> Computing gene counts.
phenotypes <- c("Scoliosis")
gene_set <- HPOExplorer::get_gene_lists(phenotypes = phenotypes,
phenotype_to_genes = gene_data)## Translating all phenotypes to HPO IDs.## ℹ All local files already up-to-date!## + Returning a vector of phenotypes (same order as input).+@@ -387,7 +390,7 @@cat(paste(length(unique(gene_set$gene_symbol)), "genes associated with",shQuote(phenotypes),":", paste(unique(gene_set$gene_symbol)[seq(5)],collapse = ", ")))get_unfinished_list_names
This function is used to find which gene lists you have not yet analysed
-@@ -72,13 +72,13 @@+diff --git a/reference/ewce_para.html b/reference/ewce_para.html index fd433e1..899a0ca 100644 --- a/reference/ewce_para.html +++ b/reference/ewce_para.html @@ -17,7 +17,7 @@all_phenotypes <- unique(gene_data$hpo_name) unfinished <- MultiEWCE::get_unfinished_list_names(list_names = all_phenotypes, save_dir_tmp = save_dir_tmp) @@ -403,30 +406,31 @@Run disease-level enrichment testsSo far, we’ve iterated over gene list grouped by phenotypes. But we can also do this at the level of diseases (which are composed of combinations of phenotypes). -
diff --git a/reference/create_dt.html b/reference/create_dt.html index c90cc77..1818df3 100644 --- a/reference/create_dt.html +++ b/reference/create_dt.html @@ -17,7 +17,7 @@+gene_data <- HPOExplorer::load_phenotype_to_genes("genes_to_phenotype.txt")## Reading cached RDS file: genes_to_phenotype.txt-## + Version: v2023-10-09++-#### Filter only to those with >=4 genes #### gene_counts <- gene_data[,list(genes=length(unique(gene_symbol))), by="disease_id"][genes>=4] list_names <- unique(gene_counts$disease_id)[seq(5)]+-all_results <- MultiEWCE::gen_results(ctd = ctd, gene_data = gene_data, list_name_column = "disease_id", list_names = list_names, annotLevel = 1, reps = 10)+## Results already exist at: /tmp/RtmpnaSTmh/gen_results.rds Use `force_new=TRUE` to overwrite.## Results already exist at: /tmp/RtmpVHxLis/gen_results.rds +## Use `force_new=TRUE` to overwrite.@@ -90,7 +90,7 @@Full analysis
Run the following code the replicate the main analysis in the study described here.
-diff --git a/index.html b/index.html index e429a5d..bd03861 100644 --- a/index.html +++ b/index.html @@ -40,7 +40,7 @@+diff --git a/authors.html b/authors.html index a166cda..58bbeeb 100644 --- a/authors.html +++ b/authors.html @@ -17,7 +17,7 @@gene_data <- HPOExplorer::load_phenotype_to_genes() gene_data[,n_gene:=length(unique(gene_symbol)),by="hpo_id"] gene_data <- gene_data[n_gene>=4,] @@ -441,7 +445,7 @@Full analysis
Session info
-@@ -188,7 +188,7 @@+utils::sessionInfo()## R Under development (unstable) (2023-11-02 r85465) ## Platform: x86_64-pc-linux-gnu @@ -466,7 +470,7 @@Session info## [1] stats graphics grDevices utils datasets methods base ## ## other attached packages: -## [1] data.table_1.14.8 ggplot2_3.4.4 MultiEWCE_0.1.8 BiocStyle_2.31.0 +## [1] data.table_1.14.8 ggplot2_3.4.4 MultiEWCE_0.1.9 BiocStyle_2.31.0 ## ## loaded via a namespace (and not attached): ## [1] later_1.3.1 bitops_1.0-7 diff --git a/articles/MultiEWCE_files/figure-html/display-1.png b/articles/MultiEWCE_files/figure-html/display-1.png index 828b0ae..e9c02ae 100644 Binary files a/articles/MultiEWCE_files/figure-html/display-1.png and b/articles/MultiEWCE_files/figure-html/display-1.png differ diff --git a/articles/docker.html b/articles/docker.html index 7341726..d7ea012 100644 --- a/articles/docker.html +++ b/articles/docker.html @@ -33,7 +33,7 @@
Session Info## [1] stats graphics grDevices utils datasets methods base ## ## other attached packages: -## [1] MultiEWCE_0.1.8 BiocStyle_2.31.0 +## [1] MultiEWCE_0.1.9 BiocStyle_2.31.0 ## ## loaded via a namespace (and not attached): ## [1] later_1.3.1 bitops_1.0-7 diff --git a/articles/index.html b/articles/index.html index 939c555..f3d2efa 100644 --- a/articles/index.html +++ b/articles/index.html @@ -17,7 +17,7 @@
-@@ -60,6 +60,24 @@+
Authors: Robert Gordon-Smith, Brian Schilder, Nathan Skene
diff --git a/news/index.html b/news/index.html index fc4d07a..fdbd8f9 100644 --- a/news/index.html +++ b/news/index.html @@ -17,7 +17,7 @@Changelog
Source:NEWS.mddiff --git a/reference/correlation_heatmap.html b/reference/correlation_heatmap.html index bf4f7cc..32cd983 100644 --- a/reference/correlation_heatmap.html +++ b/reference/correlation_heatmap.html @@ -17,7 +17,7 @@MultiEWCE 0.1.8
diff --git a/pkgdown.yml b/pkgdown.yml index 11e489c..69c450f 100644 --- a/pkgdown.yml +++ b/pkgdown.yml @@ -4,5 +4,5 @@ pkgdown_sha: ~ articles: MultiEWCE: MultiEWCE.html docker: docker.html -last_built: 2023-11-07T16:30Z +last_built: 2023-11-07T20:25Z diff --git a/reference/add_ctd.html b/reference/add_ctd.html index 9842199..3da1ca6 100644 --- a/reference/add_ctd.html +++ b/reference/add_ctd.html @@ -24,7 +24,7 @@diff --git a/reference/agg_results.html b/reference/agg_results.html index 6409696..3260359 100644 --- a/reference/agg_results.html +++ b/reference/agg_results.html @@ -18,7 +18,7 @@EWCE parallel
list_name_column = "hpo_id", gene_column = "gene_symbol", list_names = unique(gene_data[[list_name_column]]), - bg = unique(gene_data[[gene_column]]), reps = 100, annotLevel = 1, + force_new = FALSE, genelistSpecies = "human", sctSpecies = "human", + bg = get_bg(species1 = genelistSpecies, species2 = sctSpecies, overwrite = force_new), save_dir_tmp = tempdir(), - force_new = FALSE, parallel_boot = FALSE, cores = 1, verbose = FALSE @@ -110,12 +110,6 @@Arguments
- character vector of gene list names.
bg -- - List of gene symbols containing the background gene list -(including hit genes). If
bg=NULL, - an appropriate gene background will be created automatically.reps @@ -126,6 +120,11 @@ Number of random gene lists to generate (Default: 100, but should be >=10,000 for publication-quality results).
Arguments
analyse (Default: 1). +force_new ++ + Overwrite previous results +in the
save_dir_tmp.genelistSpecies + Species that
hitsgenes came from (no longer limited to just "mouse" and "human"). @@ -138,16 +137,17 @@Arguments
See list_species for all available species.bg ++ + List of gene symbols containing the background gene list +(including hit genes). If
bg=NULL, + an appropriate gene background will be created automatically.save_dir_tmp - Folder to save intermediate results files to (one file per gene list). Set to
NULLto skip saving temporary files.force_new -- - Overwrite previous results -in the
save_dir_tmp.parallel_boot @@ -181,6 +181,9 @@ Parallelise at the level of bootstrap iterations, rather than across gene lists.
Examples
gene_data = gene_data, list_names = list_names, reps = 10) +#> Background already exists at: /github/home/.cache/R/MultiEWCE/bg-human-human-gprofiler.rds +#> Use `overwrite=TRUE` to overwrite. +#> + Version: 2023-11-07 #> Computing gene counts.
Examples
#> Computing BH-corrected q-values. #> 1 significant cell type enrichment results @ q<0.05 : #> CellType annotLevel p fold_change sd_from_mean q -#> 1 microglia 1 0 2.064236 4.714929 0 +#> 1 microglia 1 0 2.042317 4.460971 0 plt <- MultiEWCE::ewce_plot(total_res = full_results$results) diff --git a/reference/example_targets.html b/reference/example_targets.html index 81f46d8..e72a88f 100644 --- a/reference/example_targets.html +++ b/reference/example_targets.html @@ -18,7 +18,7 @@ diff --git a/reference/extract_help.html b/reference/extract_help.html index c1942fa..58d8105 100644 --- a/reference/extract_help.html +++ b/reference/extract_help.html @@ -17,7 +17,7 @@ diff --git a/reference/frequency_barplot.html b/reference/frequency_barplot.html index be5c9e5..02782f0 100644 --- a/reference/frequency_barplot.html +++ b/reference/frequency_barplot.html @@ -17,7 +17,7 @@ diff --git a/reference/frequency_histogram.html b/reference/frequency_histogram.html index 1618437..105e89a 100644 --- a/reference/frequency_histogram.html +++ b/reference/frequency_histogram.html @@ -17,7 +17,7 @@ diff --git a/reference/gen_overlap.html b/reference/gen_overlap.html index 5d5a9c9..40b07a0 100644 --- a/reference/gen_overlap.html +++ b/reference/gen_overlap.html @@ -19,7 +19,7 @@ @@ -176,9 +176,9 @@Examples
#> The following object is masked from ‘package:base’: #> #> %||% -#> 1.41372561454773 +#> 2.09847497940063 #> -#> Saving results ==> /tmp/RtmpS5wtsl/gen_overlap.rds +#> Saving results ==> /tmp/Rtmp44nSCV/gen_overlap.rds diff --git a/reference/gen_results.html b/reference/gen_results.html index 47f0d47..56a4208 100644 --- a/reference/gen_results.html +++ b/reference/gen_results.html @@ -22,7 +22,7 @@ @@ -82,16 +82,16 @@Generate results
list_name_column = "hpo_id", gene_column = "gene_symbol", list_names = unique(gene_data[[list_name_column]]), - bg = unique(gene_data[[gene_column]]), reps = 100, annotLevel = 1, genelistSpecies = "human", sctSpecies = "human", + force_new = FALSE, + bg = get_bg(species1 = genelistSpecies, species2 = sctSpecies, overwrite = force_new), cores = 1, parallel_boot = FALSE, save_dir_tmp = NULL, save_dir = tempdir(), - force_new = FALSE, verbose = 1 ) @@ -121,12 +121,6 @@Arguments
character vector of gene list names.
List of gene symbols containing the background gene list
-(including hit genes). If bg=NULL,
- an appropriate gene background will be created automatically.
Number of random gene lists to generate (Default: 100, but should be >=10,000 for publication-quality results).
Arguments
See list_species for all available species. +Overwrite previous results
+in the save_dir_tmp.
List of gene symbols containing the background gene list
+(including hit genes). If bg=NULL,
+ an appropriate gene background will be created automatically.
The number of cores to run in parallel (e.g. 8) int.
Arguments
Folder to save merged results in.
Overwrite previous results
-in the save_dir_tmp.
Print messages.
Examples
reps = 10) #> Validating gene lists.. #> 2 / 5 gene lists are valid. +#> Background already exists at: /github/home/.cache/R/MultiEWCE/bg-human-human-gprofiler.rds +#> Use `overwrite=TRUE` to overwrite. +#> + Version: 2023-11-07 #> Computing gene counts. #> Computing gene counts. -#> Done in: 4 seconds. +#> Done in: 6.2 seconds. #> -#> Saving results ==> /tmp/RtmpS5wtsl/gen_results.rds +#> Saving results ==> /tmp/Rtmp44nSCV/gen_results.rds diff --git a/reference/get_bg.html b/reference/get_bg.html new file mode 100644 index 0000000..559c9a5 --- /dev/null +++ b/reference/get_bg.html @@ -0,0 +1,212 @@ + +Generate background genes given one or more species. +Caches the list to avoid excessive API calls to +g:Profiler.
+get_bg(
+ species1 = "human",
+ species2 = "human",
+ method = "gprofiler",
+ save_dir = tools::R_user_dir(package = "MultiEWCE", which = "cache"),
+ overwrite = FALSE,
+ verbose = TRUE,
+ ...
+)Arguments
+- species1 +
First species.
+
+
+- species2 +
Second species.
+
+
+- method +
R package to use for gene mapping:
"gprofiler": Slower but more species and genes.
+"homologene": Faster but fewer species and genes.
+"babelgene": Faster but fewer species and genes. +Also gives consensus scores for each gene mapping based on a + several different data sources.
+
+
+
+- save_dir +
Directory to save data to.
+
+
+- overwrite +
Should any local files of the same name be overwritten? +default
TRUE.
+
+
+- verbose +
Print messages.
+
+
+- ... +
Arguments passed on to
orthogene::create_backgroundoutput_species
+Species to convert all genes from +
species1andspecies2to first. +Default="human", but can be to either any species + supported by orthogene, including +species1orspecies2.
+
+ as_output_species
+Return background gene list as +
output_speciesorthologs, instead of the + gene names of the original input species.
+
+ use_intersect
+When
species1andspecies2are both +different fromoutput_species, this argument will determine whether +to use the intersect (TRUE) or union (FALSE) of all genes +fromspecies1andspecies2.
+
+ bg
+User supplied background list that will be returned to the +user after removing duplicate genes.
+
+ gene_map
+User-supplied
gene_mapdata table from +map_orthologs or map_genes.
+
+ non121_strategy
+How to handle genes that don't have +1:1 mappings between
input_species:output_species. +Options include:"drop_both_species" or "dbs" or 1:
+Drop genes that have duplicate +mappings in either theinput_speciesoroutput_species
+(DEFAULT).
+"drop_input_species" or "dis" or 2:
+Only drop genes that have duplicate +mappings in theinput_species.
+"drop_output_species" or "dos" or 3:
+Only drop genes that have duplicate +mappings in theoutput_species.
+"keep_both_species" or "kbs" or 4:
+Keep all genes regardless of whether +they have duplicate mappings in either species.
+"keep_popular" or "kp" or 5:
+Return only the most "popular" interspecies ortholog mappings. + This procedure tends to yield a greater number of returned genes + but at the cost of many of them not being true biological 1:1 orthologs.
+"sum","mean","median","min" or "max":
+ Whengene_dfis a matrix andgene_output="rownames", + these options will aggregate many-to-one gene mappings + (input_species-to-output_species) + after dropping any duplicate genes in theoutput_species.
+
+
+
+
+
+
Value
+ + +A vector of background genes.
+Examples
+bg <- get_bg()
+#> Background already exists at: /github/home/.cache/R/MultiEWCE/bg-human-human-gprofiler.rds
+#> Use `overwrite=TRUE` to overwrite.
+#> + Version: 2023-11-07
+Get remote data
get_data(
fname,
repo = "neurogenomics/MultiEWCE",
- storage_dir = tools::R_user_dir(package = "MultiEWCE", which = "cache"),
+ save_dir = tools::R_user_dir(package = "MultiEWCE", which = "cache"),
overwrite = TRUE,
tag = "latest",
check = FALSE
@@ -82,6 +82,10 @@ Arguments
Repository name in format "owner/repo". Defaults to guess_repo().
save_dir
+Directory to save data to.
overwrite
Should any local files of the same name be overwritten?
default TRUE.
All functions gen_results()
Generate results
+
+
+ Get background genes
@@ -155,6 +159,10 @@ All functions report_plot()
Report plot
+
+
+ Standardise genes
diff --git a/reference/is_not_analysed.html b/reference/is_not_analysed.html
index 5bb6e3a..75dcc02 100644
--- a/reference/is_not_analysed.html
+++ b/reference/is_not_analysed.html
@@ -21,7 +21,7 @@
diff --git a/reference/load_example_CTD.html b/reference/load_example_CTD.html
index a24535a..027929b 100644
--- a/reference/load_example_CTD.html
+++ b/reference/load_example_CTD.html
@@ -19,7 +19,7 @@
diff --git a/reference/load_example_results.html b/reference/load_example_results.html
index 34fdd22..86fd114 100644
--- a/reference/load_example_results.html
+++ b/reference/load_example_results.html
@@ -19,7 +19,7 @@
diff --git a/reference/load_hpo_graph.html b/reference/load_hpo_graph.html
index 314a71b..8181277 100644
--- a/reference/load_hpo_graph.html
+++ b/reference/load_hpo_graph.html
@@ -17,7 +17,7 @@
diff --git a/reference/map_tissues.html b/reference/map_tissues.html
index 09cb414..1842e19 100644
--- a/reference/map_tissues.html
+++ b/reference/map_tissues.html
@@ -17,7 +17,7 @@
diff --git a/reference/merge_results.html b/reference/merge_results.html
index 5fe81e6..bb92773 100644
--- a/reference/merge_results.html
+++ b/reference/merge_results.html
@@ -20,7 +20,7 @@
diff --git a/reference/messager.html b/reference/messager.html
index 47090f6..982ca3f 100644
--- a/reference/messager.html
+++ b/reference/messager.html
@@ -20,7 +20,7 @@
diff --git a/reference/ontology_plot.html b/reference/ontology_plot.html
index 733f129..00e03ef 100644
--- a/reference/ontology_plot.html
+++ b/reference/ontology_plot.html
@@ -22,7 +22,7 @@
diff --git a/reference/plot_ont_lvl.html b/reference/plot_ont_lvl.html
index c5cf229..596b1a5 100644
--- a/reference/plot_ont_lvl.html
+++ b/reference/plot_ont_lvl.html
@@ -18,7 +18,7 @@
diff --git a/reference/prioritise_targets.html b/reference/prioritise_targets.html
index 349f8df..3bc254e 100644
--- a/reference/prioritise_targets.html
+++ b/reference/prioritise_targets.html
@@ -72,7 +72,7 @@
diff --git a/reference/prioritise_targets_network.html b/reference/prioritise_targets_network.html
index 3b92bb3..e1bcc05 100644
--- a/reference/prioritise_targets_network.html
+++ b/reference/prioritise_targets_network.html
@@ -23,7 +23,7 @@
@@ -253,7 +253,7 @@ Examples
#> Loading required namespace: tidygraph
#> Creating network.
#> Creating plot.
-#> Saving plot ==> /tmp/RtmpS5wtsl/file71be7315db93_prioritise_targets_network.html
+#> Saving plot ==> /tmp/Rtmp44nSCV/file1f5b74a5f129_prioritise_targets_network.html
diff --git a/reference/report_plot.html b/reference/report_plot.html
index e2e8cde..73efafc 100644
--- a/reference/report_plot.html
+++ b/reference/report_plot.html
@@ -18,7 +18,7 @@
@@ -184,7 +184,7 @@ Examples
#> ℹ The deprecated feature was likely used in the MultiEWCE package.
#> Please report the issue at
#> <https://github.com/neurogenomics/MultiEWCE/issues>.
-#> Saving plot ==> /tmp/RtmpS5wtsl/file71be24c6958c_report_plot.pdf
+#> Saving plot ==> /tmp/Rtmp44nSCV/file1f5b55159f82_report_plot.pdf
#> Saving 6.67 x 6.67 in image
diff --git a/reference/standardise_genes.html b/reference/standardise_genes.html
new file mode 100644
index 0000000..fc20df5
--- /dev/null
+++ b/reference/standardise_genes.html
@@ -0,0 +1,164 @@
+
+Standardise genes — standardise_genes • MultiEWCE
+
+
+
+
+
+
+
+
+
+
+
+
+ Standardise gene symbols to HGNC.
+
+
+
+ standardise_genes(
+ dat,
+ gene_col = "gene_symbol",
+ fill_na = TRUE,
+ verbose = TRUE,
+ ...
+)
+
+
+
+ Arguments
+ - dat
+data.table
- gene_col
+character column name.
- fill_na
+logical. Fill NAs with original gene symbol.
- verbose
+logical. Print messages.
- ...
+Arguments passed on to orthogene::map_genes
genesGene list.
speciesSpecies to map against.
targettarget namespace.
mthresholdmaximum number of results per initial alias to show. Shows all by default.
drop_naDrop all genes without mappings.
+Sets gprofiler2::gconvert(filter_na=) as well
+an additional round of more comprehensive NA filtering
+by orthogene.
numeric_nsnamespace to use for fully numeric IDs (list of available namespaces).
run_map_speciesStandardise species names with
+map_species first (Default: TRUE).
+
+ Value
+
+
+data.table
+
+
+
+ Examples
+ if (FALSE) {
+dat <- data.table(gene_symbol = c("BRCA1","BRCA2","BRCA3"))
+dat2 <- standardise_genes(dat)
+}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/reference/subset_phenos.html b/reference/subset_phenos.html
index c784ea7..72ba152 100644
--- a/reference/subset_phenos.html
+++ b/reference/subset_phenos.html
@@ -18,7 +18,7 @@
diff --git a/reference/subset_results.html b/reference/subset_results.html
index 99f3239..2e0542e 100644
--- a/reference/subset_results.html
+++ b/reference/subset_results.html
@@ -17,7 +17,7 @@
diff --git a/reference/summary_plot.html b/reference/summary_plot.html
index b0e7673..c3f50e4 100644
--- a/reference/summary_plot.html
+++ b/reference/summary_plot.html
@@ -18,7 +18,7 @@
diff --git a/reference/terminal_celltypes.html b/reference/terminal_celltypes.html
index f5e2ba1..3afbd69 100644
--- a/reference/terminal_celltypes.html
+++ b/reference/terminal_celltypes.html
@@ -18,7 +18,7 @@
diff --git a/reference/ttd_check.html b/reference/ttd_check.html
index 0074a24..1baf828 100644
--- a/reference/ttd_check.html
+++ b/reference/ttd_check.html
@@ -21,7 +21,7 @@
diff --git a/sitemap.xml b/sitemap.xml
index e3721cc..e14291b 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -57,6 +57,9 @@
/reference/gen_results.html
+
+ /reference/get_bg.html
+
/reference/get_data.html
@@ -108,6 +111,9 @@
/reference/report_plot.html
+
+ /reference/standardise_genes.html
+
/reference/subset_phenos.html
Generate results
Get background genes
All functions report_plot()
Report plot
Report plot
Standardise genes
Examples
#> Loading required namespace: tidygraph #> Creating network. #> Creating plot. -#> Saving plot ==> /tmp/RtmpS5wtsl/file71be7315db93_prioritise_targets_network.html +#> Saving plot ==> /tmp/Rtmp44nSCV/file1f5b74a5f129_prioritise_targets_network.html diff --git a/reference/report_plot.html b/reference/report_plot.html index e2e8cde..73efafc 100644 --- a/reference/report_plot.html +++ b/reference/report_plot.html @@ -18,7 +18,7 @@ @@ -184,7 +184,7 @@Examples
#> ℹ The deprecated feature was likely used in the MultiEWCE package. #> Please report the issue at #> <https://github.com/neurogenomics/MultiEWCE/issues>. -#> Saving plot ==> /tmp/RtmpS5wtsl/file71be24c6958c_report_plot.pdf +#> Saving plot ==> /tmp/Rtmp44nSCV/file1f5b55159f82_report_plot.pdf #> Saving 6.67 x 6.67 in image
diff --git a/reference/standardise_genes.html b/reference/standardise_genes.html
new file mode 100644
index 0000000..fc20df5
--- /dev/null
+++ b/reference/standardise_genes.html
@@ -0,0 +1,164 @@
+
+Standardise gene symbols to HGNC.
+standardise_genes(
+ dat,
+ gene_col = "gene_symbol",
+ fill_na = TRUE,
+ verbose = TRUE,
+ ...
+)Arguments
+- dat +
data.table
+
+
+- gene_col +
character column name.
+
+
+- fill_na +
logical. Fill NAs with original gene symbol.
+
+
+- verbose +
logical. Print messages.
+
+
+- ... +
Arguments passed on to
orthogene::map_genesgenes
+Gene list.
+
+ species
+Species to map against.
+
+ target
+target namespace.
+
+ mthreshold
+maximum number of results per initial alias to show. Shows all by default.
+
+ drop_na
+Drop all genes without mappings. +Sets
gprofiler2::gconvert(filter_na=)as well +an additional round of more comprehensiveNAfiltering +by orthogene.
+
+ numeric_ns
+namespace to use for fully numeric IDs (list of available namespaces).
+
+ run_map_species
+Standardise
speciesnames with +map_species first (Default:TRUE).
+
+
+
+
+
Value
+ + +data.table
+Examples
+if (FALSE) {
+dat <- data.table(gene_symbol = c("BRCA1","BRCA2","BRCA3"))
+dat2 <- standardise_genes(dat)
+}
+