Installation
-MGnifyR is currently hosted on GitHub, and can be
-installed using via devtools. MGnifyR should
-be built using the following snippet.
MGnifyR is hosted on Bioconductor, and can be installed
+using via BiocManager.
BiocManager::install(MGnifyR)Functions for fetching the data
Search data
-Below, we fetch information on samples of drinking water.
+doQuery() function can be utilized to search results
+such as samples and studies from MGnify database. Below, we fetch
+information drinking water samples.
# Fetch studies
samples <- doQuery(
@@ -238,6 +239,8 @@ Search data= "samples",
biome_name = "root:Environmental:Aquatic:Freshwater:Drinking water",
max.hits = 10)
+The result is a table containing accession IDs and description – in
+this case – on samples.
head(samples)
#> biosample accession sample-desc
@@ -347,6 +350,8 @@ Find relevent analyses
analyses_accessions <- searchAnalysis(mg, "samples", samples$accession)
+By running the searchAnalysis() function, we get
+analysis IDs of samples that we fed as an input.
head(analyses_accessions)
#> [1] "MGYA00652201" "MGYA00652185" "MGYA00643487" "MGYA00643486" "MGYA00643485"
@@ -356,9 +361,12 @@ Find relevent analysesFetch metadata
We can now check the metadata to get hint of what kind of data we
-have.
+have. We use getMetadata() function to fetch data based on
+analysis IDs.
analyses_metadata <- getMetadata(mg, analyses_accessions)
+Metadata includes for example information on how analysis was
+conducted and what kind of samples were analyzed.
head(analyses_metadata)
#> analysis_analysis-status analysis_pipeline-version
@@ -684,7 +692,7 @@ Fetch microbiome dataTreeSE object is uniquely positioned to support
SummarizedExperiment-based microbiome data manipulation and
visualization. Moreover, it enables access to miaverse
-tools. For example, we can estimate diversity of samples.
+tools. For example, we can estimate diversity of samples…
mae[[1]] <- estimateDiversity(mae[[1]], index = "shannon")
@@ -694,6 +702,7 @@ Fetch microbiome data
plotColData(mae[[1]], "shannon", x = "sample_environment..biome.")
+… and plot abundances of most abundant phyla.
# Agglomerate data
altExps(mae[[1]]) <- splitByRanks(mae[[1]])
@@ -705,8 +714,8 @@ Fetch microbiome datatop_taxa <- getTopFeatures(altExp(mae[[1]], "Phylum"), 10)
plotAbundance(altExp(mae[[1]], "Phylum")[top_taxa, ], rank = "Phylum")
-We can perform principal component analysis to microbial profiling
-data by utilizing miaverse tools.
+We can also perform other analyses such as principal component
+analysis to microbial profiling data by utilizing miaverse tools.
# Apply relative transformation
mae[[1]] <- transformAssay(mae[[1]], method = "relabundance")
@@ -729,8 +738,10 @@ Fetch sequence filessearchFile()
, we can search files from the
database.
-# Find list of available downloads, and filter for
-dl_urls <- searchFile(mg, analyses_accessions, type = "analyses")
+dl_urls <- searchFile(mg, analyses_accessions, type = "analyses")
+The returned table contains search results related to analyses that
+we fed as an input. The table contains information on file and also URL
+address from where the file can be loaded.
target_urls <- dl_urls[
dl_urls$attributes.description.label == "Predicted alpha tmRNA", ]
@@ -817,6 +828,7 @@ Fetch sequence files# Just select a single file from the target_urls list for demonstration.
file_url <- target_urls$download_url[[1]]
cached_location <- getFile(mg, file_url)
+The function returns a path where the file is stored.
# Where are the files?
cached_location
diff --git a/pkgdown.yml b/pkgdown.yml
index 1ad39694..1827a07d 100644
--- a/pkgdown.yml
+++ b/pkgdown.yml
@@ -4,5 +4,5 @@ pkgdown_sha: ~
articles:
MGnifyR: MGnifyR.html
MGnifyR_long: MGnifyR_long.html
-last_built: 2024-02-05T08:45Z
+last_built: 2024-02-05T13:31Z
diff --git a/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS b/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS
index 87af23ed..b7733dae 100644
Binary files a/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS and b/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS differ
diff --git a/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS b/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS
index c9c07bb1..7e52904f 100644
Binary files a/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS and b/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS differ
doQuery() function can be utilized to search results
+such as samples and studies from MGnify database. Below, we fetch
+information drinking water samples.
# Fetch studies
samples <- doQuery(
@@ -238,6 +239,8 @@ Search data= "samples",
biome_name = "root:Environmental:Aquatic:Freshwater:Drinking water",
max.hits = 10)
head(samples)
#> biosample accession sample-desc
@@ -347,6 +350,8 @@ Find relevent analyses
analyses_accessions <- searchAnalysis(mg, "samples", samples$accession)
+By running the searchAnalysis() function, we get
+analysis IDs of samples that we fed as an input.
head(analyses_accessions)
#> [1] "MGYA00652201" "MGYA00652185" "MGYA00643487" "MGYA00643486" "MGYA00643485"
@@ -356,9 +361,12 @@ Find relevent analysesFetch metadata
We can now check the metadata to get hint of what kind of data we
-have.
+have. We use getMetadata() function to fetch data based on
+analysis IDs.
analyses_metadata <- getMetadata(mg, analyses_accessions)
+Metadata includes for example information on how analysis was
+conducted and what kind of samples were analyzed.
head(analyses_metadata)
#> analysis_analysis-status analysis_pipeline-version
@@ -684,7 +692,7 @@ Fetch microbiome dataTreeSE object is uniquely positioned to support
SummarizedExperiment-based microbiome data manipulation and
visualization. Moreover, it enables access to miaverse
-tools. For example, we can estimate diversity of samples.
+tools. For example, we can estimate diversity of samples…
mae[[1]] <- estimateDiversity(mae[[1]], index = "shannon")
@@ -694,6 +702,7 @@ Fetch microbiome data
plotColData(mae[[1]], "shannon", x = "sample_environment..biome.")
+… and plot abundances of most abundant phyla.
# Agglomerate data
altExps(mae[[1]]) <- splitByRanks(mae[[1]])
@@ -705,8 +714,8 @@ Fetch microbiome datatop_taxa <- getTopFeatures(altExp(mae[[1]], "Phylum"), 10)
plotAbundance(altExp(mae[[1]], "Phylum")[top_taxa, ], rank = "Phylum")
-We can perform principal component analysis to microbial profiling
-data by utilizing miaverse tools.
+We can also perform other analyses such as principal component
+analysis to microbial profiling data by utilizing miaverse tools.
# Apply relative transformation
mae[[1]] <- transformAssay(mae[[1]], method = "relabundance")
@@ -729,8 +738,10 @@ Fetch sequence filessearchFile()
, we can search files from the
database.
-# Find list of available downloads, and filter for
-dl_urls <- searchFile(mg, analyses_accessions, type = "analyses")
+dl_urls <- searchFile(mg, analyses_accessions, type = "analyses")
+The returned table contains search results related to analyses that
+we fed as an input. The table contains information on file and also URL
+address from where the file can be loaded.
target_urls <- dl_urls[
dl_urls$attributes.description.label == "Predicted alpha tmRNA", ]
@@ -817,6 +828,7 @@ Fetch sequence files# Just select a single file from the target_urls list for demonstration.
file_url <- target_urls$download_url[[1]]
cached_location <- getFile(mg, file_url)
+The function returns a path where the file is stored.
# Where are the files?
cached_location
diff --git a/pkgdown.yml b/pkgdown.yml
index 1ad39694..1827a07d 100644
--- a/pkgdown.yml
+++ b/pkgdown.yml
@@ -4,5 +4,5 @@ pkgdown_sha: ~
articles:
MGnifyR: MGnifyR.html
MGnifyR_long: MGnifyR_long.html
-last_built: 2024-02-05T08:45Z
+last_built: 2024-02-05T13:31Z
diff --git a/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS b/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS
index 87af23ed..b7733dae 100644
Binary files a/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS and b/reference/.MGnifyR_cache/analyses/MGYA00377505_format_json/.RDS differ
diff --git a/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS b/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS
index c9c07bb1..7e52904f 100644
Binary files a/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS and b/reference/.MGnifyR_cache/samples/ERS2967391_format_json/.RDS differ