From f7a7bdb03bcc2ca10e3c8309d635e005b23ff055 Mon Sep 17 00:00:00 2001 From: mattssca Date: Wed, 7 Feb 2024 12:14:18 -0800 Subject: [PATCH] Website updates --- .gitignore | 1 - _pkgdown.yml | 1 + docs/pkgdown.yml | 2 +- docs/reference/bin_splitter.html | 23 +++- docs/reference/cyto_ranger.html | 32 ++++-- docs/reference/gene_ranger.html | 19 +++- docs/reference/get_gene_info.html | 55 ++++++++- docs/reference/index.html | 5 + docs/reference/power_lifter.html | 172 +++++++++++++++++++++++++++++ docs/reference/purify_chr.html | 8 +- docs/reference/purify_regions.html | 30 +++-- docs/reference/region_ranger.html | 59 ++++++++-- docs/search.json | 2 +- docs/sitemap.xml | 3 + 14 files changed, 361 insertions(+), 51 deletions(-) create mode 100644 docs/reference/power_lifter.html diff --git a/.gitignore b/.gitignore index 891da15..23a20d4 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,3 @@ .Rproj.user .DS_Store my_bed.bed -docs diff --git a/_pkgdown.yml b/_pkgdown.yml index ac7e778..27d49f8 100644 --- a/_pkgdown.yml +++ b/_pkgdown.yml @@ -32,6 +32,7 @@ reference: - bin_splitter - cyto_ranger - gene_ranger + - power_lifter - region_ranger - title: Helpers desc: A collection of helper functions. diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 289d9fc..1b56fab 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -2,7 +2,7 @@ pandoc: 3.1.1 pkgdown: 2.0.7 pkgdown_sha: ~ articles: {} -last_built: 2024-02-06T22:53Z +last_built: 2024-02-07T20:08Z urls: reference: https://github.com/mattssca/BioMaesteR/reference article: https://github.com/mattssca/BioMaesteR/articles diff --git a/docs/reference/bin_splitter.html b/docs/reference/bin_splitter.html index 6d9c11b..007ec2f 100644 --- a/docs/reference/bin_splitter.html +++ b/docs/reference/bin_splitter.html @@ -130,10 +130,27 @@

Examples qstart = c(100, 200), qend = c(200, 300), bin_size = 10) +head(my_bins, 5) +#> bin_chr bin_start bin_end +#> 1 chr1 100 110 +#> 2 chr1 110 120 +#> 3 chr1 120 130 +#> 4 chr1 130 140 +#> 5 chr1 140 150 -#Example 2 - Call the funciton with regions from a data frame -my_regions = purify_regions(these_regions = c("chr7:1000-500000", "chr8:50000-7000000")) -these_bins = bin_splitter(these_regions = my_regions, bin_size = 100000) +#Example 2 - Call the function with regions from a data frame +my_regions = purify_regions(these_regions = c("chr7:1000-500000", + "chr8:50000-7000000")) + +these_bins = bin_splitter(these_regions = my_regions, + bin_size = 100000) +head(these_bins, 5) +#> bin_chr bin_start bin_end +#> 1 chr7 1000 101000 +#> 2 chr7 101000 201000 +#> 3 chr7 201000 301000 +#> 4 chr7 301000 401000 +#> 5 chr8 50000 150000 diff --git a/docs/reference/cyto_ranger.html b/docs/reference/cyto_ranger.html index b7a4115..4bcd0a3 100644 --- a/docs/reference/cyto_ranger.html +++ b/docs/reference/cyto_ranger.html @@ -135,23 +135,33 @@

Details

Examples

#' #Example 1 - Give the function one region as a string
-my_region = cyto_ranger(these_regions = "chr8:127735434-127742951")
+cyto_ranger(these_regions = "chr8:127735434-127742951")
+#>   chrom region_start region_end cytoBand cytoband_start cytoband_end
+#> 1  chr8    127735434  127742951   q24.21      126300000    130400000
 
 #Example 2 - Give the function multiple regions as a string
-my_regions = cyto_ranger(these_regions = c("chr8:128747680-128753674",
-                                           "chr18:60790579-60987361"),
-                         projection = "grch37")
+cyto_ranger(these_regions = c("chr8:128747680-128753674",
+                              "chr18:60790579-60987361"),
+            projection = "grch37")
+#>   chrom region_start region_end cytoBand cytoband_start cytoband_end
+#> 1    18     60790579   60987361   q21.33       59000000     61600000
+#> 2     8    128747680  128753674   q24.21      127300000    131500000
 
 #Example 3 - Individually specify the chromosome, start and end coordinates
-this_region = cyto_ranger(qchrom = "chr8",
-                          qstart = 127735434,
-                          qend = 127742951)
+cyto_ranger(qchrom = "chr8",
+            qstart = 127735434,
+            qend = 127742951)
+#>   chrom region_start region_end cytoBand cytoband_start cytoband_end
+#> 1  chr8    127735434  127742951   q24.21      126300000    130400000
 
 #Example 4 - Individually specify multiple regions with the query parameters
-these_regions = cyto_ranger(qchrom = c("chr8", "chr18"),
-                            qstart = c(128747680, 60790579),
-                            qend = c(128753674, 60987361),
-                            projection = "grch37")
+cyto_ranger(qchrom = c("chr8", "chr18"),
+            qstart = c(128747680, 60790579),
+            qend = c(128753674, 60987361),
+            projection = "grch37")
+#>   chrom region_start region_end cytoBand cytoband_start cytoband_end
+#> 1    18     60790579   60987361   q21.33       59000000     61600000
+#> 2     8    128747680  128753674   q24.21      127300000    131500000
diff --git a/docs/reference/gene_ranger.html b/docs/reference/gene_ranger.html index 8f2ff70..57fb9e8 100644 --- a/docs/reference/gene_ranger.html +++ b/docs/reference/gene_ranger.html @@ -152,19 +152,28 @@

Details

Examples

#Example 1 - Request one gene (in Hugo format) and with default parameters
-hugo_myc = gene_ranger(these_genes = "MYC")
+gene_ranger(these_genes = "MYC")
+#>   chrom     start       end width strand   gene_biotype hugo_symbol
+#> 1  chr8 127735434 127742951  7518      + protein_coding         MYC
 
 #Example 2 - Same as example one but MYC is here specified as Ensembl ID
-ensembl_myc = gene_ranger(these_genes = "ENSG00000136997")
+gene_ranger(these_genes = "ENSG00000136997")
+#>   chrom     start       end width strand   gene_biotype ensembl_gene_id
+#> 1  chr8 127735434 127742951  7518      + protein_coding ENSG00000136997
 
 #Example 3 - Request multiple genes with non-default parameters
-my_genes = gene_ranger(these_genes = c("MYC", "BCL2"),
+gene_ranger(these_genes = c("MYC", "BCL2"),
                        projection = "grch37",
                        return_as = "region")
+#>                     MYC                    BCL2 
+#> "8:128747680-128753674"  "18:60790579-60987361" 
 
 #Example 4 - Request multiple Ensembl IDs and return in bed format
-my_bed = gene_ranger(these_genes = c("ENSG00000136997", "ENSG00000171791"),
-                     return_as = "bed")
+gene_ranger(these_genes = c("ENSG00000136997", "ENSG00000171791"),
+            return_as = "bed")
+#>   chrom     start       end score strand
+#> 1 chr18  63123346  63320128    NA      -
+#> 2  chr8 127735434 127742951    NA      +
 
 #Example 5 - Write to bed file
 gene_ranger(these_genes = c("BCL2", "MYC"),
diff --git a/docs/reference/get_gene_info.html b/docs/reference/get_gene_info.html
index 254d456..e8becd5 100644
--- a/docs/reference/get_gene_info.html
+++ b/docs/reference/get_gene_info.html
@@ -114,18 +114,61 @@ 
Details
     
Examples

     
#Example 1 - Query one gene (in Hugo format) and with default parameters.
-hugo_myc = get_gene_info(these_genes = "MYC")
+get_gene_info(these_genes = "MYC")
+#>   hugo_symbol ensembl_gene_id type   gene_biotype         source gene_version
+#> 1         MYC ENSG00000136997 gene protein_coding ensembl_havana           22
+#>      gene_source  tag ccds_id score transcript_id transcript_version
+#> 1 ensembl_havana <NA>    <NA>    NA          <NA>               <NA>
+#>   transcript_name transcript_source transcript_biotype exon_number exon_id
+#> 1            <NA>              <NA>               <NA>        <NA>    <NA>
+#>   protein_id protein_version
+#> 1       <NA>            <NA>
 
 #Example 2 - Same as example 1 but MYC is here specified as Ensembl ID.
-ensembl_myc = get_gene_info(these_genes = "ENSG00000136997")
+get_gene_info(these_genes = "ENSG00000136997")
+#>   ensembl_gene_id hugo_symbol type   gene_biotype         source gene_version
+#> 1 ENSG00000136997         MYC gene protein_coding ensembl_havana           22
+#>      gene_source  tag ccds_id score transcript_id transcript_version
+#> 1 ensembl_havana <NA>    <NA>    NA          <NA>               <NA>
+#>   transcript_name transcript_source transcript_biotype exon_number exon_id
+#> 1            <NA>              <NA>               <NA>        <NA>    <NA>
+#>   protein_id protein_version
+#> 1       <NA>            <NA>
 
 #Example 3 - Request multiple genes with non-default parameters
-hugo_genes = get_gene_info(these_genes = c("MYC", "BCL2"),
-                           projection = "grch37")
+get_gene_info(these_genes = c("MYC", "BCL2"),
+              projection = "grch37")
+#>   hugo_symbol ensembl_gene_id type   gene_biotype         source gene_version
+#> 1         MYC ENSG00000136997 gene protein_coding ensembl_havana           10
+#> 2        BCL2 ENSG00000171791 gene protein_coding ensembl_havana           10
+#>      gene_source  tag ccds_id score transcript_id transcript_version
+#> 1 ensembl_havana <NA>    <NA>    NA          <NA>               <NA>
+#> 2 ensembl_havana <NA>    <NA>    NA          <NA>               <NA>
+#>   transcript_name transcript_source transcript_biotype exon_number exon_id
+#> 1            <NA>              <NA>               <NA>        <NA>    <NA>
+#> 2            <NA>              <NA>               <NA>        <NA>    <NA>
+#>   protein_id protein_version
+#> 1       <NA>            <NA>
+#> 2       <NA>            <NA>
 
 #Example 4 - Request multiple Ensembl IDs and return all columns.
-ensembl_genes = get_gene_info(these_genes = c("ENSG00000136997", "ENSG00000171791"),
-                              raw = TRUE)
+get_gene_info(these_genes = c("ENSG00000136997", "ENSG00000171791"),
+              raw = TRUE)
+#>   chrom     start       end  width strand type  tag ccds_id ensembl_gene_id
+#> 1 chr18  63123346  63320128 196783      - gene <NA>    <NA> ENSG00000171791
+#> 2  chr8 127735434 127742951   7518      + gene <NA>    <NA> ENSG00000136997
+#>   hugo_symbol         source score gene_version    gene_source   gene_biotype
+#> 1        BCL2 ensembl_havana    NA           14 ensembl_havana protein_coding
+#> 2         MYC ensembl_havana    NA           22 ensembl_havana protein_coding
+#>   transcript_id transcript_version transcript_name transcript_source
+#> 1          <NA>               <NA>            <NA>              <NA>
+#> 2          <NA>               <NA>            <NA>              <NA>
+#>   transcript_biotype exon_number exon_id exon_version protein_id
+#> 1               <NA>        <NA>    <NA>         <NA>       <NA>
+#> 2               <NA>        <NA>    <NA>         <NA>       <NA>
+#>   protein_version input_format
+#> 1            <NA>      Ensembl
+#> 2            <NA>      Ensembl
diff --git a/docs/reference/index.html b/docs/reference/index.html index 7ee3117..c20ca15 100644 --- a/docs/reference/index.html +++ b/docs/reference/index.html @@ -144,6 +144,11 @@

UtilityGene Ranger.
+ power_lifter() +
+
Power Lifter
+
+ region_ranger()
Region Ranger.
diff --git a/docs/reference/power_lifter.html b/docs/reference/power_lifter.html new file mode 100644 index 0000000..2425a65 --- /dev/null +++ b/docs/reference/power_lifter.html @@ -0,0 +1,172 @@ + +Power Lifter — power_lifter • biomaesteR + Skip to contents + + +
+
+
+

Power Lifter

+ +
power_lifter.Rd
+
+ +
+

A function to convert genomic regions from one assembly to another.

+
+ +
+

Usage

+ 
power_lifter(
+  these_regions = NULL,
+  qchrom = NULL,
+  qstart = NULL,
+  qend = NULL,
+  original_assembly = "hg38",
+  target_assembly = "grch37"
+)
+
+ +
+

Arguments

+
these_regions
+

The region(s) to be queried. Can be a data frame with +regions with the following columns; chrom, start, end. +Or in a string in the following format chr:start-end.

+ + +
qchrom
+

Query chromosome (prefixed or un-prefixed), +Required if `these_regions` is not provided.

+ + +
qstart
+

Query start position. Required if `these_regions` is not provided.

+ + +
qend
+

Query end position. Required if `these_regions` is not provided.

+ + +
original_assembly
+

The original assembly of the regions. Default is hg38

+ + +
target_assembly
+

The target assembly of the regions. Default is grch37.

+ +
+
+

Value

+ + +

A data frame with the regions in the selected target assembly.

+
+
+

Details

+

This function is a wrapper for the [rtracklayer::liftOver] function. +Specify the original assembly and the target assembly, and the function will +convert the regions accordingly. Regions can be provided as a data frame with +`these_regions`, or as a string with `qchrom`, `qstart`, and `qend`.

+
+ +
+

Examples

+ 
#Example 1 - Convert MYC region from hg38 to grch37
+power_lifter(these_regions = "chr8:127735434-127742951")
+#>   chrom     start       end width strand
+#> 1     8 128747680 128755197  7518      *
+
+#Example 2 - Convert MYC region from grch37 to hg38
+power_lifter(these_regions = "18:60790579-60987361", 
+             original_assembly = "grch37", 
+             target_assembly = "hg38")
+#> Discarding unchained sequences: 18
+#> [1] chrom  start  end    width  strand
+#> <0 rows> (or 0-length row.names)
+
+#Example 3 - Same as Example 1, but use the `qchrom`, `qstart`, and `qend`.
+power_lifter(qchrom = "chr8", 
+             qstart = 127735434, 
+             qend = 127742951)
+#>   chrom     start       end width strand
+#> 1     8 128747680 128755197  7518      *
+
+
+
+
+ + +
+

Developed by Adam Mattsson.

+
+ +
+

Site built with pkgdown 2.0.7.

+
+ +
+ + + + + + + diff --git a/docs/reference/purify_chr.html b/docs/reference/purify_chr.html index 5487fe1..f4edddf 100644 --- a/docs/reference/purify_chr.html +++ b/docs/reference/purify_chr.html @@ -109,7 +109,13 @@

DetailsExamples

#Example 1 - Add prefixes to a data frame
 my_data = data.frame(chrom = c("1", "2", "3"))
-my_data = purify_chr(projection = "hg38", incoming_table = my_data)
+
+purify_chr(projection = "hg38", 
+           incoming_table = my_data)
+#>   chrom
+#> 1  chr1
+#> 2  chr2
+#> 3  chr3
diff --git a/docs/reference/purify_regions.html b/docs/reference/purify_regions.html index feee6e6..18ea702 100644 --- a/docs/reference/purify_regions.html +++ b/docs/reference/purify_regions.html @@ -134,22 +134,32 @@

Details

Examples

#Example 1 - Give the function one region as a string
-my_region = purify_regions(these_regions = "chr1:100-500")
+purify_regions(these_regions = "chr1:100-500")
+#>    chrom start end
+#> 1:  chr1   100 500
 
 #Example 2 - Give the function multiple regions as a string
-my_regions = purify_regions(these_regions = c("chr1:100-500", "chr2:100-500"),
-                            projection = "grch37")
+purify_regions(these_regions = c("chr1:100-500", "chr2:100-500"),
+               projection = "grch37")
+#>    chrom start end
+#> 1:     1   100 500
+#> 2:     2   100 500
 
 #Example 3 - Individually specify the chromosome, start and end coordinates
-this_region = purify_regions(qchrom = "chr1",
-                             qstart = 100,
-                             qend = 500)
+purify_regions(qchrom = "chr1",
+               qstart = 100,
+               qend = 500)
+#>    chrom start end
+#> 1:  chr1   100 500
 
 #Example 4 - Individually specify multiple regions with the query parameters
-these_regions = purify_regions(qchrom = c("chr1", "chr2"),
-                               qstart = c(100, 200),
-                               qend = c(500, 600),
-                               projection = "grch37")
+purify_regions(qchrom = c("chr1", "chr2"),
+               qstart = c(100, 200),
+               qend = c(500, 600),
+               projection = "grch37")
+#>    chrom start end
+#> 1:     1   100 500
+#> 2:     2   200 600
diff --git a/docs/reference/region_ranger.html b/docs/reference/region_ranger.html index 0873874..f151593 100644 --- a/docs/reference/region_ranger.html +++ b/docs/reference/region_ranger.html @@ -137,24 +137,59 @@

Details

Examples

#Example 1 - Give the function one region as a string
-my_region = region_ranger(these_regions = "chr8:127735434-127742951")
+region_ranger(these_regions = "chr8:127735434-127742951")
+#>   region_start region_end type   gene_biotype hugo_symbol ensembl_gene_id chrom
+#> 1    127735434  127742951 gene         lncRNA      CASC11 ENSG00000249375  chr8
+#> 2    127735434  127742951 gene protein_coding         MYC ENSG00000136997  chr8
+#>       start       end width strand
+#> 1 127686343 127738987 52645      -
+#> 2 127735434 127742951  7518      +
 
 #Example 2 - Give the function multiple regions as a string
-my_regions = region_ranger(these_regions = c("chr8:128747680-128753674",
-                                             "chr18:60790579-60987361"),
-                            projection = "grch37")
+region_ranger(these_regions = c("chr8:128747680-128753674",
+              "chr18:60790579-60987361"),
+              projection = "grch37")
+#>   region_start region_end type   gene_biotype  hugo_symbol ensembl_gene_id
+#> 1     60790579   60987361 gene protein_coding         BCL2 ENSG00000171791
+#> 2     60790579   60987361 gene sense_intronic RP11-299P2.1 ENSG00000267766
+#> 3     60790579   60987361 gene         snoRNA       snoU13 ENSG00000238988
+#> 4     60790579   60987361 gene sense_intronic  RP11-28F1.2 ENSG00000267701
+#> 5    128747680  128753674 gene protein_coding          MYC ENSG00000136997
+#>   chrom     start       end  width strand
+#> 1    18  60790579  60987361 196783      -
+#> 2    18  60818347  60818553    207      -
+#> 3    18  60861822  60861898     77      -
+#> 4    18  60981035  60981315    281      -
+#> 5     8 128747680 128753674   5995      +
 
 #Example 3 - Individually specify the chromosome, start and end coordinates
-this_region = region_ranger(qchrom = "chr8",
-                            qstart = 127735434,
-                            qend = 127742951)
+region_ranger(qchrom = "chr8",
+              qstart = 127735434,
+              qend = 127742951)
+#>   region_start region_end type   gene_biotype hugo_symbol ensembl_gene_id chrom
+#> 1    127735434  127742951 gene         lncRNA      CASC11 ENSG00000249375  chr8
+#> 2    127735434  127742951 gene protein_coding         MYC ENSG00000136997  chr8
+#>       start       end width strand
+#> 1 127686343 127738987 52645      -
+#> 2 127735434 127742951  7518      +
 
 #Example 4 - Individually specify multiple regions with the query parameters
-these_regions = region_ranger(qchrom = c("chr8", "chr18"),
-                              qstart = c(128747680, 60790579),
-                              qend = c(128753674, 60987361),
-                              projection = "grch37")
-
+region_ranger(qchrom = c("chr8", "chr18"),
+              qstart = c(128747680, 60790579),
+              qend = c(128753674, 60987361),
+              projection = "grch37")
+#>   region_start region_end type   gene_biotype  hugo_symbol ensembl_gene_id
+#> 1     60790579   60987361 gene protein_coding         BCL2 ENSG00000171791
+#> 2     60790579   60987361 gene sense_intronic RP11-299P2.1 ENSG00000267766
+#> 3     60790579   60987361 gene         snoRNA       snoU13 ENSG00000238988
+#> 4     60790579   60987361 gene sense_intronic  RP11-28F1.2 ENSG00000267701
+#> 5    128747680  128753674 gene protein_coding          MYC ENSG00000136997
+#>   chrom     start       end  width strand
+#> 1    18  60790579  60987361 196783      -
+#> 2    18  60818347  60818553    207      -
+#> 3    18  60861822  60861898     77      -
+#> 4    18  60981035  60981315    281      -
+#> 5     8 128747680 128753674   5995      +
diff --git a/docs/search.json b/docs/search.json index b46961c..fddf422 100644 --- a/docs/search.json +++ b/docs/search.json @@ -1 +1 @@ -[{"path":"https://github.com/mattssca/BioMaesteR/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Adam Mattsson. Author, maintainer.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Mattsson (2024). BioMaesteR: package convenience functions generic genomic analysis within R. R package version 0.1.0.","code":"@Manual{, title = {BioMaesteR: A package with convenience functions for generic genomic analysis within R}, author = {Adam Mattsson}, year = {2024}, note = {R package version 0.1.0}, }"},{"path":[]},{"path":"https://github.com/mattssca/BioMaesteR/index.html","id":"biomaester","dir":"","previous_headings":"","what":"biomaesteR","title":"A package with convenience functions for generic genomic analysis within R","text":"biomaesteR, R package convenience functions commonly requested various types genomic analysis within R. package specialized provide bioinformatics infrastructure can used variety genomic analysis. repo also ongoing project intended demonstrating following best-practices development R packages. includes adequate package documentation (functions, bundled data objects, etc.), reproducible unit tests vignettes. Upon Pull Requests, repo also executes GitAction workflow package installed various environments thorough testing complete code base.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"A package with convenience functions for generic genomic analysis within R","text":"Open R studio run following command install development version GitHub:","code":"devtools::install_github(\"mattssca/BioMaesteR\")"},{"path":"https://github.com/mattssca/BioMaesteR/index.html","id":"website","dir":"","previous_headings":"","what":"Website","title":"A package with convenience functions for generic genomic analysis within R","text":"information, please visit BioMaesteR website.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":null,"dir":"Reference","previous_headings":"","what":"Bin Splitter — bin_splitter","title":"Bin Splitter — bin_splitter","text":"function takes region splits bins specified size.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Bin Splitter — bin_splitter","text":"","code":"bin_splitter( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, bin_size = 1000 )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Bin Splitter — bin_splitter","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. bin_size size bins split regions , default 1000.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Bin Splitter — bin_splitter","text":"data frame input regions binned specified bin size.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Bin Splitter — bin_splitter","text":"function internally calls purify_regions function properly format incoming regions.Thus, function can accept either data frame regions individual region coordinates.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Bin Splitter — bin_splitter","text":"","code":"#Example 1 - Call function with regions specified individually my_bins = bin_splitter(qchrom = c(\"chr1\", \"chr2\"), qstart = c(100, 200), qend = c(200, 300), bin_size = 10) #Example 2 - Call the funciton with regions from a data frame my_regions = purify_regions(these_regions = c(\"chr7:1000-500000\", \"chr8:50000-7000000\")) these_bins = bin_splitter(these_regions = my_regions, bin_size = 100000)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Centromeres grch37 — centromeres_grch37","title":"Centromeres grch37 — centromeres_grch37","text":"data frame centromeres coordinates respect grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Centromeres grch37 — centromeres_grch37","text":"","code":"centromeres_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Centromeres grch37 — centromeres_grch37","text":"## `centromeres_grch37` data frame 22 rows 4 columns. chrom Factor. Chromosomes without chr-prefix, 1:22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm, (always centromere).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Centromeres hg38 — centromeres_hg38","title":"Centromeres hg38 — centromeres_hg38","text":"data frame centromeres coordinates respect hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Centromeres hg38 — centromeres_hg38","text":"","code":"centromeres_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Centromeres hg38 — centromeres_hg38","text":"## `centromeres_hg38` data frame 22 rows 4 columns. chrom Factor. chr-prefixed chromosomes, chr1-chr22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm (always centromere).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Chromosome Arms grch37. — chromosome_arms_grch37","title":"Chromosome Arms grch37. — chromosome_arms_grch37","text":"data frame chromosome arm coordinates respect grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Chromosome Arms grch37. — chromosome_arms_grch37","text":"","code":"chromosome_arms_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Chromosome Arms grch37. — chromosome_arms_grch37","text":"## `chromosome_arms_grch37` data frame 44 rows 4 columns. chrom Factor. Chromosomes without chr-prefix, 1:22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm, either p q.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Chromosome Arms hg38. — chromosome_arms_hg38","title":"Chromosome Arms hg38. — chromosome_arms_hg38","text":"data frame chromosome arm coordinates respect hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Chromosome Arms hg38. — chromosome_arms_hg38","text":"","code":"chromosome_arms_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Chromosome Arms hg38. — chromosome_arms_hg38","text":"## `chromosome_arms_hg38` data frame 44 rows 4 columns. chrom Factor. chr-prefixed chromosomes, chr1-chr22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm, either p q.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":null,"dir":"Reference","previous_headings":"","what":"Cyto Ranger. — cyto_ranger","title":"Cyto Ranger. — cyto_ranger","text":"function takes region regions returns cytoband information region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Cyto Ranger. — cyto_ranger","text":"","code":"cyto_ranger( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, projection = \"hg38\" )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Cyto Ranger. — cyto_ranger","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Cyto Ranger. — cyto_ranger","text":"data frame cytoband information specified region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Cyto Ranger. — cyto_ranger","text":"Query region relevant cytoband information specified region(s). function accepts variety incoming regions. Either, regions can provided data frame `these_regions`. , following columns must exist; chrom, start, end. parameter (`these_regions`) also accept region \"region\" format, (.e chr:start-end). can region vector characters multiple regions. user can also individually specify region(s) ; `qchrom` (string), `qstart` (string, integer), `qend` (string integer). parameters can also accept vector characters multiple regions. function also handles chromosome prefixes returned object, based selected `projection`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Cyto Ranger. — cyto_ranger","text":"","code":"#' #Example 1 - Give the function one region as a string my_region = cyto_ranger(these_regions = \"chr8:127735434-127742951\") #Example 2 - Give the function multiple regions as a string my_regions = cyto_ranger(these_regions = c(\"chr8:128747680-128753674\", \"chr18:60790579-60987361\"), projection = \"grch37\") #Example 3 - Individually specify the chromosome, start and end coordinates this_region = cyto_ranger(qchrom = \"chr8\", qstart = 127735434, qend = 127742951) #Example 4 - Individually specify multiple regions with the query parameters these_regions = cyto_ranger(qchrom = c(\"chr8\", \"chr18\"), qstart = c(128747680, 60790579), qend = c(128753674, 60987361), projection = \"grch37\")"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Cytobands grch37 — cytobands_grch37","title":"Cytobands grch37 — cytobands_grch37","text":"data frame cytobands coordinates respect grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Cytobands grch37 — cytobands_grch37","text":"","code":"cytobands_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Cytobands grch37 — cytobands_grch37","text":"## `cytobands_grch37` data frame 862 rows 5 columns. chrom Factor. Chromosomes without chr-prefix, 1:22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. cytoBand Character. Cytoband name specified range. gieStain Factor. Giemsa Stain proporties described cyto band.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Cytobands hg38 — cytobands_hg38","title":"Cytobands hg38 — cytobands_hg38","text":"data frame cytobands coordinates respect hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Cytobands hg38 — cytobands_hg38","text":"","code":"cytobands_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Cytobands hg38 — cytobands_hg38","text":"## `cytobands_hg38` data frame 1549 rows 5 columns. chrom Factor. chr-prefixed chromosomes, chr1-chr22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. cytoBand Character. Cytoband name specified range. gieStain Factor. Giemsa Stain proporties described cyto band.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Gene Coordinates grch37. — gene_coordinates_grch37","title":"Gene Coordinates grch37. — gene_coordinates_grch37","text":"gene coordinates respect grch37. data set downloaded ensembl.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Gene Coordinates grch37. — gene_coordinates_grch37","text":"","code":"gene_coordinates_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Gene Coordinates grch37. — gene_coordinates_grch37","text":"## `gene_coordinates_grch37` data frame 57905 rows 5 columns. chrom Factor. chromosome (un-prefixed) gene residing . start Integer. start coordinates gene. end Integer. end coordinates gene. width Integer. width gene. strand Defined + forward - reverse. type Feature type name. Current allowed features ; gene, transcript, exon, CDS, Selenocysteine, start_codon, stop_codon UTR tag collection additional key value tags ccds_id CCDS identifier linked transcript ensembl_gene_id Character. Ensembl gene ID. hugo_symbol Character. Gene symbol Hugo format. source Name program generated feature, data source (database project name) score floating point value indiciating score feature gene_version stable identifier version gene gene_source annotation source gene gene_biotype biotype gene transcript_id stable identifier transcript transcript_version stable identifier version transcript transcript_name symbold transcript derived gene name transcript_source annotation source transcript transcript_biotype biotype transcript exon_number Position exon transcript exon_id stable identifier exon exon_version stable identifier version exon protein_id Stable identifier transcript's protein protein_version Stable identifier version transcript's protein","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Gene Coordinates hg38. — gene_coordinates_hg38","title":"Gene Coordinates hg38. — gene_coordinates_hg38","text":"gene coordinates respect hg38. data set downloaded ensembl.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Gene Coordinates hg38. — gene_coordinates_hg38","text":"","code":"gene_coordinates_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Gene Coordinates hg38. — gene_coordinates_hg38","text":"## `gene_coordinates_hg38` data frame 62754 rows 5 columns. chrom Factor. chromosome (un-prefixed) gene residing . start Integer. start coordinates gene. end Integer. end coordinates gene. width Integer. width gene. strand Defined + forward - reverse. type Feature type name. Current allowed features ; gene, transcript, exon, CDS, Selenocysteine, start_codon, stop_codon UTR tag collection additional key value tags ccds_id CCDS identifier linked transcript ensembl_gene_id Character. Ensembl gene ID. hugo_symbol Character. Gene symbol Hugo format. source Name program generated feature, data source (database project name) score floating point value indiciating score feature gene_version stable identifier version gene gene_source annotation source gene gene_biotype biotype gene transcript_id stable identifier transcript transcript_version stable identifier version transcript transcript_name symbold transcript derived gene name transcript_source annotation source transcript transcript_biotype biotype transcript exon_number Position exon transcript exon_id stable identifier exon exon_version stable identifier version exon protein_id Stable identifier transcript's protein protein_version Stable identifier version transcript's protein","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":null,"dir":"Reference","previous_headings":"","what":"Gene Ranger. — gene_ranger","title":"Gene Ranger. — gene_ranger","text":"Return coordinates different formats one gene set genes.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Gene Ranger. — gene_ranger","text":"","code":"gene_ranger( these_genes = NULL, projection = \"hg38\", return_as = \"data.frame\", write_to_bed = FALSE, bed_path = NULL, track_name = NULL, track_description = NULL )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Gene Ranger. — gene_ranger","text":"these_genes Specify genes interest. function accepts multiple genes. Genes can specified either Hugo Format Ensembl IDs. function figure format requesting. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38. return_as Speciy format returned object. Possible values ; data.frame (default). mode, following columns kept; chrom, start, end, width, strand, gene_biotype, gene symbol (Hugo Ensembl format, depending user specifies `these_genes`). `return_as = \"bed\"`, function returns standard bed columns chrom, start, end. also attaches following optional columns; score strand. user can also request return \"region\" format (chr:start-end). write_to_bed Boolean parameter. Set TRUE (default FALSE) write output bed file. bed_path `write_to_bed = TRUE`, parameter required. Specify path generated ebd file. track_name `write_to_bed = TRUE`, parameter required. Specify track name generated bed file. track_description `write_to_bed = TRUE`, parameter required. Specify track description generated bed file.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Gene Ranger. — gene_ranger","text":"data frame coordinates requested gene. See `return_as` information controlling return function.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Gene Ranger. — gene_ranger","text":"function takes gene set genes `these_genes` parameter returns genomic coordinates selected projection. Genes can formatted one following formats; Hugo Symbol Ensembl Gene ID. user gets decide projection `projection` parameter (hg38 grch37 available). Furthermore, function flexible return formats available. information see parameter description `return_as`. Note user sets `write_to_bed = TRUE`, function writes bed file (.e nothing returned).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Gene Ranger. — gene_ranger","text":"","code":"#Example 1 - Request one gene (in Hugo format) and with default parameters hugo_myc = gene_ranger(these_genes = \"MYC\") #Example 2 - Same as example one but MYC is here specified as Ensembl ID ensembl_myc = gene_ranger(these_genes = \"ENSG00000136997\") #Example 3 - Request multiple genes with non-default parameters my_genes = gene_ranger(these_genes = c(\"MYC\", \"BCL2\"), projection = \"grch37\", return_as = \"region\") #Example 4 - Request multiple Ensembl IDs and return in bed format my_bed = gene_ranger(these_genes = c(\"ENSG00000136997\", \"ENSG00000171791\"), return_as = \"bed\") #Example 5 - Write to bed file gene_ranger(these_genes = c(\"BCL2\", \"MYC\"), projection = \"grch37\", write_to_bed = TRUE, bed_path = \"my_bed\", track_name = \"MYC and BCL2\", track_description = \"Genes of interest\") #> SUCCESS! bed file written to my_bed #> NULL"},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":null,"dir":"Reference","previous_headings":"","what":"Get Gene Info — get_gene_info","title":"Get Gene Info — get_gene_info","text":"Convenience function returning information gene set genes. function internally called [BioMaesteR::get_gene_region].","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Get Gene Info — get_gene_info","text":"","code":"get_gene_info(these_genes = NULL, projection = \"hg38\", raw = FALSE)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Get Gene Info — get_gene_info","text":"these_genes Required argument. gene genes interest. projection desired projection, default hg38. raw Default FALSE, set TRUE keeping columns.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Get Gene Info — get_gene_info","text":"data frame gene information.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Get Gene Info — get_gene_info","text":"Give function gene set genes (vector characters), specify projection (, hg38 default projection) return gene information based bundled data. default function run `raw = FALSE`, returns subset columns. instead user wants everything back (.e available columns) toggle `raw` `TRUE`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Get Gene Info — get_gene_info","text":"","code":"#Example 1 - Query one gene (in Hugo format) and with default parameters. hugo_myc = get_gene_info(these_genes = \"MYC\") #Example 2 - Same as example 1 but MYC is here specified as Ensembl ID. ensembl_myc = get_gene_info(these_genes = \"ENSG00000136997\") #Example 3 - Request multiple genes with non-default parameters hugo_genes = get_gene_info(these_genes = c(\"MYC\", \"BCL2\"), projection = \"grch37\") #Example 4 - Request multiple Ensembl IDs and return all columns. ensembl_genes = get_gene_info(these_genes = c(\"ENSG00000136997\", \"ENSG00000171791\"), raw = TRUE)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":null,"dir":"Reference","previous_headings":"","what":"Purify Chromosomes. — purify_chr","title":"Purify Chromosomes. — purify_chr","text":"Helper function dealing chromosome prefixes based selected projection.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Purify Chromosomes. — purify_chr","text":"","code":"purify_chr(projection = NULL, incoming_table = NULL)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Purify Chromosomes. — purify_chr","text":"projection Required parameter, needed determine chromosomes prefixed . incoming_table Required parameter, data frame check prefixes.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Purify Chromosomes. — purify_chr","text":"data frame columns incoming data frame, prefixes added removed based selected projection.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Purify Chromosomes. — purify_chr","text":"function accepts data frame column check prefixes. function add remove prefixes based selected projection. function expects column named \"chrom\" incoming data frame.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Purify Chromosomes. — purify_chr","text":"","code":"#Example 1 - Add prefixes to a data frame my_data = data.frame(chrom = c(\"1\", \"2\", \"3\")) my_data = purify_chr(projection = \"hg38\", incoming_table = my_data)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":null,"dir":"Reference","previous_headings":"","what":"Purify Regions. — purify_regions","title":"Purify Regions. — purify_regions","text":"Helper function cleaning standardize regions.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Purify Regions. — purify_regions","text":"","code":"purify_regions( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, projection = \"hg38\" )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Purify Regions. — purify_regions","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Purify Regions. — purify_regions","text":"data table three columns, chrom, start, end.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Purify Regions. — purify_regions","text":"function accepts variety incoming regions. Either, regions can provided data frame `these_regions`. , following columns must exist; chrom, start, end. parameter (`these_regions`) also accept region \"region\" format, (.e chr:start-end). can region vector characters multiple regions. user can also individually specify region(s) ; `qchrom` (string), `qstart` (string, integer), `qend` (string integer). parameters can also accept vector characters multiple regions. function also handles chromosome prefixes returned object, based selected `projection`. addition, function also checks provided start coordinate equal greater end coordinate chromosome. also ensures specified ranges within actual chromosomal range.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Purify Regions. — purify_regions","text":"","code":"#Example 1 - Give the function one region as a string my_region = purify_regions(these_regions = \"chr1:100-500\") #Example 2 - Give the function multiple regions as a string my_regions = purify_regions(these_regions = c(\"chr1:100-500\", \"chr2:100-500\"), projection = \"grch37\") #Example 3 - Individually specify the chromosome, start and end coordinates this_region = purify_regions(qchrom = \"chr1\", qstart = 100, qend = 500) #Example 4 - Individually specify multiple regions with the query parameters these_regions = purify_regions(qchrom = c(\"chr1\", \"chr2\"), qstart = c(100, 200), qend = c(500, 600), projection = \"grch37\")"},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":null,"dir":"Reference","previous_headings":"","what":"Region Ranger. — region_ranger","title":"Region Ranger. — region_ranger","text":"Return genes residing defined region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Region Ranger. — region_ranger","text":"","code":"region_ranger( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, projection = \"hg38\", raw = FALSE )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Region Ranger. — region_ranger","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38. raw Set TRUE return columns. Default FALSE.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Region Ranger. — region_ranger","text":"data frame genomic events residing specified region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Region Ranger. — region_ranger","text":"Query region return genomic events residing inside specified region. function accepts variety incoming regions. Either, regions can provided data frame `these_regions`. , following columns must exist; chrom, start, end. parameter (`these_regions`) also accept region \"region\" format, (.e chr:start-end). can region vector characters multiple regions. user can also individually specify region(s) ; `qchrom` (string), `qstart` (string, integer), `qend` (string integer). parameters can also accept vector characters multiple regions. function also handles chromosome prefixes returned object, based selected `projection`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Region Ranger. — region_ranger","text":"","code":"#Example 1 - Give the function one region as a string my_region = region_ranger(these_regions = \"chr8:127735434-127742951\") #Example 2 - Give the function multiple regions as a string my_regions = region_ranger(these_regions = c(\"chr8:128747680-128753674\", \"chr18:60790579-60987361\"), projection = \"grch37\") #Example 3 - Individually specify the chromosome, start and end coordinates this_region = region_ranger(qchrom = \"chr8\", qstart = 127735434, qend = 127742951) #Example 4 - Individually specify multiple regions with the query parameters these_regions = region_ranger(qchrom = c(\"chr8\", \"chr18\"), qstart = c(128747680, 60790579), qend = c(128753674, 60987361), projection = \"grch37\")"},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":null,"dir":"Reference","previous_headings":"","what":"Sanity Check Regions. — sanity_check_regions","title":"Sanity Check Regions. — sanity_check_regions","text":"Helper function ensuring provided regions valid.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Sanity Check Regions. — sanity_check_regions","text":"","code":"sanity_check_regions(incoming_regions = NULL, projection = NULL)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Sanity Check Regions. — sanity_check_regions","text":"incoming_regions data frame regions following columns; chrom, start, end. projection projection.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Sanity Check Regions. — sanity_check_regions","text":"Nothing.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Sanity Check Regions. — sanity_check_regions","text":"function checks provided start coordinate equal greater end coordinate chromosome. also ensures specified ranges within actual chromosomal range.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Sanity Check Regions. — sanity_check_regions","text":"","code":"#Example 1 - Give the function one region as a string my_regions = data.frame(chrom = c(\"chr1\", \"chr2\"), start = c(100, 100), end = c(200, 200)) sanity_check_regions(incoming_regions = my_regions, projection = \"hg38\") #> NULL"}] +[{"path":"https://github.com/mattssca/BioMaesteR/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Adam Mattsson. Author, maintainer.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Mattsson (2024). BioMaesteR: package convenience functions generic genomic analysis within R. R package version 0.1.0.","code":"@Manual{, title = {BioMaesteR: A package with convenience functions for generic genomic analysis within R}, author = {Adam Mattsson}, year = {2024}, note = {R package version 0.1.0}, }"},{"path":[]},{"path":"https://github.com/mattssca/BioMaesteR/index.html","id":"biomaester","dir":"","previous_headings":"","what":"biomaesteR","title":"A package with convenience functions for generic genomic analysis within R","text":"biomaesteR, R package convenience functions commonly requested various types genomic analysis within R. package specialized provide bioinformatics infrastructure can used variety genomic analysis. repo also ongoing project intended demonstrating following best-practices development R packages. includes adequate package documentation (functions, bundled data objects, etc.), reproducible unit tests vignettes. Upon Pull Requests, repo also executes GitAction workflow package installed various environments thorough testing complete code base.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"A package with convenience functions for generic genomic analysis within R","text":"Open R studio run following command install development version GitHub:","code":"devtools::install_github(\"mattssca/BioMaesteR\")"},{"path":"https://github.com/mattssca/BioMaesteR/index.html","id":"website","dir":"","previous_headings":"","what":"Website","title":"A package with convenience functions for generic genomic analysis within R","text":"information, please visit BioMaesteR website.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":null,"dir":"Reference","previous_headings":"","what":"Bin Splitter — bin_splitter","title":"Bin Splitter — bin_splitter","text":"function takes region splits bins specified size.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Bin Splitter — bin_splitter","text":"","code":"bin_splitter( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, bin_size = 1000 )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Bin Splitter — bin_splitter","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. bin_size size bins split regions , default 1000.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Bin Splitter — bin_splitter","text":"data frame input regions binned specified bin size.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Bin Splitter — bin_splitter","text":"function internally calls purify_regions function properly format incoming regions.Thus, function can accept either data frame regions individual region coordinates.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/bin_splitter.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Bin Splitter — bin_splitter","text":"","code":"#Example 1 - Call function with regions specified individually my_bins = bin_splitter(qchrom = c(\"chr1\", \"chr2\"), qstart = c(100, 200), qend = c(200, 300), bin_size = 10) head(my_bins, 5) #> bin_chr bin_start bin_end #> 1 chr1 100 110 #> 2 chr1 110 120 #> 3 chr1 120 130 #> 4 chr1 130 140 #> 5 chr1 140 150 #Example 2 - Call the function with regions from a data frame my_regions = purify_regions(these_regions = c(\"chr7:1000-500000\", \"chr8:50000-7000000\")) these_bins = bin_splitter(these_regions = my_regions, bin_size = 100000) head(these_bins, 5) #> bin_chr bin_start bin_end #> 1 chr7 1000 101000 #> 2 chr7 101000 201000 #> 3 chr7 201000 301000 #> 4 chr7 301000 401000 #> 5 chr8 50000 150000"},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Centromeres grch37 — centromeres_grch37","title":"Centromeres grch37 — centromeres_grch37","text":"data frame centromeres coordinates respect grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Centromeres grch37 — centromeres_grch37","text":"","code":"centromeres_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Centromeres grch37 — centromeres_grch37","text":"## `centromeres_grch37` data frame 22 rows 4 columns. chrom Factor. Chromosomes without chr-prefix, 1:22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm, (always centromere).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Centromeres hg38 — centromeres_hg38","title":"Centromeres hg38 — centromeres_hg38","text":"data frame centromeres coordinates respect hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Centromeres hg38 — centromeres_hg38","text":"","code":"centromeres_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/centromeres_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Centromeres hg38 — centromeres_hg38","text":"## `centromeres_hg38` data frame 22 rows 4 columns. chrom Factor. chr-prefixed chromosomes, chr1-chr22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm (always centromere).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Chromosome Arms grch37. — chromosome_arms_grch37","title":"Chromosome Arms grch37. — chromosome_arms_grch37","text":"data frame chromosome arm coordinates respect grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Chromosome Arms grch37. — chromosome_arms_grch37","text":"","code":"chromosome_arms_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Chromosome Arms grch37. — chromosome_arms_grch37","text":"## `chromosome_arms_grch37` data frame 44 rows 4 columns. chrom Factor. Chromosomes without chr-prefix, 1:22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm, either p q.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Chromosome Arms hg38. — chromosome_arms_hg38","title":"Chromosome Arms hg38. — chromosome_arms_hg38","text":"data frame chromosome arm coordinates respect hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Chromosome Arms hg38. — chromosome_arms_hg38","text":"","code":"chromosome_arms_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/chromosome_arms_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Chromosome Arms hg38. — chromosome_arms_hg38","text":"## `chromosome_arms_hg38` data frame 44 rows 4 columns. chrom Factor. chr-prefixed chromosomes, chr1-chr22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. arm Factor. Chromosome arm, either p q.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":null,"dir":"Reference","previous_headings":"","what":"Cyto Ranger. — cyto_ranger","title":"Cyto Ranger. — cyto_ranger","text":"function takes region regions returns cytoband information region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Cyto Ranger. — cyto_ranger","text":"","code":"cyto_ranger( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, projection = \"hg38\" )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Cyto Ranger. — cyto_ranger","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Cyto Ranger. — cyto_ranger","text":"data frame cytoband information specified region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Cyto Ranger. — cyto_ranger","text":"Query region relevant cytoband information specified region(s). function accepts variety incoming regions. Either, regions can provided data frame `these_regions`. , following columns must exist; chrom, start, end. parameter (`these_regions`) also accept region \"region\" format, (.e chr:start-end). can region vector characters multiple regions. user can also individually specify region(s) ; `qchrom` (string), `qstart` (string, integer), `qend` (string integer). parameters can also accept vector characters multiple regions. function also handles chromosome prefixes returned object, based selected `projection`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cyto_ranger.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Cyto Ranger. — cyto_ranger","text":"","code":"#' #Example 1 - Give the function one region as a string cyto_ranger(these_regions = \"chr8:127735434-127742951\") #> chrom region_start region_end cytoBand cytoband_start cytoband_end #> 1 chr8 127735434 127742951 q24.21 126300000 130400000 #Example 2 - Give the function multiple regions as a string cyto_ranger(these_regions = c(\"chr8:128747680-128753674\", \"chr18:60790579-60987361\"), projection = \"grch37\") #> chrom region_start region_end cytoBand cytoband_start cytoband_end #> 1 18 60790579 60987361 q21.33 59000000 61600000 #> 2 8 128747680 128753674 q24.21 127300000 131500000 #Example 3 - Individually specify the chromosome, start and end coordinates cyto_ranger(qchrom = \"chr8\", qstart = 127735434, qend = 127742951) #> chrom region_start region_end cytoBand cytoband_start cytoband_end #> 1 chr8 127735434 127742951 q24.21 126300000 130400000 #Example 4 - Individually specify multiple regions with the query parameters cyto_ranger(qchrom = c(\"chr8\", \"chr18\"), qstart = c(128747680, 60790579), qend = c(128753674, 60987361), projection = \"grch37\") #> chrom region_start region_end cytoBand cytoband_start cytoband_end #> 1 18 60790579 60987361 q21.33 59000000 61600000 #> 2 8 128747680 128753674 q24.21 127300000 131500000"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Cytobands grch37 — cytobands_grch37","title":"Cytobands grch37 — cytobands_grch37","text":"data frame cytobands coordinates respect grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Cytobands grch37 — cytobands_grch37","text":"","code":"cytobands_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Cytobands grch37 — cytobands_grch37","text":"## `cytobands_grch37` data frame 862 rows 5 columns. chrom Factor. Chromosomes without chr-prefix, 1:22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. cytoBand Character. Cytoband name specified range. gieStain Factor. Giemsa Stain proporties described cyto band.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Cytobands hg38 — cytobands_hg38","title":"Cytobands hg38 — cytobands_hg38","text":"data frame cytobands coordinates respect hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Cytobands hg38 — cytobands_hg38","text":"","code":"cytobands_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/cytobands_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Cytobands hg38 — cytobands_hg38","text":"## `cytobands_hg38` data frame 1549 rows 5 columns. chrom Factor. chr-prefixed chromosomes, chr1-chr22. start Integer. Start coordinates specified chromosome arm. end Integer. End coordinates specified chromosome arm. cytoBand Character. Cytoband name specified range. gieStain Factor. Giemsa Stain proporties described cyto band.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_grch37.html","id":null,"dir":"Reference","previous_headings":"","what":"Gene Coordinates grch37. — gene_coordinates_grch37","title":"Gene Coordinates grch37. — gene_coordinates_grch37","text":"gene coordinates respect grch37. data set downloaded ensembl.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_grch37.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Gene Coordinates grch37. — gene_coordinates_grch37","text":"","code":"gene_coordinates_grch37"},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_grch37.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Gene Coordinates grch37. — gene_coordinates_grch37","text":"## `gene_coordinates_grch37` data frame 57905 rows 5 columns. chrom Factor. chromosome (un-prefixed) gene residing . start Integer. start coordinates gene. end Integer. end coordinates gene. width Integer. width gene. strand Defined + forward - reverse. type Feature type name. Current allowed features ; gene, transcript, exon, CDS, Selenocysteine, start_codon, stop_codon UTR tag collection additional key value tags ccds_id CCDS identifier linked transcript ensembl_gene_id Character. Ensembl gene ID. hugo_symbol Character. Gene symbol Hugo format. source Name program generated feature, data source (database project name) score floating point value indiciating score feature gene_version stable identifier version gene gene_source annotation source gene gene_biotype biotype gene transcript_id stable identifier transcript transcript_version stable identifier version transcript transcript_name symbold transcript derived gene name transcript_source annotation source transcript transcript_biotype biotype transcript exon_number Position exon transcript exon_id stable identifier exon exon_version stable identifier version exon protein_id Stable identifier transcript's protein protein_version Stable identifier version transcript's protein","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_hg38.html","id":null,"dir":"Reference","previous_headings":"","what":"Gene Coordinates hg38. — gene_coordinates_hg38","title":"Gene Coordinates hg38. — gene_coordinates_hg38","text":"gene coordinates respect hg38. data set downloaded ensembl.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_hg38.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Gene Coordinates hg38. — gene_coordinates_hg38","text":"","code":"gene_coordinates_hg38"},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_coordinates_hg38.html","id":"format","dir":"Reference","previous_headings":"","what":"Format","title":"Gene Coordinates hg38. — gene_coordinates_hg38","text":"## `gene_coordinates_hg38` data frame 62754 rows 5 columns. chrom Factor. chromosome (un-prefixed) gene residing . start Integer. start coordinates gene. end Integer. end coordinates gene. width Integer. width gene. strand Defined + forward - reverse. type Feature type name. Current allowed features ; gene, transcript, exon, CDS, Selenocysteine, start_codon, stop_codon UTR tag collection additional key value tags ccds_id CCDS identifier linked transcript ensembl_gene_id Character. Ensembl gene ID. hugo_symbol Character. Gene symbol Hugo format. source Name program generated feature, data source (database project name) score floating point value indiciating score feature gene_version stable identifier version gene gene_source annotation source gene gene_biotype biotype gene transcript_id stable identifier transcript transcript_version stable identifier version transcript transcript_name symbold transcript derived gene name transcript_source annotation source transcript transcript_biotype biotype transcript exon_number Position exon transcript exon_id stable identifier exon exon_version stable identifier version exon protein_id Stable identifier transcript's protein protein_version Stable identifier version transcript's protein","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":null,"dir":"Reference","previous_headings":"","what":"Gene Ranger. — gene_ranger","title":"Gene Ranger. — gene_ranger","text":"Return coordinates different formats one gene set genes.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Gene Ranger. — gene_ranger","text":"","code":"gene_ranger( these_genes = NULL, projection = \"hg38\", return_as = \"data.frame\", write_to_bed = FALSE, bed_path = NULL, track_name = NULL, track_description = NULL )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Gene Ranger. — gene_ranger","text":"these_genes Specify genes interest. function accepts multiple genes. Genes can specified either Hugo Format Ensembl IDs. function figure format requesting. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38. return_as Speciy format returned object. Possible values ; data.frame (default). mode, following columns kept; chrom, start, end, width, strand, gene_biotype, gene symbol (Hugo Ensembl format, depending user specifies `these_genes`). `return_as = \"bed\"`, function returns standard bed columns chrom, start, end. also attaches following optional columns; score strand. user can also request return \"region\" format (chr:start-end). write_to_bed Boolean parameter. Set TRUE (default FALSE) write output bed file. bed_path `write_to_bed = TRUE`, parameter required. Specify path generated ebd file. track_name `write_to_bed = TRUE`, parameter required. Specify track name generated bed file. track_description `write_to_bed = TRUE`, parameter required. Specify track description generated bed file.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Gene Ranger. — gene_ranger","text":"data frame coordinates requested gene. See `return_as` information controlling return function.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Gene Ranger. — gene_ranger","text":"function takes gene set genes `these_genes` parameter returns genomic coordinates selected projection. Genes can formatted one following formats; Hugo Symbol Ensembl Gene ID. user gets decide projection `projection` parameter (hg38 grch37 available). Furthermore, function flexible return formats available. information see parameter description `return_as`. Note user sets `write_to_bed = TRUE`, function writes bed file (.e nothing returned).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/gene_ranger.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Gene Ranger. — gene_ranger","text":"","code":"#Example 1 - Request one gene (in Hugo format) and with default parameters gene_ranger(these_genes = \"MYC\") #> chrom start end width strand gene_biotype hugo_symbol #> 1 chr8 127735434 127742951 7518 + protein_coding MYC #Example 2 - Same as example one but MYC is here specified as Ensembl ID gene_ranger(these_genes = \"ENSG00000136997\") #> chrom start end width strand gene_biotype ensembl_gene_id #> 1 chr8 127735434 127742951 7518 + protein_coding ENSG00000136997 #Example 3 - Request multiple genes with non-default parameters gene_ranger(these_genes = c(\"MYC\", \"BCL2\"), projection = \"grch37\", return_as = \"region\") #> MYC BCL2 #> \"8:128747680-128753674\" \"18:60790579-60987361\" #Example 4 - Request multiple Ensembl IDs and return in bed format gene_ranger(these_genes = c(\"ENSG00000136997\", \"ENSG00000171791\"), return_as = \"bed\") #> chrom start end score strand #> 1 chr18 63123346 63320128 NA - #> 2 chr8 127735434 127742951 NA + #Example 5 - Write to bed file gene_ranger(these_genes = c(\"BCL2\", \"MYC\"), projection = \"grch37\", write_to_bed = TRUE, bed_path = \"my_bed\", track_name = \"MYC and BCL2\", track_description = \"Genes of interest\") #> SUCCESS! bed file written to my_bed #> NULL"},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":null,"dir":"Reference","previous_headings":"","what":"Get Gene Info — get_gene_info","title":"Get Gene Info — get_gene_info","text":"Convenience function returning information gene set genes. function internally called [BioMaesteR::get_gene_region].","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Get Gene Info — get_gene_info","text":"","code":"get_gene_info(these_genes = NULL, projection = \"hg38\", raw = FALSE)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Get Gene Info — get_gene_info","text":"these_genes Required argument. gene genes interest. projection desired projection, default hg38. raw Default FALSE, set TRUE keeping columns.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Get Gene Info — get_gene_info","text":"data frame gene information.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Get Gene Info — get_gene_info","text":"Give function gene set genes (vector characters), specify projection (, hg38 default projection) return gene information based bundled data. default function run `raw = FALSE`, returns subset columns. instead user wants everything back (.e available columns) toggle `raw` `TRUE`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/get_gene_info.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Get Gene Info — get_gene_info","text":"","code":"#Example 1 - Query one gene (in Hugo format) and with default parameters. get_gene_info(these_genes = \"MYC\") #> hugo_symbol ensembl_gene_id type gene_biotype source gene_version #> 1 MYC ENSG00000136997 gene protein_coding ensembl_havana 22 #> gene_source tag ccds_id score transcript_id transcript_version #> 1 ensembl_havana NA #> transcript_name transcript_source transcript_biotype exon_number exon_id #> 1 #> protein_id protein_version #> 1 #Example 2 - Same as example 1 but MYC is here specified as Ensembl ID. get_gene_info(these_genes = \"ENSG00000136997\") #> ensembl_gene_id hugo_symbol type gene_biotype source gene_version #> 1 ENSG00000136997 MYC gene protein_coding ensembl_havana 22 #> gene_source tag ccds_id score transcript_id transcript_version #> 1 ensembl_havana NA #> transcript_name transcript_source transcript_biotype exon_number exon_id #> 1 #> protein_id protein_version #> 1 #Example 3 - Request multiple genes with non-default parameters get_gene_info(these_genes = c(\"MYC\", \"BCL2\"), projection = \"grch37\") #> hugo_symbol ensembl_gene_id type gene_biotype source gene_version #> 1 MYC ENSG00000136997 gene protein_coding ensembl_havana 10 #> 2 BCL2 ENSG00000171791 gene protein_coding ensembl_havana 10 #> gene_source tag ccds_id score transcript_id transcript_version #> 1 ensembl_havana NA #> 2 ensembl_havana NA #> transcript_name transcript_source transcript_biotype exon_number exon_id #> 1 #> 2 #> protein_id protein_version #> 1 #> 2 #Example 4 - Request multiple Ensembl IDs and return all columns. get_gene_info(these_genes = c(\"ENSG00000136997\", \"ENSG00000171791\"), raw = TRUE) #> chrom start end width strand type tag ccds_id ensembl_gene_id #> 1 chr18 63123346 63320128 196783 - gene ENSG00000171791 #> 2 chr8 127735434 127742951 7518 + gene ENSG00000136997 #> hugo_symbol source score gene_version gene_source gene_biotype #> 1 BCL2 ensembl_havana NA 14 ensembl_havana protein_coding #> 2 MYC ensembl_havana NA 22 ensembl_havana protein_coding #> transcript_id transcript_version transcript_name transcript_source #> 1 #> 2 #> transcript_biotype exon_number exon_id exon_version protein_id #> 1 #> 2 #> protein_version input_format #> 1 Ensembl #> 2 Ensembl"},{"path":"https://github.com/mattssca/BioMaesteR/reference/power_lifter.html","id":null,"dir":"Reference","previous_headings":"","what":"Power Lifter — power_lifter","title":"Power Lifter — power_lifter","text":"function convert genomic regions one assembly another.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/power_lifter.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Power Lifter — power_lifter","text":"","code":"power_lifter( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, original_assembly = \"hg38\", target_assembly = \"grch37\" )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/power_lifter.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Power Lifter — power_lifter","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. original_assembly original assembly regions. Default hg38 target_assembly target assembly regions. Default grch37.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/power_lifter.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Power Lifter — power_lifter","text":"data frame regions selected target assembly.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/power_lifter.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Power Lifter — power_lifter","text":"function wrapper [rtracklayer::liftOver] function. Specify original assembly target assembly, function convert regions accordingly. Regions can provided data frame `these_regions`, string `qchrom`, `qstart`, `qend`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/power_lifter.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Power Lifter — power_lifter","text":"","code":"#Example 1 - Convert MYC region from hg38 to grch37 power_lifter(these_regions = \"chr8:127735434-127742951\") #> chrom start end width strand #> 1 8 128747680 128755197 7518 * #Example 2 - Convert MYC region from grch37 to hg38 power_lifter(these_regions = \"18:60790579-60987361\", original_assembly = \"grch37\", target_assembly = \"hg38\") #> Discarding unchained sequences: 18 #> [1] chrom start end width strand #> <0 rows> (or 0-length row.names) #Example 3 - Same as Example 1, but use the `qchrom`, `qstart`, and `qend`. power_lifter(qchrom = \"chr8\", qstart = 127735434, qend = 127742951) #> chrom start end width strand #> 1 8 128747680 128755197 7518 *"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":null,"dir":"Reference","previous_headings":"","what":"Purify Chromosomes. — purify_chr","title":"Purify Chromosomes. — purify_chr","text":"Helper function dealing chromosome prefixes based selected projection.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Purify Chromosomes. — purify_chr","text":"","code":"purify_chr(projection = NULL, incoming_table = NULL)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Purify Chromosomes. — purify_chr","text":"projection Required parameter, needed determine chromosomes prefixed . incoming_table Required parameter, data frame check prefixes.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Purify Chromosomes. — purify_chr","text":"data frame columns incoming data frame, prefixes added removed based selected projection.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Purify Chromosomes. — purify_chr","text":"function accepts data frame column check prefixes. function add remove prefixes based selected projection. function expects column named \"chrom\" incoming data frame.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_chr.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Purify Chromosomes. — purify_chr","text":"","code":"#Example 1 - Add prefixes to a data frame my_data = data.frame(chrom = c(\"1\", \"2\", \"3\")) purify_chr(projection = \"hg38\", incoming_table = my_data) #> chrom #> 1 chr1 #> 2 chr2 #> 3 chr3"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":null,"dir":"Reference","previous_headings":"","what":"Purify Regions. — purify_regions","title":"Purify Regions. — purify_regions","text":"Helper function cleaning standardize regions.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Purify Regions. — purify_regions","text":"","code":"purify_regions( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, projection = \"hg38\" )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Purify Regions. — purify_regions","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Purify Regions. — purify_regions","text":"data table three columns, chrom, start, end.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Purify Regions. — purify_regions","text":"function accepts variety incoming regions. Either, regions can provided data frame `these_regions`. , following columns must exist; chrom, start, end. parameter (`these_regions`) also accept region \"region\" format, (.e chr:start-end). can region vector characters multiple regions. user can also individually specify region(s) ; `qchrom` (string), `qstart` (string, integer), `qend` (string integer). parameters can also accept vector characters multiple regions. function also handles chromosome prefixes returned object, based selected `projection`. addition, function also checks provided start coordinate equal greater end coordinate chromosome. also ensures specified ranges within actual chromosomal range.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/purify_regions.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Purify Regions. — purify_regions","text":"","code":"#Example 1 - Give the function one region as a string purify_regions(these_regions = \"chr1:100-500\") #> chrom start end #> 1: chr1 100 500 #Example 2 - Give the function multiple regions as a string purify_regions(these_regions = c(\"chr1:100-500\", \"chr2:100-500\"), projection = \"grch37\") #> chrom start end #> 1: 1 100 500 #> 2: 2 100 500 #Example 3 - Individually specify the chromosome, start and end coordinates purify_regions(qchrom = \"chr1\", qstart = 100, qend = 500) #> chrom start end #> 1: chr1 100 500 #Example 4 - Individually specify multiple regions with the query parameters purify_regions(qchrom = c(\"chr1\", \"chr2\"), qstart = c(100, 200), qend = c(500, 600), projection = \"grch37\") #> chrom start end #> 1: 1 100 500 #> 2: 2 200 600"},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":null,"dir":"Reference","previous_headings":"","what":"Region Ranger. — region_ranger","title":"Region Ranger. — region_ranger","text":"Return genes residing defined region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Region Ranger. — region_ranger","text":"","code":"region_ranger( these_regions = NULL, qchrom = NULL, qstart = NULL, qend = NULL, projection = \"hg38\", raw = FALSE )"},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Region Ranger. — region_ranger","text":"these_regions region(s) queried. Can data frame regions following columns; chrom, start, end. string following format chr:start-end. qchrom Query chromosome (prefixed un-prefixed), Required `these_regions` provided. qstart Query start position. Required `these_regions` provided. qend Query end position. Required `these_regions` provided. projection desired projection want back coordinates . Available projections hg38 grch37. Default hg38. raw Set TRUE return columns. Default FALSE.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Region Ranger. — region_ranger","text":"data frame genomic events residing specified region(s).","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Region Ranger. — region_ranger","text":"Query region return genomic events residing inside specified region. function accepts variety incoming regions. Either, regions can provided data frame `these_regions`. , following columns must exist; chrom, start, end. parameter (`these_regions`) also accept region \"region\" format, (.e chr:start-end). can region vector characters multiple regions. user can also individually specify region(s) ; `qchrom` (string), `qstart` (string, integer), `qend` (string integer). parameters can also accept vector characters multiple regions. function also handles chromosome prefixes returned object, based selected `projection`.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/region_ranger.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Region Ranger. — region_ranger","text":"","code":"#Example 1 - Give the function one region as a string region_ranger(these_regions = \"chr8:127735434-127742951\") #> region_start region_end type gene_biotype hugo_symbol ensembl_gene_id chrom #> 1 127735434 127742951 gene lncRNA CASC11 ENSG00000249375 chr8 #> 2 127735434 127742951 gene protein_coding MYC ENSG00000136997 chr8 #> start end width strand #> 1 127686343 127738987 52645 - #> 2 127735434 127742951 7518 + #Example 2 - Give the function multiple regions as a string region_ranger(these_regions = c(\"chr8:128747680-128753674\", \"chr18:60790579-60987361\"), projection = \"grch37\") #> region_start region_end type gene_biotype hugo_symbol ensembl_gene_id #> 1 60790579 60987361 gene protein_coding BCL2 ENSG00000171791 #> 2 60790579 60987361 gene sense_intronic RP11-299P2.1 ENSG00000267766 #> 3 60790579 60987361 gene snoRNA snoU13 ENSG00000238988 #> 4 60790579 60987361 gene sense_intronic RP11-28F1.2 ENSG00000267701 #> 5 128747680 128753674 gene protein_coding MYC ENSG00000136997 #> chrom start end width strand #> 1 18 60790579 60987361 196783 - #> 2 18 60818347 60818553 207 - #> 3 18 60861822 60861898 77 - #> 4 18 60981035 60981315 281 - #> 5 8 128747680 128753674 5995 + #Example 3 - Individually specify the chromosome, start and end coordinates region_ranger(qchrom = \"chr8\", qstart = 127735434, qend = 127742951) #> region_start region_end type gene_biotype hugo_symbol ensembl_gene_id chrom #> 1 127735434 127742951 gene lncRNA CASC11 ENSG00000249375 chr8 #> 2 127735434 127742951 gene protein_coding MYC ENSG00000136997 chr8 #> start end width strand #> 1 127686343 127738987 52645 - #> 2 127735434 127742951 7518 + #Example 4 - Individually specify multiple regions with the query parameters region_ranger(qchrom = c(\"chr8\", \"chr18\"), qstart = c(128747680, 60790579), qend = c(128753674, 60987361), projection = \"grch37\") #> region_start region_end type gene_biotype hugo_symbol ensembl_gene_id #> 1 60790579 60987361 gene protein_coding BCL2 ENSG00000171791 #> 2 60790579 60987361 gene sense_intronic RP11-299P2.1 ENSG00000267766 #> 3 60790579 60987361 gene snoRNA snoU13 ENSG00000238988 #> 4 60790579 60987361 gene sense_intronic RP11-28F1.2 ENSG00000267701 #> 5 128747680 128753674 gene protein_coding MYC ENSG00000136997 #> chrom start end width strand #> 1 18 60790579 60987361 196783 - #> 2 18 60818347 60818553 207 - #> 3 18 60861822 60861898 77 - #> 4 18 60981035 60981315 281 - #> 5 8 128747680 128753674 5995 +"},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":null,"dir":"Reference","previous_headings":"","what":"Sanity Check Regions. — sanity_check_regions","title":"Sanity Check Regions. — sanity_check_regions","text":"Helper function ensuring provided regions valid.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Sanity Check Regions. — sanity_check_regions","text":"","code":"sanity_check_regions(incoming_regions = NULL, projection = NULL)"},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Sanity Check Regions. — sanity_check_regions","text":"incoming_regions data frame regions following columns; chrom, start, end. projection projection.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Sanity Check Regions. — sanity_check_regions","text":"Nothing.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Sanity Check Regions. — sanity_check_regions","text":"function checks provided start coordinate equal greater end coordinate chromosome. also ensures specified ranges within actual chromosomal range.","code":""},{"path":"https://github.com/mattssca/BioMaesteR/reference/sanity_check_regions.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Sanity Check Regions. — sanity_check_regions","text":"","code":"#Example 1 - Give the function one region as a string my_regions = data.frame(chrom = c(\"chr1\", \"chr2\"), start = c(100, 100), end = c(200, 200)) sanity_check_regions(incoming_regions = my_regions, projection = \"hg38\") #> NULL"}] diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 973dbab..5a67430 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -51,6 +51,9 @@ https://github.com/mattssca/BioMaesteR/reference/index.html + + https://github.com/mattssca/BioMaesteR/reference/power_lifter.html + https://github.com/mattssca/BioMaesteR/reference/purify_chr.html