Gene frequencies

Creates a data frame of VDJ gene counts and frequencies.

Usage

geneFreq(productive_nt, locus = "V|D|J", family = FALSE)

Arguments

productive_nt

A tibble of productive sequences generated by the LymphoSeq function productiveSeq where the parameter aggregate is set to "nucleotide".

locus

A character vector indicating which VDJ genes to include in the output. Available options include "VDJ", "DJ", "VJ", "DJ", "V", "D", or "J".

family

A Boolean value indicating whether or not family names instead of gene names are used. If TRUE, then family names are used and if FALSE, gene names are used.

Value

Returns a data frame with the repertoire_id names, VDJ gene name, duplicate_count, and \100\

Examples

file_path <- system.file("extdata", "TCRB_sequencing", package = "LymphoSeqTest")

stable <- readImmunoSeq(path = file_path)
#> Rows: 1 Columns: 144
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: ","
#> chr (69): sequence_id, sequence, sequence_aa, locus, v_call, d_call, d2_call...
#> dbl (70): v_score, v_identity, v_support, d_score, d_identity, d_support, d2...
#> lgl  (5): rev_comp, productive, vj_in_frame, stop_codon, complete_vdj
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (33): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (4): vFamilyTies, jFamilyTies, jGeneNameTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (34): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (3): jFamilyTies, jGeneNameTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 414 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (34): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (3): jFamilyTies, jGeneNameTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (34): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (3): jFamilyTies, jGeneNameTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (34): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (3): jFamilyTies, jGeneNameTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (35): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (2): jFamilyTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 920 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (29): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vFami...
#> dbl (14): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (9): vGeneAllele, vGeneAlleleTies, dGeneAllele, dFamilyTies, dGeneAllel...
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (29): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vFami...
#> dbl (14): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (9): vGeneAllele, vGeneAlleleTies, dGeneAllele, dFamilyTies, dGeneAllel...
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (29): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vFami...
#> dbl (14): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (9): vGeneAllele, vGeneAlleleTies, dGeneAllele, dFamilyTies, dGeneAllel...
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 1000 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (34): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (15): count (templates/reads), frequencyCount (%), cdr3Length, vDeletion...
#> lgl  (3): jFamilyTies, jGeneNameTies, jGeneAlleleTies
#> 
#> ℹ Use `spec()` to retrieve the full column specification for this data.
#> ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")

ntable <- productiveSeq(study_table = stable, aggregate = "nucleotide")

geneFreq(ntable, locus = "VDJ", family = FALSE)
#> # A tibble: 655 × 5
#>    repertoire_id gene_name     duplicate_count gene_type gene_frequency
#>    <chr>         <chr>                   <dbl> <chr>              <dbl>
#>  1 TRB_CD4_949   NA                      11177 d_call            0.303 
#>  2 TRB_CD4_949   TCRBD01-01               3034 d_call            0.0822
#>  3 TRB_CD4_949   TCRBD01-01*01           14087 d_call            0.382 
#>  4 TRB_CD4_949   TCRBD02-01                597 d_call            0.0162
#>  5 TRB_CD4_949   TCRBD02-01*01             760 d_call            0.0206
#>  6 TRB_CD4_949   TCRBD02-01*02            7258 d_call            0.197 
#>  7 TRB_CD4_949   TCRBJ01-01*01            5168 j_call            0.201 
#>  8 TRB_CD4_949   TCRBJ01-02*01            1229 j_call            0.0477
#>  9 TRB_CD4_949   TCRBJ01-03*01            2348 j_call            0.0911
#> 10 TRB_CD4_949   TCRBJ01-04*01             590 j_call            0.0229
#> # … with 645 more rows