Summarize per-chain values for each cell using a function or purrr-style lambda. This is useful for plotting or filtering cells based on the V(D)J meta.data.
Usage
summarize_vdj(
input,
data_cols,
fn = NULL,
...,
chain = NULL,
chain_col = global$chain_col,
col_names = "{.col}",
return_df = FALSE,
sep = global$sep
)Arguments
- input
Single cell object or data.frame containing V(D)J data. If a data.frame is provided, the cell barcodes should be stored as row names.
- data_cols
meta.data column(s) containing V(D)J data to summarize for each cell
- fn
Function to apply to each selected column, possible values can be either a function, e.g. mean, or a purrr-style lambda, e.g. ~ mean(.x, na.rm = TRUE). If NULL, the mean will be calculated for numeric values, non-numeric columns will be combined into a single string.
- ...
Additional arguments to pass to fn
- chain
Chain to use for summarizing V(D)J data
- chain_col
meta.data column(s) containing chains for each cell
- col_names
A glue specification that describes how to name the output columns, use {.col} to refer to the original column name. If col_names is NULL, the original column names will be used.
- return_df
Return results as a data.frame. If FALSE, results will be added to the input object.
- sep
Separator used for storing per cell V(D)J data
Examples
# Summarize numeric columns
# by default the mean will be calculated for numeric columns
res <- summarize_vdj(
vdj_sce,
data_cols = c("all_del", "all_ins")
)
head(slot(res, "colData"), 3)
#> DataFrame with 3 rows and 49 columns
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> <character> <numeric> <integer> <factor>
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> 1_AATCCAGCATTACGAC-1 avid_1 6 4 0
#> 1_ACAGCTAGTCTGGTCG-1 avid_1 15 4 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> <factor> <numeric> <numeric> <character>
#> 1_AAGCCGCAGCTTATCG-1 0 -5.977054 -2.418108 NA
#> 1_AATCCAGCATTACGAC-1 0 1.282983 -0.700069 NA
#> 1_ACAGCTAGTCTGGTCG-1 0 -0.537163 0.133260 NA
#> exact_subclonotype_id chains n_chains
#> <numeric> <character> <integer>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA
#> cdr3 cdr3_nt cdr3_length cdr3_nt_length
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_gene d_gene j_gene c_gene
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> isotype reads umis productive
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> full_length paired v_ins v_del
#> <character> <logical> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_mis d_ins d_del d_mis
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> j_ins j_del j_mis c_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_del c_mis all_ins all_del
#> <character> <character> <numeric> <numeric>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> all_mis vd_ins vd_del dj_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> dj_del v_mis_freq d_mis_freq j_mis_freq
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_mis_freq all_mis_freq
#> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA
# Specifying a different summary function
# this calculates the median number of insertions and deletions for each
# cell
res <- summarize_vdj(
vdj_sce,
data_cols = c("all_del", "all_ins"),
fn = stats::median
)
head(slot(res, "colData"), 3)
#> DataFrame with 3 rows and 49 columns
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> <character> <numeric> <integer> <factor>
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> 1_AATCCAGCATTACGAC-1 avid_1 6 4 0
#> 1_ACAGCTAGTCTGGTCG-1 avid_1 15 4 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> <factor> <numeric> <numeric> <character>
#> 1_AAGCCGCAGCTTATCG-1 0 -5.977054 -2.418108 NA
#> 1_AATCCAGCATTACGAC-1 0 1.282983 -0.700069 NA
#> 1_ACAGCTAGTCTGGTCG-1 0 -0.537163 0.133260 NA
#> exact_subclonotype_id chains n_chains
#> <numeric> <character> <integer>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA
#> cdr3 cdr3_nt cdr3_length cdr3_nt_length
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_gene d_gene j_gene c_gene
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> isotype reads umis productive
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> full_length paired v_ins v_del
#> <character> <logical> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_mis d_ins d_del d_mis
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> j_ins j_del j_mis c_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_del c_mis all_ins all_del
#> <character> <character> <numeric> <numeric>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> all_mis vd_ins vd_del dj_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> dj_del v_mis_freq d_mis_freq j_mis_freq
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_mis_freq all_mis_freq
#> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA
# Summarize values for a specific chain
res <- summarize_vdj(
vdj_sce,
data_cols = c("all_del", "all_ins"),
chain = "IGK"
)
head(slot(res, "colData"), 3)
#> DataFrame with 3 rows and 49 columns
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> <character> <numeric> <integer> <factor>
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> 1_AATCCAGCATTACGAC-1 avid_1 6 4 0
#> 1_ACAGCTAGTCTGGTCG-1 avid_1 15 4 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> <factor> <numeric> <numeric> <character>
#> 1_AAGCCGCAGCTTATCG-1 0 -5.977054 -2.418108 NA
#> 1_AATCCAGCATTACGAC-1 0 1.282983 -0.700069 NA
#> 1_ACAGCTAGTCTGGTCG-1 0 -0.537163 0.133260 NA
#> exact_subclonotype_id chains n_chains
#> <numeric> <character> <integer>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA
#> cdr3 cdr3_nt cdr3_length cdr3_nt_length
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_gene d_gene j_gene c_gene
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> isotype reads umis productive
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> full_length paired v_ins v_del
#> <character> <logical> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_mis d_ins d_del d_mis
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> j_ins j_del j_mis c_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_del c_mis all_ins all_del
#> <character> <character> <numeric> <numeric>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> all_mis vd_ins vd_del dj_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> dj_del v_mis_freq d_mis_freq j_mis_freq
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_mis_freq all_mis_freq
#> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA
# Specifying new names for summarized columns
# use {.col} to refer to the original column name
res <- summarize_vdj(
vdj_sce,
data_cols = c("all_del", "all_ins"),
fn = stats::median,
col_names = "median_{.col}"
)
head(slot(res, "colData"), 1)
#> DataFrame with 1 row and 51 columns
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> <character> <numeric> <integer> <factor>
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> <factor> <numeric> <numeric> <character>
#> 1_AAGCCGCAGCTTATCG-1 0 -5.97705 -2.41811 NA
#> exact_subclonotype_id chains n_chains
#> <numeric> <character> <integer>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> cdr3 cdr3_nt cdr3_length cdr3_nt_length
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> v_gene d_gene j_gene c_gene
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> isotype reads umis productive
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> full_length paired v_ins v_del
#> <character> <logical> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> v_mis d_ins d_del d_mis
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> j_ins j_del j_mis c_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> c_del c_mis all_ins all_del
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> all_mis vd_ins vd_del dj_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> dj_del v_mis_freq d_mis_freq j_mis_freq
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> c_mis_freq all_mis_freq median_all_del
#> <character> <character> <numeric>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> median_all_ins
#> <numeric>
#> 1_AAGCCGCAGCTTATCG-1 NA
# Return a data.frame instead of adding the results to the input object
res <- summarize_vdj(
vdj_sce,
data_cols = c("all_del", "all_ins"),
return_df = TRUE
)
head(res, 1)
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> 1_AAGCCGCAGCTTATCG-1 0 -5.977054 -2.418108 <NA>
#> exact_subclonotype_id chains n_chains cdr3 cdr3_nt
#> 1_AAGCCGCAGCTTATCG-1 NA <NA> NA <NA> <NA>
#> cdr3_length cdr3_nt_length v_gene d_gene j_gene
#> 1_AAGCCGCAGCTTATCG-1 <NA> <NA> <NA> <NA> <NA>
#> c_gene isotype reads umis productive full_length
#> 1_AAGCCGCAGCTTATCG-1 <NA> <NA> <NA> <NA> <NA> <NA>
#> paired v_ins v_del v_mis d_ins d_del d_mis j_ins
#> 1_AAGCCGCAGCTTATCG-1 NA <NA> <NA> <NA> <NA> <NA> <NA> <NA>
#> j_del j_mis c_ins c_del c_mis all_ins all_del
#> 1_AAGCCGCAGCTTATCG-1 <NA> <NA> <NA> <NA> <NA> NA NA
#> all_mis vd_ins vd_del dj_ins dj_del v_mis_freq
#> 1_AAGCCGCAGCTTATCG-1 <NA> <NA> <NA> <NA> <NA> <NA>
#> d_mis_freq j_mis_freq c_mis_freq all_mis_freq
#> 1_AAGCCGCAGCTTATCG-1 <NA> <NA> <NA> <NA>
# Using a lambda function to summarize values
# use '.x' to refer to values in the column
# this creates a new column showing the unique chains for each cell
res <- summarize_vdj(
vdj_sce,
data_cols = "chains",
fn = ~ paste0(unique(.x), collapse = "_"),
col_names = "unique_chains"
)
head(slot(res, "colData"), 3)
#> DataFrame with 3 rows and 50 columns
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> <character> <numeric> <integer> <factor>
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> 1_AATCCAGCATTACGAC-1 avid_1 6 4 0
#> 1_ACAGCTAGTCTGGTCG-1 avid_1 15 4 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> <factor> <numeric> <numeric> <character>
#> 1_AAGCCGCAGCTTATCG-1 0 -5.977054 -2.418108 NA
#> 1_AATCCAGCATTACGAC-1 0 1.282983 -0.700069 NA
#> 1_ACAGCTAGTCTGGTCG-1 0 -0.537163 0.133260 NA
#> exact_subclonotype_id chains n_chains
#> <numeric> <character> <integer>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA
#> cdr3 cdr3_nt cdr3_length cdr3_nt_length
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_gene d_gene j_gene c_gene
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> isotype reads umis productive
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> full_length paired v_ins v_del
#> <character> <logical> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_mis d_ins d_del d_mis
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> j_ins j_del j_mis c_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_del c_mis all_ins all_del
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> all_mis vd_ins vd_del dj_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> dj_del v_mis_freq d_mis_freq j_mis_freq
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_mis_freq all_mis_freq unique_chains
#> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA
# Creating an index column to use for filtering/plotting
# this creates a column indicating which cells have no insertions
# the V(D)J data can be filtered based on this new column
res <- summarize_vdj(
vdj_sce,
data_cols = "all_ins",
fn = ~ all(.x == 0),
col_names = "no_insertions"
)
res <- filter_vdj(
res,
filt = no_insertions
)
head(slot(res, "colData"), 3)
#> DataFrame with 3 rows and 50 columns
#> orig.ident nCount_RNA nFeature_RNA RNA_snn_res.0.3
#> <character> <numeric> <integer> <factor>
#> 1_AAGCCGCAGCTTATCG-1 avid_1 0 0 0
#> 1_AATCCAGCATTACGAC-1 avid_1 6 4 0
#> 1_ACAGCTAGTCTGGTCG-1 avid_1 15 4 0
#> seurat_clusters UMAP_1 UMAP_2 clonotype_id
#> <factor> <numeric> <numeric> <character>
#> 1_AAGCCGCAGCTTATCG-1 0 -5.977054 -2.418108 NA
#> 1_AATCCAGCATTACGAC-1 0 1.282983 -0.700069 NA
#> 1_ACAGCTAGTCTGGTCG-1 0 -0.537163 0.133260 NA
#> exact_subclonotype_id chains n_chains
#> <numeric> <character> <integer>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA
#> cdr3 cdr3_nt cdr3_length cdr3_nt_length
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_gene d_gene j_gene c_gene
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> isotype reads umis productive
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> full_length paired v_ins v_del
#> <character> <logical> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> v_mis d_ins d_del d_mis
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> j_ins j_del j_mis c_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_del c_mis all_ins all_del
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> all_mis vd_ins vd_del dj_ins
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> dj_del v_mis_freq d_mis_freq j_mis_freq
#> <character> <character> <character> <character>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA NA
#> c_mis_freq all_mis_freq no_insertions
#> <character> <character> <logical>
#> 1_AAGCCGCAGCTTATCG-1 NA NA NA
#> 1_AATCCAGCATTACGAC-1 NA NA NA
#> 1_ACAGCTAGTCTGGTCG-1 NA NA NA