Skip to contents

Search for T cell receptor beta CDR3 amino acid sequences with known antigen specificity from iReceptor2

Source: R/searchDB.R
searchDB.Rd

Search for published T cell receptor beta CDR3 amino acid sequences with known antigen specificity in a list of data frames.

Usage

searchDB(study_table, credential)

Arguments

study_table

A tibble generated by the LymphoSeq functions searchPublished or topSeqs. "aminoAcid", "frequencyCount", and "count" are required columns.

Value

Returns a tibble of with sample name and instance in the sample that the published TCR sequence appeared along with additional information including disease status, sample type, and PubMed ID (PMID) for the reference where the sequence was characterized.

Examples

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

study_table <- 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")

productive_aa <- productiveSeq(study_table = study_table, aggregate = "aminoAcid")

top_seqs <- topSeqs(productive_table = productive_aa, top = 1)
searchDB(study_table = top_seqs, credential="Adaptive")
#> # A tibble: 8 × 151
#>   sequence_id sequence    sequence_aa rev_comp productive vj_in_frame stop_codon
#>         <int> <chr>       <chr>       <lgl>    <lgl>      <lgl>       <lgl>     
#> 1          48 CAGCCTGCAG… CASSQDWERL… FALSE    TRUE       NA          FALSE     
#> 2          19 ATCCTGGAGT… CASSLQGREK… FALSE    TRUE       NA          FALSE     
#> 3           4 GAGTCAGCTA… CASSESAGST… FALSE    TRUE       NA          FALSE     
#> 4           3 CAGCCCTCAG… CASSPAGAYY… FALSE    TRUE       NA          FALSE     
#> 5           1 CAGCGCACAG… CASSPPTGER… FALSE    TRUE       NA          FALSE     
#> 6          32 CAGCCCTCAG… CASSPAGAYY… FALSE    TRUE       NA          FALSE     
#> 7           9 CAGCCCTCAG… CASSPAGAYY… FALSE    TRUE       NA          FALSE     
#> 8           3 CAGCCCTCAG… CASSPAGAYY… FALSE    TRUE       NA          FALSE     
#> # … with 144 more variables: complete_vdj <lgl>, locus <chr>, v_call <chr>,
#> #   d_call <chr>, d2_call <chr>, j_call <chr>, c_call <chr>,
#> #   sequence_alignment <chr>, sequence_alignment_aa <chr>,
#> #   germline_alignment <chr>, germline_alignment_aa <chr>, junction <chr>,
#> #   junction_aa <chr>, np1 <chr>, np1_aa <chr>, np2 <chr>, np2_aa <chr>,
#> #   np3 <chr>, np3_aa <chr>, cdr1 <chr>, cdr1_aa <chr>, cdr2 <chr>,
#> #   cdr2_aa <chr>, cdr3 <chr>, cdr3_aa <chr>, fwr1 <chr>, fwr1_aa <chr>, …