Creates line plot tracking amino acid frequencies across multiple samples
Arguments
- study_table
A tibble of productive amino acid sequences generated by LymphoSeq2 function
productiveSeq()where the aggregate parameter was set to "junction_aa"- sample_list
A character vector of one or more repertoire_ids to track. If set to NULL (the default), all repertoire_ids in the sequence matrix will be tracked.
- sequence_track
An optional character vector of one or more amino acid sequences to track. If set to NULL (the default), will pull all junction_aa sequences from the sequence matrix.
Value
Returns a line plot showing the amino acid frequencies across multiple samples in the sequence matrix where each line represents one unique sequence.
Examples
file_path <- system.file("extdata", "TCRB_sequencing",
package = "LymphoSeq2")
study_table <- LymphoSeq2::readImmunoSeq(path = file_path, threads = 1)
#> Dataset Analysis:
#> Files: 10, Total: 0.00 GB, Largest: 0.0 MB
#> Available memory: 13.7 GB
study_table <- LymphoSeq2::topSeqs(study_table, top = 100)
amino_table <- LymphoSeq2::productiveSeq(
study_table = study_table,
aggregate = "junction_aa"
)
top_freq <- LymphoSeq2::topFreq(amino_table, frequency = 0.001)
# Track clones without mapping or tracking specific sequences
LymphoSeq2::cloneTrack(amino_table)
#> # A tibble: 810 × 12
#> repertoire_id junction_aa v_call d_call j_call v_family d_family j_family
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 TRB_CD4_949 CAISVGGSSPLHF TRBV1… TRBD0… TRBJ0… V10 D02 J01
#> 2 TRB_CD4_949 CASDGGFRNTIYF TRBV1… TRBD0… TRBJ0… V19 D02 J01
#> 3 TRB_CD4_949 CASGGLNTEAFF NA NA TRBJ0… NA NA J01
#> 4 TRB_CD4_949 CASGLVAGSTLGGE… TRBV1… TRBD0… TRBJ0… V12 D02 J02
#> 5 TRB_CD4_949 CASGTGGETQYF TRBV0… TRBD0… TRBJ0… V06 D02 J02
#> 6 TRB_CD4_949 CASHSSGNTIYF TRBV0… NA TRBJ0… V06 NA J01
#> 7 TRB_CD4_949 CASKPPGQGGYGYTF TRBV0… TRBD0… TRBJ0… V06 D01 J01
#> 8 TRB_CD4_949 CASMIDPSGNTIYF TRBV0… NA TRBJ0… V05 NA J01
#> 9 TRB_CD4_949 CASNARVDSPLHF TRBV0… TRBD0… TRBJ0… V06 D01 J01
#> 10 TRB_CD4_949 CASRLGESPLHF NA NA TRBJ0… NA NA J01
#> # ℹ 800 more rows
#> # ℹ 4 more variables: reading_frame <chr>, duplicate_count <int>,
#> # duplicate_frequency <dbl>, seen <int>
# Track top 20 clones mapping to the CD4 and CD8 samples
LymphoSeq2::cloneTrack(amino_table,
sample_list = c("TRB_CD4_949", "TRB_CD8_949"),
sequence_track = top_freq$junction_aa[1:20]
)
#> # A tibble: 20 × 12
#> repertoire_id junction_aa v_call d_call j_call v_family d_family j_family
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 TRB_CD4_949 CASSWEQGTNYGYTF TRBV2… TRBD0… TRBJ0… V28 D01 J01
#> 2 TRB_CD8_949 CAIKMETPNGEQYF TRBV1… NA TRBJ0… V10 NA J02
#> 3 TRB_CD8_949 CAISESGVLNEKLFF TRBV1… NA TRBJ0… V10 NA J01
#> 4 TRB_CD8_949 CASRDGQGSGNTIYF TRBV0… TRBD0… TRBJ0… V06 D01 J01
#> 5 TRB_CD8_949 CASSEALPGMVPLHF TRBV0… TRBD0… TRBJ0… V02 D01 J01
#> 6 TRB_CD8_949 CASSGGVAAFSSYN… TRBV0… TRBD0… TRBJ0… V05 D01 J01
#> 7 TRB_CD8_949 CASSLAGDSQETQYF TRBV2… NA TRBJ0… V28 NA J02
#> 8 TRB_CD8_949 CASSLQGREKLFF TRBV2… TRBD0… TRBJ0… V27 D01 J01
#> 9 TRB_CD8_949 CASSPAGAYYNEQFF NA TRBD0… TRBJ0… NA D02 J02
#> 10 TRB_CD8_949 CASSPFDRGPDTEA… TRBV2… TRBD0… TRBJ0… V28 D01 J01
#> 11 TRB_CD8_949 CASSPGTGTYGYTF TRBV1… TRBD0… TRBJ0… V10 D01 J01
#> 12 TRB_CD8_949 CASSPLDGLTNEQFF TRBV2… NA TRBJ0… V28 NA J02
#> 13 TRB_CD8_949 CASSPPTGERDTQYF TRBV0… TRBD0… TRBJ0… V07 D02 J02
#> 14 TRB_CD8_949 CASSPSRNTEAFF TRBV0… TRBD0… TRBJ0… V04 D02 J01
#> 15 TRB_CD8_949 CASSQDLGQAFSPL… TRBV0… TRBD0… TRBJ0… V04 D01 J01
#> 16 TRB_CD8_949 CASSQDLMTVDSLF… TRBV0… TRBD0… TRBJ0… V04 D01 J02
#> 17 TRB_CD8_949 CASSQDRTGQYGYTF TRBV0… TRBD0… TRBJ0… V04 D01 J01
#> 18 TRB_CD8_949 CASSQDSSDTEAFF TRBV0… NA TRBJ0… V04 NA J01
#> 19 TRB_CD8_949 CASSQDWERLGEQFF TRBV1… TRBD0… TRBJ0… V14 D02 J02
#> 20 TRB_CD8_949 CASSREGDQPQHF TRBV0… TRBD0… TRBJ0… V05 D01 J01
#> # ℹ 4 more variables: reading_frame <chr>, duplicate_count <int>,
#> # duplicate_frequency <dbl>, seen <int>
# Track the top 10 clones from top.freq
LymphoSeq2::cloneTrack(
study_table = amino_table,
sequence_track = top_freq$junction_aa[1:10]
)
#> # A tibble: 75 × 12
#> repertoire_id junction_aa v_call d_call j_call v_family d_family j_family
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 TRB_CD8_949 CAIKMETPNGEQYF TRBV1… NA TRBJ0… V10 NA J02
#> 2 TRB_CD8_949 CASRDGQGSGNTIYF TRBV0… TRBD0… TRBJ0… V06 D01 J01
#> 3 TRB_CD8_949 CASSLQGREKLFF TRBV2… TRBD0… TRBJ0… V27 D01 J01
#> 4 TRB_CD8_949 CASSPFDRGPDTEA… TRBV2… TRBD0… TRBJ0… V28 D01 J01
#> 5 TRB_CD8_949 CASSPGTGTYGYTF TRBV1… TRBD0… TRBJ0… V10 D01 J01
#> 6 TRB_CD8_949 CASSQDLGQAFSPL… TRBV0… TRBD0… TRBJ0… V04 D01 J01
#> 7 TRB_CD8_949 CASSQDLMTVDSLF… TRBV0… TRBD0… TRBJ0… V04 D01 J02
#> 8 TRB_CD8_949 CASSQDRTGQYGYTF TRBV0… TRBD0… TRBJ0… V04 D01 J01
#> 9 TRB_CD8_949 CASSQDSSDTEAFF TRBV0… NA TRBJ0… V04 NA J01
#> 10 TRB_CD8_949 CASSREGDQPQHF TRBV0… TRBD0… TRBJ0… V05 D01 J01
#> # ℹ 65 more rows
#> # ℹ 4 more variables: reading_frame <chr>, duplicate_count <int>,
#> # duplicate_frequency <dbl>, seen <int>
# Track clones mapping to the CD4 and CD8 samples while ignoring all others
LymphoSeq2::cloneTrack(
study_table = amino_table,
sample_list = c("TRB_CD4_949", "TRB_CD8_949")
)
#> # A tibble: 161 × 12
#> repertoire_id junction_aa v_call d_call j_call v_family d_family j_family
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 TRB_CD4_949 CAISVGGSSPLHF TRBV1… TRBD0… TRBJ0… V10 D02 J01
#> 2 TRB_CD4_949 CASDGGFRNTIYF TRBV1… TRBD0… TRBJ0… V19 D02 J01
#> 3 TRB_CD4_949 CASGGLNTEAFF NA NA TRBJ0… NA NA J01
#> 4 TRB_CD4_949 CASGLVAGSTLGGE… TRBV1… TRBD0… TRBJ0… V12 D02 J02
#> 5 TRB_CD4_949 CASGTGGETQYF TRBV0… TRBD0… TRBJ0… V06 D02 J02
#> 6 TRB_CD4_949 CASHSSGNTIYF TRBV0… NA TRBJ0… V06 NA J01
#> 7 TRB_CD4_949 CASKPPGQGGYGYTF TRBV0… TRBD0… TRBJ0… V06 D01 J01
#> 8 TRB_CD4_949 CASMIDPSGNTIYF TRBV0… NA TRBJ0… V05 NA J01
#> 9 TRB_CD4_949 CASNARVDSPLHF TRBV0… TRBD0… TRBJ0… V06 D01 J01
#> 10 TRB_CD4_949 CASRLGESPLHF NA NA TRBJ0… NA NA J01
#> # ℹ 151 more rows
#> # ℹ 4 more variables: reading_frame <chr>, duplicate_count <int>,
#> # duplicate_frequency <dbl>, seen <int>
# Track clones mapping to the CD4 and CD8 samples and track 2 specific
#sequences
LymphoSeq2::cloneTrack(
study_table = amino_table, sample_list = c("TRB_CD4_949", "TRB_CD8_949"),
sequence_track = c("CASSPPTGERDTQYF", "CASSQDRTGQYGYTF")
)
#> # A tibble: 2 × 12
#> repertoire_id junction_aa v_call d_call j_call v_family d_family j_family
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
#> 1 TRB_CD8_949 CASSPPTGERDTQYF TRBV07… TRBD0… TRBJ0… V07 D02 J02
#> 2 TRB_CD8_949 CASSQDRTGQYGYTF TRBV04… TRBD0… TRBJ0… V04 D01 J01
#> # ℹ 4 more variables: reading_frame <chr>, duplicate_count <int>,
#> # duplicate_frequency <dbl>, seen <int>