Generate MSA alignment figures from the results of alignSeq
See also
The function utilizes ggmsa package for visualizations. Further details on ggmsa can be found at the link mentioned below. https://cran.r-project.org/web/packages/ggmsa/vignettes/ggmsa.html
Examples
file_path <- system.file("extdata", "IGH_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: 694 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (25): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (10): vFamilyTies, vOrphon, dOrphon, jOrphon, vFunction, dFunction, jFun...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 41 rows [14, 15, 33, 36, 48, 78, 119, 123, 130, 135, 149, 167, 176, 190, 198, 210, 245, 247, 250, 262, ...].
#> 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 (25): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (8): vFamilyTies, vOrphon, dOrphon, jOrphon, vFunction, dFunction, jFun...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 58 rows [31, 33, 40, 41, 90, 96, 109, 117, 146, 154, 178, 189, 238, 252, 255, 260, 270, 278, 315, 320, ...].
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 694 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (25): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (10): vFamilyTies, vOrphon, dOrphon, jOrphon, vFunction, dFunction, jFun...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 41 rows [14, 15, 33, 36, 48, 78, 119, 123, 130, 135, 149, 167, 176, 190, 198, 210, 245, 247, 250, 262, ...].
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 694 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (26): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (9): vOrphon, dOrphon, jOrphon, vFunction, dFunction, jFunction, fracti...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 10 rows [204, 206, 265, 347, 410, 411, 419, 512, 582, 608].
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 492 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (25): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (18): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (9): jGeneAlleleTies, vOrphon, dOrphon, jOrphon, vFunction, dFunction, ...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 3 rows [134, 143, 251].
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 209 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (25): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (10): jGeneAlleleTies, vOrphon, dOrphon, jOrphon, vFunction, dFunction, ...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 20 rows [4, 27, 34, 37, 52, 53, 55, 69, 81, 87, 88, 90, 95, 108, 111, 131, 151, 158, 160, 200].
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 436 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (25): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (10): jGeneAlleleTies, vOrphon, dOrphon, jOrphon, vFunction, dFunction, ...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 47 rows [21, 22, 28, 59, 63, 69, 78, 79, 82, 87, 90, 91, 116, 121, 149, 170, 182, 188, 216, 237, ...].
#> 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 (26): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (17): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (9): vOrphon, dOrphon, jOrphon, vFunction, dFunction, jFunction, fracti...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 27 rows [117, 121, 146, 157, 178, 199, 296, 310, 322, 323, 324, 325, 349, 351, 363, 420, 421, 467, 468, 484, ...].
#> 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 (26): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (18): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (8): vOrphon, dOrphon, jOrphon, vFunction, dFunction, jFunction, vAlign...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 85 rows [38, 58, 79, 83, 92, 119, 127, 145, 149, 161, 162, 169, 187, 191, 199, 237, 250, 272, 275, 283, ...].
#> Joining, by = c("sequence", "sequence_aa", "v_call", "d_call", "d2_call",
#> "j_call", "junction", "junction_aa", "duplicate_count", "clone_id",
#> "repertoire_id")
#> Rows: 275 Columns: 52
#> ── Column specification ────────────────────────────────────────────────────────
#> Delimiter: "\t"
#> chr (24): nucleotide, aminoAcid, vMaxResolved, vFamilyName, vGeneName, vGene...
#> dbl (18): count (reads), frequencyCount (%), cdr3Length, vDeletion, n1Insert...
#> lgl (10): vFamilyTies, jGeneAlleleTies, vOrphon, dOrphon, jOrphon, vFunction...
#>
#> 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.
#> Warning: Expected 2 pieces. Additional pieces discarded in 24 rows [9, 29, 40, 42, 61, 84, 87, 101, 104, 106, 108, 119, 146, 170, 177, 192, 201, 206, 214, 248, ...].
#> 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(stable, aggregate = "junction")
msa <- alignSeq(ntable, repertoire_id = "IGH_MVQ92552A_BL", type = "junction",
method = "ClustalW")
#> use default substitution matrix