55 | ![]()
58 |
59 | Content not found. Please use links in the navbar.
60 |
61 | ${s.title}
`;
142 | } else if (s.previous_headings == "") {
143 | return `${s.dir} > ${s.title}
> ${s.what}`;
144 | } else {
145 | return `${s.dir} > ${s.title}
> ${s.previous_headings} > ${s.what}`;
146 | }
147 | },
148 | },
149 | },
150 | ]).on('autocomplete:selected', function(event, s) {
151 | window.location.href = s.path + "?q=" + q + "#" + s.id;
152 | });
153 | });
154 | })(window.jQuery || window.$)
155 |
156 |
157 |
--------------------------------------------------------------------------------
/R/viewTrees.R:
--------------------------------------------------------------------------------
1 | #' Visualize the trees
2 | #'
3 | #' @param phyloTree phyloTree: The tree is in Parenthetic format.
4 | #' @param tree.format the format of tree, S4 or list. Default is S4.
5 | #' @param normal.node the sample name of normal sample in the tree.
6 | #' @param group a list that used to indicate the sample groups.
7 | #' @param group.colors an array indicates the colors of sample groups.
8 | #' @param showBootstrap whether showing the bootstrap values. Default is TRUE.
9 | #' @param title title of the plot.
10 | #' @param hexpand_ratio hexpand ratio. see \code{\link[ggtree]{hexpand}}
11 | #'
12 | #' @examples
13 | #' # This dist file is the output of MEDICC
14 | #' dist <- system.file(package = "MPTevol", "extdata", "tree_final.dist")
15 | #'
16 | #' # plot CNA trees without colored samples.
17 | #' plotCNAtree(dist = dist)
18 | #'
19 | #' # create a list to indicate the sample groups.
20 | #' grp <- list(
21 | #' NORMAL = "NORMAL",
22 | #' Breast = paste0("Breast_", 1:5),
23 | #' Coad = paste0("Coad_", 1:5),
24 | #' Lung = paste0("Lung_", 1:5),
25 | #' OveryLM = paste0("OveryLM_", 1:5),
26 | #' OveryRM = paste0("OveryRM_", 1:6),
27 | #' UterusM = paste0("UterusM_", c(1:7))
28 | #' )
29 | #'
30 | #' plotCNAtree(dist = dist, grp = grp)
31 | #' @return a ggtree object
32 | #' @export
33 | viewTrees <- function(phyloTree,
34 | tree.format = "S4",
35 | normal.node = "NORMAL",
36 | group = NULL,
37 | group.colors = NULL,
38 | title = "Cancer",
39 | showBootstrap = TRUE,
40 | hexpand_ratio = 0.3) {
41 | if (tree.format == "S4") {
42 | mtree <- phyloTree@tree
43 | } else {
44 | mtree <- phyloTree$tree
45 | }
46 |
47 | # all.length = mtree$edge.length
48 | root.length <- rev(mtree$edge.length)[1]
49 |
50 | # set outgroup and removing the Normal
51 | mtree <- treeio::root(mtree, outgroup = normal.node)
52 | mtree <- treeio::drop.tip(mtree, normal.node)
53 |
54 | # grp <- list(
55 | # ACA = mtree$tip.label[grepl("Aca", mtree$tip.label)] ,
56 | # NEC = mtree$tip.label[grepl("Nec", mtree$tip.label)]
57 | # )
58 |
59 | # combined bootstrap values.
60 |
61 | if (showBootstrap) {
62 | bootstrap.value <- ifelse(tree.format == "S4",
63 | phyloTree@bootstrap.value,
64 | phyloTree$bootstrap.value
65 | )
66 |
67 | bp2 <- data.frame(
68 | node = 1:treeio::Nnode(mtree) + treeio::Ntip(mtree),
69 | bootstrap = bootstrap.value
70 | )
71 | mtree <- dplyr::full_join(mtree, bp2, by = "node")
72 | }
73 |
74 | p_trees <- ggtree::ggtree(mtree, size = 1) +
75 | ggtree::geom_tiplab(size = 4) +
76 | # add scale bars.
77 | ggtree::geom_treescale(fontsize = 4, linesize = 1, x = 0.1) +
78 | # set root length
79 | ggtree::geom_rootedge(rootedge = root.length, size = 1, colour = "grey40") +
80 | ggtree::hexpand(hexpand_ratio, direction = 1)
81 |
82 | if (showBootstrap) {
83 | p_trees <- p_trees +
84 | ggtree::geom_nodepoint(ggplot2::aes(fill = cut(bootstrap, c(0, 70, 90, 100))),
85 | shape = 21, size = 2
86 | ) +
87 | ggtree::geom_nodelab(ggplot2::aes(label = round(bootstrap)), hjust = -0.2, size = 3.5) +
88 | ggplot2::labs(title = title) +
89 | ggplot2::scale_fill_manual(
90 | values = c("black", "grey", "white"), guide = "legend",
91 | name = "Bootstrap Percentage(BP)",
92 | breaks = c("(90,100]", "(70,90]", "(0,70]"),
93 | labels = expression(BP >= 90, 70 <= BP * " < 90", BP < 70)
94 | )
95 | } else {
96 | p_trees <- p_trees +
97 | ggplot2::labs(title = title)
98 | }
99 |
100 | # color the groups
101 | if (!is.null(group)) {
102 | # check samples ids between trees and grp
103 | if (!identical(sort(purrr::reduce(group, c)), sort(mtree@phylo$tip.label))) {
104 | stop("the samplenames in grp were not identical to sample names in the tree")
105 | }
106 |
107 | p_trees <- ggtree::groupOTU(p_trees, group, "Sites")
108 |
109 | # get levels
110 | Sites <- levels(p_trees$data$Sites)
111 |
112 | if (!is.null(group.colors)) {
113 | if (!identical(sort(names(group.colors)), sort(levels(p_trees$data$Sites)))) {
114 | # get levels that were not in the group.colors
115 | Site1 <- setdiff(levels(p_trees$data$Sites), names(group.colors))
116 |
117 | Site.colors <- setNames(
118 | c(set.colors(n = length(Site1), rev = T), group.colors),
119 | nm = c(Site1, names(group.colors))
120 | )
121 |
122 | Site.colors <- Site.colors[levels(p_trees$data$Sites)]
123 | } else {
124 | Site.colors <- group.colors[levels(p_trees$data$Sites)]
125 | }
126 | } else {
127 | Site.colors <- set.colors(n = length(Sites))
128 | }
129 |
130 | p_trees <- p_trees + ggplot2::aes(color = Sites) +
131 | ggplot2::scale_colour_manual(
132 | values = Site.colors
133 | )
134 | }
135 |
136 | p_trees <- p_trees +
137 | ggtree::theme_tree(
138 | plot.title = ggplot2::element_text(hjust = 0.5)
139 | )
140 |
141 | p_trees
142 | }
143 |
--------------------------------------------------------------------------------
/docs/404.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
53 |
77 |
78 |
79 |
80 |
81 |
82 |
83 |
84 |
--------------------------------------------------------------------------------
/docs/news/index.html:
--------------------------------------------------------------------------------
1 |
2 |
54 |
63 |
64 |
65 |
76 |
35 |
47 |
48 |
49 |
58 |
59 |
60 |
61 |
62 |
63 |
64 |
65 |
--------------------------------------------------------------------------------
/R/calPropDriver.R:
--------------------------------------------------------------------------------
1 | #' calPropDriver calculates the proportions of driver mutation for mutation sets.
2 | #'
3 | #' The mutations are classified by `classifyMut()` internally.
4 | #'
5 | #' @param maf Maf or MafList object generated by `readMaf()` function
6 | #' @param patient.id Select the specific patients. Default `NULL`, all patients are included.
7 | #' @param driverGene The driver Gene names (Genes Symbols)
8 | #' @param vaf.cutoff Removing mutations of low variant allele frequency (VAF).
9 | #' @param class The class which would be represented.
10 | #' "SP" (Shared pattern: Public/Shared/Private), other options: "CS" (Clonal status: Clonal/Subclonl)
11 | #' and "SPCS". see [MesKit::classifyMut()].
12 | #' @param classByTumor Logical (Default: `FALSE`). Classify mutations based on "Tumor_ID".
13 | #' @param silent.columns The `Variant_Classification` field in the MAF files that indicates the silent mutations. Defaults: c("Silent", "3'Flank", "IGR", "Intron", "RNA")
14 | #'
15 | #' @examples
16 | #'
17 | #' # Get the driver gene.
18 | #' driverGene <- read.delim(system.file(package = "MPTevol", "extdata", "IntOGen-Drivers-Cancer_Genes.tsv"), header = T) %>%
19 | #' filter(CANCER_TYPE %in% c("BRCA", "COREAD", "LUAD", "LUSC")) %>%
20 | #' pull(SYMBOL) %>%
21 | #' unique()
22 | #'
23 | #' prop = calPropDriver(maf, patient.id = "BRCA", driverGene = driverGene)
24 | #'
25 | #' prop$BRCA$plot
26 | #'
27 | #'
28 | #' @export
29 | #'
30 | calPropDriver <- function(maf,
31 | patient.id = NULL,
32 | driverGene,
33 | class = "SP",
34 | classByTumor = FALSE,
35 | vaf.cutoff = 0.01,
36 | silent.columns = NULL
37 | ) {
38 |
39 | # To do: be careful about the samples and tumors.
40 |
41 | class.levels <- NULL
42 | if (class == "SP") {
43 | class.levels <- c("Public", "Shared", "Private")
44 | } else if (class == "CS") {
45 | class.levels <- c("Clonal", "Subclonl")
46 | } else if (class == "SPCS") {
47 | class.levels <- c("Public_Clonal", "Shared_Clonal", "Shared_Subclonal", "Private_Subclonal")
48 | }
49 |
50 | if(is.null(silent.columns)){
51 | silent.columns = c("Silent", "3'Flank", "IGR", "Intron", "RNA")
52 | }
53 |
54 | ######################################################################
55 |
56 | estProp <- function(patient.id, maf_input, maf_class) {
57 | # Merge the maf input and mutation class
58 | message(patient.id)
59 |
60 | maf_merge <- maf_input[[patient.id]] %>%
61 | dplyr::mutate(Mut_ID = stringr::str_c(Hugo_Symbol, Chromosome, Start_Position,
62 | Reference_Allele, Tumor_Seq_Allele2,
63 | sep = ":"
64 | )) %>%
65 | dplyr::left_join(
66 | maf_class[[patient.id]]
67 | ) %>%
68 | dplyr::select(
69 | Hugo_Symbol, Chromosome, Start_Position, End_Position,
70 | Reference_Allele, Tumor_Seq_Allele2, Tumor_Sample_Barcode,
71 | Mutation_Type, Patient_ID, Tumor_ID, Variant_Classification, VAF
72 | )
73 |
74 | maf_data = maf_merge %>%
75 | #only keep non-silent mutations
76 | filter(!Variant_Classification %in% silent.columns) %>%
77 | mutate(is.driver = ifelse(Hugo_Symbol %in% driverGene, TRUE, FALSE) ) %>%
78 | mutate(type = paste(Tumor_ID, Mutation_Type, sep = ":") ) %>%
79 | group_by(Tumor_ID, Mutation_Type, is.driver) %>%
80 | summarise(num = n()) %>%
81 | group_by(Tumor_ID, Mutation_Type) %>%
82 | mutate(num_total = sum(num)) %>%
83 | filter(is.driver) %>%
84 | mutate(prop = num/num_total,
85 | Mutation_Type = factor(Mutation_Type, levels = class.levels)
86 | )
87 |
88 |
89 | p1 = maf_data %>%
90 | ggplot2::ggplot(ggplot2::aes(x = Tumor_ID, y = prop, fill = Mutation_Type)) +
91 | ggplot2::geom_bar(stat = "identity", position = ggplot2::position_dodge(width = 0.90)) +
92 | theme_bw() +
93 | ggplot2::labs(x = NULL, y = latex2exp::TeX("Prop of driver mutations")) +
94 | ggplot2::scale_fill_manual(values = set.colors(length(unique(maf_data$Mutation_Type)))) +
95 | ggplot2::theme(
96 | axis.title.x = element_blank(),
97 | axis.text.x = element_text(angle = 0, hjust = 0.5, size = 14),
98 | axis.title.y = element_text(size = 16)
99 | )
100 |
101 |
102 | list(
103 | maf.prop = maf_data,
104 | plot = p1
105 | )
106 | }
107 | ##########################################################################
108 | # running
109 |
110 | # Get the mutation groups.
111 | maf_input <- MesKit::subMaf(maf, patient.id = patient.id, mafObj = FALSE, use.tumorSampleLabel = TRUE)
112 |
113 | # get mutation classifications.
114 | maf_class <- MesKit::classifyMut(maf, patient.id = patient.id, class = class, classByTumor = classByTumor)
115 |
116 | # Note the different format between maf_input and maf_class when the patient.id is a single value.
117 | if (!is.null(patient.id)) {
118 | maf_class1 <- list()
119 | maf_class1[[patient.id]] <- maf_class
120 | maf_class <- maf_class1
121 | }
122 |
123 | prop <- lapply(names(maf_input), estProp, maf_input, maf_class)
124 | names(prop) <- names(maf_input)
125 |
126 | return(
127 | prop
128 | )
129 | }
130 |
131 |
132 |
133 |
--------------------------------------------------------------------------------
/R/tree2timescape.R:
--------------------------------------------------------------------------------
1 | #' tree2timescape
2 | #'
3 | #' This function generates the input of timescape to visual the fisher plot of
4 | #' clonal evolution by using the results of [inferClonalTree()].
5 | #'
6 | #' @param results the clonal trees that generated by [inferClonalTree()].
7 | #' @param samples the samples to show in the fisher plot.
8 | #'
9 | #' @import clonevol
10 | #' @export
11 | tree2timescape <- function(results, samples = NULL) {
12 | if (is.null(samples)) {
13 | samples <- names(results$models)
14 | } else {
15 | if (!all(samples %in% names(results$models))) {
16 | stop("check input samplesNames : ", samples[!samples %in% names(results$models)])
17 | }
18 | }
19 |
20 | # store the clonevol results in a list
21 | res <- list(
22 | samples = samples, clonevol.clone.names = NULL, clonevol.clone.colors = NULL,
23 | timepoints = seq(1, length(samples)), num.models = nrow(results$matched$index),
24 | parents = list(), cell.fractions = list(), all = list()
25 | )
26 |
27 | clonevol.clone.names <- NULL
28 | clone.nums <- NULL
29 | clonevol.clone.colors <- NULL
30 |
31 | # create the needed inputs to fishplot
32 | for (i in 1:nrow(results$matched$index)) {
33 | vv <- NULL
34 | for (s in samples) {
35 | v <- results$models[[s]][[results$matched$index[i, s]]]
36 | # if (rescale){v = rescale.vaf(v)}
37 | v <- clonevol:::rescale.vaf(v)
38 | v <- v[, c("lab", "vaf", "parent", "color")]
39 |
40 | ## scale vaf and make cell.frac
41 | max.vaf <- max(v$vaf)
42 | scale <- 0.5 / max.vaf * 2 * 100
43 | v$vaf <- v$vaf * scale
44 | v$vaf[v$vaf > 100] <- 100 # safeguard against rounding error making some vaf slightly > 100
45 |
46 | colnames(v) <- c("clone", s, "parent", "color")
47 | v <- v[!is.na(v$parent) & v$clone != "0", ]
48 | if (is.null(vv)) {
49 | vv <- v
50 | } else {
51 | vv <- merge(vv, v, all = TRUE)
52 | }
53 | }
54 | for (s in samples) {
55 | vv[is.na(vv[[s]]), s] <- 0
56 | }
57 | vv <- vv[order(as.integer(vv$clone)), ]
58 | vv$parent[vv$parent == "-1"] <- 0
59 | rownames(vv) <- vv$clone
60 |
61 | ## fishplot requires clones to be named in sequential order. Do that, but
62 | ## store the clonevol-generated names and colors for pass-through
63 | if (is.null(clone.nums)) {
64 | clone.nums <- c(0, seq(1, nrow(vv)))
65 | names(clone.nums) <- c(0, vv$clone)
66 |
67 | clonevol.clone.names <- names(clone.nums)
68 | names(clonevol.clone.names) <- as.character(clone.nums)
69 | res$clonevol.clone.names <- clonevol.clone.names[-1]
70 |
71 | clonevol.clone.colors <- c("white", vv$color)
72 | names(clonevol.clone.colors) <- as.character(clone.nums)
73 | res$clonevol.clone.colors <- clonevol.clone.colors[-1]
74 | }
75 | vv$clone <- clone.nums[vv$clone]
76 | vv$parent <- clone.nums[vv$parent]
77 |
78 | par <- vv$parent
79 | frac <- vv[, samples]
80 | res$parents[[i]] <- par
81 | res$cell.fractions[[i]] <- as.matrix(frac)
82 | res$all[[i]] <- vv
83 | }
84 |
85 | ##############################
86 | # for timescape input
87 |
88 | times <- list(
89 | clonal_prev = list(),
90 | tree_edges = list(),
91 | clone_colours = list()
92 | )
93 |
94 | for (i in 1:res$num.models) {
95 | # re-set ancestor clonal prev
96 |
97 | # get sum of prev of certain clone.
98 | clonal_prev_ancestor <- res$all[[i]] %>%
99 | dplyr::mutate(clone = rownames(.)) %>%
100 | data.table::melt(
101 | id.vars = c("clone", "parent"),
102 | measure.vars = samples
103 | ) %>%
104 | dplyr::group_by(variable, parent) %>%
105 | dplyr::summarise(sumvalue = sum(value)) %>%
106 | dplyr::rename(clone = parent) %>%
107 | dplyr::mutate(clone = as.character(clone))
108 |
109 | # prev = curent - ancestor
110 | times$clonal_prev[[i]] <- res$all[[i]] %>%
111 | dplyr::mutate(clone = rownames(.)) %>%
112 | data.table::melt(
113 | id.vars = c("clone", "parent"),
114 | measure.vars = samples
115 | ) %>%
116 | dplyr::left_join(clonal_prev_ancestor) %>%
117 | dplyr::mutate(
118 | sumvalue = ifelse(is.na(sumvalue), 0, sumvalue),
119 | value1 = value - sumvalue,
120 | # set value1 = 0 if value1 <=0
121 | value1 = ifelse(value1 < 0, 0, value1)
122 | ) %>%
123 | dplyr::select(clone, variable, value1) %>%
124 | dplyr::rename(
125 | clone_id = clone,
126 | timepoint = variable,
127 | clonal_prev = value1
128 | ) %>% # set arrange of samples.
129 | dplyr::mutate(timepoint = factor(timepoint, levels = samples)) %>%
130 | dplyr::arrange(timepoint) %>%
131 | dplyr::mutate(timepoint = as.character(timepoint))
132 |
133 | # re-mapping clone ids.
134 | cloneNames <- setNames(
135 | c(0, rownames(res$all[[i]])),
136 | nm = c(0, res$all[[i]]$clone)
137 | )
138 |
139 | times$tree_edges[[i]] <- data.frame(
140 | source = cloneNames[as.character(res$parents[[i]])],
141 | target = rownames(res$all[[i]])
142 | ) %>%
143 | filter(source != "0")
144 |
145 | times$clone_colours[[i]] <- data.frame(
146 | clone_id = rownames(res$all[[i]]),
147 | colour = res$all[[i]]$color
148 | )
149 | }
150 |
151 | times
152 | }
153 |
--------------------------------------------------------------------------------
/docs/reference/Seg-class.html:
--------------------------------------------------------------------------------
1 |
2 |
35 |
81 |
82 |
83 |
84 |
85 |
86 |
87 |
88 |
--------------------------------------------------------------------------------
/docs/reference/set.colors.html:
--------------------------------------------------------------------------------
1 |
2 |
36 |
70 |
71 |
72 |
37 | ![]()
40 |
41 |
42 | Segment Class
38 | 39 |Seg-class.Rd
43 |
45 |
46 |
47 | Segment Class
44 |
48 |
68 |
69 | Slots
49 | 50 | 51 |data
52 | data.tableof segment file containing CNA information.
53 |
54 |
55 | sample.inof
56 | data.frameof sample information per patient.
57 |
58 |
59 | ref.build
60 | human reference genome version. Default 'hg19'. Optional: 'hg18' or 'hg38'.
61 |
62 |
63 | allele
64 | Indicate whether this is allele-specific CNAs. Default: TRUE.
65 |
66 |
67 |
35 |
74 |
75 |
76 |
77 |
78 |
79 |
80 |
81 |
--------------------------------------------------------------------------------
/docs/reference/write.fasta.html:
--------------------------------------------------------------------------------
1 |
2 |
36 |
63 |
64 |
65 |
37 | ![]()
40 |
41 |
42 | Color setting
38 | 39 |set.colors.Rd
43 |
45 |
46 |
50 |
51 |
60 |
61 | Color setting
44 |
35 |
64 |
65 |
66 |
75 |
76 |
77 |
78 |
79 |
80 |
81 |
82 |
--------------------------------------------------------------------------------
/docs/reference/pipe.html:
--------------------------------------------------------------------------------
1 |
2 |
35 |
65 |
66 |
67 |
76 |
77 |
78 |
79 |
80 |
81 |
82 |
83 |
--------------------------------------------------------------------------------
/R/plotVafCluster.R:
--------------------------------------------------------------------------------
1 | #' plotVafCluster
2 | #'
3 | #' Plot variant clustering in each sample by using combination of box,
4 | #' violin and jitter plots.
5 | #'
6 | #' @param variants data frame of the variants.
7 | #' At least cluster column and VAF or CCF columns are required.
8 | #' Cluster column should contain cluster identities as continuous integer values
9 | #' starting from 1.
10 | #' @param cluster.col.name the column names that containing cluster
11 | #' information (Default = "cluster").
12 | #' @param vaf.col.names the column names of samples containing VAF.
13 | #' @param violin whether plotting violin (Default = FALSE).
14 | #' @param box whether plotting box (Default = TRUE).
15 | #' @param jitter whether plotting jitter plot (Default = TRUE).
16 | #' @param founding.cluster the name of founding clones, one of the most important parameters. For most of circumstances, the founding cluster is the cluster with the highest average CCF cluster.
17 | #' @param clone.colors setting clone colors.
18 | #' @param highlight column name to indicate whether highlight the sites (TRUE or FALSE).
19 | #' @param highlight.note.col.name highlight context.
20 | #' @param output.file the output file name (Default = NULL)
21 | #' @import clonevol
22 | #' @return a ggplot object
23 | #' @export
24 | plotVafCluster <- function(variants,
25 | cluster.col.name = "cluster",
26 | vaf.col.names,
27 | clone.colors = NULL,
28 | violin = FALSE,
29 | box = TRUE,
30 | jitter = TRUE,
31 | founding.cluster = 1,
32 | output.file = NULL,
33 | highlight = NULL,
34 | highlight.note.col.name = NULL) {
35 | if (is.null(clone.colors)) {
36 |
37 | # Visualizing the variant clusters
38 | set.colors <- c(
39 | "#C6C6C6", "#6FDCBF", "#5AA36E", "#E99692",
40 | "#B4D985", "#EA7D23", "#E53CFB", "#4B85B7",
41 | "#8439FA", "#BD8736", "#B3B371", "#A7C7DE",
42 | "#EE97FC", "#57C222", "#BFABD0", "#44589B",
43 | "#794C18",
44 | RColorBrewer::brewer.pal(n = 10, name = "Paired")
45 | )
46 |
47 | clone.colors <- set.colors[1:length(unique(variants[, cluster.col.name]))]
48 | }
49 |
50 | pp <- clonevol::plot.variant.clusters(variants,
51 | show.cluster.size = F,
52 | show.cluster.label = F,
53 | cluster.col.name = cluster.col.name,
54 | vaf.col.names = vaf.col.names,
55 | violin = violin,
56 | box = box,
57 | jitter = jitter,
58 | jitter.shape = 1,
59 | variant.class.col.name = cluster.col.name,
60 | # vaf.limits =
61 | jitter.color = clone.colors,
62 | jitter.size = 1.2,
63 | jitter.alpha = 1,
64 | jitter.width = 0.2,
65 | jitter.center.method = "median",
66 | jitter.center.size = 1,
67 | jitter.center.color = "darkgray",
68 | jitter.center.display.value = "none",
69 | display.plot = FALSE,
70 | horizontal = TRUE,
71 | order.by.total.vaf = F,
72 | highlight = highlight,
73 | highlight.shape = 21,
74 | highlight.color = "blue",
75 | highlight.fill.color = "green",
76 | highlight.size = 2.5,
77 | highlight.note.col.name = NULL,
78 | highlight.note.size = 2,
79 | highlight.note.color = "blue",
80 | highlight.note.angle = 0,
81 | founding.cluster = founding.cluster,
82 | ccf = FALSE
83 | )
84 |
85 | # add annotation of driver genes.
86 | if (!is.null(highlight)) {
87 | if (any(mutdata[, highlight])) {
88 | labels <- pp[[1]]$data
89 | # select colors for annotation.
90 | clone.colors.sel <- unique(clone.colors[labels[, cluster.col.name][labels[, highlight]]])
91 |
92 | pp1 <- labels %>%
93 | dplyr::filter(is.driver) %>%
94 | dplyr::mutate(cluster_1 = factor(cluster)) %>%
95 | ggplot2::ggplot(ggplot2::aes(y = cluster, x = 1, label = gene_site)) +
96 | ggplot2::theme_classic() +
97 | ggplot2::geom_point(ggplot2::aes(color = cluster_1), size = 3) +
98 | ggrepel::geom_text_repel(
99 | nudge_x = 0.15,
100 | direction = "y",
101 | hjust = 0,
102 | segment.size = 0.2,
103 | size = 3,
104 | ) +
105 | ggplot2::ylim(0, length(clone.colors) + 1) +
106 | ggplot2::xlim(1, 0.8) +
107 | ggplot2::scale_color_manual(values = clone.colors.sel, guide = "none") +
108 | ggplot2::theme(
109 | axis.line = ggplot2::element_blank(),
110 | axis.ticks = ggplot2::element_blank(),
111 | axis.text = ggplot2::element_blank(),
112 | axis.title.x = ggplot2::element_blank(),
113 | axis.title.y = ggplot2::element_blank(),
114 | plot.title = ggplot2::element_text(hjust = 0.5)
115 | )
116 |
117 | pp[[length(pp) + 1]] <- pp1
118 | }
119 | }
120 |
121 | if (!is.null(output.file)) {
122 | pdf(output.file, width = 2 * length(pp), height = 4)
123 | ggpubr::ggarrange(plotlist = pp, ncol = length(pp), align = "h")
124 | dev.off()
125 | }
126 |
127 | ggpubr::ggarrange(plotlist = pp, ncol = length(pp), align = "h")
128 | }
129 |
--------------------------------------------------------------------------------
/docs/authors.html:
--------------------------------------------------------------------------------
1 |
2 |
35 |
83 |
84 |
85 |
86 |
87 |
88 |
89 |
90 |
--------------------------------------------------------------------------------
/docs/reference/getKaKs.html:
--------------------------------------------------------------------------------
1 |
2 |
36 |
72 |
73 |
74 |
37 | ![]()
39 |
40 | Authors and Citation
38 |
41 |
52 |
53 | Authors
42 | 43 |
54 |
70 | Citation
55 | 56 | 57 |Chen Q, Wang S (2022). 58 | MPTevol: Clonal Evolutionary History and Metastatic Routines Analysis for 59 | Multiple Primary Tumors. 60 | R package version 0.1.0. 61 |
62 |@Manual{,
63 | title = {MPTevol: Clonal Evolutionary History and Metastatic Routines Analysis for
64 | Multiple Primary Tumors},
65 | author = {Qinjian Chen and Shixiang Wang},
66 | year = {2022},
67 | note = {R package version 0.1.0},
68 | }
69 |
35 |
74 |
75 |
76 |
77 |
78 |
79 |
80 |
81 |
--------------------------------------------------------------------------------
/docs/reference/plotCNAProfile.html:
--------------------------------------------------------------------------------
1 |
2 |
36 |
63 |
64 |
65 |
37 | ![]()
40 |
41 |
42 | getKaKs compares Ka/Ks between different groups
38 | 39 |getKaKs.Rd
43 |
45 |
46 |
50 |
51 | getKaKs compares Ka/Ks between different groups
44 |
52 |
60 |
61 | Arguments
53 |- df 54 |
data. Six columns are required to calculate the Ka/Ks, 55 | including "Tumor_Sample_Barcode","Chromosome","Start_Position", 56 | "Reference_Allele","Tumor_Seq_Allele2" and "VAF".
57 | - vaf_cutoff 58 |
VAF cutoff. Removing mutations with low variant allele frequency (VAF).
59 |
37 |
75 |
76 |
77 |
78 |
79 |
80 |
81 |
82 |
--------------------------------------------------------------------------------
/docs/reference/MPTevol-package.html:
--------------------------------------------------------------------------------
1 |
2 |
38 |
64 |
65 |
66 |
39 | ![]()
42 |
43 |
44 | Visualize CNA profile
40 | 41 |plotCNAProfile.Rd
45 |
48 |
49 |
53 |
54 |
61 |
62 | This function plots the allele-specific CNAs of multiple-samples.
46 | See readCNAProfile() for examples.
35 |
65 |
66 |
67 |
68 |
69 |
70 |
71 |
72 |
--------------------------------------------------------------------------------
/docs/reference/tree2timescape.html:
--------------------------------------------------------------------------------
1 |
2 |
36 |
54 |
55 |
56 |
37 | ![]()
40 |
41 |
42 | MPTevol: Clonal Evolutionary History and Metastatic Routines Analysis for Multiple Primary Tumors
38 | 39 |MPTevol-package.Rd
43 |
45 |
46 |
47 | Provides a practical computation framework for dissecting the evolution of multiple primary tumors (MPT), reducing analysis complexity with modular design.
44 |
48 |
52 |
53 | Author
49 |Maintainer: Qinjian Chen chenqingjian2010@163.com (ORCID)
50 |Authors:
Shixiang Wang w_shixiang@163.com (ORCID)
51 |
37 |
75 |
76 |
77 |
78 |
79 |
80 |
81 |
82 |
--------------------------------------------------------------------------------
/R/readMaf.R:
--------------------------------------------------------------------------------
1 | #' readMaf
2 | #' @description Read tab delimited MAF (can be plain text or *.gz compressed) file along with sample information file.
3 | #'
4 | #' @param mafFile A tab delimited MAF file (plain text or *.gz compressed). Required.
5 | #' @param clinicalFile A clinical data file includes Tumor_Sample_Barcode, Tumor_ID, Patient_ID. Tumor_Sample_Label is optional. Default NULL.
6 | #' @param ccfFile A CCF file of somatic mutations. Default NULL.
7 | #' @param adjusted.VAF Whether adjusted VAF is included in mafFile. Default FALSE.
8 | #' @param nonSyn.vc List of Variant classifications which are considered as non-silent. Default NULL, use Variant Classifications with "Frame_Shift_Del","Frame_Shift_Ins","Splice_Site","Translation_Start_Site","Nonsense_Mutation","Nonstop_Mutation","In_Frame_Del","In_Frame_Ins","Missense_Mutation"
9 | #' @param use.indel.ccf Whether include indels in ccfFile. Default FALSE.
10 | #' @param ccf.conf.level The confidence level of CCF to identify clonal or subclonal.
11 | #' Only works when "CCF_std" or "CCF_CI_high" is provided in ccfFile. Default 0.95.
12 | #' @param remove.empty.VAF Whether removing the mutations with VAF=0. When making the comparison of pair-wide CCF, retained mutations with VAF=0.
13 | #' @param refBuild Human reference genome version. Default 'hg19'. Optional: 'hg18' or 'hg38'.
14 | #'
15 | #' @examples
16 | #' maf.File <- system.file("extdata/", "CRC_HZ.maf", package = "MesKit")
17 | #' clin.File <- system.file("extdata/", "CRC_HZ.clin.txt", package = "MesKit")
18 | #' ccf.File <- system.file("extdata/", "CRC_HZ.ccf.tsv", package = "MesKit")
19 | #' maf <- readMaf(mafFile=maf.File,clinicalFile = clin.File, refBuild="hg19")
20 | #' maf <- readMaf(mafFile=maf.File, clinicalFile = clin.File, ccfFile=ccf.File, refBuild="hg19")
21 | #' @return an object of Maf or MafList.
22 | #' @import methods
23 | #' @importFrom data.table fread setkey
24 | #' @importFrom stats qnorm
25 | #' @export readMaf
26 |
27 | ## read.maf main function
28 | readMaf <- function(
29 | mafFile,
30 | clinicalFile,
31 | ccfFile = NULL,
32 | adjusted.VAF = FALSE,
33 | nonSyn.vc = NULL,
34 | use.indel.ccf = FALSE,
35 | ccf.conf.level = 0.95,
36 | remove.empty.VAF = TRUE,
37 | refBuild = "hg19"
38 | ) {
39 |
40 | refBuild <- match.arg(refBuild, choices = c('hg18', 'hg19', 'hg38'), several.ok = FALSE)
41 |
42 | ## get non-silent muation types
43 | if (is.null(nonSyn.vc)) {
44 | nonSyn.vc <- c(
45 | "Frame_Shift_Del",
46 | "Frame_Shift_Ins",
47 | "Splice_Site",
48 | "Translation_Start_Site",
49 | "Nonsense_Mutation",
50 | "Nonstop_Mutation",
51 | "In_Frame_Del",
52 | "In_Frame_Ins",
53 | "Missense_Mutation"
54 | )
55 | }
56 |
57 | maf_data <- data.table::fread(
58 | file = mafFile,
59 | quote = "",
60 | header = TRUE,
61 | data.table = TRUE,
62 | fill = TRUE,
63 | sep = '\t',
64 | skip = "Hugo_Symbol",
65 | stringsAsFactors = FALSE
66 | )
67 |
68 | clin_data <- data.table::fread(
69 | file = clinicalFile,
70 | quote = "",
71 | header = TRUE,
72 | data.table = TRUE,
73 | fill = TRUE,
74 | sep = '\t',
75 | stringsAsFactors = FALSE
76 | )
77 |
78 |
79 | ## merge maf data and clinical data
80 | maf_col <- colnames(maf_data)
81 | clin_col <- colnames(clin_data)
82 | is_col <- intersect(maf_col, clin_col)
83 | is_col <- is_col[is_col!="Tumor_Sample_Barcode"]
84 | maf_data <- dplyr::select(maf_data, -all_of(is_col))
85 | maf_data <- dplyr::left_join(
86 | maf_data,
87 | clin_data,
88 | by = c(
89 | "Tumor_Sample_Barcode"
90 | )
91 | )
92 |
93 | # check maf data
94 | maf_data <- validMaf(maf_data, remove.empty.VAF)
95 |
96 | ## calculate Total_allele_depth
97 | maf_data <- maf_data %>%
98 | dplyr::mutate(Total_allele_depth = .data$Ref_allele_depth + .data$Alt_allele_depth) %>%
99 | as.data.frame()
100 |
101 | if(adjusted.VAF){
102 | maf_data$VAF_adj <- maf_data$VAF
103 | }
104 |
105 |
106 | ## read ccf files
107 | if (!is.null(ccfFile)) {
108 | ccf_data <- suppressWarnings(data.table::fread(
109 | ccfFile,
110 | quote = "",
111 | header = TRUE,
112 | fill = TRUE,
113 | sep = '\t',
114 | stringsAsFactors = FALSE
115 | ))
116 | ## check ccf_data
117 | ccf_data <- validCCF(ccf_data, maf_data, use.indel.ccf = use.indel.ccf)
118 | ## merge ccf_data to maf_data
119 | maf_data <- MesKit:::readCCF(maf_data, ccf_data, ccf.conf.level, sample.info, adjusted.VAF, use.indel.ccf = use.indel.ccf)
120 | }
121 |
122 | ## calculate average adjust VAF
123 | if("VAF_adj" %in% colnames(maf_data)){
124 | maf_data <- maf_data %>%
125 | dplyr::group_by(.data$Patient_ID, .data$Tumor_ID, .data$Chromosome,
126 | .data$Start_Position, .data$Reference_Allele,.data$Tumor_Seq_Allele2) %>%
127 | dplyr::mutate(Tumor_Average_VAF = round(
128 | sum(.data$VAF_adj * .data$Total_allele_depth)/
129 | sum(.data$Total_allele_depth)
130 | ,3))
131 |
132 | }
133 |
134 | maf_data <- maf_data %>%
135 | dplyr::ungroup() %>%
136 | dplyr::select(-"Total_allele_depth") %>%
137 | as.data.frame()
138 |
139 | data_list <- split(maf_data, maf_data$Patient_ID)
140 | maf_patient_list <- list()
141 | for(data in data_list){
142 | patient <- unique(data$Patient_ID)
143 | sample.info <- data %>%
144 | dplyr::select("Tumor_Sample_Barcode","Tumor_ID") %>%
145 | dplyr::distinct(.data$Tumor_Sample_Barcode, .keep_all = TRUE)
146 | if(nrow(sample.info) < 2){
147 | n <- nrow(sample.info)
148 | stop(paste0(patient," has only ",n," tumor samples.",
149 | "A minimum of two tumor samples are required for each patient."))
150 | }
151 | ## set Maf
152 | maf <- MesKit:::Maf(
153 | data = data.table::setDT(data),
154 | sample.info = as.data.frame(sample.info),
155 | nonSyn.vc = nonSyn.vc,
156 | ref.build = refBuild
157 | )
158 | maf_patient_list[[patient]] <- maf
159 | }
160 |
161 | if(length(data_list) > 1){
162 | ## set MafList
163 | maf_list <- MesKit:::MafList(maf_patient_list)
164 | return(maf_list)
165 | }else{
166 | return(maf_patient_list[[1]])
167 | }
168 | }
169 |
170 |
171 |
172 |
--------------------------------------------------------------------------------
/R/validation.R:
--------------------------------------------------------------------------------
1 | validMaf <- function(maf_data, remove.empty.VAF = TRUE){
2 | ## check required columns
3 | maf_standardcol <- c("Hugo_Symbol","Chromosome","Start_Position","End_Position",
4 | "Variant_Classification", "Variant_Type", "Reference_Allele",
5 | "Tumor_Seq_Allele2","Ref_allele_depth","Alt_allele_depth",
6 | "VAF", "Tumor_Sample_Barcode","Patient_ID","Tumor_ID")
7 |
8 | if(!all(maf_standardcol %in% colnames(maf_data))){
9 | missing_fileds_maf <- maf_standardcol[!maf_standardcol %in% colnames(maf_data)]
10 | info <- paste(missing_fileds_maf, collapse = ",")
11 | stop(paste0("Missing ", info, " from mafFile"))
12 | }
13 |
14 | maf_data$Chromosome <- as.character(maf_data$Chromosome)
15 | maf_data$Tumor_Sample_Barcode <- as.character(maf_data$Tumor_Sample_Barcode)
16 | maf_data$Patient_ID <- as.character(maf_data$Patient_ID)
17 | maf_data$Tumor_ID <- as.character(maf_data$Tumor_ID)
18 |
19 | #***** modify by CQJ ******
20 | # retaining mutations with VAF==0, thus the pair-wide comparisons of CCF are optimal.
21 |
22 | if(remove.empty.VAF ){
23 | ## remove VAF = 0
24 | maf_data <- maf_data[maf_data$VAF!=0]
25 | }
26 |
27 |
28 | ## remove mutation in chromosome M and chromosome MT
29 | maf_data <- maf_data[!maf_data$Chromosome %in% c("M", "MT")]
30 |
31 | ## sort HugoSymbol
32 | # maf_data <- preprocess_HugoSymbol(maf_data)
33 |
34 | ## Rescale vaf coloum 0-1
35 | if(max(maf_data$VAF, na.rm = TRUE) > 1){
36 | maf_data$VAF <- as.numeric(as.character(maf_data$VAF))/100
37 | }
38 |
39 | return(maf_data)
40 | }
41 |
42 |
43 | validCCF <- function(ccf_data, maf_data, use.indel.ccf){
44 |
45 | patients_in_maf <- sort(unique(maf_data$Patient_ID))
46 | patients_in_ccf <- sort(unique(ccf_data$Patient_ID))
47 | if(!identical(patients_in_maf, patients_in_ccf)){
48 | patient_setdiff <- setdiff(patients_in_maf, patients_in_ccf)
49 | warning("Patient: ",paste0(paste(patient_setdiff, collapse = ", "), " are not in ccf data"))
50 | }
51 |
52 | tsb_in_maf <- sort(unique(maf_data$Tumor_Sample_Barcode))
53 | tsb_in_ccf <- sort(unique(ccf_data$Tumor_Sample_Barcode))
54 | if(!identical(tsb_in_maf, tsb_in_ccf)){
55 | tsb_setdiff <- setdiff(tsb_in_maf, tsb_in_ccf)
56 | warning("Tumor sample barcodes: ",paste0(paste(tsb_setdiff, collapse = ", "), " are not in ccf data"))
57 | }
58 |
59 |
60 | ccf_standardcol <- c("Patient_ID", "Tumor_Sample_Barcode", "Chromosome", "Start_Position", "CCF")
61 |
62 | #***** modify by CQJ ******
63 | #* add the Cluster information in CCF data.
64 |
65 | if("Cluster" %in% colnames(ccf_data)){
66 |
67 | ccf_data$Cluster = as.integer(ccf_data$Cluster)
68 |
69 | if( all(is.na(ccf_data$Cluster))) {
70 | warning("Please checking the Cluster column, the Cluster should be integer")
71 | }else{
72 | ccf_standardcol = c(ccf_standardcol, "Cluster")
73 | }
74 | }
75 |
76 |
77 | if(!all(ccf_standardcol %in% colnames(ccf_data))){
78 | missing_fileds_ccf <- ccf_standardcol[!ccf_standardcol %in% colnames(ccf_data)]
79 | info <- paste(missing_fileds_ccf, collapse = ", ")
80 | stop(paste0("Missing ", info, " from ccfFile"))
81 | }
82 |
83 | if(use.indel.ccf){
84 | indel.ccf.col <- c("Reference_Allele", "Tumor_Seq_Allele2")
85 | if(!all(indel.ccf.col %in% colnames(ccf_data))){
86 | missing_fileds_ccf <- indel.ccf.col[!indel.ccf.col %in% colnames(ccf_data)]
87 | info <- paste(missing_fileds_ccf, collapse = ", ")
88 | stop(paste0("Missing ", info, " from ccfFile when use.indel.ccf is TRUE"))
89 | }
90 | }else{
91 | indel.ccf.col <- NULL
92 | }
93 |
94 | ccf_data$Patient_ID <- as.character(ccf_data$Patient_ID)
95 | ccf_data$Tumor_Sample_Barcode <- as.character(ccf_data$Tumor_Sample_Barcode)
96 | ccf_data$Chromosome <- as.character(ccf_data$Chromosome)
97 | ccf_data$CCF <- as.numeric(ccf_data$CCF)
98 | # if("CCF_Std" %in% colnames(ccf_data)){
99 | # ccf_data$CCF_Std <- as.numeric(ccf_data$CCF_Std)
100 | # }
101 |
102 |
103 | # if("CCF_Std" %in% colnames(ccf_data)){
104 | # ccf_data$CCF_Std <- as.numeric(ccf_data$CCF_Std)
105 | # ccf_data <- dplyr::select(ccf_data, "Patient_ID", "Tumor_Sample_Barcode", "Chromosome", "Start_Position", "CCF", "CCF_Std", dplyr::all_of(indel.ccf.col))
106 | # }else{
107 | # ccf_data <- dplyr::select(ccf_data, "Patient_ID", "Tumor_Sample_Barcode", "Chromosome", "Start_Position", "CCF", dplyr::all_of(indel.ccf.col))
108 | # }
109 | #
110 |
111 | keep.columns = c("Patient_ID", "Tumor_Sample_Barcode", "Chromosome", "Start_Position", "CCF")
112 |
113 | if("CCF_Std" %in% colnames(ccf_data)){
114 | keep.columns = c(keep.columns, "CCF_Std")
115 | }
116 |
117 | if("Cluster" %in% colnames(ccf_data)){
118 | keep.columns = c(keep.columns, "Cluster")
119 | }
120 |
121 | ccf_data <- dplyr::select(ccf_data,
122 | dplyr::all_of(keep.columns),
123 | dplyr::all_of(indel.ccf.col))
124 |
125 |
126 | return(ccf_data)
127 | }
128 |
129 | validSeg <- function(seg){
130 | seg_standardcol <- c("Patient_ID","Tumor_Sample_Barcode",
131 | "Chromosome","Start_Position",
132 | "End_Position")
133 | if(!all(seg_standardcol %in% colnames(seg))){
134 | missing_fileds_seg <- seg_standardcol[!seg_standardcol %in% colnames(seg)]
135 | info <- paste(missing_fileds_seg, collapse = ", ")
136 | stop(paste0("Missing ", info, " from segFile"))
137 | }
138 | seg$Chromosome = gsub(pattern = 'chr', replacement = '', x = seg$Chromosome, fixed = TRUE)
139 | seg$Chromosome = gsub(pattern = 'X', replacement = '23', x = seg$Chromosome, fixed = TRUE)
140 | seg$Chromosome = gsub(pattern = 'Y', replacement = '24', x = seg$Chromosome, fixed = TRUE)
141 |
142 | seg$Patient_ID <- as.character(seg$Patient_ID)
143 | seg$Tumor_Sample_Barcode <- as.character(seg$Tumor_Sample_Barcode)
144 | seg$Start_Position <- as.numeric(seg$Start_Position)
145 | seg$End_Position <- as.numeric(seg$End_Position)
146 |
147 | return(seg)
148 | }
149 |
150 |
151 | validClinicalData <- function(clin_data, maf_data){
152 | ## check Tumor_Sample_Barcode of maf data and clinical data
153 | clin_tb_count <- table(clin_data$Tumor_Sample_Barcode)
154 | if(length(which(clin_tb_count > 1)) > 0){
155 | rep_tb <- names(clin_tb_count)[which(clin_tb_count > 1)]
156 | stop(paste0("There are more than one ", paste(rep_tb, collapse = ", "), " in clinical data!"))
157 | }
158 |
159 |
160 | maf_tb <- unique(maf_data$Tumor_Sample_Barcode)
161 | clin_tb <- unique(clin_data$Tumor_Sample_Barcode)
162 | tb_setdiff <- setdiff(maf_tb, clin_tb)
163 |
164 | if(length(tb_setdiff) > 0){
165 | stop(paste0("Information about Tumor_Sample_Barcode ", paste(tb_setdiff, collapse = ", "), " cannot be found in clinical data!"))
166 | }
167 |
168 | return(clin_data)
169 |
170 | }
171 |
172 |
173 |
--------------------------------------------------------------------------------
/R/plotCNATree.R:
--------------------------------------------------------------------------------
1 | # library(ggtree)
2 | # library(treeio)
3 | # library(phangorn)
4 | # library(MEDICCquant)
5 |
6 |
7 | #' plotCNAtree plots phylogenetic trees of CNAs
8 | #'
9 | #' The CNAs trees were constructed by MEDICC.
10 | #'
11 | #' @param dist dist files that generated by MEDICC.
12 | #' @param bootstrap.rep.num number of bootstrap steps.
13 | #' @param group a list that used to indicate the sample groups
14 | #' @param group.colors an array indicates the colors of sample groups.
15 | #' @param title title of the plot.
16 | #' @param normal.node the sample name of normal sample in the tree.
17 | #' @param hexpand_ratio hexpand ratio. see \code{\link[ggtree]{hexpand}}
18 | #'
19 | #' @examples
20 | #' # read samples distances.
21 | #' # This dist file is the output of MEDICC
22 | #' dist <- system.file(package = "MPTevol", "extdata", "tree_final.dist")
23 | #'
24 | #' # set group information
25 | #' group <- list(
26 | #' NORMAL = "NORMAL",
27 | #' Breast = paste0("Breast_", 1:5),
28 | #' Coad = paste0("Coad_", 1:5),
29 | #' Lung = paste0("Lung_", 1:5),
30 | #' OveryLM = paste0("OveryLM_", 1:5),
31 | #' OveryRM = paste0("OveryRM_", 1:6),
32 | #' UterusM = paste0("UterusM_", c(1:7))
33 | #' )
34 | #'
35 | #' # set group colors
36 | #' group.colors <- setNames(set.colors(n = length(group)), nm = names(group))
37 | #'
38 | #' # built trees
39 | #' tree <- plotCNAtree(
40 | #' dist = dist,
41 | #' group = group,
42 | #' group.colors = group.colors
43 | #' )
44 | #'
45 | #' tree$plot
46 | #' @import ggtree
47 | #' @import treeio
48 | #' @import phangorn
49 | #' @import ape
50 | #' @export
51 | plotCNAtree <- function(dist,
52 | bootstrap.rep.num = 500,
53 | group = NULL,
54 | group.colors = NULL,
55 | title = "Cancer",
56 | normal.node = "NORMAL",
57 | hexpand_ratio = 0.3) {
58 | message("Calculate the bootstraps")
59 |
60 | # get trees and using NJ to get the bootstraps.
61 | phyloTree <- bootstrap.trees(
62 | dist = dist,
63 | title = title,
64 | bootstrap.rep.num = bootstrap.rep.num
65 | )
66 |
67 | mtree <- phyloTree$tree
68 | bootstrap.value <- phyloTree$bootstrap.value
69 |
70 |
71 | # all.length = mtree$edge.length
72 | root.length <- rev(mtree$edge.length)[1]
73 |
74 | # set outgroup and removing the Normal
75 | mtree <- treeio::root(mtree, outgroup = normal.node)
76 | mtree <- treeio::drop.tip(mtree, normal.node)
77 |
78 | # combined bootstrap
79 | bp2 <- data.frame(
80 | node = 1:(treeio::Nnode(mtree)) + treeio::Ntip(mtree),
81 | bootstrap = bootstrap.value
82 | )
83 | mtree <- dplyr::full_join(mtree, bp2, by = "node")
84 |
85 | p_trees <- ggtree::ggtree(mtree, size = 1) +
86 | ggtree::geom_tiplab(size = 4) +
87 | ggtree::geom_treescale(fontsize = 6, linesize = 1, offset = 1) +
88 | # set root length
89 | ggtree::geom_rootedge(rootedge = root.length, size = 1, colour = "grey40") +
90 | ggtree::hexpand(hexpand_ratio, direction = 1)
91 |
92 | p_trees <- p_trees +
93 | ggtree::geom_nodepoint(ggplot2::aes(fill = cut(bootstrap, c(0, 70, 90, 100))),
94 | shape = 21, size = 2.5
95 | ) +
96 | ggplot2::scale_fill_manual(
97 | values = c("black", "grey", "white"), guide = "legend",
98 | name = "Bootstrap Percentage(BP)",
99 | breaks = c("(90,100]", "(70,90]", "(0,70]"),
100 | labels = expression(BP >= 90, 70 <= BP * " < 90", BP < 70)
101 | ) +
102 | ggtree::theme_tree(legend.position = c(0.8, 0.25))
103 |
104 | if (!is.null(group)) {
105 |
106 | # check samples ids between trees and group
107 | if (!identical(sort(purrr::reduce(group, c)), sort(mtree@phylo$tip.label))) {
108 | stop("the samplenames in group were not identical to sample names in the tree")
109 | }
110 |
111 | p_trees <- ggtree::groupOTU(p_trees, group, "Sites")
112 |
113 | # get levels
114 | Sites <- levels(p_trees$data$Sites)
115 |
116 | if (!is.null(group.colors)) {
117 | if (!identical(sort(names(group.colors)), sort(levels(p_trees$data$Sites)))) {
118 |
119 | # get levels that were not in the group.colors
120 | Site1 <- setdiff(levels(p_trees$data$Sites), names(group.colors))
121 | Site.colors <- setNames(
122 | c(set.colors(n = length(Site1), rev = T), group.colors),
123 | nm = c(Site1, names(group.colors))
124 | )
125 |
126 | Site.colors <- Site.colors[levels(p_trees$data$Sites)]
127 | } else {
128 | Site.colors <- group.colors[levels(p_trees$data$Sites)]
129 | }
130 | } else {
131 | Site.colors <- set.colors(n = length(Sites))
132 | }
133 |
134 | p_trees <- p_trees +
135 | ggplot2::aes(color = Sites) +
136 | ggplot2::scale_colour_manual(
137 | values = Site.colors
138 | )
139 | }
140 |
141 |
142 | p_trees <- p_trees +
143 | ggplot2::labs(title = title) +
144 | ggplot2::theme(plot.title = ggplot2::element_text(hjust = 0.5))
145 |
146 | return(
147 | list(
148 | phyloTree = phyloTree,
149 | plot = p_trees
150 | )
151 | )
152 | }
153 |
154 |
155 |
156 | ########################################################################################
157 |
158 | # Supporting Functions
159 |
160 |
161 | # functions to get the bootstrap values.
162 |
163 | medicc.resample.distance.matrices <- function(D, niter = 100) {
164 | result <- list()
165 | # pb=txtProgressBar(min=0,max=niter,style=3)
166 | for (s in 1:niter) {
167 | # setTxtProgressBar(pb,s)
168 | Dnew <- as.matrix(D)
169 | for (i in 1:nrow(Dnew)) {
170 | for (j in 1:i) {
171 | Dnew[i, j] <- rnorm(1, mean = Dnew[i, j], sd = sqrt(Dnew[i, j]))
172 | Dnew[j, i] <- Dnew[i, j]
173 | }
174 | }
175 | Dnew[Dnew < 0] <- 0
176 | Dnew <- round(Dnew)
177 | Dnew <- as.dist(Dnew)
178 | result[[s]] <- Dnew
179 | }
180 | return(result)
181 | }
182 |
183 |
184 | bootstrap.trees <- function(dist, bootstrap.rep.num = 1000, title = "Cancer") {
185 |
186 | # using NJ to create a new tree with bootstrap values.
187 | getTrees <- function(D) {
188 | matTree <- ape::nj(D)
189 | root_num <- which(matTree$tip.label == "diploid")
190 | matTree <- treeio::root(matTree, root_num)
191 | matTree
192 | }
193 |
194 | D <- as.matrix(read.table(dist, row.names = 1, skip = 1))
195 | colnames(D) <- rownames(D)
196 |
197 | matTree <- getTrees(D) # getTrees is defined the beginning of this function.
198 | # plot(matTree)
199 | # bootstrap
200 | # resampled trees.
201 | resampled <- medicc.resample.distance.matrices(D, bootstrap.rep.num)
202 |
203 | bootstrap.value <- prop.clades(matTree, lapply(resampled, getTrees), rooted = is.rooted(matTree)) / bootstrap.rep.num * 100
204 |
205 | # bootstrap.value <- ape::boot.phylo(matTree, mut_dat, function(e){nj(dist.gene(e))},B = bootstrap.rep.num,quiet = TRUE,rooted = TRUE)/(bootstrap.rep.num)*100
206 |
207 | # plot( matTree, main = title)
208 | # nodelabels(bootstrap.value)
209 |
210 | # for MesKit to plot trees.
211 | matTree$tip.label[which(matTree$tip.label == "diploid")] <- "NORMAL"
212 |
213 | phyloTree <- list(
214 | tree = matTree,
215 | bootstrap.value = bootstrap.value[1:(length(bootstrap.value) - 1)],
216 | patientID = title
217 | )
218 |
219 | phyloTree
220 | }
221 |
--------------------------------------------------------------------------------
/R/calKaKs.R:
--------------------------------------------------------------------------------
1 | #' calKaKs calculates the Ka/Ks of each group
2 | #'
3 | #' The mutations are classified by `classifyMut()` internally.
4 | #'
5 | #' @param maf Maf or MafList object generated by `readMaf()` function
6 | #' @param patient.id Select the specific patients. Default `NULL`, all patients are included.
7 | #' @param vaf.cutoff Removing mutations with low variant allele frequency (VAF).
8 | #' @param class The class which would be represented.
9 | #' "SP" (Shared pattern: Public/Shared/Private), other options: "CS" (Clonal status: Clonal/Subclonl)
10 | #' and "SPCS". see [MesKit::classifyMut()].
11 | #' @param parallel If `TRUE` (default), run in parallel.
12 | #'
13 | #' @examples
14 | #' library(MesKit)
15 | #' data.type <- "split1"
16 | #'
17 | #' maf <- readMaf(
18 | #' mafFile = system.file(package = "MPTevol", "extdata", sprintf("meskit.%s.mutation.txt", data.type)),
19 | #' ccfFile = system.file(package = "MPTevol", "extdata", sprintf("meskit.%s.CCF.txt", data.type)),
20 | #' clinicalFile = system.file(package = "MPTevol", "extdata", sprintf("meskit.%s.clinical.txt", data.type)),
21 | #' refBuild = "hg19",
22 | #' ccf.conf.level = 0.95
23 | #' )
24 | #'
25 | #' # calKaKas
26 | #' kaks <- calKaKs(maf, patient.id = "Breast", class = "SP", parallel = TRUE, vaf.cutoff = 0.05)
27 | #' kaks
28 | #' kaks <- calKaKs(maf, patient.id = "Breast", class = "CS", parallel = TRUE, vaf.cutoff = 0.05)
29 | #' kaks
30 | #' kaks <- calKaKs(maf, class = "SP", parallel = TRUE, vaf.cutoff = 0.05)
31 | #' kaks
32 | #' @export
33 | calKaKs <- function(maf,
34 | patient.id = NULL,
35 | class = "SP",
36 | classByTumor = FALSE,
37 | vaf.cutoff = 0.05,
38 | parallel = TRUE) {
39 |
40 | # To do: be careful about the samples and tumors.
41 |
42 | class.levels <- NULL
43 | if (class == "SP") {
44 | class.levels <- c("Public", "Shared", "Private")
45 | } else if (class == "CS") {
46 | class.levels <- c("Clonal", "Subclonl")
47 | } else if (class == "SPCS") {
48 | class.levels <- c("Public_Clonal", "Shared_Clonal", "Shared_Subclonal", "Private_Subclonal")
49 | }
50 |
51 | ######################################################################
52 |
53 | estKaKs <- function(patient.id, maf_input, maf_class) {
54 | # Merge the maf input and mutation class
55 | message(patient.id)
56 |
57 | maf_merge <- maf_input[[patient.id]] %>%
58 | dplyr::mutate(Mut_ID = stringr::str_c(Hugo_Symbol, Chromosome, Start_Position,
59 | Reference_Allele, Tumor_Seq_Allele2,
60 | sep = ":"
61 | )) %>%
62 | dplyr::left_join(
63 | maf_class[[patient.id]]
64 | ) %>%
65 | dplyr::select(
66 | Hugo_Symbol, Chromosome, Start_Position, End_Position,
67 | Reference_Allele, Tumor_Seq_Allele2, Tumor_Sample_Barcode,
68 | Mutation_Type, Patient_ID, Tumor_ID, Variant_Classification, VAF
69 | )
70 |
71 | maf_list <- maf_merge %>%
72 | split(paste(maf_merge$Tumor_ID, maf_merge$Mutation_Type, sep = ":"))
73 |
74 | # We use the easypar to do parallel calculations.
75 | if (parallel) {
76 | maf_KaKs <- easypar::run(
77 | FUN = getKaKs,
78 | PARAMS = lapply(1:length(maf_list), function(x) {
79 | list(df = maf_list[[x]], vaf.cutoff = vaf.cutoff)
80 | }),
81 | parallel = TRUE,
82 | outfile = NULL,
83 | export = NULL,
84 | packages = "tidyverse",
85 | filter_errors = FALSE
86 | )
87 | } else {
88 | maf_KaKs <- lapply(maf_list, getKaKs)
89 | }
90 |
91 | names(maf_KaKs) <- names(maf_list)
92 |
93 | # Remving groups that fail to calculate the KaKs
94 | maf_KaKs <- maf_KaKs[lapply(maf_KaKs, function(x) is.numeric(nrow(x))) %>% unlist()]
95 | KaKs_data <- list()
96 |
97 | for (i in names(maf_KaKs)) {
98 | KaKs_data[[i]] <- maf_KaKs[[i]] %>%
99 | dplyr::mutate(type = i)
100 | }
101 |
102 | KaKs_data <- purrr::reduce(KaKs_data, rbind)
103 |
104 | KaKs_data <- KaKs_data %>%
105 | dplyr::mutate(
106 | Tumor_ID = mapply(function(x) x[1], stringr::str_split(type, ":")),
107 | Type = mapply(function(x) x[2], stringr::str_split(type, ":"))
108 | ) %>%
109 | dplyr::mutate(
110 | Type = factor(Type, levels = class.levels)
111 | ) %>%
112 | dplyr::filter(!is.na(Type))
113 |
114 |
115 | p1 <- KaKs_data %>%
116 | dplyr::filter(name %in% c("wall")) %>%
117 | dplyr::mutate(name = factor(name, levels = c("wall"))) %>%
118 | # mutate(Type = factor(Type, levels = c("Shared_Clonal","Private_Clonal","Private_Subclonal") )) %>%
119 | ggplot2::ggplot(ggplot2::aes(x = Tumor_ID, y = mle, fill = Type)) +
120 | # ggpubr::theme_pubr() +
121 | ggplot2::geom_bar(stat = "identity", position = ggplot2::position_dodge(width = 0.90)) +
122 | # geom_linerange(aes(ymin = cilow, ymax = cihigh), position = position_dodge(width = 0.90) ) +
123 | ggplot2::geom_hline(yintercept = 1, linetype = 2, size = 1) +
124 | ggplot2::labs(x = NULL, y = latex2exp::TeX("Dn/Ds ($\\omega_{all}$)")) +
125 | ggplot2::scale_fill_manual(values = set.colors(length(unique(KaKs_data$Type)))) +
126 | ggplot2::theme(
127 | axis.title.x = element_blank(),
128 | axis.text.x = element_text(angle = 0, hjust = 0.5, size = 14)
129 | )
130 |
131 | list(
132 | KaKs_data = KaKs_data,
133 | plot = p1
134 | )
135 | }
136 | ##########################################################################
137 | # running
138 |
139 | # Get the mutation groups.
140 | maf_input <- MesKit::subMaf(maf, patient.id = patient.id, mafObj = FALSE, use.tumorSampleLabel = TRUE)
141 |
142 | # get mutation classifications.
143 | maf_class <- MesKit::classifyMut(maf, patient.id = patient.id, class = class, classByTumor = classByTumor)
144 |
145 | # Note the different format between maf_input and maf_class when the patient.id is a single value.
146 | if (!is.null(patient.id)) {
147 | maf_class1 <- list()
148 | maf_class1[[patient.id]] <- maf_class
149 | maf_class <- maf_class1
150 | }
151 |
152 | kaks <- lapply(names(maf_input), estKaKs, maf_input, maf_class)
153 | names(kaks) <- names(maf_input)
154 |
155 | return(
156 | kaks
157 | )
158 | }
159 |
160 |
161 |
162 |
163 | #' getKaKs compares Ka/Ks between different groups
164 | #'
165 | #' @param df data. Six columns are required to calculate the Ka/Ks,
166 | #' including "Tumor_Sample_Barcode","Chromosome","Start_Position",
167 | #' "Reference_Allele","Tumor_Seq_Allele2" and "VAF".
168 | #' @param vaf.cutoff VAF cutoff. Removing mutations with low variant allele frequency (VAF).
169 | #'
170 | #' @details The Ka/Ks is calculated by [dndscv::dndscv()]
171 | #'
172 | #' @export
173 | getKaKs <- function(df, vaf.cutoff = 0.05) {
174 | data(list = sprintf("submod_%s", "13r_3w"), package = "dndscv") # TODO not valid operation in package
175 |
176 | mutations <- df %>%
177 | dplyr::filter(VAF >= vaf.cutoff) %>%
178 | dplyr::select(c("Tumor_Sample_Barcode", "Chromosome", "Start_Position", "Reference_Allele", "Tumor_Seq_Allele2"))
179 |
180 | if (nrow(mutations) <= 40) {
181 | stop("without enough mutations")
182 | }
183 |
184 | kaks <- dndscv::dndscv(
185 | mutations = mutations,
186 | max_muts_per_gene_per_sample = Inf,
187 | max_coding_muts_per_sample = Inf,
188 | # gene_list = intersect( Genes_Covered, genes),
189 | sm = submod_13r_3w,
190 | outp = 1
191 | )
192 |
193 | kaks$globaldnds
194 | }
195 |
--------------------------------------------------------------------------------
/docs/reference/readCNAProfile.html:
--------------------------------------------------------------------------------
1 |
2 |
38 |
64 |
65 |
66 |
39 | ![]()
42 |
43 |
44 | tree2timescape
40 | 41 |tree2timescape.Rd
45 |
48 |
49 |
53 |
54 |
61 |
62 | This function generates the input of timescape to visual the fisher plot of
46 | clonal evolution by using the results of inferClonalTree().
37 |
91 |
92 |
93 |
94 |
95 |
96 |
97 |
98 |
--------------------------------------------------------------------------------
/R/splitSegment.R:
--------------------------------------------------------------------------------
1 | #' Split the segment regions into several parts
2 | #'
3 | #' According to their shared status.
4 | #' The function first obtains the common shared regions across samples.
5 | #' The corresponding A allele and B allele are output as the format requirements of MEDICC.
6 | #'
7 | #' @param segfiles The allele-specific copy number alterations files generated by **sequenza**.
8 | #' @param sampleid the corresponding sample ids.
9 | #' @param out.dir output dir.
10 | #' @param project.names the project names used in the output.
11 | #' @param N.baf quality control for the sequenza output.
12 | #' @param cnv_min_length quality control for the sequenza output.
13 | #' @param max_CNt quality control for the sequenza output.
14 | #' @param minLength output control: the min length of CNVs to output.
15 | #' @param maxCNV output control: the max CNV to output. When the raw CNV greater than maxCNV, then its value was set to maxCNV.
16 | #' @param medicc.py the position of meidcc.py.
17 | #' @param python the position of meidcc.py.
18 | #'
19 | #' @details
20 | #' This function takes the **sequenza** results as the input and outputs
21 | #' the format requirements of MEDICC.
22 | #'
23 | #' @import GenomicRanges
24 | #' @import ComplexHeatmap
25 | #' @export
26 | splitSegment <- function(segfiles,
27 | sampleid,
28 | project.names = "tumor",
29 | out.dir = "data",
30 | N.baf = 30, cnv_min_length = 1e5, max_CNt = 15,
31 | minLength = 1e5, maxCNV = 4,
32 | medicc.py = "medicc.py",
33 | python = "python") {
34 | seglist <- list()
35 | # read segs
36 | for (i in 1:length(sampleid)) {
37 | seg <- read.delim(file = segfiles[i], header = T, stringsAsFactors = F) %>%
38 | # dplyr::filter(chromosome == "chr1") %>%
39 | dplyr::mutate(sample = sampleid[i])
40 |
41 | seglist[[i]] <- seg
42 | }
43 |
44 | # removing low-confidence regions
45 | # seglist = base::Reduce(rbind, seglist) %>%
46 | # dplyr::filter(N.BAF >= N.baf & (end.pos - start.pos) >= cnv_min_length & CNt <= max_CNt)
47 |
48 | # change low-confidence regions into 2,1,1
49 | seglist <- base::Reduce(rbind, seglist) %>%
50 | dplyr::mutate(keep = ifelse(N.BAF >= N.baf &
51 | (end.pos - start.pos) >= cnv_min_length &
52 | CNt <= max_CNt, TRUE, FALSE)) %>%
53 | dplyr::mutate(
54 | CNt = ifelse(keep, CNt, 2),
55 | A = ifelse(keep, A, 1),
56 | B = ifelse(keep, B, 1)
57 | )
58 |
59 | gseg <- GenomicRanges::GRanges(
60 | seqnames = seglist$chromosome,
61 | ranges = IRanges::IRanges(seglist$start.pos, seglist$end.pos),
62 | strand = "+"
63 | )
64 |
65 | # metadata columns can be added to a GRanges object
66 | GenomicRanges::mcols(gseg) <- seglist
67 |
68 | # split regions into small regions.
69 | segdis <- GenomicRanges::disjoin(gseg)
70 | # add region infor to data
71 | GenomicRanges::mcols(segdis) <- data.frame(segdis)
72 |
73 | # set the minimal site of each segs.
74 | # minLength = 1e5
75 |
76 | # get overlaps regions
77 | overlaps <- GenomicRanges::findOverlaps(segdis, gseg)
78 |
79 | # combined information
80 | merge <- cbind(
81 | GenomicRanges::mcols(segdis[queryHits(overlaps), ]),
82 | GenomicRanges::mcols(gseg[subjectHits(overlaps), ])
83 | ) %>%
84 | base::as.data.frame() %>%
85 | # filter seg length
86 | dplyr::filter(width >= minLength) %>%
87 | dplyr::select(seqnames, start, end, width, CNt, A, B, sample)
88 |
89 | # removing neutral region. CNt = 2 and A = 1 and B =1.
90 | merge_summary <- merge %>%
91 | dplyr::group_by(seqnames, start, end, width, CNt, A, B) %>%
92 | dplyr::summarise(num = dplyr::n()) %>%
93 | dplyr::filter(num == length(sampleid))
94 |
95 | merge <- dplyr::left_join(merge, merge_summary) %>%
96 | dplyr::filter(is.na(num)) %>%
97 | dplyr::mutate(num = NULL)
98 |
99 | # major info: A
100 | merge_A <- merge %>%
101 | dplyr::select(seqnames, start, end, width, A, sample) %>%
102 | tidyr::spread(key = sample, value = A, fill = 1)
103 | # change cnv number when it >=10
104 | tmp <- merge_A[, 5:ncol(merge_A)]
105 | tmp[tmp >= maxCNV] <- maxCNV
106 | merge_A <- cbind(merge_A[, 1:4], tmp)
107 |
108 | # minor info: B
109 | merge_B <- merge %>%
110 | dplyr::select(seqnames, start, end, width, B, sample) %>%
111 | tidyr::spread(key = sample, value = B, fill = 1)
112 |
113 | tmp <- merge_B[, 5:ncol(merge_B)]
114 | tmp[tmp >= maxCNV] <- maxCNV
115 | merge_B <- cbind(merge_B[, 1:4], tmp)
116 |
117 | if (!file.exists(out.dir)) {
118 | system(paste0("mkdir ", out.dir))
119 | }
120 |
121 | file <- sprintf("%s/%s.descr.txt", out.dir, project.names)
122 |
123 | # output
124 | write.table(merge_A, file = sprintf("%s/%s.major.txt", out.dir, project.names), quote = F, row.names = F, sep = "\t")
125 | write.table(merge_B, file = sprintf("%s/%s.minor.txt", out.dir, project.names), quote = F, row.names = F, sep = "\t")
126 |
127 | write.fasta(merge_A = merge_A, major = "major", out.dir = out.dir, project.names = project.names)
128 | write.fasta(merge_A = merge_B, major = "minor", out.dir = out.dir, project.names = project.names)
129 |
130 | # plot the heatmaps to provide better quality controls
131 | major <- merge_A %>%
132 | dplyr::mutate(seq = stringr::str_c(seqnames, start, end, sep = "_")) %>%
133 | tibble::column_to_rownames(var = "seq") %>%
134 | dplyr::mutate(seqnames = NULL, start = NULL, end = NULL, width = NULL)
135 |
136 | minor <- merge_B %>%
137 | dplyr::mutate(seq = stringr::str_c(seqnames, start, end, sep = "_")) %>%
138 | tibble::column_to_rownames(var = "seq") %>%
139 | dplyr::mutate(seqnames = NULL, start = NULL, end = NULL, width = NULL)
140 |
141 | plist <- list()
142 | plist$major <- ComplexHeatmap::Heatmap(major,
143 | row_names_gp = grid::gpar(fontsize = 6)
144 | )
145 |
146 | plist$minor <- ComplexHeatmap::Heatmap(minor,
147 | row_names_gp = grid::gpar(fontsize = 6)
148 | )
149 |
150 | message(
151 | sprintf("nohup %s %s %s/%s.descr.txt %s/%s.run -v >%s.run.info.txt &", python, medicc.py, out.dir, project.names, out.dir, project.names, project.names)
152 | )
153 |
154 | return(list(
155 | major = merge_A,
156 | minor = merge_B,
157 | plist = plist
158 | ))
159 | }
160 |
161 | #' write.fasta
162 | #'
163 | #' Prepare the formate of MEDICC input.
164 | #'
165 | #' @param project.names the project names used in the output.
166 | write.fasta <- function(merge_A, major = "major", out.dir = "data", project.names = "tumor") {
167 | system(sprintf("mkdir %s", out.dir))
168 | chrs <- unique(merge_A$seqnames)[!(unique(merge_A$seqnames) %in% c("chrX", "chrY"))]
169 | num <- ncol(merge_A)
170 |
171 | for (i in chrs) {
172 | merge_B <- subset(merge_A, seqnames == i)
173 | text <- rep("0", 2 * (num - 3))
174 | text[1] <- ">diploid"
175 | text[2] <- paste0(rep(1, nrow(merge_B)), collapse = "")
176 |
177 | for (j in 5:num) {
178 | text[2 * (j - 3) - 1] <- sprintf(">%s", colnames(merge_B)[j])
179 | text[2 * (j - 3)] <- merge_B[, j] %>% stringr::str_c(collapse = "")
180 | }
181 | write.table(text, file = sprintf("%s/%s_%s_%s.fasta", out.dir, project.names, major, i), quote = F, col.names = F, row.names = F)
182 | }
183 |
184 | # write desc
185 | chrinfo <- rep("0", length(chrs))
186 | for (i in 1:length(chrs)) {
187 | chrinfo[i] <- sprintf(
188 | "%s %s %s", chrs[i],
189 | sprintf("%s_%s_%s.fasta", project.names, "major", chrs[i]),
190 | sprintf("%s_%s_%s.fasta", project.names, "minor", chrs[i])
191 | )
192 | }
193 | write.table(chrinfo, file = sprintf("%s/%s.descr.txt", out.dir, project.names), quote = F, col.names = F, row.names = F)
194 | }
195 |
--------------------------------------------------------------------------------
/docs/reference/index.html:
--------------------------------------------------------------------------------
1 |
2 |
38 |
80 |
81 |
82 |
39 | ![]()
42 |
43 |
44 | Read CNA Profiles
40 | 41 |readCNAProfile.Rd
45 |
48 |
49 |
53 |
54 | We used a CNAqc object, containing a set of mutations, CNA calls and tumor purity values.
46 | The CNAqc was used to deal with the allele-specific CNAs.
55 |
68 |
72 |
77 |
78 | Arguments
56 |- maf 57 |
Maf or MafList object generated by
readMaf()function
58 | - seg 59 |
seg or seglist.
60 | - Patient_ID 61 |
Patient_ID: select the specific patients. 62 | IF not indicate, the input is Maf and seg, or the input is MafList and segList.
63 | - purity 64 |
purity information for each samples.
65 | - ref 66 |
human reference genome version. Default 'hg19'. Optional: 'hg18' or 'hg38'.
67 |
35 |
144 |
145 |
146 |
147 |
148 |
149 |
150 |
151 |
--------------------------------------------------------------------------------
36 |
133 |
134 |
135 |
37 | ![]()
39 |
40 | Function reference
38 |
47 |
48 |
49 |
50 |
51 |
132 | -
52 |
53 |
calKaKs()54 |
55 | - calKaKs calculates the Ka/Ks of each group 56 |
-
57 |
58 |
calRoutines()59 |
60 | - calRoutines calculates the H index and JSI index according to the pair-wise comparison of CCF 61 |
-
62 |
63 |
getClinSites()64 |
65 | - getClinSites captures the clinical targetable sites of oncokb based on the mutation status 66 |
-
67 |
68 |
getKaKs()69 |
70 | - getKaKs compares Ka/Ks between different groups 71 |
-
72 |
73 |
inferClonalTrees()74 |
75 | - inferClonalTrees 76 |
-
77 |
78 |
plotCNAProfile()79 |
80 | - Visualize CNA profile 81 |
-
82 |
83 |
plotCNAtree()84 |
85 | - plotCNAtree plots phylogenetic trees of CNAs 86 |
-
87 |
88 |
plotMutTree()89 |
90 | - plotMutTree plots phylogenetic tree of mutations 91 |
-
92 |
93 |
plotVafCluster()94 |
95 | - plotVafCluster 96 |
-
97 |
98 |
readCNAProfile()99 |
100 | - Read CNA Profiles 101 |
-
102 |
103 |
Seg-class104 |
105 | - Segment Class 106 |
-
107 |
108 |
set.colors()109 |
110 | - Color setting 111 |
-
112 |
113 |
splitSegment()114 |
115 | - Split the segment regions into several parts 116 |
-
117 |
118 |
tree2timescape()119 |
120 | - tree2timescape 121 |
-
122 |
123 |
viewTrees()124 |
125 | - Visualize the trees 126 |
-
127 |
128 |
write.fasta()129 |
130 | - write.fasta 131 |