PGAP2 0.1.2__py3-none-any.whl

pgap2/__init__.py

@@ -0,0 +1,4 @@
+import importlib.metadata
+
+__version__ = importlib.metadata.version("pgap2")
+__author__ = 'Congfan Bu'

pgap2/dependencies/draw_post_profile.r

@@ -0,0 +1,193 @@
+#!/usr/bin/env Rscript
+# install.packages(c("ggplot2", "dplyr", "optparse", "readr", "scales", "patchwork"))
+library(ggpubr)
+
+library(dplyr)
+library(optparse)
+library(patchwork)
+
+# 设置命令行参数解析
+option_list <- list(
+  make_option(c("-a", "--pan_group_stat"), type = "character", help = "postprocess.pan_group_stat.tsv"),
+  make_option(c("-b", "--clust_strain_freq"), type = "character", help = "postprocess.clust_strain_freq.tsv"),
+  make_option(c("-c", "--rarefaction"), type = "character", help = "postprocess.rarefaction.tsv"),
+  make_option(c("-d", "--new_clusters"), type = "character", help = "postprocess.new_clusters.tsv"),
+  make_option(c("-e", "--para_stat"), type = "character", help = "postprocess.para_stat.tsv"),
+  make_option(c("-s", "--single_file"), type = "logical", action = "store_true", default = FALSE, help = "Generate each plot to the single file"),
+  make_option(c("-o", "--output_dir"), type = "character", help = "Output directory")
+)
+
+# 解析命令行参数
+opt_parser <- OptionParser(option_list = option_list)
+opt <- parse_args(opt_parser)
+
+# 创建输出目录
+if (!dir.exists(opt$output_dir)) {
+  dir.create(opt$output_dir)
+}
+
+# 读取饼图数据文件
+
+pan_group_stat_data <- read.csv(opt$pan_group_stat, header = TRUE, sep = "\t")
+
+clust_strain_freq_data <- read.csv(opt$clust_strain_freq, header = TRUE, sep = "\t")
+
+rarefaction_data <- read.csv(opt$rarefaction, header = TRUE, sep = "\t")
+
+new_clusters_data <- read.csv(opt$new_clusters, header = TRUE, sep = "\t")
+
+para_stat_data <- read.csv(opt$para_stat, header = TRUE, sep = "\t")
+
+#-----------------------------------------------------------------------------#
+# 保存图形
+save_para_plots <- function(A, B, single_file, output_dir) {
+  if (single_file) {
+    ggsave(file.path(output_dir, "postprocess.para_stat.pdf"), A + ggtitle(""))
+    ggsave(file.path(output_dir, "postprocess.para_stat_facet.pdf"), B + ggtitle(""))
+  } else {
+    combined_plot <- A + B +
+      plot_layout(
+        ncol = 2, # 2列
+        nrow = 1, # 2行
+        widths = c(1, 1), # 第一列宽度为第二列的两倍
+        heights = c(1, 1) # 两行的高度相等
+      )
+    ggsave(file.path(output_dir, "pgap2.postprocess_stat_para.pdf"), combined_plot, width = 10.52, height = 5.8)
+  }
+}
+
+save_basic_plots <- function(A, B, C, D, single_file, output_dir) {
+  if (single_file) {
+    ggsave(file.path(output_dir, "postprocess.pan_group_stat.pdf"), A)
+    ggsave(file.path(output_dir, "postprocess.clust_strain_freq.pdf"), B)
+    ggsave(file.path(output_dir, "postprocess.rarefaction.pdf"), C)
+    ggsave(file.path(output_dir, "postprocess.new_clusters.pdf"), D)
+  } else {
+    combined_plot <- A + B + C + D +
+      plot_layout(
+        ncol = 2, # 2列
+        nrow = 2, # 2行
+        widths = c(1, 1), # 第一列宽度为第二列的两倍
+        heights = c(1, 1) # 两行的高度相等
+      )
+    ggsave(file.path(output_dir, "pgap2.postprocess_profile.pdf"), combined_plot, width = 9.52, height = 7.25)
+  }
+}
+
+draw_pan_group_stat <- function(pan_group_stat_data) {
+  labs <- paste0(pan_group_stat_data$Group, ": ", pan_group_stat_data$Count, " (", pan_group_stat_data$Proportion, "%)")
+
+  pan_group_stat <- ggpie(pan_group_stat_data, "Count",
+    label = labs,
+    fill = "Group", color = "white", lab.pos = "in", size = 1,
+    palette = c("#B8DBB3", "#72B063", "#719AAC", "#E29135", "#94C6CD"),
+    lab.font = c(4, "plain", "black"),
+  ) + theme(
+    legend.position = "none",
+    plot.margin = margin(0, 0, 0, 0), # 去除空白边距
+    axis.text = element_blank(), # 隐藏坐标轴
+    axis.title = element_blank()
+  ) + ggtitle("A")
+  return(pan_group_stat)
+}
+
+draw_clust_strain_freq <- function(clust_strain_freq_data) {
+  clust_strain_freq <- gghistogram(clust_strain_freq_data,
+    x = "Freq", bins = 50, fill = "#B8DBB3",
+    xlab = "Genome Frequency", ylab = "Gene Cluster Number"
+  ) + scale_y_log10() + ggtitle("B")
+  return(clust_strain_freq)
+}
+
+
+draw_rarefaction <- function(rarefaction_data) {
+  rarefaction <- ggscatter(rarefaction_data,
+    x = "Strain", y = "Sampling", color = "Type", fill = NA, alpha = 0.5, size = 1, palette = c("#72B063", "#719AAC"),
+    xlab = "Genome Number", ylab = "Gene Cluster Number"
+  ) + theme(
+    axis.line = element_line(linewidth = 0),
+    panel.background = element_blank(),
+    panel.border = element_rect(color = "black", fill = NA, linewidth = 0.5), # 添加边框
+    panel.grid = element_blank(), # 去除网格线
+    plot.margin = margin(10, 10, 10, 10), # 增加图形的外边距，防止文字被裁剪
+    legend.position = c(0.15, 0.85), # 将图例放到图框内
+    legend.box = "horizontal", # 使图例在框内水平排列
+    legend.background = element_blank(), # 去除图例背景
+    legend.key.size = unit(0.5, "cm"), # 控制图例块的大小
+    legend.title = element_text(size = 10), # 设置图例标题字体大小
+    legend.text = element_text(size = 8) # 设置图例文本字体大小
+  ) + guides(color = guide_legend(override.aes = list(alpha = 1))) + ggtitle("C")
+  # ggboxplot(rarefaction.data, color = 'Type', x = 'Strain', y = 'Sampling',fill=NA) +
+  #  theme(
+  #    axis.line = element_line(linewidth = 0),
+  #    panel.border = element_rect(color = "black", fill = NA, linewidth = 0.75),  # 添加边框
+  #    panel.grid = element_blank(),  # 去除网格线
+  #    plot.margin = margin(10, 10, 10, 10)  # 增加图形的外边距，防止文字被裁剪
+  #  )+
+  #  scale_x_discrete(breaks = unique(rarefaction.data$Strain)[seq(1, length(unique(rarefaction.data$Strain)), by = 5)])
+
+  return(rarefaction)
+}
+
+draw_new_clusters <- function(new_clusters_data) {
+  new_clusters <- ggbarplot(new_clusters_data,
+    x = "Strain", y = "Sampling", add = "mean_se", fill = "#94C6CD",
+    xlab = "Genome Number", ylab = "New Gene Cluster Number"
+  ) + theme(
+    axis.line = element_line(linewidth = 0),
+    panel.background = element_blank(),
+    panel.border = element_rect(color = "black", fill = NA, linewidth = 0.5), # 添加边框
+    panel.grid = element_blank(), # 去除网格线
+    plot.margin = margin(10, 10, 10, 10), # 增加图形的外边距，防止文字被裁剪
+    legend.box = "horizontal", # 使图例在框内水平排列
+    legend.key.size = unit(0.5, "cm"), # 控制图例块的大小
+    legend.title = element_text(size = 10), # 设置图例标题字体大小
+    legend.text = element_text(size = 8) # 设置图例文本字体大小
+  ) + guides(color = guide_legend(override.aes = list(alpha = 1))) + ggtitle("D")
+  return(new_clusters)
+}
+
+draw_para_stat <- function(para_stat_data) {
+  para_stat_data$duplication_degree <- log(para_stat_data$Para_gene / para_stat_data$Para_strain)
+  para_stat_a <- ggscatter(para_stat_data,
+    x = "Para_strain", y = "Para_gene", size = "duplication_degree",
+    color = "black", shape = 21, fill = "Group",
+    conf.int = TRUE,
+    palette = c("#B8DBB3", "#72B063", "#719AAC", "#E29135", "#94C6CD"),
+    xlab = "Paralogous Strain",
+    ylab = "Paralogous Gene"
+  ) +
+    geom_abline(slope = 1, intercept = 0, linetype = "dashed", color = "red") + # 添加 x = y 线
+    guides(
+      size = "none" # 隐藏 size 图例
+    ) + ggtitle("A")
+  return(para_stat_a)
+}
+
+draw_para_stat_facet <- function(para_stat_data) {
+  para_stat_data$duplication_degree <- log(para_stat_data$Para_gene / para_stat_data$Para_strain)
+  para_stat_b <- ggscatter(para_stat_data,
+    x = "Para_strain", y = "Para_gene", size = "duplication_degree", color = "duplication_degree",
+    conf.int = TRUE, facet.by = "Group",
+    xlab = "Paralogous Strain",
+    ylab = "Paralogous Gene"
+  ) +
+    geom_abline(slope = 1, intercept = 0, linetype = "dashed", color = "red") + # 添加 x = y 线
+    scale_y_log10() + scale_x_log10() + # 对数缩放
+    scale_color_gradient(low = "#dddfe6", high = "#d90429") +
+    labs(color = "Dup degree") +
+    guides(
+      size = "none" # 隐藏 size 图例
+    ) + ggtitle("B")
+  return(para_stat_b)
+}
+
+A <- draw_pan_group_stat(pan_group_stat_data)
+B <- draw_clust_strain_freq(clust_strain_freq_data)
+C <- draw_rarefaction(rarefaction_data)
+D <- draw_new_clusters(new_clusters_data)
+E <- draw_para_stat(para_stat_data)
+F <- draw_para_stat_facet(para_stat_data)
+
+save_basic_plots(A, B, C, D, opt$single_file, opt$output_dir)
+save_para_plots(E, F, opt$single_file, opt$output_dir)

pgap2/dependencies/draw_post_stat.r

@@ -0,0 +1,97 @@
+#!/usr/bin/env Rscript
+library(ggpubr)
+
+library(dplyr)
+library(optparse)
+library(patchwork)
+
+# 设置命令行参数解析
+option_list <- list(
+  make_option(c("-a", "--stat_attrs"), type = "character", help = "postprocess.stat_attrs.tsv"),
+  make_option(c("-s", "--single_file"), action = "store_true", default = FALSE, help = "Generate each plot to the single file"),
+  make_option(c("-o", "--output_dir"), type = "character", help = "Output directory")
+)
+
+# 解析命令行参数
+opt_parser <- OptionParser(option_list = option_list)
+opt <- parse_args(opt_parser)
+
+# 创建输出目录
+if (!dir.exists(opt$output_dir)) {
+  dir.create(opt$output_dir)
+}
+
+stat_attrs_data <- read.csv(opt$stat_attrs, header = TRUE, sep = "\t")
+
+
+#-----------------------------------------------------------------------------#
+# 保存图形
+
+save_basic_plots <- function(A, B, C, D, single_file, output_dir) {
+  if (single_file) {
+    ggsave(file.path(output_dir, "postprocess.stat_attrs_mean.pdf"), A)
+    ggsave(file.path(output_dir, "postprocess.stat_attrs_min.pdf"), B)
+    ggsave(file.path(output_dir, "postprocess.stat_attrs_var.pdf"), C)
+    ggsave(file.path(output_dir, "postprocess.stat_attrs_uni.pdf"), D)
+  } else {
+    combined_plot <- A + B + C + D +
+      plot_layout(
+        guides = "collect",
+        ncol = 2, # 2列
+        nrow = 2, # 2行
+        widths = c(1, 1), # 第一列宽度为第二列的两倍
+        heights = c(1, 1)
+      ) +
+      theme(legend.position = "bottom")
+    ggsave(file.path(output_dir, "pgap2.postprocess_stat.pdf"), combined_plot, width = 8.6, height = 7.4)
+  }
+}
+
+draw_stat_attr <- function(stat_attrs_data, attr, xlab_name) {
+  if (attr == "mean" || attr == "min") {
+    left_position <- 0.15
+  } else {
+    left_position <- 0.85
+  }
+
+
+  attr_plot <- ggline(subset(stat_attrs_data, Attr == attr),
+    x = "Edge", y = "Prop",
+    color = "Group", scales = "free", size = 1,
+    xlab = xlab_name, ylab = "Gene Cluster Proportion",
+    palette = c("#B8DBB3", "#72B063", "#719AAC", "#E29135", "#94C6CD")
+  ) +
+    scale_y_log10() +
+    theme(
+      axis.text.x = element_text(angle = 45, hjust = 1),
+      axis.line = element_line(linewidth = 0),
+      panel.background = element_blank(),
+      panel.border = element_rect(color = "black", fill = NA, linewidth = 0.5), # 添加边框
+      panel.grid = element_blank(), # 去除网格线
+      plot.margin = margin(10, 10, 10, 10), # 增加图形的外边距，防止文字被裁剪
+      legend.box = "vertical", # 使图例在框内水平排列
+      legend.position = c(left_position, 0.85),
+      legend.background = element_blank(),
+      legend.direction = "vertical",
+      legend.key.size = unit(0.5, "cm"), # 控制图例块的大小
+      legend.title = element_text(size = 10), # 设置图例标题字体大小
+      legend.text = element_text(size = 8)
+    ) +
+    guides(color = guide_legend(override.aes = list(alpha = 1))) + ggtitle(toupper(attr))
+
+  return(attr_plot)
+}
+
+
+stat_attrs_data <- stat_attrs_data %>%
+  group_by(Attr, Group) %>% # 按 Attr 分组
+  mutate(Prop = Count / sum(Count)) %>% # 计算每行的 Prop 值
+  ungroup() # 取消分组
+stat_attrs_data$Group <- factor(stat_attrs_data$Group, levels = c("Strict_core", "Core", "Soft_core", "Shell", "Cloud"))
+
+A <- draw_stat_attr(stat_attrs_data, "mean", xlab_name = "Gene Identity")
+B <- draw_stat_attr(stat_attrs_data, "min", xlab_name = "Gene Identity")
+C <- draw_stat_attr(stat_attrs_data, "var", xlab_name = "Gene Cluster Variance")
+D <- draw_stat_attr(stat_attrs_data, "uni", xlab_name = "Gene Identity")
+
+save_basic_plots(A, B, C, D, opt$single_file, opt$output_dir)

pgap2/dependencies/draw_prep.r

@@ -0,0 +1,159 @@
+#!/usr/bin/env Rscript
+
+library(ggpubr)
+library(ggrepel)
+
+library(dplyr)
+library(tidyr)
+library(optparse)
+library(patchwork)
+
+# 设置命令行参数解析
+option_list <- list(
+  make_option(c("-a", "--stat_attrs"), type = "character", help = "preprocess.stat.tsv"),
+  make_option(c("-b", "--gene_code"), type = "character", help = "preprocess.gene_code.csv"),
+  make_option(c("-c", "--ani_thre"), type = "character", help = "ANI threshold"),
+  make_option(c("-s", "--single_file"), action = "store_true", default = FALSE, help = "Generate each plot to the single file"),
+  make_option(c("-o", "--output_dir"), type = "character", help = "Output directory")
+)
+
+# 解析命令行参数
+opt_parser <- OptionParser(option_list = option_list)
+opt <- parse_args(opt_parser)
+
+# 创建输出目录
+if (!dir.exists(opt$output_dir)) {
+  dir.create(opt$output_dir)
+}
+
+input_prep <- read.csv(opt$stat_attrs, header = TRUE, sep = "\t")
+input_code <- read.csv(opt$gene_code, header = TRUE, sep = ",", row.names = 1)
+
+
+#-----------------------------------------------------------------------------#
+# 保存图形
+
+save_basic_plots <- function(A, B, C, D, E, single_file, output_dir) {
+  if (single_file) {
+    ggsave(file.path(output_dir, "preprocess.ANI.pdf"), A)
+    ggsave(file.path(output_dir, "preprocess.gene_number.pdf"), B)
+    ggsave(file.path(output_dir, "preprocess.half_core.pdf"), C)
+    ggsave(file.path(output_dir, "preprocess.proportion.pdf"), D)
+    ggsave(file.path(output_dir, "preprocess.gene_code.pdf"), E)
+  } else {
+    p1 <- A + ggtitle("A") +
+      B + ggtitle("B") +
+      C + ggtitle("C") +
+      plot_layout(guides = "collect", ncol = 3)
+    p2 <- D + ggtitle("D") +
+      E + ggtitle("E") +
+      plot_layout(guides = "collect", ncol = 2) & # 合并图例
+      theme(legend.position = "right")
+    combined_plot <- p1 / p2 + plot_layout(heights = c(1, 2))
+    ggsave(file.path(output_dir, "pgap2.preprocess.pdf"), combined_plot, width = 9.8, height = 8.4)
+  }
+}
+
+draw_ani <- function(input_prep, ani_thre) {
+  p <- ggviolin(input_prep,
+    y = "ani", add = "jitter",
+    add.params = list(size = 3, color = "black", fill = "#B8DBB3", shape = 21),
+    xlab = "Genome", ylab = "ANI"
+  ) +
+    geom_hline(yintercept = ani_thre, linetype = "dotted", col = "red") +
+    theme(legend.position = "none") +
+    scale_x_discrete(labels = c("")) +
+    # 使用 geom_text_repel() 添加标签和箭头
+    geom_text_repel(
+      data = subset(input_prep, ani == 100 | is_outlier_ani == 1), # 筛选满足条件的数据
+      aes(x = as.factor(1), y = ani, label = strain), # 标签位置与数据
+      arrow = arrow(type = "closed", length = unit(0.1, "inches")), # 添加箭头
+      vjust = -0.5, size = 3, color = "black", # 标签和箭头的样式
+      box.padding = 0.2, min.segment.length = 1 # 调整标签与点的间距
+    )
+  return(p)
+}
+
+draw_gene_number <- function(input_prep) {
+  p <- ggviolin(input_prep,
+    y = "total_gene_num", add = "jitter", xlab = "Genome", ylab = "Number of genes",
+    add.params = list(size = 3, color = "black", fill = "#B8DBB3", shape = 21)
+  ) + theme(legend.position = "None") + scale_x_discrete(labels = c(""))
+  return(p)
+}
+
+draw_half_core <- function(input_prep) {
+  p <- ggscatter(input_prep,
+    x = "half_core", y = "single_cloud",
+    size = "total_gene_num", color = "total_gene_num", xlab = "Half core", ylab = "Single cloud"
+  ) +
+    guides(size = "none", color = guide_colorbar(barheight = 5)) +
+    scale_color_gradient(high = "#990033", low = "white") +
+    theme(legend.position = "right") +
+    labs(color = "Count")
+  return(p)
+}
+
+draw_proportion <- function(input_prep) {
+  input_prep$others <- input_prep$total_gene_num - input_prep$half_core - input_prep$single_cloud
+  used_prep <- input_prep %>% select(strain, total_gene_num, half_core, single_cloud, others)
+  # Transform the data into a long format
+  long_data <- used_prep %>%
+    pivot_longer(cols = c(half_core, single_cloud, others), names_to = "Category", values_to = "Count") %>%
+    mutate(
+      Category = factor(Category, levels = c("single_cloud", "others", "half_core")), # Reorder the categories
+      strain = factor(strain, levels = used_prep$strain)
+    ) # Maintain the order of strains
+
+  p <- ggplot(long_data, aes(x = strain, y = Count, fill = Category)) +
+    geom_bar(position = "fill", stat = "identity") +
+    coord_flip() +
+    theme_minimal() +
+    labs(x = "Strains", y = "Proportion", fill = "Category") +
+    scale_fill_manual(values = c("single_cloud" = "#72B063", "others" = "#719AAC", "half_core" = "#E29135"), labels = c("Single", "Others", "Half")) +
+    scale_x_discrete(
+      breaks = function(x) {
+        y_levels <- levels(factor(long_data$strain))
+        # 如果类别数大于 20，选择均匀的 20 个类别
+        if (length(y_levels) > 25) {
+          return(y_levels[seq(1, length(y_levels), length.out = 25)]) # 选择 20 个类别
+        } else {
+          return(y_levels) # 如果类别少于 20 个，显示所有
+        }
+      }
+    )
+  return(p)
+}
+
+draw_gene_code <- function(input_code) {
+  df <- as.data.frame(as.table(as.matrix(input_code)))
+  df <- df %>%
+    rename(Count = Freq)
+  df$Count <- as.numeric(as.character(df$Count))
+  p <- ggplot(df, aes(x = Var1, y = Var2, fill = Count)) +
+    geom_tile() +
+    scale_fill_gradient2(high = "#990033", low = "white") +
+    theme_bw() +
+    theme(panel.grid = element_blank(), axis.text.x = element_text(angle = 90, hjust = 0.5, vjust = 0.5), ) +
+    xlab("Start|Stop codon") +
+    ylab(NULL) +
+    scale_y_discrete(
+      breaks = function(x) {
+        # 获取 Var2 的所有类别
+        y_levels <- levels(factor(df$Var2))
+        if (length(y_levels) > 25) {
+          return(y_levels[seq(1, length(y_levels), length.out = 25)])
+        } else {
+          return(y_levels) # 如果类别少于 20 个，显示所有
+        }
+      }
+    )
+  return(p)
+}
+
+A <- draw_ani(input_prep, as.numeric(opt$ani_thre))
+B <- draw_gene_number(input_prep)
+C <- draw_half_core(input_prep)
+D <- draw_proportion(input_prep)
+E <- draw_gene_code(input_code)
+save_basic_plots(A, B, C, D, E, opt$single_file, opt$output_dir)

pgap2/dependencies/maskrc-svg.py

@@ -0,0 +1,236 @@
+#!/usr/bin/env python3
+# Script by Jason Kwong & Torsten Seemann
+# Script to mask recombination from CFML output and draw SVG of recombinant regions
+
+# Usage
+import argparse
+from argparse import RawTextHelpFormatter
+
+parser = argparse.ArgumentParser(
+	formatter_class=RawTextHelpFormatter,
+	description='Mask recombination from ClonalFrameML/Gubbins output and draw SVG of recombinant regions',
+	usage='\n  %(prog)s --aln FASTA --out OUTFILE [--gubbins] <PREFIX>')
+parser.add_argument('prefix', metavar='PREFIX', help='prefix used for CFML/Gubbins input files (required)')
+parser.add_argument('--gubbins', action='store_true', help='parse as Gubbins instead of ClonalFrameML')
+parser.add_argument('--aln', metavar='FASTA', required=True, help='multiFASTA alignment used as input for CFML (required)')
+parser.add_argument('--out', metavar='OUTFILE', default='maskrc.aln', help='output file for masked alignment (default="maskrc.aln")')
+parser.add_argument('--symbol', metavar='CHAR', default='?', help='symbol to use for masking (default="?")')
+parser.add_argument('--regions', metavar='FILE', help='output recombinant regions to file')
+parser.add_argument('--svg', metavar='FILE', help='draw SVG output of recombinant regions and save as specified file')
+parser.add_argument('--svgsize', metavar='WIDExHIGH', default='800x600', help='specify width and height of SVG in pixels (default="800x600")')
+parser.add_argument('--svgorder', metavar='FILE', help='specify file containing list of taxa (1 per line) in desired order')
+parser.add_argument('--svgcolour', metavar='COLOUR', default='black', help='specify colour of recombination regions in HEX format (default=black)')
+parser.add_argument('--consensus', action='store_true', help='add consensus row of recombination hotspots')
+parser.add_argument('--version', action='version', version='%(prog)s 0.5')
+
+args = parser.parse_args()
+
+prefix = str(args.prefix)
+treefn = prefix + ('.labelled_tree.newick', '.final_tree.tre')[args.gubbins]
+coordfn = prefix + ('.importation_status.txt', '.recombination_predictions.gff')[args.gubbins]
+
+import os
+import sys
+import csv
+from collections import defaultdict
+from ete3 import Tree
+from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.Seq import MutableSeq
+from Bio.SeqRecord import SeqRecord
+import svgwrite
+from BCBio import GFF
+import pprint
+
+# Functions
+def msg(*args, **kwargs):
+	print(*args, file=sys.stderr, **kwargs)
+
+def err(*args, **kwargs):
+	msg(*args, **kwargs)
+	sys.exit(1);
+
+def check_file(f):
+	msg('Checking file: {}'.format(f))
+	if os.path.isfile(f) == False:
+		err('ERROR: Cannot find "{}". Check output files exist in this directory.'.format(f))
+
+# Check input files (output from CFML)
+check_file(treefn)
+check_file(coordfn)
+
+# Setup lists and dictionary
+d = defaultdict(list)
+seqLIST = []
+leafLIST = []
+t = Tree(treefn, format=1)
+
+# Set taxa order for SVG
+if args.svgorder:
+	msg('Setting taxa order using --svgorder {}'.format(args.svgorder));
+	with open(args.svgorder) as file:
+		for row in file:
+			leafLIST.append(row.rstrip())
+else:
+	msg('Setting taxa order using leaves from: {}'.format(treefn));
+	for leaf in t:
+		leafLIST.append(leaf.name)
+
+# gubbins GFF
+# node="internal_13->2016-04538";neg_log_likelihood="3764.359443";taxa="2016-04538";snp_count="108"; 
+# node="internal_ROOT->internal_10";neg_log_likelihood="47939.649932";taxa=" 2016-23066 2015-19014";snp_count="8";
+# node="internal_15->internal_16";neg_log_likelihood="574.375212";taxa=" 2008-16004 2010-22387";snp_count="39";
+# node="internal_15->internal_16";neg_log_likelihood="418.840895";taxa=" 2008-16004 2010-22387";snp_count="38";
+# node="internal_12->internal_14";neg_log_likelihood="17258.115166";taxa=" 2012-21203  2008-20031  2008-16004 2010-22387";
+
+# clonalframeml "BED"
+#Node    		Beg     End
+#2016-11776      5624    6619
+#2016-11776      10778   11326
+#Reference       2489729 2490893
+#NODE_10 		1165936 1166465
+
+# internal
+# ['Reference', ['2434777', '2434933', 'ancestral']],
+# ['2016-17702', ['2483546', '2485711', 'ancestral']],
+# ['2016-17705', ['2483546', '2485711', 'ancestral']],
+# ['2016-11776', ['2483546', '2485711', 'ancestral']],
+# ['2016-11778', ['2483546', '2485711', 'ancestral']],
+# ['2016-11777', ['2483546', '2485711', 'ancestral']],
+# ['2016-17701', ['2483546', '2485711', 'ancestral']],
+# ['Reference', ['2483546', '2485711', 'ancestral']]]
+ 
+if args.gubbins:
+	msg('Parsing Gubbins file: {}'.format(coordfn))
+	with open(coordfn) as gff:
+		for rec in GFF.parse(gff):
+			for f in rec.features:
+				taxa = f.qualifiers['taxa'][0].strip().split()
+				state = ('ancestral', 'extant')[ len(taxa)==1 ]
+				for taxon in taxa:
+					# BCBio-GFF module parser seems to extract coordinate-1 for f.location.start
+					seqLIST.append( [ taxon, [ int(f.location.start)+1, int(f.location.end), state ] ] )
+else:
+	msg('Parsing ClonalFrameML file: {}'.format(coordfn))
+	with open(coordfn) as csvfile:
+		RCseqs = csv.reader(csvfile, delimiter='\t')
+		next(csvfile)
+		for row in RCseqs:
+			seq = row[0]
+			RCstart = row[1]
+			RCstop = row[2]
+			node = t.search_nodes(name=seq)[0]
+			if node.is_leaf():
+				leaf_names = [node.name]
+				z = 'extant'
+			else:
+				leaves = node.get_leaves()
+				leaf_names = [leaf.name for leaf in leaves]
+				z = 'ancestral'
+			for l in leaf_names:
+				seqLIST.append([l, [RCstart, RCstop, z]])
+
+# Build dictionary of recombinant regions
+for k,v in seqLIST:
+	d[k].append(v)
+
+# Mask recombination in sequences
+seqALN = []
+for record in SeqIO.parse(args.aln, 'fasta'):
+	msg('Reading {} ... '.format(record.id))
+	seqlen = len(record.seq)
+	regions = d.get(record.id, None)
+	newrec = MutableSeq(str(record.seq))
+	if regions:
+		for a in regions:
+			start = int(a[0]) - 1
+			end = int(a[1])
+			lenMASK = end - start
+			newrec[start:end] = (args.symbol)*lenMASK
+	seqALN.append(SeqRecord(Seq(str(newrec)), record.id, description=''))
+
+# Write masked alignment to file
+msg('Writing masked alignment to {} ... '.format(args.out))
+SeqIO.write(seqALN, args.out, 'fasta')
+
+# Write recombinant regions to file
+if args.regions:
+	with open(args.regions, 'w') as csvfile:
+		csvwriter = csv.writer(csvfile, delimiter='\t')
+		for k,v in list(d.items()):
+			for b in v:
+				x = b[0]
+				y = b[1]
+				z = b[2]
+				csvwriter.writerow([k,x,y,z])
+
+# Draw SVG
+svgsize = args.svgsize.split('x',1)
+width = int(svgsize[0])
+height = int(svgsize[1])
+numseqs = len(leafLIST)
+h = height/float(numseqs)
+s = width/float(int(seqlen))
+fsize = int(h*0.9)
+font = 'font-size:{}px; font-family:Arial'.format(fsize)
+colour = args.svgcolour
+main_colour = 'black'
+ancestral_colour = '#A9A9A9'
+interval = 500000		# Tick interval in bp
+
+dwg = svgwrite.Drawing(args.svg)
+
+def rect(x,p,w,colour):		# Draw regions
+	dwg.add(dwg.rect(insert=((x*s)+5, (p*h)+5), size=(w, h*0.8), fill=colour))
+	if args.consensus:
+		dwg.add(dwg.rect(insert=((x*s)+5, 5), size=(w, h*0.8), fill=main_colour))
+
+def label(n,p):			# Sequence ID labels
+	dwg.add(dwg.text(n, insert=((seqlen*s)+15, (((p+1)*h)-(0.2*h))+5), fill=main_colour, style=font))
+
+def ticks(q):			# Draw tick marks
+	count = interval
+	while count < seqlen:
+		dwg.add(dwg.line((count*s,((q)*h)), (count*s,((q)*h)-3), stroke=main_colour))
+		dwg.add(dwg.text((count/1000000.0), insert=((count*s)-6, ((q)*h)+13), fill=main_colour, style=font))
+		count = count + interval
+
+def box(width,h):		# Box with 5px margin
+	dwg.add(dwg.line((0,0), ((width+10),0), stroke=main_colour))
+	dwg.add(dwg.line(((width+10),0), ((width+10),((p+1)*h)), stroke=main_colour))
+	dwg.add(dwg.line(((width+10),((p+1)*h)), (0,((p+1)*h)), stroke=main_colour))
+	dwg.add(dwg.line((0,((p+1)*h)), (0,0), stroke=main_colour))
+
+# Draw recombinant regions and labels
+if args.svg:
+	msg('Drawing SVG to {} ...'.format(args.svg))
+	if args.consensus:
+		p = 1
+		dwg.add(dwg.text('Consensus', insert=((seqlen*s)+15, (0.8*h)+5), fill=main_colour, style=font))
+	else:
+		p = 0
+	for seq in leafLIST:
+		v = d.get(seq, None)
+		if v:
+			for b in v:
+				x = int(b[0])
+				y = int(b[1])
+				z = b[2]
+				w = (y-x)*s
+				if w < 1:
+					w = 1
+				if z == 'extant':
+					rect(x,p,w,colour)		# regions
+				elif z == 'ancestral':
+					rect(x,p,w,ancestral_colour)
+		label(seq,p)			# labels
+		p = p+1
+	# Draw bounding box
+	box(width,h)
+	# Add tick marks
+	ticks(p+1)
+	dwg.save()
+
+# Exit
+msg('Done.')
+sys.exit(0)