In oacar/pgsNetwork: This package is used for ref

knitr::opts_chunk$set(echo = TRUE,warnings=FALSE)

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

library(tidyverse)
library(ggsignif)
library(ggpubr)
load('analysis/data/derived_data/0629_markdown/pccvaluesboth.RData')

xd=cpcc_list#[adj_res_weights<0.2&cpcc_list>0.2]
yd=adj_res_weights#[adj_res_weights<0.2&cpcc_list>0.2]
ggplot()+geom_point(aes(x=xd,y=yd))+ylab('Our PCC values')+xlab('Costanzo PCC values')+theme_bw()

Both PCC>0.2

xd=cpcc_list[adj_res_weights>0.2&cpcc_list>0.2]
yd=adj_res_weights[adj_res_weights>0.2&cpcc_list>0.2]
ggplot()+geom_point(aes(x=xd,y=yd))+ylab('Our PCC values')+xlab('Costanzo PCC values')+theme_bw()+geom_smooth(method=lm, se=FALSE)+stat_cor(method = "pearson")#, label.x = 3, label.y = 30)

Different points

There are 12200 costanzo>0.2 but mine<0.2 and 8000 other way

xd=cpcc_list[(adj_res_weights<0.2&cpcc_list>=0.2)|(adj_res_weights>=0.2&cpcc_list<0.2)]
yd=adj_res_weights[(adj_res_weights<0.2&cpcc_list>=0.2)|(adj_res_weights>=0.2&cpcc_list<0.2)]
ggplot()+geom_point(aes(x=xd,y=yd))+ylab('Our PCC values')+xlab('Costanzo PCC values')+theme_bw()

Shortest path calculation on Costanzo data

comb_nw_data <- readRDS('analysis/data/derived_data/0629_markdown/0621_cpcc_combnwdata_upper.rds')
cbar <- ggplot(comb_nw_data, aes(x=type,y=data,color=group,fill=group,group = as.factor(group))) +
    stat_summary(fun.y = mean, geom = "point",position = position_dodge(width=1)) +
    stat_summary(fun.data = mean_se, geom = "errorbar",position = position_dodge(width=1))+ggtitle('costanzo_pcc_values')+ylab('Shortest path distance')+xlab('')+ coord_cartesian(ylim = c(4, 5))#+ylim(4,5)
cbar
ggplot(comb_nw_data%>%filter(type=='proto-gene'), aes(x=data,fill=group,color=group))+
    #geom_freqpoly(binwidth=3,position=position_dodge())
        geom_bar(stat='count',aes(y=..prop..),position=position_dodge())+ggtitle('proto-gene')+xlab('Shortest path distance')
# ggplot(comb_nw_data%>%filter(type=='nonessential'), aes(x=data,fill=group,color=group))+
#  #   geom_freqpoly(binwidth=3,position=position_dodge())
#         geom_bar(stat='count',aes(y=..prop..),position=position_dodge())+ggtitle('nonessential')+xlab('Shortest path distance')
# ggplot(comb_nw_data%>%filter(type=='essential'), aes(x=data,fill=group,color=group))+
#     #geom_freqpoly(binwidth=3,position=position_dodge())
#         geom_bar(stat='count',aes(y=..prop..),position=position_dodge())+ggtitle('essential')+xlab('Shortest path distance')

Shortest path calculation on my pcc

comb_nw_data <- readRDS('analysis/data/derived_data/0629_markdown/0625_mpcc_combnwdata.rds')
mbar <- ggplot(comb_nw_data, aes(x=type,y=data,color=group,fill=group,group = as.factor(group))) +
    stat_summary(fun.y = mean, geom = "point",position = position_dodge(width=1)) +
    stat_summary(fun.data = mean_se, geom = "errorbar",position = position_dodge(width=1))+ggtitle('new_pcc_values')+ylab('Shortest path distance')+xlab('')+ coord_cartesian(ylim = c(4, 5))#+ylim(4,5)
mbar
ggplot(comb_nw_data%>%filter(type=='proto-gene'), aes(x=data,fill=group,color=group))+
    #geom_freqpoly(binwidth=3,position=position_dodge())
        geom_bar(stat='count',aes(y=..prop..),position=position_dodge())+ggtitle('proto-gene')+xlab('Shortest path distance')
# ggplot(comb_nw_data%>%filter(type=='nonessential'), aes(x=data,fill=group,color=group))+
#  #   geom_freqpoly(binwidth=3,position=position_dodge())
#         geom_bar(stat='count',aes(y=..prop..),position=position_dodge())+ggtitle('nonessential')+xlab('Shortest path distance')
# ggplot(comb_nw_data%>%filter(type=='essential'), aes(x=data,fill=group,color=group))+
#     #geom_freqpoly(binwidth=3,position=position_dodge())
#         geom_bar(stat='count',aes(y=..prop..),position=position_dodge())+ggtitle('essential')+xlab('Shortest path distance')

side by side

library(cowplot)
plot_grid(cbar,mbar)

SAFE layout weighted shortest path

Costanzo

comb_nw_data <- readRDS('analysis/data/derived_data/0629_markdown/0625_cpcc_combnwdata.rds')

cwbar <- ggplot(comb_nw_data, aes(x=type,y=data,color=group,fill=group,group = as.factor(group))) +
    stat_summary(fun.y = mean, geom = "point",position = position_dodge(width=1)) +
    stat_summary(fun.data = mean_se, geom = "errorbar",position = position_dodge(width=1))+ggtitle('costanzo_pcc_values')+ylab('Weighted shortest path distance')+xlab('')+ coord_cartesian(ylim = c(30, 50))#+ylim(30,50)
cwbar
ggplot(comb_nw_data%>%filter(type=='proto-gene'), aes(x=data,fill=group,color=group,y=..density..))+
    geom_freqpoly(binwidth=3,position=position_dodge())+ggtitle('proto-gene')+xlab('Weighted shortest path distance')
#        geom_bar(stat='count',aes(y=..prop..),position=position_dodge())

# ggplot(comb_nw_data%>%filter(type=='nonessential'), aes(x=data,fill=group,color=group,y=..density..))+
#    geom_freqpoly(binwidth=3,position=position_dodge())+ggtitle('nonessential')+xlab('Weighted shortest path distance')
#  #       geom_bar(stat='count',aes(y=..prop..),position=position_dodge())
# 
# ggplot(comb_nw_data%>%filter(type=='essential'), aes(x=data,fill=group,color=group,y=..density..))+
#     geom_freqpoly(binwidth=3,position=position_dodge())+ggtitle('essential')+xlab('Weighted shortest path distance')

Mine

comb_nw_data <- readRDS('analysis/data/derived_data/0629_markdown/0624_mpcc_combnwdata_upper.rds')

mwbar <- ggplot(comb_nw_data, aes(x=type,y=data,color=group,fill=group,group = as.factor(group))) +
    stat_summary(fun.y = mean, geom = "point",position = position_dodge(width=1)) +
    stat_summary(fun.data = mean_se, geom = "errorbar",position = position_dodge(width=1))+ggtitle('new_pcc_values')+ylab('Weighted shortest path distance')+xlab('')+ coord_cartesian(ylim = c(30, 50))#+ylim(30,50)
mwbar
ggplot(comb_nw_data%>%filter(type=='proto-gene'), aes(x=data,fill=group,color=group,y=..density..))+
    geom_freqpoly(binwidth=3,position=position_dodge())+ggtitle('proto-gene')+xlab('Weighted shortest path distance')
#        geom_bar(stat='count',aes(y=..prop..),position=position_dodge())

# ggplot(comb_nw_data%>%filter(type=='nonessential'), aes(x=data,fill=group,color=group,y=..density..))+
#    geom_freqpoly(binwidth=3,position=position_dodge())+ggtitle('nonessential')+xlab('Weighted shortest path distance')
#  #       geom_bar(stat='count',aes(y=..prop..),position=position_dodge())
# 
# ggplot(comb_nw_data%>%filter(type=='essential'), aes(x=data,fill=group,color=group,y=..density..))+
#     geom_freqpoly(binwidth=3,position=position_dodge())+ggtitle('essential')+xlab('Weighted shortest path distance')

sidebyside

plot_grid(cwbar,mwbar)

PCC network analysis results

rm(list=ls())
gc()
library(plyr)
load("~/Main/anne/network_analysis/0409/pccData.Rdata")
load("~/Main/anne/network_analysis/0530essential/pcc_essential.RData")
sm.list.pcc$type <- revalue(sm.list.pcc$type, c("actual" = "Proto-gene", "simulation" = "Non-essential"))
sm.list.nodeg.pcc.mean <- readRDS("~/Main/anne/network_analysis/0409/sm.list.nodeg.pcc.mean.rds")
sm.list.nodeg.pcc$type <- revalue(sm.list.nodeg.pcc$type, c("actual" = "Proto-gene", "simulation" = "Non-essential"))

sm.list.nodeg.pcc <- readRDS("~/Main/anne/network_analysis/0409/sm.list.nodeg.pcc.rds")
sm.list.nodeg.pcc$type <- revalue(sm.list.nodeg.pcc$type, c("actual" = "Proto-gene", "simulation" = "Non-essential"))

pcc_degree_mean_df <- bind_rows(
  data.frame(data = sm.list.nodeg.pcc.mean$nn.mean, type = "Proto-gene"), data.frame(data = sm.list.nodeg.pcc.mean$nones.mean, type = "Non-essential"),
  data.frame(data = pcc_essentialmeandf$degree, type = "Essential")
)
pcc_degree_mean_df$type <- factor(pcc_degree_mean_df$type, levels = c("Proto-gene", "Non-essential", "Essential"))
ggboxdegpcc <- ggplot(
  pcc_degree_mean_df,
  aes(x = type, y = data, fill = type)
) + geom_boxplot() +  scale_x_discrete(labels=element_blank())+
  ylab("Mean") + xlab("") + theme(legend.position = "none", axis.title.y = element_text(size = 25)) + scale_fill_manual(values = c("#00BFC4", "#FF3300", "orange")) # ggplot(subset(sm.list2,group=='proto-gene'),aes(x=type,color=type))+geom_boxplot(aes(y=betweenness))

pcc_degree_df <- bind_rows(subset(sm.list.nodeg.pcc, group == "proto-gene"), pcc_essentialdf)
pcc_degree_df$type <- factor(pcc_degree_df$type, levels = c("Proto-gene", "Non-essential", "essential"))

gglinedegpcc <- ggplot(pcc_degree_df, aes(x = (degree), color = type, fill = type)) +
  geom_freqpoly(aes(y = c(
    ..count..[..group.. == 1] / sum(..count..[..group.. == 1]),
    ..count..[..group.. == 2] / sum(..count..[..group.. == 2]),
    ..count..[..group.. == 3] / sum(..count..[..group.. == 3])
  )),
  position = "identity", binwidth = 2
  ) + xlim(1, NA) + labs(color = "") + scale_color_manual(values = c("#00BFC4", "#FF3300", "orange")) + theme(legend.position = "none", axis.title.y = element_text(size = 30), axis.title.x = element_text(size = 30)) + # scale_fill_discrete(name='')+
  ylab("Percentage") + xlab("Degree") + scale_y_continuous(labels = scales::percent) # sm.l# pgs.data <- as.tbl(data.frame(matrix(ncol=7,nrow=86)))

degpcc_c <- ggdraw() +
  draw_plot(gglinedegpcc + theme(legend.justification = "bottom"), 0, 0, 1, 1) +
  draw_plot(ggboxdegpcc + # scale_color_viridis(discrete = TRUE) +
    theme(legend.justification = "top"), 0.45, 0.46, 0.58, 0.59)


# betweenness--------
pcc_btw_mean_df <- bind_rows(
  data.frame(data = sm.list.nodeg.pcc.mean$nn.btw.mean, type = "Proto-gene"), data.frame(data = sm.list.nodeg.pcc.mean$nones.btw.mean, type = "Non-essential"),
  data.frame(data = pcc_essentialmeandf$betweenness, type = "essential")
)
pcc_btw_mean_df$type <- factor(pcc_btw_mean_df$type, levels = c("Proto-gene", "Non-essential", "essential"))
ggboxbtwpcc <- ggplot(
  pcc_btw_mean_df,
  aes(x = type, y = data, fill = type)
) + geom_boxplot() + scale_x_discrete(labels=element_blank())+
  ylab("Mean") + xlab("") + theme(legend.position = "none", axis.title.y = element_text(size = 25)) + scale_fill_manual(values = c("#00BFC4", "#FF3300", "orange")) # ggplot(subset(sm.list2,group=='proto-gene'),aes(x=type,color=type))+geom_boxplot(aes(y=betweenness))

pcc_btw_df <- bind_rows(subset(sm.list.nodeg.pcc, group == "proto-gene"), pcc_essentialdf)
pcc_btw_df$type <- factor(pcc_btw_df$type, levels = c("Proto-gene", "Non-essential", "essential"))

gglinebtwpcc <- ggplot(pcc_btw_df, aes(x = (betweenness), color = type, fill = type)) +
  geom_freqpoly(aes(y = c(
    ..count..[..group.. == 1] / sum(..count..[..group.. == 1]),
    ..count..[..group.. == 2] / sum(..count..[..group.. == 2]),
    ..count..[..group.. == 3] / sum(..count..[..group.. == 3])
  )),
  position = "identity", binwidth = 0.001
  ) + xlim(0, NA) + labs(color = "") + scale_color_manual(values = c("#00BFC4", "#FF3300", "orange")) + theme(legend.position = "none", axis.title.y = element_text(size = 30), axis.title.x = element_text(size = 30)) + # scale_fill_discrete(name='')+
  ylab("Percentage") + xlab("Betweenness") + scale_y_continuous(labels = scales::percent) # sm.l# pgs.data <- as.tbl(data.frame(matrix(ncol=7,nrow=86)))

btwpcc_c <- ggdraw() +
  draw_plot(gglinebtwpcc + theme(legend.justification = "bottom"), 0, 0, 1, 1) +
  draw_plot(ggboxbtwpcc + # scale_color_viridis(discrete = TRUE) +
    theme(legend.justification = "top"), 0.45, 0.46, 0.58, 0.59)


# trans------

pcc_trans_mean_df <- bind_rows(
  data.frame(data = sm.list.nodeg.pcc.mean$nn.trans.mean, type = "Proto-gene"), data.frame(data = sm.list.nodeg.pcc.mean$nones.trans.mean, type = "Non-essential"),
  data.frame(data = pcc_essentialmeandf$trans, type = "Essential")
)
pcc_trans_mean_df$type <- factor(pcc_trans_mean_df$type, levels = c("Proto-gene", "Non-essential", "Essential"))
ggboxtranspcc <- ggplot(
  pcc_trans_mean_df,
  aes(x = type, y = data, fill = type)
) + geom_boxplot() + scale_x_discrete(labels=element_blank())+
  ylab("Mean") + xlab("") + theme(legend.position = "none", axis.title.y = element_text(size = 25)) + scale_fill_manual(values = c("#00BFC4", "#FF3300", "orange")) # ggplot(subset(sm.list2,group=='proto-gene'),aes(x=type,color=type))+geom_boxplot(aes(y=betweenness))

pcc_trans_df <- bind_rows(subset(sm.list.nodeg.pcc, group == "proto-gene"), pcc_essentialdf)
pcc_trans_df$type <- factor(pcc_trans_df$type, levels = c("Proto-gene", "Non-essential", "essential"))

gglinetranspcc <- ggplot(pcc_trans_df, aes(x = (trans), color = type, fill = type)) +
  geom_freqpoly(aes(y = c(
    ..count..[..group.. == 1] / sum(..count..[..group.. == 1]),
    ..count..[..group.. == 2] / sum(..count..[..group.. == 2]),
    ..count..[..group.. == 3] / sum(..count..[..group.. == 3])
  )),
  position = "identity", binwidth = 0.1
  ) + xlim(0, NA) + labs(color = "") + scale_color_manual(values = c("#00BFC4", "#FF3300", "orange")) + theme(legend.position = "none", axis.title.y = element_text(size = 30), axis.title.x = element_text(size = 30)) + # scale_fill_discrete(name='')+
  ylab("Percentage") + xlab("Clustering Coefficient") + scale_y_continuous(labels = scales::percent) # sm.l# pgs.data <- as.tbl(data.frame(matrix(ncol=7,nrow=86)))

transpcc_c <- ggdraw() +
  draw_plot(gglinetranspcc + theme(legend.justification = "bottom"), 0, 0, 1, 1) +
  draw_plot(ggboxtranspcc + # scale_color_viridis(discrete = TRUE) +
    theme(legend.justification = "top"), 0.45, 0.46, 0.58, 0.59) #+
# draw_plot_label(c("A", "B"), c(0, 0.5), c(1, 0.92), size = 15)
legend <- get_legend(gglinebtwpcc + theme(legend.position = "bottom", legend.text = element_text(size = 20), legend.key.size = unit(5, "line")))

#plot_grid(degpcc,btwpcc,transpcc,legend)



load('analysis/data/derived_data/0629_markdown/mypcccalculationdataframes.RData')
# load('pcc_essential.RData')
# save(sm.list2,sm.list,sm.means,sm.means2,pcc_essentialdf,pcc_essentialmeandf,file='analysis/data/derived_data/0629_markdown/mypcccalculationdataframes.RData')
sm.list.pcc <- sm.list2
sm.list.nodeg.pcc <- sm.list
#sm.list.nodeg.int$type <- revalue(sm.list.nodeg.int$type, c("actual"="Actual", "simulation"="Simulation"))
sm.list.pcc$type <- revalue(sm.list.pcc$type, c("actual" = "Proto-gene", "simulation" = "Non-essential"))

sm.list.nodeg.pcc$type <- revalue(sm.list.nodeg.pcc$type, c("actual" = "Proto-gene", "simulation" = "Non-essential"))
sm.list.nodeg.pcc.mean <- sm.means
sm.list.pcc.mean <- sm.means2

# degree--------
pcc_degree_mean_df <- bind_rows(
  data.frame(data = sm.list.nodeg.pcc.mean$nn.mean, type = "Proto-gene"), data.frame(data = sm.list.nodeg.pcc.mean$nones.mean, type = "Non-essential"),
  data.frame(data = pcc_essentialmeandf$degree, type = "Essential")
)
pcc_degree_mean_df$type <- factor(pcc_degree_mean_df$type, levels = c("Proto-gene", "Non-essential", "Essential"))
ggboxdegpcc <- ggplot(
  pcc_degree_mean_df,
  aes(x = type, y = data, fill = type)
) + geom_boxplot() +  scale_x_discrete(labels=element_blank())+
  ylab("Mean") + xlab("") + theme(legend.position = "none", axis.title.y = element_text(size = 25)) + scale_fill_manual(values = c("#00BFC4", "#FF3300", "orange")) # ggplot(subset(sm.list2,group=='proto-gene'),aes(x=type,color=type))+geom_boxplot(aes(y=betweenness))

pcc_degree_df <- bind_rows(subset(sm.list.nodeg.pcc, group == "proto-gene"), pcc_essentialdf)
pcc_degree_df$type <- factor(pcc_degree_df$type, levels = c("Proto-gene", "Non-essential", "essential"))

gglinedegpcc <- ggplot(pcc_degree_df, aes(x = (degree), color = type, fill = type)) +
  geom_freqpoly(aes(y = c(
    ..count..[..group.. == 1] / sum(..count..[..group.. == 1]),
    ..count..[..group.. == 2] / sum(..count..[..group.. == 2]),
    ..count..[..group.. == 3] / sum(..count..[..group.. == 3])
  )),
  position = "identity", binwidth = 2
  ) + xlim(1, NA) + labs(color = "") + scale_color_manual(values = c("#00BFC4", "#FF3300", "orange")) + theme(legend.position = "none", axis.title.y = element_text(size = 30), axis.title.x = element_text(size = 30)) + # scale_fill_discrete(name='')+
  ylab("Percentage") + xlab("Degree") + scale_y_continuous(labels = scales::percent) # sm.l# pgs.data <- as.tbl(data.frame(matrix(ncol=7,nrow=86)))

degpcc_m <- ggdraw() +
  draw_plot(gglinedegpcc + theme(legend.justification = "bottom"), 0, 0, 1, 1) +
  draw_plot(ggboxdegpcc + # scale_color_viridis(discrete = TRUE) +
    theme(legend.justification = "top"), 0.45, 0.46, 0.58, 0.59)


# betweenness--------
pcc_btw_mean_df <- bind_rows(
  data.frame(data = sm.list.pcc.mean$nn.btw.mean, type = "Proto-gene"), data.frame(data = sm.list.pcc.mean$nones.btw.mean, type = "Non-essential"),
  data.frame(data = pcc_essentialmeandf$betweenness, type = "essential")
)
pcc_btw_mean_df$type <- factor(pcc_btw_mean_df$type, levels = c("Proto-gene", "Non-essential", "essential"))
ggboxbtwpcc <- ggplot(
  pcc_btw_mean_df,
  aes(x = type, y = data, fill = type)
) + geom_boxplot() + scale_x_discrete(labels=element_blank())+
  ylab("Mean") + xlab("") + theme(legend.position = "none", axis.title.y = element_text(size = 25)) + scale_fill_manual(values = c("#00BFC4", "#FF3300", "orange")) # ggplot(subset(sm.list2,group=='proto-gene'),aes(x=type,color=type))+geom_boxplot(aes(y=betweenness))

pcc_btw_df <- bind_rows(subset(sm.list.pcc, group == "proto-gene"), pcc_essentialdf)
pcc_btw_df$type <- factor(pcc_btw_df$type, levels = c("Proto-gene", "Non-essential", "essential"))

gglinebtwpcc <- ggplot(pcc_btw_df, aes(x = (betweenness), color = type, fill = type)) +
  geom_freqpoly(aes(y = c(
    ..count..[..group.. == 1] / sum(..count..[..group.. == 1]),
    ..count..[..group.. == 2] / sum(..count..[..group.. == 2]),
    ..count..[..group.. == 3] / sum(..count..[..group.. == 3])
  )),
  position = "identity", binwidth = 0.001
  ) + xlim(0, NA) + labs(color = "") + scale_color_manual(values = c("#00BFC4", "#FF3300", "orange")) + theme(legend.position = "none", axis.title.y = element_text(size = 30), axis.title.x = element_text(size = 30)) + # scale_fill_discrete(name='')+
  ylab("Percentage") + xlab("Betweenness") + scale_y_continuous(labels = scales::percent) # sm.l# pgs.data <- as.tbl(data.frame(matrix(ncol=7,nrow=86)))

btwpcc_m <- ggdraw() +
  draw_plot(gglinebtwpcc + theme(legend.justification = "bottom"), 0, 0, 1, 1) +
  draw_plot(ggboxbtwpcc + # scale_color_viridis(discrete = TRUE) +
    theme(legend.justification = "top"), 0.45, 0.46, 0.58, 0.59)


# trans------

pcc_trans_mean_df <- bind_rows(
  data.frame(data = sm.list.pcc.mean$nn.trans.mean, type = "Proto-gene"), data.frame(data = sm.list.pcc.mean$nones.trans.mean, type = "Non-essential"),
  data.frame(data = pcc_essentialmeandf$trans, type = "Essential")
)
pcc_trans_mean_df$type <- factor(pcc_trans_mean_df$type, levels = c("Proto-gene", "Non-essential", "Essential"))
ggboxtranspcc <- ggplot(
  pcc_trans_mean_df,
  aes(x = type, y = data, fill = type)
) + geom_boxplot() + scale_x_discrete(labels=element_blank())+
  ylab("Mean") + xlab("") + theme(legend.position = "none", axis.title.y = element_text(size = 25)) + scale_fill_manual(values = c("#00BFC4", "#FF3300", "orange")) # ggplot(subset(sm.list2,group=='proto-gene'),aes(x=type,color=type))+geom_boxplot(aes(y=betweenness))

pcc_trans_df <- bind_rows(subset(sm.list.pcc, group == "proto-gene"), pcc_essentialdf)
pcc_trans_df$type <- factor(pcc_trans_df$type, levels = c("Proto-gene", "Non-essential", "essential"))

gglinetranspcc <- ggplot(pcc_trans_df, aes(x = (trans), color = type, fill = type)) +
  geom_freqpoly(aes(y = c(
    ..count..[..group.. == 1] / sum(..count..[..group.. == 1]),
    ..count..[..group.. == 2] / sum(..count..[..group.. == 2]),
    ..count..[..group.. == 3] / sum(..count..[..group.. == 3])
  )),
  position = "identity", binwidth = 0.1
  ) + xlim(0, NA) + labs(color = "") + scale_color_manual(values = c("#00BFC4", "#FF3300", "orange")) + theme(legend.position = "none", axis.title.y = element_text(size = 30), axis.title.x = element_text(size = 30)) + # scale_fill_discrete(name='')+
  ylab("Percentage") + xlab("Clustering Coefficient") + scale_y_continuous(labels = scales::percent) # sm.l# pgs.data <- as.tbl(data.frame(matrix(ncol=7,nrow=86)))

transpcc_m <- ggdraw() +
  draw_plot(gglinetranspcc + theme(legend.justification = "bottom"), 0, 0, 1, 1) +
  draw_plot(ggboxtranspcc + # scale_color_viridis(discrete = TRUE) +
    theme(legend.justification = "top"), 0.45, 0.46, 0.58, 0.59) #+
# draw_plot_label(c("A", "B"), c(0, 0.5), c(1, 0.92), size = 15)


plot_grid( degpcc_c,degpcc_m,scale = 0.9)
plot_grid( btwpcc_c, btwpcc_m, scale = 0.9)
plot_grid(transpcc_c,transpcc_m, scale = 0.9)

comb_avg_cpcc <- readRDS('analysis/data/derived_data/0629_markdown/comb_avg_pcc_costanzo.rds')
cwbar <- ggplot(comb_avg_cpcc, aes(x=type,y=data,color=type)) +geom_boxplot()
    stat_summary(fun.y = mean, geom = "point",position = position_dodge(width=1)) +
    stat_summary(fun.data = mean_se, geom = "errorbar",position = position_dodge(width=1))+ggtitle('costanzo_pcc_values')+ylab('Weighted shortest path distance')+xlab('')
cwbar


comb_avg_mpcc <- readRDS('analysis/data/derived_data/0629_markdown/comb_avg_pcc_mine.rds')
mwbar <- ggplot(comb_avg_cpcc, aes(x=type,y=data,color=type)) +geom_boxplot()
    stat_summary(fun.y = mean, geom = "point",position = position_dodge(width=1)) +
    stat_summary(fun.data = mean_se, geom = "errorbar",position = position_dodge(width=1))+ggtitle('costanzo_pcc_values')+ylab('Weighted shortest path distance')+xlab('')
mwbar