tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

breakage

Browse source
This commit is contained in:
Tanushree Tunstall 2022-08-05 12:45:16 +01:00
parent 14f8f5d6d4
commit c0f59bc9c9
5 changed files with 74 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

28
scripts/functions/bp_lineage_diversity.R
View file

@ -23,14 +23,19 @@ lin_count_bp_diversity <- function( lf_data = lin_wf
, my_xals = 22 # x axis label size
, my_yals = 22 # y axis label size
, my_lls = 22 # legend label size
, bar_col_labels = c("Mutations", "Total Samples")
, bar_col_values = c("grey50", "gray75")
, bar_col_labels = "" #c("Mutations", "Total Samples")
, bar_col_values = c("gray50", "gray75")
, bar_leg_name = ""
, leg_location = "top"
, y_log10 = FALSE
, y_scale_percent = FALSE
#, y_label = c("Count", "SNP diversity")
, y_label = c("SNP diversity")
, bp_plot_title = ""
, title_colour = "chocolate4"
, subtitle_text = NULL
, sts = 20
, subtitle_colour = "#350E20FF" #brown
) {
if(!all_lineages){
lf_data = lf_data[lf_data[[x_categ]]%in%use_lineages,]
@ -58,7 +63,13 @@ lin_count_bp_diversity <- function( lf_data = lin_wf
, axis.title.y = element_text(size = my_yals
, colour = "black")
, legend.position = leg_location
, legend.text = element_text(size = my_lls)) +
, legend.text = element_text(size = my_lls)
, plot.title = element_text(size = my_lls
, colour = title_colour
, hjust = 0.5)
, plot.subtitle = element_text(size = sts
, hjust = 0.5
, colour = subtitle_colour)) +
geom_label(aes(label = eval(parse(text = display_label_col)))
, size = d_lab_size
@ -72,7 +83,13 @@ lin_count_bp_diversity <- function( lf_data = lin_wf
scale_fill_manual(values = bar_col_values
, name = bar_leg_name
, labels = bar_col_labels) +
labs(title = ""
# labs(title = ""
# , x = ""
# , y = y_label
# , colour = "black")
#
labs(title = bp_plot_title
, subtitle = subtitle_text
, x = ""
, y = y_label
, colour = "black")
@ -90,7 +107,8 @@ lin_count_bp_diversity <- function( lf_data = lin_wf
scale_y_continuous(labels = scales::percent_format(accuracy = 1)) +
#scale_y_continuous(labels = scales::percent) +
labs(title = ""
labs(title = bp_plot_title
, subtitle = subtitle_text
, x = ""
, y = y_label
, colour = "black")

23
scripts/functions/combining_dfs_plotting.R
View file

@ -343,6 +343,29 @@ combining_dfs_plotting <- function( my_df_u
, "\nNo. of rows merged_df3: ", nrow(merged_df3))
quit()
}
#---------------------------------------------
# add columns that are needed to generate plots with revised colnames and strings
#----------------------------------------------
merged_df3['sensitivity'] = ifelse(merged_df3['dst_mode'] == 1, "R", "S")
merged_df3['mutation_info_labels'] = ifelse(merged_df3['mutation_info_labels'] == "DM", "R", "S")
merged_df2['sensitivity'] = ifelse(merged_df2['dst_mode'] == 1, "R", "S")
merged_df2['mutation_info_labels'] = ifelse(merged_df2['mutation_info_labels'] == "DM", "R", "S")
#check1 = all(table(merged_df3["mutation_info_labels"]) == table(merged_df3['sensitivity']))
#check2 = all(table(merged_df2["mutation_info_labels"]) == table(merged_df2['sensitivity']))
check1 = all(merged_df3["mutation_info_labels"] == merged_df3['sensitivity'])
check2 = all(merged_df2["mutation_info_labels"] == merged_df2['sensitivity'])
if(check1 && check2){
cat("PASS: merged_df3 and merged_df2 have mutation info labels as R and S"
, "\nIt also has sensitivity column"
, "\nThese are identical")
}else{
stop("Abort: merged_df3 or merged_df2 can't be created because of lable mismatch")
}
return(list( merged_df2
, merged_df3
))

15
scripts/functions/dm_om_data.R
View file

@ -37,6 +37,11 @@
#1) df to choose (merged_df3 or merged_df2)
#2)
##################################################################
DistCutOff = 10
LigDist_colname # = "ligand_distance" # from globals
ppi2Dist_colname = "interface_dist"
naDist_colname = "TBC"
dm_om_wf_lf_data <- function(df
, gene_name = gene # from globals
, colnames_to_extract
@ -51,6 +56,15 @@ dm_om_wf_lf_data <- function(df
, dr_other_muts_labels = c("DM", "OM") # only used if ^^ = ""
, categ_cols_to_factor){
df = as.data.frame(df)
df['sensitivity'] = ifelse(df['dst_mode'] == 1, "R", "S")
table(df['sensitivity'])
df[[mut_info_label_colname]] = ifelse(df[[mut_info_label_colname]] == "DM", "R", "S")
table(df[[mut_info_label_colname]])
# Initialise the required dfs based on gene name
geneL_normal = c("pnca")
#geneL_na_dy = c("gid")
@ -124,6 +138,7 @@ dm_om_wf_lf_data <- function(df
, mut_colname, mut_info_colname, mut_info_label_colname
, aa_pos_colname
, LigDist_colname
, ppi2Dist_colname, naDist_colname
, "duet_stability_change" , "duet_scaled" , "duet_outcome"
, "ligand_affinity_change", "affinity_scaled" , "ligand_outcome"
, "ddg_foldx" , "foldx_scaled" , "foldx_outcome"

1
scripts/plotting/get_plotting_dfs.R
View file

@ -144,6 +144,7 @@ cat(s3)
# location: scripts/functions/corr_plot_data.R
####################################################################
# make sure the above script works because merged_df2_combined is needed
merged_df3 = as.data.frame(merged_df3)
corr_df_m3_f = corr_data_extract(merged_df3, extract_scaled_cols = F)
head(corr_df_m3_f)

7
scripts/plotting/plotting_thesis/lineage_barplots_combined.R
View file

@ -48,7 +48,12 @@ lin_diversityP = lin_count_bp_diversity(lf_data = lineage_dfL[['lin_wf']]
, y_log10 = F
, y_scale_percent = F
, leg_location = "top"
, y_label = "SNP diversity")
, y_label = "Percent" #"SNP diversity"
, bp_plot_title = "SNP diversity"
, title_colour = "black" #"chocolate4"
, subtitle_text = NULL
, sts = 20
, subtitle_colour = "#350E20FF")
#=============================================
# Output plots: Lineage count and Diversity