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

added placeholder defaults for functions in R to make sure that R shiny layput works with a data set for meeting tomorrow

Browse source
This commit is contained in:
Tanushree Tunstall 2022-02-14 19:33:00 +00:00
parent 0460ca1708
commit d38521e03a
11 changed files with 120 additions and 83 deletions
Download patch file Download diff file Expand all files Collapse all files

15
scripts/functions/bp_lineage.R
View file

@ -4,11 +4,11 @@
# Lineage Diversity barplot # Lineage Diversity barplot
######################################## ########################################
lin_count_bp <- function( lf_data lin_count_bp <- function( lf_data = lin_lf
, x_categ = "" , x_categ = "sel_lineages"
, y_count = "" , y_count = "p_count"
, bar_fill_categ = "" , bar_fill_categ = "count_categ"
, display_label_col = "" , display_label_col = "p_count"
, bar_stat_stype = "identity" , bar_stat_stype = "identity"
, x_lab_angle = 90 , x_lab_angle = 90
, d_lab_size = 5 , d_lab_size = 5
@ -20,13 +20,14 @@ lin_count_bp <- function( lf_data
, my_xals = 22 # x axis label size , my_xals = 22 # x axis label size
, my_yals = 22 # y axis label size , my_yals = 22 # y axis label size
, my_lls = 22 # legend label size , my_lls = 22 # legend label size
, bar_col_labels = "" , bar_col_labels = c("Mutations", "Total Samples")
, bar_col_values = "" , bar_col_values = c("grey50", "gray75")
, bar_leg_name = "" , bar_leg_name = ""
, leg_location = "top" , leg_location = "top"
, y_log10 = FALSE , y_log10 = FALSE
, y_scale_percent = FALSE , y_scale_percent = FALSE
, y_label = c("Count", "SNP diversity") , y_label = c("Count", "SNP diversity")
#, y_label = c("Count")
) { ) {
g = ggplot(lf_data g = ggplot(lf_data
, aes( x = factor( eval(parse(text = x_categ)), ordered = T ) , aes( x = factor( eval(parse(text = x_categ)), ordered = T )

6
scripts/functions/bp_subcolours.R
View file

@ -36,9 +36,9 @@ ColourPalleteMulti = function(df, group, subgroup){
bp_stability_hmap <- function(plotdf = merged_df3 bp_stability_hmap <- function(plotdf = merged_df3
, xvar_colname = "position" , xvar_colname = "position"
#, bar_col_colname = "group" #, bar_col_colname = "group"
, stability_colname = "" , stability_colname = "duet_scaled"
, stability_outcome_colname = "" , stability_outcome_colname = "duet_outcome"
, p_title = "" # "Protein stability (DUET)" , p_title = "DUET" # "Protein stability (DUET)"
, my_xaxls = 12 # x-axis label size , my_xaxls = 12 # x-axis label size
, my_yaxls = 20 # y-axis label size , my_yaxls = 20 # y-axis label size
, my_xaxts = 18 # x-axis text size , my_xaxts = 18 # x-axis text size

45
scripts/functions/consurfP.R
View file

@ -12,7 +12,7 @@
# wideP(): # wideP():
# input args # input args
#========================================================== #==========================================================
wideP_point <- function(plotdf wideP_consurf <- function(plotdf
, xvar_colname = "position" , xvar_colname = "position"
, yvar_colname = "consurf_score" , yvar_colname = "consurf_score"
, yvar_colourN_colname = "consurf_colour_rev" # num from 0-1 , yvar_colourN_colname = "consurf_colour_rev" # num from 0-1
@ -542,24 +542,51 @@ wideP_point <- function(plotdf
}else{ }else{
cat("\nNo annotation for xvar requested") cat("\nNo annotation for xvar requested")
} }
#==============================================
if (A_xvar_lig){ if (A_xvar_lig){
legs = grid.arrange(legend1 legs = cowplot::plot_grid(legend1
, legend2 , legend2
, ncol = 1 , ncol = 1
, heights = c(3/4,1)) , align = "hv"
out2 = grid.arrange( out + theme(legend.position = "none") , rel_heights = c(3/4,1))
, legs
, ncol = 2 out2 = cowplot::plot_grid( out + theme(legend.position = "none")
, widths = c(9/10, 0.5/10) , legs
, ncol = 2
, align = "hv"
, rel_widths = c(9/10, 0.5/10)
) )
}else{ }else{
out2 = grid.arrange( out + theme(legend.position = "none") out2 = cowplot::plot_grid( out + theme(legend.position = "none")
, legend1 , legend1
, ncol = 2 , ncol = 2
, widths = c(9/10, 0.5/10) , align = "hv"
, rel_widths = c(9/10, 0.5/10)
) )
} }
#==============================================
#==============================================
# if (A_xvar_lig){
# legs = grid.arrange(legend1
# , legend2
# , ncol = 1
# , heights = c(3/4,1))
#
# out2 = grid.arrange( out + theme(legend.position = "none")
# , legs
# , ncol = 2
# , widths = c(9/10, 0.5/10)
# )
# }else{
# out2 = grid.arrange( out + theme(legend.position = "none")
# , legend1
# , ncol = 2
# , widths = c(9/10, 0.5/10)
# )
# }
#==============================================
return(out2) return(out2)
#return(out2) #return(out2)

8
scripts/functions/lf_bp.R
View file

@ -6,10 +6,10 @@
# beeswarm # beeswarm
############################# #############################
lf_bp <- function(lf_df lf_bp <- function(lf_df = lf_duet
, p_title = "" , p_title = "DUET-DDG"
, colour_categ = "" , colour_categ = "duet_outcome"
, x_grp = "mutation_info" , x_grp = "mutation_info_labels"
, y_var = "param_value" , y_var = "param_value"
, facet_var = "param_type" , facet_var = "param_type"
, n_facet_row = 1 , n_facet_row = 1

4
scripts/functions/stability_count_bp.R
View file

@ -15,8 +15,8 @@ theme_set(theme_grey())
## ...opt args ## ...opt args
#========================================================== #==========================================================
stability_count_bp <- function(plotdf stability_count_bp <- function(plotdf
, df_colname = "" , df_colname = "duet_outcome"
, leg_title = "Legend Title" , leg_title = "DUET"
, ats = 25 # axis text size , ats = 25 # axis text size
, als = 22 # axis label size , als = 22 # axis label size
, lts = 20 # legend text size , lts = 20 # legend text size

21
scripts/functions/tests/test_bp.R
View file

@ -5,19 +5,18 @@ getwd()
#=========================================== #===========================================
# load functions, data, dirs, hardocded vars # load functions, data, dirs, hardocded vars
# that will be used in testing the functions # that will be used in testing the functions
#drug = "streptomycin"
#gene = "gid"
#source("plotting_data.R")
#infile = paste0("~/git/Data/", drug, "/output/", gene, "_comb_stab_struc_params.csv")
#infile_df = read.csv(infile)
#=========================================== #===========================================
drug = "streptomycin"
gene = "gid"
source("plotting_data.R")
infile = paste0("~/git/Data/", drug, "/output/", gene, "_comb_stab_struc_params.csv")
infile_df = read.csv(infile)
lig_dist = 5 lig_dist = 5
pd_df = plotting_data(infile_df pd_df = plotting_data(infile_df
, lig_dist_colname = 'ligand_distance' , lig_dist_colname = 'ligand_distance'
, lig_dist_cutoff = lig_dist) , lig_dist_cutoff = lig_dist)
my_df = pd_df[[1]] my_df = pd_df[[1]]
my_df_u = pd_df[[2]] my_df_u = pd_df[[2]]
@ -42,8 +41,8 @@ print(paste0("plot filename:", basic_bp_duet))
# function only # function only
stability_count_bp(plotdf = my_df_u stability_count_bp(plotdf = my_df_u
, df_colname = "duet_outcome" , df_colname = "ligand_outcome"
, leg_title = "DUET outcome" , leg_title = "Lig outcome"
, label_categories = c("Destabilising", "Stabilising") , label_categories = c("Destabilising", "Stabilising")
, leg_position = "top") , leg_position = "top")

8
scripts/functions/tests/test_bp_lineage.R
View file

@ -20,8 +20,8 @@ levels(lin_lf_plot$sel_lineages_f)
#========================= #=========================
# Lineage count plot # Lineage count plot
#========================= #=========================
lin_count_bp(lin_lf_plot lin_count_bp(lin_lf_plot = lin_lf
, x_categ = "sel_lineages_f" , x_categ = "sel_lineages"
, y_count = "p_count" , y_count = "p_count"
, bar_fill_categ = "count_categ" , bar_fill_categ = "count_categ"
, display_label_col = "p_count" , display_label_col = "p_count"
@ -51,8 +51,8 @@ levels(lin_wf_plot$sel_lineages_f)
#========================= #=========================
# Lineage Diversity plot # Lineage Diversity plot
#========================= #=========================
lin_count_bp(lin_wf_plot lin_count_bp(lin_wf_plot = lin_wf
, x_categ = "sel_lineages_f" , x_categ = "sel_lineages"
, y_count = "snp_diversity" , y_count = "snp_diversity"
, display_label_col = "snp_diversity_f" , display_label_col = "snp_diversity_f"
, bar_stat_stype = "identity" , bar_stat_stype = "identity"

40
scripts/functions/tests/test_consurfP.R
View file

@ -4,9 +4,9 @@ library(ggplot2)
library(tidyverse) library(tidyverse)
library(cowplot) library(cowplot)
library(gridExtra) library(gridExtra)
source("consurf_plot_func.R") source("~/git/LSHTM_analysis/scripts/functions/consurfP.R")
# ########################################################################### ############################################################################
# merged_df3 = read.csv("~/git/Data/cycloserine/output/alr_all_params.csv"); source("~/git/LSHTM_analysis/config/alr.R") # merged_df3 = read.csv("~/git/Data/cycloserine/output/alr_all_params.csv"); source("~/git/LSHTM_analysis/config/alr.R")
# if ( tolower(gene) == "alr") { # if ( tolower(gene) == "alr") {
# aa_pos_lig1 = NULL # aa_pos_lig1 = NULL
@ -15,13 +15,13 @@ source("consurf_plot_func.R")
# p_title = gene # p_title = gene
# } # }
########################################################################### ###########################################################################
# merged_df3 = read.csv("~/git/Data/ethambutol/output/embb_all_params.csv"); source("~/git/LSHTM_analysis/config/embb.R") merged_df3 = read.csv("~/git/Data/ethambutol/output/embb_all_params.csv"); source("~/git/LSHTM_analysis/config/embb.R")
# if ( tolower(gene) == "embb") { if ( tolower(gene) == "embb") {
# aa_pos_lig1 = aa_pos_ca aa_pos_lig1 = aa_pos_ca
# aa_pos_lig2 = aa_pos_cdl aa_pos_lig2 = aa_pos_cdl
# aa_pos_lig3 = aa_pos_dsl aa_pos_lig3 = aa_pos_dsl
# p_title = gene p_title = gene
# } }
########################################################################### ###########################################################################
# merged_df3 = read.csv("~/git/Data/streptomycin/output/gid_all_params.csv"); source("~/git/LSHTM_analysis/config/gid.R") # merged_df3 = read.csv("~/git/Data/streptomycin/output/gid_all_params.csv"); source("~/git/LSHTM_analysis/config/gid.R")
# if ( tolower(gene) == "gid") { # if ( tolower(gene) == "gid") {
@ -47,13 +47,13 @@ source("consurf_plot_func.R")
# p_title = gene # p_title = gene
# } # }
########################################################################### ###########################################################################
merged_df3 = read.csv("~/git/Data/rifampicin/output/rpob_all_params.csv"); source("~/git/LSHTM_analysis/config/rpob.R") # merged_df3 = read.csv("~/git/Data/rifampicin/output/rpob_all_params.csv"); source("~/git/LSHTM_analysis/config/rpob.R")
if ( tolower(gene) == "rpob") { # if ( tolower(gene) == "rpob") {
aa_pos_lig1 = NULL # aa_pos_lig1 = NULL
aa_pos_lig2 = NULL # aa_pos_lig2 = NULL
aa_pos_lig3 = NULL # aa_pos_lig3 = NULL
p_title = gene # p_title = gene
} # }
######################################################################### #########################################################################
consurf_palette1 = c("0" = "yellow2" consurf_palette1 = c("0" = "yellow2"
@ -84,21 +84,21 @@ consurf_palette2 = c("0" = "yellow2"
aa_pos_hbond = c(2, 4) aa_pos_hbond = c(2, 4)
aa_pos_other = c(3, 4, 14, 10) aa_pos_other = c(3, 4, 14, 10)
wideP_point (plotdf = merged_df3 wideP_consurf(plotdf = merged_df3
, xvar_colname = "position" , xvar_colname = "position"
, yvar_colname = "consurf_score" , yvar_colname = "consurf_score"
, yvar_colourN_colname = "consurf_colour_rev" , yvar_colourN_colname = "consurf_colour_rev"
, ylab = "Consurf score" , ylab = "Consurf score"
, plot_error_bars = F , plot_error_bars = T
, upper_EB_colname = "consurf_ci_upper" , upper_EB_colname = "consurf_ci_upper"
, lower_EB_colname = "consurf_ci_lower" , lower_EB_colname = "consurf_ci_lower"
, plot_type = "point" , plot_type = "point"
, point_colours = consurf_palette2 , point_colours = consurf_palette2
, leg_title1 = "Consurf" , leg_title1 = "Consurf"
, leg_labels = c("0"="Insufficient Data" , leg_labels = c("0"="Insufficient Data"
, "1"= "Variable" , "1" = "Variable"
, "2", "3", "4", "5", "6", "7", "8" , "2", "3", "4", "5", "6", "7", "8"
, "9"= "Conserved") , "9" = "Conserved")
# axes title and label sizes # axes title and label sizes
, x_axts = 8 , x_axts = 8

1
scripts/functions/tests/test_corr_plot_data.R
View file

@ -5,3 +5,4 @@ source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
m3 = corr_data_extract(merged_df3); head(m3) m3 = corr_data_extract(merged_df3); head(m3)
m2 = corr_data_extract(meregd_df2); head(m2) m2 = corr_data_extract(meregd_df2); head(m2)
m3S = corr_data_extract(merged_df3, extract_scaled_cols = T); head(m3S) m3S = corr_data_extract(merged_df3, extract_scaled_cols = T); head(m3S)

2
scripts/functions/tests/test_lf_bp.R
View file

@ -15,7 +15,7 @@ source("../functions/lf_bp.R")
lf_bp(lf_df = lf_encomddg lf_bp(lf_df = lf_encomddg
, p_title = "ENCoM-DDG" , p_title = "ENCoM-DDG"
, colour_categ = "ddg_encom_outcome" , colour_categ = "ddg_encom_outcome"
, x_grp = "mutation_info" , x_grp = "mutation_info_labels"
, y_var = "param_value" , y_var = "param_value"
, facet_var = "param_type" , facet_var = "param_type"
, n_facet_row = 1 , n_facet_row = 1

49
scripts/functions/tests/test_logo_plots.R
View file

@ -1,5 +1,5 @@
source("~/git/LSHTM_analysis/config/gid.R") #source("~/git/LSHTM_analysis/config/gid.R")
#source("~/git/LSHTM_analysis/config/pnca.R") source("~/git/LSHTM_analysis/config/pnca.R")
#source("~/git/LSHTM_analysis/config/embb.R") #source("~/git/LSHTM_analysis/config/embb.R")
#source("~/git/LSHTM_analysis/config/katg.R") #source("~/git/LSHTM_analysis/config/katg.R")
#source("~/git/LSHTM_analysis/config/alr.R") #source("~/git/LSHTM_analysis/config/alr.R")
@ -12,7 +12,7 @@ source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
# mainly OR # mainly OR
# script: logoP_or.R # script: logoP_or.R
################################ ################################
LogoPlotCustomH (plot_df = merged_df3 LP1<- LogoPlotCustomH (plot_df = merged_df3
, x_axis_colname = "position" , x_axis_colname = "position"
, y_axis_colname = "or_mychisq" , y_axis_colname = "or_mychisq"
, symbol_colname = "mutant_type" , symbol_colname = "mutant_type"
@ -25,10 +25,10 @@ LogoPlotCustomH (plot_df = merged_df3
, y_lab = "Odds Ratio" , y_lab = "Odds Ratio"
, x_ats = 10 # text size , x_ats = 10 # text size
, x_tangle = 90 # text angle , x_tangle = 90 # text angle
, y_ats = 22 , y_ats = 15
, y_tangle = 0 , y_tangle = 0
, x_tts = 19 # title size , x_tts = 13 # title size
, y_tts = 22 , y_tts = 13
#, leg_pos = c(0.05,-0.12) #, leg_pos = c(0.05,-0.12)
, leg_pos = "top" , leg_pos = "top"
, leg_dir = "horizontal" , leg_dir = "horizontal"
@ -36,30 +36,29 @@ LogoPlotCustomH (plot_df = merged_df3
, leg_tts = 16 # leg title size , leg_tts = 16 # leg title size
) )
######################################## ########################################
# Logo plot showing nsSNPs by positions # Logo plot showing nsSNPs by positions
# wild-type and mutant aa # wild-type and mutant aa
# script: logoP_snp.R # script: logoP_snp.R
######################################## ########################################
LogoPlotSnps(plot_df = merged_df3 LP2<- LogoPlotSnps(plot_df = merged_df3
, x_axis_colname = "position" , x_axis_colname = "position"
, symbol_mut_colname = "mutant_type" , symbol_mut_colname = "mutant_type"
, symbol_wt_colname = "wild_type" , symbol_wt_colname = "wild_type"
, omit_snp_count = c(1)# can be 0,1, 2, etc. , omit_snp_count = c(1)# can be 0,1, 2, etc.# DD
, my_logo_col = "chemistry" , my_logo_col = "chemistry" #DD
, x_lab = "Wild-type position" , x_lab = "Wild-type position"
, y_lab = "nsSNP count" , y_lab = "nsSNP count"
, x_ats = 10 # text size , x_ats = 10
, x_tangle = 90 # text angle , x_tangle = 90
, y_ats = 18 , y_ats = 15
, y_tangle = 0 , y_tangle = 0
, x_tts = 18 # title size , x_tts = 13
, y_tts = 18 , y_tts = 13
, leg_pos = "top" # can be top, left, right and bottom or c(0.8, 0.9) , leg_pos = "top" # can be top, left, right and bottom or c(0.8, 0.9)
, leg_dir = "horizontal" # can be vertical or horizontal , leg_dir = "horizontal" # can be vertical or horizontal
, leg_ts = 14 # leg text size , leg_ts = 14
, leg_tts = 16 # leg title size , leg_tts = 16
) )
#################################################### ####################################################
@ -76,13 +75,12 @@ LogoPlotSnps(plot_df = merged_df3
# to select a small dataset: see test_ed_pfm_data.R # to select a small dataset: see test_ed_pfm_data.R
##################################################### #####################################################
LP3<- LogoPlotMSA(msaSeq_mut = msa_seq
LogoPlotMSA(msaSeq_mut = msa_seq
, msaSeq_wt = wt_seq , msaSeq_wt = wt_seq
, logo_type = c("EDLogo") # "EDLogo", bits_pfm", "probability_pfm", "bits_raw", "probability_raw") , logo_type = c("EDLogo") # "EDLogo", bits_pfm", "probability_pfm", "bits_raw", "probability_raw")
, EDScore_type = c("log") , EDScore_type = c("log")
, bg_prob = NULL , bg_prob = NULL
, my_logo_col = "taylor" , my_logo_col = "chemistry"
#, plot_positions = c(5:10, 92, 195, 118:119) #, plot_positions = c(5:10, 92, 195, 118:119)
, x_axis_offset = 0.02 , x_axis_offset = 0.02
, x_axis_offset_filtered = 0.05 , x_axis_offset_filtered = 0.05
@ -101,3 +99,14 @@ LogoPlotMSA(msaSeq_mut = msa_seq
, leg_ts = 16 , leg_ts = 16
, leg_tts = 16 , leg_tts = 16
) )
out_logoP = cowplot::plot_grid(LP3, LP1, LP2
, nrow = 3
, ncol = 1
, rel_width = c(1/3, 0.5/3, 1/3)
, rel_heights = c(1, 1, 1)
, align = "hv")
out_logoP