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

finding seq discrepancy in MSA for embb

Browse source
This commit is contained in:
Tanushree Tunstall 2022-01-17 19:11:10 +00:00
parent af04c69d66
commit 68a092037b
4 changed files with 36 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

6
scripts/functions/logoP_snp.R
View file

@ -195,10 +195,10 @@ LogoPlotSnps <- function(plot_df
cat('\nDone: p0')
# further customisation
mut_logo_p <<- p0 + theme(legend.position = leg_pos
mut_logo_p = p0 + theme(legend.position = leg_pos
, legend.direction = leg_dir
#, legend.title = element_blank()
, legend.title = element_text(size = y_tts
, legend.title = element_text(size = leg_tts
, colour = ytt_col)
, legend.text = element_text(size = leg_ts)
@ -246,7 +246,7 @@ LogoPlotSnps <- function(plot_df
cat('\nDone: p1')
# further customisation
wt_logo_p <<- p1 +
wt_logo_p = p1 +
theme(legend.position = "none"
, legend.direction = leg_dir

25
scripts/functions/tests/test_logo_plots.R
View file

@ -1,4 +1,6 @@
source("~/git/LSHTM_analysis/config/gid.R")
#source("~/git/LSHTM_analysis/config/gid.R")
source("~/git/LSHTM_analysis/config/alr.R")
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
################################
@ -56,3 +58,24 @@ LogoPlotSnps(plot_df = merged_df3
, leg_tts = 16 # leg title size
)
########################################
# Logo plot MSA
# Mutant and wild-type
# wild-type and mutant aa
# script: logoP_msa.R
########################################
# msa1 = read.csv("/home/tanu/git/Data/cycloserine/output/alr_msa.csv", header = F)
# head(msa1)
# msa_seq= msa1$V1
# head(msa_seq)
#
# msa2 = read.csv("/home/tanu/git/Data/cycloserine/input/alr.1fasta", header = F)
# head(msa2)
# wt_seq = msa2$V1
# head(wt_seq)
#
# # BOTH WORK
# LogoPlotMSA(msa_seq, wt_seq)
# LogoPlotMSA(msa1, msa2)

3
scripts/gene_targets_names.txt
View file

@ -1,7 +1,6 @@
embb ethambutol
rpob rifampicin
alr cycloserine
katg isoniazid
pnca pyrazinamide
gid streptomycin
embb ethambutol

11
scripts/run_mutate2.sh
View file

@ -30,6 +30,8 @@ while read -r gene drug; do
echo "Running mutate.py on data file $MSA_MAP"
python3 mutate.py -v -o ${DATA_DIR}/${drug}/output/${gene}_msa_interim.csv $MSA_MAP $DATA_DIR/${drug}/input/${gene}_f2.fasta
echo "mutate.py completed"
sed -E 's/>.*//g;/^$/d' ${DATA_DIR}/${drug}/output/${gene}_msa_interim.csv > ${DATA_DIR}/${drug}/output/${gene}_msa.csv
wc -l ${DATA_DIR}/${drug}/output/${gene}_msa.csv
echo
done < gene_targets_names.txt
@ -37,14 +39,17 @@ done < gene_targets_names.txt
# Stop here so we don't run the examples below :)
exit
########################################################################
#
########################################################################
# make sure there is no new line at the end of the mutation file (snps.csv)
# check
cat output/gid_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort | head
cat output/gid_metadata.csv | rev | cut -d, -f1 |rev | tail -n +2 |sort | head
cat output/gid_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort | uniq -c > output/gid_metadata_mut_count.csv
cat output/gid_metadata.csv | rev | cut -d, -f1 |rev | tail -n +2 |sort | uniq -c > output/gid_metadata_mut_count.csv
cat output/gid_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort > gid_msa_snp.csv
cat output/gid_metadata.csv | rev | cut -d, -f1 |rev | tail -n +2 |sort > gid_msa_snp.csv
sed -i 's/^/gid,/' gid_msa_snp.csv
#cp gid_msa_snp.csv gid_mut_map.csv