horrible lineage analysis hell
This commit is contained in:
parent
ce0f12382e
commit
478df927cc
10 changed files with 1669 additions and 101 deletions
|
|
@ -2,12 +2,21 @@
|
|||
|
||||
#source("~/git/LSHTM_analysis/config/alr.R")
|
||||
#source("~/git/LSHTM_analysis/config/embb.R")
|
||||
##source("~/git/LSHTM_analysis/config/gid.R")
|
||||
#source("~/git/LSHTM_analysis/config/gid.R")
|
||||
#source("~/git/LSHTM_analysis/config/katg.R")
|
||||
#source("~/git/LSHTM_analysis/config/pnca.R")
|
||||
source("~/git/LSHTM_analysis/config/rpob.R")
|
||||
|
||||
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
|
||||
#############################
|
||||
# GET the actual merged dfs
|
||||
#############################
|
||||
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
|
||||
|
||||
#############################
|
||||
# Output files: merged data
|
||||
#############################
|
||||
outfile_merged_df3 = paste0(outdir, '/', tolower(gene), '_merged_df3.csv')
|
||||
outfile_merged_df2 = paste0(outdir, '/', tolower(gene), '_merged_df2.csv')
|
||||
|
||||
################################################
|
||||
# Add acticve site indication
|
||||
|
|
@ -18,46 +27,90 @@ merged_df2_comp$active_site = as.integer(merged_df2_comp$position %in% active_aa
|
|||
merged_df3$active_site = as.integer(merged_df3$position %in% active_aa_pos)
|
||||
merged_df3_comp$active_site = as.integer(merged_df3_comp$position %in% active_aa_pos)
|
||||
|
||||
# sanity check
|
||||
# check
|
||||
cols_sel = c('mutationinformation', 'dst', 'mutation_info_labels', 'dm_om_numeric', 'dst_mode')
|
||||
|
||||
check_mdf2 = merged_df2[, cols_sel]
|
||||
check_mdf2T = table(check_mdf2$mutationinformation, check_mdf2$dst_mode)
|
||||
ft_mdf2 = as.data.frame.matrix(check_mdf2T)
|
||||
|
||||
#==================
|
||||
# CHECK: dst mode
|
||||
#===================
|
||||
dst_check = all((ft_mdf2[,1]==0)==(ft_mdf2[,2]!=0)); dst_check
|
||||
|
||||
#=======================
|
||||
# CHECK: dst mode labels
|
||||
#=======================
|
||||
table(merged_df2$mutation_info_labels_orig)
|
||||
table(merged_df2$mutation_info_labels_v1)
|
||||
table(merged_df2$mutation_info_labels)
|
||||
|
||||
dst_check1 = table(merged_df2$dst_mode)[1] == table(merged_df2$mutation_info_labels)[2]
|
||||
dst_check2 = table(merged_df2$dst_mode)[2] == table(merged_df2$mutation_info_labels)[1]
|
||||
|
||||
check12 = all(dst_check && all(dst_check1 == dst_check2))
|
||||
|
||||
if (check12) {
|
||||
cat('\nPASS: dst mode labels verified. merged_df3 CAN be trusted! ')
|
||||
}else{
|
||||
stop('FAIL: Something is wrong with the dst_mode column. Quitting!')
|
||||
``}
|
||||
|
||||
#==========================
|
||||
# CHECK: active site labels
|
||||
#==========================
|
||||
table(merged_df2$active_site)
|
||||
table(merged_df3$active_site)
|
||||
|
||||
if( all(table(merged_df2$active_site) == table(as.integer(merged_df2$position %in% active_aa_pos))) &&
|
||||
all(table(merged_df3$active_site) == table(as.integer(merged_df3$position %in% active_aa_pos)))
|
||||
){
|
||||
aa_check1 = all( table(merged_df2$active_site) == table(as.integer(merged_df2$position %in% active_aa_pos)) )
|
||||
aa_check2 = all( table(merged_df3$active_site) == table(as.integer(merged_df3$position %in% active_aa_pos)) )
|
||||
|
||||
if ( all(aa_check1 && aa_check2) ){
|
||||
cat('\nActive site indications successfully applied to merged_dfs for gene:', tolower(gene))
|
||||
}
|
||||
|
||||
|
||||
gene
|
||||
gene_match
|
||||
|
||||
nrow(merged_df3)
|
||||
##############################################
|
||||
#=============
|
||||
# mutation_info: revised labels
|
||||
#==============
|
||||
table(merged_df3$mutation_info)
|
||||
sum(table(merged_df3$mutation_info))
|
||||
table(merged_df3$mutation_info_orig)
|
||||
##############################################
|
||||
###########################################
|
||||
#========================
|
||||
# CHECK: drtype: revised labels [Merged_df2]
|
||||
#=========================
|
||||
table(merged_df2$drtype) #orig
|
||||
table(merged_df2$drtype_mode)
|
||||
# mapping 2.1: numeric
|
||||
# drtype_map = {'XDR': 5
|
||||
# , 'Pre-XDR': 4
|
||||
# , 'MDR': 3
|
||||
# , 'Pre-MDR': 2
|
||||
# , 'Other': 1
|
||||
# , 'Sensitive': 0}
|
||||
|
||||
#=============
|
||||
# <drug>, dst_mode: revised labels
|
||||
#==============
|
||||
table(merged_df3$dst) # orig
|
||||
sum(table(merged_df3$dst))
|
||||
# create a labels col that is mapped based on drtype_mode
|
||||
merged_df2$drtype_mode_labels = merged_df2$drtype_mode
|
||||
merged_df2$drtype_mode_labels = as.factor(merged_df2$drtype_mode)
|
||||
levels(merged_df2$drtype_mode_labels)
|
||||
levels(merged_df2$drtype_mode_labels) <- c('Sensitive', 'Other'
|
||||
, 'Pre-MDR', 'MDR'
|
||||
, 'Pre-XDR', 'XDR')
|
||||
levels(merged_df2$drtype_mode_labels)
|
||||
# check
|
||||
a1 = all(table(merged_df2$drtype_mode) == table(merged_df2$drtype_mode_labels))
|
||||
b1 = sum(table(merged_df2$drtype_mode_labels)) == nrow(merged_df2)
|
||||
|
||||
table(merged_df3$dst_mode)
|
||||
#table(merged_df3[dr_muts_col])
|
||||
sum(table(merged_df3$drtype_mode))
|
||||
if (all(a1 && b1)){
|
||||
cat("\nPASS: added drtype mode labels to merged_df2")
|
||||
}else{
|
||||
stop("FAIL: could not add drtype mode labels to merged_df2")
|
||||
##quit()
|
||||
}
|
||||
#################################################
|
||||
|
||||
##############################################
|
||||
#=============
|
||||
# drtype: revised labels
|
||||
#==============
|
||||
#=======================
|
||||
# CHECK: drtype: revised labels [merged_df3]
|
||||
#=======================
|
||||
table(merged_df3$drtype) #orig
|
||||
|
||||
table(merged_df3$drtype_mode)
|
||||
# mapping 2.1: numeric
|
||||
# drtype_map = {'XDR': 5
|
||||
|
|
@ -70,35 +123,80 @@ table(merged_df3$drtype_mode)
|
|||
# create a labels col that is mapped based on drtype_mode
|
||||
merged_df3$drtype_mode_labels = merged_df3$drtype_mode
|
||||
merged_df3$drtype_mode_labels = as.factor(merged_df3$drtype_mode)
|
||||
|
||||
levels(merged_df3$drtype_mode_labels)
|
||||
|
||||
levels(merged_df3$drtype_mode_labels) <- c('Sensitive', 'Other'
|
||||
, 'Pre-MDR', 'MDR'
|
||||
, 'Pre-XDR', 'XDR')
|
||||
levels(merged_df3$drtype_mode_labels)
|
||||
|
||||
a2 = all(table(merged_df3$drtype_mode) == table(merged_df3$drtype_mode_labels))
|
||||
b2 = sum(table(merged_df3$drtype_mode_labels)) == nrow(merged_df3)
|
||||
# check
|
||||
#table(merged_df3$drtype)
|
||||
table(merged_df3$drtype_mode)
|
||||
table(merged_df3$drtype_mode_labels)
|
||||
sum(table(merged_df3$drtype_mode_labels))
|
||||
if (all(a2 && b2)){
|
||||
cat("\nPASS: added drtype mode labels to merged_df3")
|
||||
}else{
|
||||
stop("FAIL: could not add drtype mode labels to merged_df3")
|
||||
##quit()
|
||||
}
|
||||
##############################################
|
||||
# lineage
|
||||
table(merged_df3$lineage)
|
||||
sum(table(merged_df3$lineage_labels))
|
||||
#===============
|
||||
# CHECK: lineage
|
||||
#===============
|
||||
l1 = table(merged_df3$lineage) == table(merged_df3$lineage_labels)
|
||||
l2 = table(merged_df2$lineage) == table(merged_df2$lineage_labels)
|
||||
l3 = sum(table(merged_df2$lineage_labels)) == nrow(merged_df2)
|
||||
l4 = sum(table(merged_df3$lineage_labels)) == nrow(merged_df3)
|
||||
|
||||
cat("\nWriting merged_df3 for:"
|
||||
if (all(l1 && l2 && l3 && l4) ){
|
||||
cat("\nPASS: lineage and lineage labels are identical!")
|
||||
}else{
|
||||
stop("FAIL: could not verify lineage labels")
|
||||
##quit()
|
||||
}
|
||||
|
||||
###############################################
|
||||
# #=============
|
||||
# # mutation_info: revised labels
|
||||
# #==============
|
||||
# table(merged_df3$mutation_info)
|
||||
# sum(table(merged_df3$mutation_info))
|
||||
# table(merged_df3$mutation_info_orig)
|
||||
##############################################
|
||||
|
||||
# #=============
|
||||
# # <drug>, dst_mode: revised labels
|
||||
# #==============
|
||||
# table(merged_df3$dst) # orig
|
||||
# sum(table(merged_df3$dst))
|
||||
#
|
||||
# table(merged_df3$dst_mode)
|
||||
# #table(merged_df3[dr_muts_col])
|
||||
# sum(table(merged_df3$drtype_mode))
|
||||
|
||||
##############################################
|
||||
if ( all( check12 && aa_check1 && aa_check2 && a1 && b1 && a2 && b2 && l1 && l2 && l3 && l4) ){
|
||||
cat("\nWriting merged_dfs for:"
|
||||
, "\nDrug:", drug
|
||||
, "\nGene:", gene)
|
||||
# write file
|
||||
outfile_merged_df3 = paste0(outdir, '/', tolower(gene), '_merged_df3.csv')
|
||||
outfile_merged_df3
|
||||
write.csv(merged_df3, outfile_merged_df3)
|
||||
|
||||
write.csv(merged_df3, outfile_merged_df3)
|
||||
write.csv(merged_df2, outfile_merged_df2)
|
||||
|
||||
cat(paste("\nmerged df3 filename:", outfile_merged_df3
|
||||
, "\nmerged df2 filename:", outfile_merged_df2))
|
||||
|
||||
} else{
|
||||
stop("FAIL: Not able to write merged dfs. Please check numbers!")
|
||||
#quit()
|
||||
}
|
||||
|
||||
outfile_merged_df2 = paste0(outdir, '/', tolower(gene), '_merged_df2.csv')
|
||||
outfile_merged_df2
|
||||
write.csv(merged_df2, outfile_merged_df2)
|
||||
# write file
|
||||
# outfile_merged_df3 = paste0(outdir, '/', tolower(gene), '_merged_df3.csv')
|
||||
# outfile_merged_df3
|
||||
# write.csv(merged_df3, outfile_merged_df3)
|
||||
#
|
||||
# outfile_merged_df2 = paste0(outdir, '/', tolower(gene), '_merged_df2.csv')
|
||||
# outfile_merged_df2
|
||||
# write.csv(merged_df2, outfile_merged_df2)
|
||||
|
||||
###################################################
|
||||
###################################################
|
||||
|
|
@ -133,5 +231,3 @@ write.csv(merged_df2, outfile_merged_df2)
|
|||
# # drtype: MDR and XDR
|
||||
# #table(df3$drtype) orig i.e. incorrect ones!
|
||||
# table(df3$drtype_mode_labels)
|
||||
#
|
||||
#
|
||||
|
|
|
|||
|
|
@ -60,9 +60,12 @@ import collections
|
|||
#%% dir and local imports
|
||||
homedir = os.path.expanduser('~')
|
||||
# set working dir
|
||||
os.getcwd()
|
||||
os.chdir(homedir + '/git/LSHTM_analysis/scripts')
|
||||
os.getcwd()
|
||||
# os.getcwd()
|
||||
# os.chdir(homedir + '/git/LSHTM_analysis/scripts')
|
||||
# os.getcwd()
|
||||
|
||||
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/')
|
||||
|
||||
#=======================================================================
|
||||
#%% command line args
|
||||
arg_parser = argparse.ArgumentParser()
|
||||
|
|
@ -1550,6 +1553,29 @@ gene_LF3['dst_multimode'].value_counts()
|
|||
#gene_LF3['dst_noNA'] = gene_LF3['dst_multimode'].apply(lambda x: np.nanmax(x))
|
||||
gene_LF3['dst_mode'] = gene_LF3['dst_multimode'].apply(lambda x: np.nanmax(x)) #ML
|
||||
|
||||
#-----------------------------------------------------------------------------
|
||||
#-----------------------------------------------------------------------------
|
||||
# NOTE: unexpected weirdness with above, so redoing it!
|
||||
mmdf = pd.DataFrame(gene_LF3.groupby('mutationinformation')['dst_mode'].agg(multimode))
|
||||
mmdf['dst2'] = mmdf['dst_mode'].apply(lambda x: int(max(x)))
|
||||
mmdf=mmdf.reset_index()
|
||||
|
||||
# rename cols to make sure merge will have the names you expect
|
||||
mmdf2 = mmdf.rename(columns = {'dst_mode':'dst_multimode', 'dst2':'dst_mode'})
|
||||
|
||||
# IMPORTANT!
|
||||
gene_LF3_copy = gene_LF3.copy()
|
||||
gene_LF3_copy.drop(["dst_mode", "dst_multimode", "dst_multimode_all"], axis = 1, inplace = True)
|
||||
|
||||
# Now merge gene_LF3.copy and mmdf2
|
||||
gene_LF3_merged = pd.merge(gene_LF3_copy, mmdf2, on='mutationinformation')
|
||||
df_check4 = gene_LF3_merged[['mutationinformation', 'dst', 'dst_multimode', 'dst_mode', 'position' ]]
|
||||
|
||||
# now reassign the merged df to gene_LF3 for integration with downstream
|
||||
gene_LF3 = gene_LF3_merged.copy()
|
||||
#-----------------------------------------------------------------------------
|
||||
#-----------------------------------------------------------------------------
|
||||
|
||||
# sanity checks
|
||||
#gene_LF3['dst_noNA'].equals(gene_LF3['dst_mode'])
|
||||
gene_LF3[drug].value_counts()
|
||||
|
|
@ -1700,10 +1726,24 @@ lf_lin_split['lineage_numeric'].value_counts()
|
|||
# Add lineage_list: ALL values:
|
||||
#--------------------------------
|
||||
# Add all lineages for each mutation
|
||||
lf_lin_split['lineage_corrupt_list'] = lf_lin_split['lineage_corrupt']
|
||||
lf_lin_split['lineage_corrupt_list'].value_counts()
|
||||
#lf_lin_split['lineage_corrupt_list'] = lf_lin_split['lineage_corrupt'].copy()
|
||||
#lf_lin_split['lineage_corrupt_list'].value_counts()
|
||||
lf_lin_split['lineage_corrupt'].value_counts()
|
||||
|
||||
#lf_lin_split['lineage_corrupt_list'] = lf_lin_split['mutationinformation'].map(lf_lin_split.groupby('mutationinformati
|
||||
lf_lin_split['lineage_corrupt_list'] = lf_lin_split.groupby('mutationinformation').lineage_corrupt_list.apply(list)
|
||||
#lf_lin_split['lineage_corrupt_list'] = lf_lin_split.groupby('mutationinformation').lineage_corrupt_list.apply(list)
|
||||
lf_lin_tmp =lf_lin_split.groupby('Mut').lineage_corrupt.apply(list)
|
||||
lf_lin_tmp = lf_lin_tmp.reset_index()
|
||||
lf_lin_tmp.rename(columns={'lineage_corrupt': 'lineage_corrupt_list' }, inplace=True)
|
||||
#lf_lin_split['lineage_corrupt_list'] = lf_lin_split.groupby('Mut').lineage_corrupt_list.apply(list).copy()
|
||||
|
||||
#lf_lin_split['lineage_corrupt_list'] = lf_lin_tmp
|
||||
lf_lin_merged = pd.merge(lf_lin_split, lf_lin_tmp, on='Mut')
|
||||
lf_lin_split.shape
|
||||
lf_lin_merged.shape
|
||||
|
||||
# REASSIGN merged
|
||||
lf_lin_split = lf_lin_merged.copy()
|
||||
lf_lin_split['lineage_corrupt_list'].value_counts()
|
||||
|
||||
#--------------------------------
|
||||
|
|
@ -1727,10 +1767,18 @@ lf_lin_split['lineage_ulist'] = lf_lin_split['lineage_set'].apply(lambda x : li
|
|||
#-------------------------------------
|
||||
# Lineage numeric mode: multimode
|
||||
#-------------------------------------
|
||||
lf_lin_split['lineage_multimode'] = lf_lin_split.groupby('mutationinformation')['lineage_numeric'].agg(multimode)
|
||||
lf_lin_split['lineage_multimode'].value_counts()
|
||||
#lf_lin_split['lineage_multimode'] = lf_lin_split.groupby('mutationinformation')['lineage_numeric'].agg(multimode)
|
||||
#lf_lin_split['lineage_multimode'] = lf_lin_split.groupby('Mut')['lineage_numeric'].agg(multimode)
|
||||
|
||||
# cant take max as it doesn't mean anyting!
|
||||
lin_mm_tmp = pd.DataFrame(lf_lin_split.groupby('Mut')['lineage_numeric'].agg(multimode))
|
||||
lin_mm_tmp=lin_mm_tmp.reset_index()
|
||||
lin_mm_tmp.rename(columns={'lineage_numeric':'lineage_multimode'}, inplace=True)
|
||||
|
||||
lf_lin_split_merged = pd.merge(lf_lin_split, lin_mm_tmp, on='Mut')
|
||||
#lf_lin_split['lineage_multimode'].value_counts() # cant take max as it doesn't mean anyting!
|
||||
|
||||
#REASSIGN
|
||||
lf_lin_split = lf_lin_split_merged.copy()
|
||||
|
||||
###############################################################################
|
||||
#%% Select only the columns you want to merge from lf_lin_split
|
||||
|
|
|
|||
|
|
@ -185,9 +185,6 @@ combining_dfs_plotting <- function( my_df_u
|
|||
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
# Quick formatting: ordering df and pretty labels
|
||||
|
||||
#------------------------------
|
||||
|
|
@ -198,36 +195,12 @@ combining_dfs_plotting <- function( my_df_u
|
|||
#-----------------------
|
||||
# mutation_info_labels
|
||||
#-----------------------
|
||||
merged_df2$mutation_info_labels = ifelse(merged_df2$mutation_info == dr_muts_col
|
||||
, "DM", "OM")
|
||||
merged_df2$mutation_info_labels = factor(merged_df2$mutation_info_labels)
|
||||
#merged_df2$mutation_info_labels = ifelse(merged_df2$mutation_info == dr_muts_col
|
||||
# , "DM", "OM")
|
||||
#merged_df2$mutation_info_labels = factor(merged_df2$mutation_info_labels)
|
||||
#-----------------------
|
||||
# lineage labels
|
||||
#-----------------------
|
||||
# merged_df2$lineage_labels = gsub("lineage", "L", merged_df2$lineage)
|
||||
|
||||
# Already solved upstream where lineage now contains L prefix
|
||||
# merged_df2$lineage_labels = factor(merged_df2$lineage_labels, c("L1"
|
||||
# , "L2"
|
||||
# , "L3"
|
||||
# , "L4"
|
||||
# , "L5"
|
||||
# , "L6"
|
||||
# , "L7"
|
||||
# , "LBOV"
|
||||
# , "L1;L2"
|
||||
# , "L1;L3"
|
||||
# , "L1;L4"
|
||||
# , "L2;L3"
|
||||
# , "L2;L3;L4"
|
||||
# , "L2;L4"
|
||||
# , "L2;L6"
|
||||
# , "L2;LBOV"
|
||||
# , "L3;L4"
|
||||
# , "L4;L6"
|
||||
# , "L4;L7"
|
||||
# , ""))
|
||||
|
||||
merged_df2$lineage_labels = merged_df2$lineage
|
||||
#merged_df2$lineage_labels = as.factor(merged_df2$lineage_labels)
|
||||
#merged_df2$lineage_labels = factor(merged_df2$lineage_labels)
|
||||
|
|
|
|||
806
scripts/ml/combined_model/COPY_ml_data_combined_7030.py
Normal file
806
scripts/ml/combined_model/COPY_ml_data_combined_7030.py
Normal file
|
|
@ -0,0 +1,806 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Created on Sun Mar 6 13:41:54 2022
|
||||
|
||||
@author: tanu
|
||||
"""
|
||||
def setvars(gene,drug):
|
||||
#https://stackoverflow.com/questions/51695322/compare-multiple-algorithms-with-sklearn-pipeline
|
||||
import os, sys
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
print(np.__version__)
|
||||
print(pd.__version__)
|
||||
import pprint as pp
|
||||
from copy import deepcopy
|
||||
from collections import Counter
|
||||
from sklearn.impute import KNNImputer as KNN
|
||||
from imblearn.over_sampling import RandomOverSampler
|
||||
from imblearn.under_sampling import RandomUnderSampler
|
||||
from imblearn.over_sampling import SMOTE
|
||||
from sklearn.datasets import make_classification
|
||||
from imblearn.combine import SMOTEENN
|
||||
from imblearn.combine import SMOTETomek
|
||||
|
||||
from imblearn.over_sampling import SMOTENC
|
||||
from imblearn.under_sampling import EditedNearestNeighbours
|
||||
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
|
||||
|
||||
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
|
||||
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
|
||||
|
||||
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
|
||||
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
||||
|
||||
from sklearn.pipeline import Pipeline, make_pipeline
|
||||
import argparse
|
||||
import re
|
||||
#%% GLOBALS
|
||||
tts_split = "70_30"
|
||||
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
||||
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'accuracy' : make_scorer(accuracy_score)
|
||||
, 'fscore' : make_scorer(f1_score)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
, 'jcc' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
#, shuffle = False, random_state= None)
|
||||
, shuffle = True,**rs)
|
||||
|
||||
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
||||
, n_repeats = 3
|
||||
, **rs)
|
||||
|
||||
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
||||
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
||||
#%% FOR LATER: Combine ED logo data
|
||||
###########################################################################
|
||||
|
||||
homedir = os.path.expanduser("~")
|
||||
|
||||
geneL_basic = ['pnca']
|
||||
geneL_na = ['gid']
|
||||
geneL_na_ppi2 = ['rpob']
|
||||
geneL_ppi2 = ['alr', 'embb', 'katg']
|
||||
|
||||
#num_type = ['int64', 'float64']
|
||||
num_type = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
|
||||
cat_type = ['object', 'bool']
|
||||
|
||||
#==============
|
||||
# directories
|
||||
#==============
|
||||
datadir = homedir + '/git/Data/'
|
||||
indir = datadir + drug + '/input/'
|
||||
outdir = datadir + drug + '/output/'
|
||||
|
||||
#=======
|
||||
# input
|
||||
#=======
|
||||
|
||||
#---------
|
||||
# File 1
|
||||
#---------
|
||||
infile_ml1 = outdir + gene.lower() + '_merged_df3.csv'
|
||||
#infile_ml2 = outdir + gene.lower() + '_merged_df2.csv'
|
||||
|
||||
my_features_df = pd.read_csv(infile_ml1, index_col = 0)
|
||||
my_features_df = my_features_df.reset_index(drop = True)
|
||||
my_features_df.index
|
||||
|
||||
my_features_df.dtypes
|
||||
mycols = my_features_df.columns
|
||||
|
||||
#---------
|
||||
# File 2
|
||||
#---------
|
||||
infile_aaindex = outdir + 'aa_index/' + gene.lower() + '_aa.csv'
|
||||
aaindex_df = pd.read_csv(infile_aaindex, index_col = 0)
|
||||
aaindex_df.dtypes
|
||||
|
||||
#-----------
|
||||
# check for non-numerical columns
|
||||
#-----------
|
||||
if any(aaindex_df.dtypes==object):
|
||||
print('\naaindex_df contains non-numerical data')
|
||||
|
||||
aaindex_df_object = aaindex_df.select_dtypes(include = cat_type)
|
||||
print('\nTotal no. of non-numerial columns:', len(aaindex_df_object.columns))
|
||||
|
||||
expected_aa_ncols = len(aaindex_df.columns) - len(aaindex_df_object.columns)
|
||||
|
||||
#-----------
|
||||
# Extract numerical data only
|
||||
#-----------
|
||||
print('\nSelecting numerical data only')
|
||||
aaindex_df = aaindex_df.select_dtypes(include = num_type)
|
||||
|
||||
#---------------------------
|
||||
# aaindex: sanity check 1
|
||||
#---------------------------
|
||||
if len(aaindex_df.columns) == expected_aa_ncols:
|
||||
print('\nPASS: successfully selected numerical columns only for aaindex_df')
|
||||
else:
|
||||
print('\nFAIL: Numbers mismatch'
|
||||
, '\nExpected ncols:', expected_aa_ncols
|
||||
, '\nGot:', len(aaindex_df.columns))
|
||||
|
||||
#---------------
|
||||
# check for NA
|
||||
#---------------
|
||||
print('\nNow checking for NA in the remaining aaindex_cols')
|
||||
c1 = aaindex_df.isna().sum()
|
||||
c2 = c1.sort_values(ascending=False)
|
||||
print('\nCounting aaindex_df cols with NA'
|
||||
, '\nncols with NA:', sum(c2>0), 'columns'
|
||||
, '\nDropping these...'
|
||||
, '\nOriginal ncols:', len(aaindex_df.columns)
|
||||
)
|
||||
aa_df = aaindex_df.dropna(axis=1)
|
||||
|
||||
print('\nRevised df ncols:', len(aa_df.columns))
|
||||
|
||||
c3 = aa_df.isna().sum()
|
||||
c4 = c3.sort_values(ascending=False)
|
||||
|
||||
print('\nChecking NA in revised df...')
|
||||
|
||||
if sum(c4>0):
|
||||
sys.exit('\nFAIL: aaindex_df still contains cols with NA, please check and drop these before proceeding...')
|
||||
else:
|
||||
print('\nPASS: cols with NA successfully dropped from aaindex_df'
|
||||
, '\nProceeding with combining aa_df with other features_df')
|
||||
|
||||
#---------------------------
|
||||
# aaindex: sanity check 2
|
||||
#---------------------------
|
||||
expected_aa_ncols2 = len(aaindex_df.columns) - sum(c2>0)
|
||||
if len(aa_df.columns) == expected_aa_ncols2:
|
||||
print('\nPASS: ncols match'
|
||||
, '\nExpected ncols:', expected_aa_ncols2
|
||||
, '\nGot:', len(aa_df.columns))
|
||||
else:
|
||||
print('\nFAIL: Numbers mismatch'
|
||||
, '\nExpected ncols:', expected_aa_ncols2
|
||||
, '\nGot:', len(aa_df.columns))
|
||||
|
||||
# Important: need this to identify aaindex cols
|
||||
aa_df_cols = aa_df.columns
|
||||
print('\nTotal no. of columns in clean aa_df:', len(aa_df_cols))
|
||||
|
||||
###############################################################################
|
||||
#%% Combining my_features_df and aaindex_df
|
||||
#===========================
|
||||
# Merge my_df + aaindex_df
|
||||
#===========================
|
||||
|
||||
if aa_df.columns[aa_df.columns.isin(my_features_df.columns)] == my_features_df.columns[my_features_df.columns.isin(aa_df.columns)]:
|
||||
print('\nMerging on column: mutationinformation')
|
||||
|
||||
if len(my_features_df) == len(aa_df):
|
||||
expected_nrows = len(my_features_df)
|
||||
print('\nProceeding to merge, expected nrows in merged_df:', expected_nrows)
|
||||
else:
|
||||
sys.exit('\nNrows mismatch, cannot merge. Please check'
|
||||
, '\nnrows my_df:', len(my_features_df)
|
||||
, '\nnrows aa_df:', len(aa_df))
|
||||
|
||||
#-----------------
|
||||
# Reset index: mutationinformation
|
||||
# Very important for merging
|
||||
#-----------------
|
||||
aa_df = aa_df.reset_index()
|
||||
|
||||
expected_ncols = len(my_features_df.columns) + len(aa_df.columns) - 1 # for the no. of merging col
|
||||
|
||||
#-----------------
|
||||
# Merge: my_features_df + aa_df
|
||||
#-----------------
|
||||
merged_df = pd.merge(my_features_df
|
||||
, aa_df
|
||||
, on = 'mutationinformation')
|
||||
|
||||
#---------------------------
|
||||
# aaindex: sanity check 3
|
||||
#---------------------------
|
||||
if len(merged_df.columns) == expected_ncols:
|
||||
print('\nPASS: my_features_df and aa_df successfully combined'
|
||||
, '\nnrows:', len(merged_df)
|
||||
, '\nncols:', len(merged_df.columns))
|
||||
else:
|
||||
sys.exit('\nFAIL: could not combine my_features_df and aa_df'
|
||||
, '\nCheck dims and merging cols!')
|
||||
|
||||
#--------
|
||||
# Reassign so downstream code doesn't need to change
|
||||
#--------
|
||||
my_df = merged_df.copy()
|
||||
|
||||
#%% Data: my_df
|
||||
# Check if non structural pos have crept in
|
||||
# IDEALLY remove from source! But for rpoB do it here
|
||||
# Drop NA where numerical cols have them
|
||||
if gene.lower() in geneL_na_ppi2:
|
||||
#D1148 get rid of
|
||||
na_index = my_df['mutationinformation'].index[my_df['mcsm_na_affinity'].apply(np.isnan)]
|
||||
my_df = my_df.drop(index=na_index)
|
||||
|
||||
# FIXED: complete data for all muts inc L114M, F115L, V123L, V125I, V131M
|
||||
# if gene.lower() in ['embb']:
|
||||
# na_index = my_df['mutationinformation'].index[my_df['ligand_distance'].apply(np.isnan)]
|
||||
# my_df = my_df.drop(index=na_index)
|
||||
|
||||
# # Sanity check for non-structural positions
|
||||
# print('\nChecking for non-structural postions')
|
||||
# na_index = my_df['mutationinformation'].index[my_df['ligand_distance'].apply(np.isnan)]
|
||||
# if len(na_index) > 0:
|
||||
# print('\nNon-structural positions detected for gene:', gene.lower()
|
||||
# , '\nTotal number of these detected:', len(na_index)
|
||||
# , '\These are at index:', na_index
|
||||
# , '\nOriginal nrows:', len(my_df)
|
||||
# , '\nDropping these...')
|
||||
# my_df = my_df.drop(index=na_index)
|
||||
# print('\nRevised nrows:', len(my_df))
|
||||
# else:
|
||||
# print('\nNo non-structural positions detected for gene:', gene.lower()
|
||||
# , '\nnrows:', len(my_df))
|
||||
|
||||
|
||||
###########################################################################
|
||||
#%% Add lineage calculation columns
|
||||
#FIXME: Check if this can be imported from config?
|
||||
total_mtblineage_uc = 8
|
||||
lineage_colnames = ['lineage_list_all', 'lineage_count_all', 'lineage_count_unique', 'lineage_list_unique', 'lineage_multimode']
|
||||
#bar = my_df[lineage_colnames]
|
||||
my_df['lineage_proportion'] = my_df['lineage_count_unique']/my_df['lineage_count_all']
|
||||
my_df['dist_lineage_proportion'] = my_df['lineage_count_unique']/total_mtblineage_uc
|
||||
###########################################################################
|
||||
#%% Active site annotation column
|
||||
# change from numberic to categorical
|
||||
|
||||
if my_df['active_site'].dtype in num_type:
|
||||
my_df['active_site'] = my_df['active_site'].astype(object)
|
||||
my_df['active_site'].dtype
|
||||
#%% AA property change
|
||||
#--------------------
|
||||
# Water prop change
|
||||
#--------------------
|
||||
my_df['water_change'] = my_df['wt_prop_water'] + str('_to_') + my_df['mut_prop_water']
|
||||
my_df['water_change'].value_counts()
|
||||
|
||||
water_prop_changeD = {
|
||||
'hydrophobic_to_neutral' : 'change'
|
||||
, 'hydrophobic_to_hydrophobic' : 'no_change'
|
||||
, 'neutral_to_neutral' : 'no_change'
|
||||
, 'neutral_to_hydrophobic' : 'change'
|
||||
, 'hydrophobic_to_hydrophilic' : 'change'
|
||||
, 'neutral_to_hydrophilic' : 'change'
|
||||
, 'hydrophilic_to_neutral' : 'change'
|
||||
, 'hydrophilic_to_hydrophobic' : 'change'
|
||||
, 'hydrophilic_to_hydrophilic' : 'no_change'
|
||||
}
|
||||
|
||||
my_df['water_change'] = my_df['water_change'].map(water_prop_changeD)
|
||||
my_df['water_change'].value_counts()
|
||||
|
||||
#--------------------
|
||||
# Polarity change
|
||||
#--------------------
|
||||
my_df['polarity_change'] = my_df['wt_prop_polarity'] + str('_to_') + my_df['mut_prop_polarity']
|
||||
my_df['polarity_change'].value_counts()
|
||||
|
||||
polarity_prop_changeD = {
|
||||
'non-polar_to_non-polar' : 'no_change'
|
||||
, 'non-polar_to_neutral' : 'change'
|
||||
, 'neutral_to_non-polar' : 'change'
|
||||
, 'neutral_to_neutral' : 'no_change'
|
||||
, 'non-polar_to_basic' : 'change'
|
||||
, 'acidic_to_neutral' : 'change'
|
||||
, 'basic_to_neutral' : 'change'
|
||||
, 'non-polar_to_acidic' : 'change'
|
||||
, 'neutral_to_basic' : 'change'
|
||||
, 'acidic_to_non-polar' : 'change'
|
||||
, 'basic_to_non-polar' : 'change'
|
||||
, 'neutral_to_acidic' : 'change'
|
||||
, 'acidic_to_acidic' : 'no_change'
|
||||
, 'basic_to_acidic' : 'change'
|
||||
, 'basic_to_basic' : 'no_change'
|
||||
, 'acidic_to_basic' : 'change'}
|
||||
|
||||
my_df['polarity_change'] = my_df['polarity_change'].map(polarity_prop_changeD)
|
||||
my_df['polarity_change'].value_counts()
|
||||
|
||||
#--------------------
|
||||
# Electrostatics change
|
||||
#--------------------
|
||||
my_df['electrostatics_change'] = my_df['wt_calcprop'] + str('_to_') + my_df['mut_calcprop']
|
||||
my_df['electrostatics_change'].value_counts()
|
||||
|
||||
calc_prop_changeD = {
|
||||
'non-polar_to_non-polar' : 'no_change'
|
||||
, 'non-polar_to_polar' : 'change'
|
||||
, 'polar_to_non-polar' : 'change'
|
||||
, 'non-polar_to_pos' : 'change'
|
||||
, 'neg_to_non-polar' : 'change'
|
||||
, 'non-polar_to_neg' : 'change'
|
||||
, 'pos_to_polar' : 'change'
|
||||
, 'pos_to_non-polar' : 'change'
|
||||
, 'polar_to_polar' : 'no_change'
|
||||
, 'neg_to_neg' : 'no_change'
|
||||
, 'polar_to_neg' : 'change'
|
||||
, 'pos_to_neg' : 'change'
|
||||
, 'pos_to_pos' : 'no_change'
|
||||
, 'polar_to_pos' : 'change'
|
||||
, 'neg_to_polar' : 'change'
|
||||
, 'neg_to_pos' : 'change'
|
||||
}
|
||||
|
||||
my_df['electrostatics_change'] = my_df['electrostatics_change'].map(calc_prop_changeD)
|
||||
my_df['electrostatics_change'].value_counts()
|
||||
|
||||
#--------------------
|
||||
# Summary change: Create a combined column summarising these three cols
|
||||
#--------------------
|
||||
detect_change = 'change'
|
||||
check_prop_cols = ['water_change', 'polarity_change', 'electrostatics_change']
|
||||
#my_df['aa_prop_change'] = (my_df.values == detect_change).any(1).astype(int)
|
||||
my_df['aa_prop_change'] = (my_df[check_prop_cols].values == detect_change).any(1).astype(int)
|
||||
my_df['aa_prop_change'].value_counts()
|
||||
my_df['aa_prop_change'].dtype
|
||||
|
||||
my_df['aa_prop_change'] = my_df['aa_prop_change'].map({1:'change'
|
||||
, 0: 'no_change'})
|
||||
|
||||
my_df['aa_prop_change'].value_counts()
|
||||
my_df['aa_prop_change'].dtype
|
||||
|
||||
#%% IMPUTE values for OR [check script for exploration: UQ_or_imputer]
|
||||
#--------------------
|
||||
# Impute OR values
|
||||
#--------------------
|
||||
#or_cols = ['or_mychisq', 'log10_or_mychisq', 'or_fisher']
|
||||
sel_cols = ['mutationinformation', 'or_mychisq', 'log10_or_mychisq']
|
||||
or_cols = ['or_mychisq', 'log10_or_mychisq']
|
||||
|
||||
print("count of NULL values before imputation\n")
|
||||
print(my_df[or_cols].isnull().sum())
|
||||
|
||||
my_dfI = pd.DataFrame(index = my_df['mutationinformation'] )
|
||||
|
||||
|
||||
my_dfI = pd.DataFrame(KNN(n_neighbors=3, weights="uniform").fit_transform(my_df[or_cols])
|
||||
, index = my_df['mutationinformation']
|
||||
, columns = or_cols )
|
||||
my_dfI.columns = ['or_rawI', 'logorI']
|
||||
my_dfI.columns
|
||||
my_dfI = my_dfI.reset_index(drop = False) # prevents old index from being added as a column
|
||||
my_dfI.head()
|
||||
print("count of NULL values AFTER imputation\n")
|
||||
print(my_dfI.isnull().sum())
|
||||
|
||||
#-------------------------------------------
|
||||
# OR df Merge: with original based on index
|
||||
#-------------------------------------------
|
||||
#my_df['index_bm'] = my_df.index
|
||||
mydf_imputed = pd.merge(my_df
|
||||
, my_dfI
|
||||
, on = 'mutationinformation')
|
||||
#mydf_imputed = mydf_imputed.set_index(['index_bm'])
|
||||
|
||||
my_df['log10_or_mychisq'].isna().sum()
|
||||
mydf_imputed['log10_or_mychisq'].isna().sum()
|
||||
mydf_imputed['logorI'].isna().sum() # should be 0
|
||||
|
||||
len(my_df.columns)
|
||||
len(mydf_imputed.columns)
|
||||
|
||||
#-----------------------------------------
|
||||
# REASSIGN my_df after imputing OR values
|
||||
#-----------------------------------------
|
||||
my_df = mydf_imputed.copy()
|
||||
|
||||
if my_df['logorI'].isna().sum() == 0:
|
||||
print('\nPASS: OR values imputed, data ready for ML')
|
||||
else:
|
||||
sys.exit('\nFAIL: something went wrong, Data not ready for ML. Please check upstream!')
|
||||
|
||||
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
|
||||
#---------------------------------------
|
||||
# TODO: try other imputation like MICE
|
||||
#---------------------------------------
|
||||
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
|
||||
|
||||
#%%########################################################################
|
||||
#==========================
|
||||
# Data for ML
|
||||
#==========================
|
||||
my_df_ml = my_df.copy()
|
||||
|
||||
# Build column names to mask for affinity chanhes
|
||||
if gene.lower() in geneL_basic:
|
||||
#X_stabilityN = common_cols_stabiltyN
|
||||
gene_affinity_colnames = []# not needed as its the common ones
|
||||
cols_to_mask = ['ligand_affinity_change']
|
||||
|
||||
if gene.lower() in geneL_ppi2:
|
||||
gene_affinity_colnames = ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
#X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
|
||||
cols_to_mask = ['ligand_affinity_change', 'mcsm_ppi2_affinity']
|
||||
|
||||
if gene.lower() in geneL_na:
|
||||
gene_affinity_colnames = ['mcsm_na_affinity']
|
||||
#X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
|
||||
cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity']
|
||||
|
||||
if gene.lower() in geneL_na_ppi2:
|
||||
gene_affinity_colnames = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
#X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
|
||||
cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity']
|
||||
|
||||
#=======================
|
||||
# Masking columns:
|
||||
# (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
|
||||
#=======================
|
||||
my_df_ml['mutationinformation'][my_df_ml['ligand_distance']>10].value_counts()
|
||||
my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
|
||||
my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask].value_counts()
|
||||
|
||||
# mask the mcsm affinity related columns where ligand distance > 10
|
||||
my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask] = 0
|
||||
(my_df_ml['ligand_affinity_change'] == 0).sum()
|
||||
|
||||
mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask]
|
||||
|
||||
#===================================================
|
||||
# write file for check
|
||||
mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
|
||||
mask_check.to_csv(outdir + 'ml/' + gene.lower() + '_mask_check.csv')
|
||||
#===================================================
|
||||
###############################################################################
|
||||
#%% Feature groups (FG): Build X for Input ML
|
||||
############################################################################
|
||||
#===========================
|
||||
# FG1: Evolutionary features
|
||||
#===========================
|
||||
X_evolFN = ['consurf_score'
|
||||
, 'snap2_score'
|
||||
, 'provean_score']
|
||||
|
||||
###############################################################################
|
||||
#========================
|
||||
# FG2: Stability features
|
||||
#========================
|
||||
#--------
|
||||
# common
|
||||
#--------
|
||||
X_common_stability_Fnum = [
|
||||
'duet_stability_change'
|
||||
, 'ddg_foldx'
|
||||
, 'deepddg'
|
||||
, 'ddg_dynamut2'
|
||||
, 'contacts']
|
||||
#--------
|
||||
# FoldX
|
||||
#--------
|
||||
X_foldX_Fnum = [ 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
|
||||
, 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
|
||||
, 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
|
||||
, 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
|
||||
, 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss'
|
||||
, 'volumetric_rr', 'volumetric_mm', 'volumetric_ss']
|
||||
|
||||
X_stability_FN = X_common_stability_Fnum + X_foldX_Fnum
|
||||
|
||||
###############################################################################
|
||||
#===================
|
||||
# FG3: Affinity features
|
||||
#===================
|
||||
common_affinity_Fnum = ['ligand_distance'
|
||||
, 'ligand_affinity_change'
|
||||
, 'mmcsm_lig']
|
||||
|
||||
# if gene.lower() in geneL_basic:
|
||||
# X_affinityFN = common_affinity_Fnum
|
||||
# else:
|
||||
# X_affinityFN = common_affinity_Fnum + gene_affinity_colnames
|
||||
|
||||
X_affinityFN = common_affinity_Fnum + gene_affinity_colnames
|
||||
|
||||
###############################################################################
|
||||
#============================
|
||||
# FG4: Residue level features
|
||||
#============================
|
||||
#-----------
|
||||
# AA index
|
||||
#-----------
|
||||
X_aaindex_Fnum = list(aa_df_cols)
|
||||
print('\nTotal no. of features for aaindex:', len(X_aaindex_Fnum))
|
||||
|
||||
#-----------------
|
||||
# surface area
|
||||
# depth
|
||||
# hydrophobicity
|
||||
#-----------------
|
||||
X_str_Fnum = ['rsa'
|
||||
#, 'asa'
|
||||
, 'kd_values'
|
||||
, 'rd_values']
|
||||
|
||||
#---------------------------
|
||||
# Other aa properties
|
||||
# active site indication
|
||||
#---------------------------
|
||||
X_aap_Fcat = ['ss_class'
|
||||
# , 'wt_prop_water'
|
||||
# , 'mut_prop_water'
|
||||
# , 'wt_prop_polarity'
|
||||
# , 'mut_prop_polarity'
|
||||
# , 'wt_calcprop'
|
||||
# , 'mut_calcprop'
|
||||
, 'aa_prop_change'
|
||||
, 'electrostatics_change'
|
||||
, 'polarity_change'
|
||||
, 'water_change'
|
||||
, 'active_site']
|
||||
|
||||
X_resprop_FN = X_aaindex_Fnum + X_str_Fnum + X_aap_Fcat
|
||||
###############################################################################
|
||||
#========================
|
||||
# FG5: Genomic features
|
||||
#========================
|
||||
X_gn_mafor_Fnum = ['maf'
|
||||
#, 'logorI'
|
||||
# , 'or_rawI'
|
||||
# , 'or_mychisq'
|
||||
# , 'or_logistic'
|
||||
# , 'or_fisher'
|
||||
# , 'pval_fisher'
|
||||
]
|
||||
|
||||
X_gn_linegae_Fnum = ['lineage_proportion'
|
||||
, 'dist_lineage_proportion'
|
||||
#, 'lineage' # could be included as a category but it has L2;L4 formatting
|
||||
, 'lineage_count_all'
|
||||
, 'lineage_count_unique'
|
||||
]
|
||||
|
||||
# X_gn_Fcat = ['drtype_mode_labels' # beware then you can't use it to predict [USED it for uq_v1, not v2]
|
||||
# #, 'gene_name' # will be required for the combined stuff
|
||||
# ]
|
||||
X_gn_Fcat = []
|
||||
|
||||
X_genomicFN = X_gn_mafor_Fnum + X_gn_linegae_Fnum + X_gn_Fcat
|
||||
###############################################################################
|
||||
#========================
|
||||
# FG6 collapsed: Structural : Atability + Affinity + ResidueProp
|
||||
#========================
|
||||
X_structural_FN = X_stability_FN + X_affinityFN + X_resprop_FN
|
||||
|
||||
###############################################################################
|
||||
#========================
|
||||
# BUILDING all features
|
||||
#========================
|
||||
all_featuresN = X_evolFN + X_structural_FN + X_genomicFN
|
||||
|
||||
###############################################################################
|
||||
#%% Define training and test data
|
||||
#================================================================
|
||||
# Training and BLIND test set: 70/30
|
||||
# dst with actual values : training set
|
||||
# dst with imputed values : THROW AWAY [unrepresentative]
|
||||
#================================================================
|
||||
my_df_ml[drug].isna().sum()
|
||||
|
||||
# blind_test_df = my_df_ml[my_df_ml[drug].isna()]
|
||||
# blind_test_df.shape
|
||||
|
||||
training_df = my_df_ml[my_df_ml[drug].notna()]
|
||||
training_df.shape
|
||||
|
||||
# Target 1: dst_mode
|
||||
training_df[drug].value_counts()
|
||||
training_df['dst_mode'].value_counts()
|
||||
|
||||
####################################################################
|
||||
#====================================
|
||||
# ML data: Train test split: 70/30
|
||||
# with stratification
|
||||
# 70% : training_data for CV
|
||||
# 30% : blind test
|
||||
#=====================================
|
||||
x_features = training_df[all_featuresN]
|
||||
y_target = training_df['dst_mode']
|
||||
|
||||
# sanity check
|
||||
if not 'dst_mode' in x_features.columns:
|
||||
print('\nPASS: x_features has no target variable')
|
||||
x_ncols = len(x_features.columns)
|
||||
print('\nNo. of columns for x_features:', x_ncols)
|
||||
# NEED It for scaling law split
|
||||
#https://towardsdatascience.com/finally-why-we-use-an-80-20-split-for-training-and-test-data-plus-an-alternative-method-oh-yes-edc77e96295d
|
||||
else:
|
||||
sys.exit('\nFAIL: x_features has target variable included. FIX it and rerun!')
|
||||
#-------------------
|
||||
# train-test split
|
||||
#-------------------
|
||||
#x_train, x_test, y_train, y_test # traditional var_names
|
||||
# so my downstream code doesn't need to change
|
||||
X, X_bts, y, y_bts = train_test_split(x_features, y_target
|
||||
, test_size = 0.33
|
||||
, **rs
|
||||
, stratify = y_target)
|
||||
yc1 = Counter(y)
|
||||
yc1_ratio = yc1[0]/yc1[1]
|
||||
|
||||
yc2 = Counter(y_bts)
|
||||
yc2_ratio = yc2[0]/yc2[1]
|
||||
|
||||
###############################################################################
|
||||
#======================================================
|
||||
# Determine categorical and numerical features
|
||||
#======================================================
|
||||
numerical_cols = X.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_cols
|
||||
categorical_cols = X.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_cols
|
||||
|
||||
################################################################################
|
||||
# IMPORTANT sanity checks
|
||||
if len(X.columns) == len(X_evolFN) + len(X_stability_FN) + len(X_affinityFN) + len(X_resprop_FN) + len(X_genomicFN):
|
||||
print('\nPASS: ML data with input features, training and test generated...'
|
||||
, '\n\nTotal no. of input features:' , len(X.columns)
|
||||
, '\n--------No. of numerical features:' , len(numerical_cols)
|
||||
, '\n--------No. of categorical features:' , len(categorical_cols)
|
||||
|
||||
, '\n\nTotal no. of evolutionary features:' , len(X_evolFN)
|
||||
|
||||
, '\n\nTotal no. of stability features:' , len(X_stability_FN)
|
||||
, '\n--------Common stabilty cols:' , len(X_common_stability_Fnum)
|
||||
, '\n--------Foldx cols:' , len(X_foldX_Fnum)
|
||||
|
||||
, '\n\nTotal no. of affinity features:' , len(X_affinityFN)
|
||||
, '\n--------Common affinity cols:' , len(common_affinity_Fnum)
|
||||
, '\n--------Gene specific affinity cols:' , len(gene_affinity_colnames)
|
||||
|
||||
, '\n\nTotal no. of residue level features:', len(X_resprop_FN)
|
||||
, '\n--------AA index cols:' , len(X_aaindex_Fnum)
|
||||
, '\n--------Residue Prop cols:' , len(X_str_Fnum)
|
||||
, '\n--------AA change Prop cols:' , len(X_aap_Fcat)
|
||||
|
||||
, '\n\nTotal no. of genomic features:' , len(X_genomicFN)
|
||||
, '\n--------MAF+OR cols:' , len(X_gn_mafor_Fnum)
|
||||
, '\n--------Lineage cols:' , len(X_gn_linegae_Fnum)
|
||||
, '\n--------Other cols:' , len(X_gn_Fcat)
|
||||
)
|
||||
else:
|
||||
print('\nFAIL: numbers mismatch'
|
||||
, '\nExpected:',len(X_evolFN) + len(X_stability_FN) + len(X_affinityFN) + len(X_resprop_FN) + len(X_genomicFN)
|
||||
, '\nGot:', len(X.columns))
|
||||
sys.exit()
|
||||
###############################################################################
|
||||
print('\n-------------------------------------------------------------'
|
||||
, '\nSuccessfully split data: ALL features'
|
||||
, '\nactual values: training set'
|
||||
, '\nSplit:', tts_split
|
||||
#, '\nimputed values: blind test set'
|
||||
|
||||
, '\n\nTotal data size:', len(X) + len(X_bts)
|
||||
|
||||
, '\n\nTrain data size:', X.shape
|
||||
, '\ny_train numbers:', yc1
|
||||
|
||||
, '\n\nTest data size:', X_bts.shape
|
||||
, '\ny_test_numbers:', yc2
|
||||
|
||||
, '\n\ny_train ratio:',yc1_ratio
|
||||
, '\ny_test ratio:', yc2_ratio
|
||||
, '\n-------------------------------------------------------------'
|
||||
)
|
||||
##########################################################################
|
||||
# Quick check
|
||||
#(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
|
||||
for i in range(len(cols_to_mask)):
|
||||
ind = i+1
|
||||
print('\nindex:', i, '\nind:', ind)
|
||||
print('\nMask count check:'
|
||||
, (my_df_ml[cols_to_mask[i]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
|
||||
)
|
||||
|
||||
print('Original Data\n', Counter(y)
|
||||
, 'Data dim:', X.shape)
|
||||
###########################################################################
|
||||
#%%
|
||||
###########################################################################
|
||||
# RESAMPLING
|
||||
###########################################################################
|
||||
#------------------------------
|
||||
# Simple Random oversampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
print('\nSimple Random OverSampling\n', Counter(y_ros))
|
||||
print(X_ros.shape)
|
||||
|
||||
#------------------------------
|
||||
# Simple Random Undersampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rus, y_rus = undersample.fit_resample(X, y)
|
||||
print('\nSimple Random UnderSampling\n', Counter(y_rus))
|
||||
print(X_rus.shape)
|
||||
|
||||
#------------------------------
|
||||
# Simple combine ROS and RUS
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rouC, y_rouC = undersample.fit_resample(X_ros, y_ros)
|
||||
print('\nSimple Combined Over and UnderSampling\n', Counter(y_rouC))
|
||||
print(X_rouC.shape)
|
||||
|
||||
#------------------------------
|
||||
# SMOTE_NC: oversampling
|
||||
# [numerical + categorical]
|
||||
#https://stackoverflow.com/questions/47655813/oversampling-smote-for-binary-and-categorical-data-in-python
|
||||
#------------------------------
|
||||
# Determine categorical and numerical features
|
||||
numerical_ix = X.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_ix
|
||||
num_featuresL = list(numerical_ix)
|
||||
numerical_colind = X.columns.get_indexer(list(numerical_ix) )
|
||||
numerical_colind
|
||||
|
||||
categorical_ix = X.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_ix
|
||||
categorical_colind = X.columns.get_indexer(list(categorical_ix))
|
||||
categorical_colind
|
||||
|
||||
k_sm = 5 # 5 is default
|
||||
sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
|
||||
X_smnc, y_smnc = sm_nc.fit_resample(X, y)
|
||||
print('\nSMOTE_NC OverSampling\n', Counter(y_smnc))
|
||||
print(X_smnc.shape)
|
||||
globals().update(locals()) # TROLOLOLOLOLOLS
|
||||
#print("i did a horrible hack :-)")
|
||||
###############################################################################
|
||||
#%% SMOTE RESAMPLING for NUMERICAL ONLY*
|
||||
# #------------------------------
|
||||
# # SMOTE: Oversampling
|
||||
# # [Numerical ONLY]
|
||||
# #------------------------------
|
||||
# k_sm = 1
|
||||
# sm = SMOTE(sampling_strategy = 'auto', k_neighbors = k_sm, **rs)
|
||||
# X_sm, y_sm = sm.fit_resample(X, y)
|
||||
# print(X_sm.shape)
|
||||
# print('\nSMOTE OverSampling\n', Counter(y_sm))
|
||||
# y_sm_df = y_sm.to_frame()
|
||||
# y_sm_df.value_counts().plot(kind = 'bar')
|
||||
|
||||
# #------------------------------
|
||||
# # SMOTE: Over + Undersampling COMBINED
|
||||
# # [Numerical ONLY]
|
||||
# #-----------------------------
|
||||
# sm_enn = SMOTEENN(enn=EditedNearestNeighbours(sampling_strategy='all', **rs, **njobs ))
|
||||
# X_enn, y_enn = sm_enn.fit_resample(X, y)
|
||||
# print(X_enn.shape)
|
||||
# print('\nSMOTE Over+Under Sampling combined\n', Counter(y_enn))
|
||||
|
||||
###########################################################################
|
||||
# TODO: Find over and undersampling JUST for categorical data
|
||||
###########################################################################
|
||||
|
||||
print('\n#################################################################'
|
||||
, '\nDim of X for gene:', gene.lower(), '\n', X.shape
|
||||
, '\n###############################################################')
|
||||
73
scripts/ml/combined_model/ml_data_combined
Normal file
73
scripts/ml/combined_model/ml_data_combined
Normal file
|
|
@ -0,0 +1,73 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Created on Sat Jun 25 11:07:30 2022
|
||||
|
||||
@author: tanu
|
||||
"""
|
||||
|
||||
import sys, os
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
import re
|
||||
|
||||
###############################################################################
|
||||
homedir = os.path.expanduser("~")
|
||||
sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/functions')
|
||||
###############################################################################
|
||||
#====================
|
||||
# Import ML functions
|
||||
#====================
|
||||
#from MultClfs import *
|
||||
from GetMLData import *
|
||||
from SplitTTS import *
|
||||
#%% Load all gene files #######################################################
|
||||
# param dict
|
||||
combined_model_paramD = {'data_combined_model' : True
|
||||
, 'use_or' : False
|
||||
, 'omit_all_genomic_features': False
|
||||
, 'write_maskfile' : False
|
||||
, 'write_outfile' : False }
|
||||
|
||||
pnca_df = getmldata('pncA', 'pyrazinamide' , **combined_model_paramD)
|
||||
embb_df = getmldata('embB', 'ethambutol' , **combined_model_paramD)
|
||||
katg_df = getmldata('katG', 'isoniazid' , **combined_model_paramD)
|
||||
rpob_df = getmldata('rpoB', 'rifampicin' , **combined_model_paramD)
|
||||
gid_df = getmldata('gid' , 'streptomycin' , **combined_model_paramD)
|
||||
alr_df = getmldata('alr' , 'cycloserine' , **combined_model_paramD)
|
||||
|
||||
# quick check
|
||||
foo = pd.concat([alr_df, pnca_df])
|
||||
check1 = foo.filter(regex= '.*_affinity|gene_name|ligand_distance', axis = 1)
|
||||
# So, pd.concat will join correctly but introduce NAs.
|
||||
# TODO: discuss whether to make these 0 and use it or just omit
|
||||
# For now I am omitting these i.e combining only on common columns
|
||||
|
||||
expected_nrows = len(pnca_df) + len(embb_df) + len(katg_df) + len(rpob_df) + len(gid_df) + len(alr_df)
|
||||
|
||||
# finding common columns
|
||||
dfs_combine = [pnca_df, embb_df, katg_df, rpob_df, gid_df, alr_df]
|
||||
common_cols = list(set.intersection(*(set(df.columns) for df in dfs_combine)))
|
||||
expected_ncols = np.min([len(pnca_df.columns)] + [len(embb_df.columns)] + [len(katg_df.columns)] + [len(rpob_df.columns)] + [len(gid_df.columns)] + [len(alr_df.columns)])
|
||||
expected_ncols
|
||||
|
||||
if len(common_cols) == expected_ncols:
|
||||
print('\nProceeding to combine based on common cols (n):', len(common_cols))
|
||||
combined_df = pd.concat([df[common_cols] for df in dfs_combine], ignore_index = False)
|
||||
print('\nSuccessfully combined dfs:'
|
||||
, '\nNo. of dfs combined:', len(dfs_combine)
|
||||
, '\nDim of combined df:', combined_df.shape)
|
||||
else:
|
||||
print('\nFAIL: could not combine dfs, length mismatch'
|
||||
, '\nExpected ncols:', expected_ncols
|
||||
, '\nGot:', len(common_cols))
|
||||
#%% split data into different data types
|
||||
tts_7030_paramD = {'data_type' : 'actual'
|
||||
, 'split_type' : '70_30'
|
||||
, 'oversampling' : True}
|
||||
|
||||
data_CM_7030D = split_tts(ml_input_data = combined_df
|
||||
, **tts_7030_paramD
|
||||
, dst_colname = 'dst'
|
||||
, target_colname = 'dst_mode'
|
||||
, include_gene_name = False) # when not doing leave one group out
|
||||
221
scripts/ml/combined_model/untitled0.py
Normal file
221
scripts/ml/combined_model/untitled0.py
Normal file
|
|
@ -0,0 +1,221 @@
|
|||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
Created on Sat Jun 25 11:07:30 2022
|
||||
|
||||
@author: tanu
|
||||
"""
|
||||
|
||||
import sys, os
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
import os, sys
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
print(np.__version__)
|
||||
print(pd.__version__)
|
||||
import pprint as pp
|
||||
from copy import deepcopy
|
||||
from collections import Counter
|
||||
from sklearn.impute import KNNImputer as KNN
|
||||
from imblearn.over_sampling import RandomOverSampler
|
||||
from imblearn.under_sampling import RandomUnderSampler
|
||||
from imblearn.over_sampling import SMOTE
|
||||
from sklearn.datasets import make_classification
|
||||
from imblearn.combine import SMOTEENN
|
||||
from imblearn.combine import SMOTETomek
|
||||
|
||||
from imblearn.over_sampling import SMOTENC
|
||||
from imblearn.under_sampling import EditedNearestNeighbours
|
||||
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
|
||||
|
||||
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
|
||||
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
|
||||
|
||||
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
|
||||
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
||||
|
||||
from sklearn.pipeline import Pipeline, make_pipeline
|
||||
import argparse
|
||||
import re
|
||||
homedir = os.path.expanduser("~")
|
||||
#%% Globals
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
#%% Define split_tts function #################################################
|
||||
def split_tts(ml_input_data
|
||||
, data_type = ['actual', 'complete', 'reverse']
|
||||
, split_type = ['70_30', '80_20', 'sl']
|
||||
, oversampling = True
|
||||
, dst_colname = 'dst'# determine how to subset the actual vs reverse data
|
||||
, target_colname = 'dst_mode'):
|
||||
|
||||
print('\nInput params:'
|
||||
, '\nDim of input df:' , ml_input_data.shape
|
||||
, '\nData type to split:', data_type
|
||||
, '\nSplit type:' , split_type
|
||||
, '\ntarget colname:' , target_colname)
|
||||
|
||||
if oversampling:
|
||||
print('\noversampling enabled')
|
||||
else:
|
||||
print('\nNot generating oversampled or undersampled data')
|
||||
|
||||
#====================================
|
||||
# evaluating use_data_type
|
||||
#====================================
|
||||
if data_type == 'actual':
|
||||
ml_data = ml_input_data[ml_input_data[dst_colname].notna()]
|
||||
if data_type == 'complete':
|
||||
ml_data = ml_input_data.copy()
|
||||
if data_type == 'reverse':
|
||||
ml_data = ml_input_data[ml_input_data[dst_colname].isna()]
|
||||
#if_data_type == none
|
||||
|
||||
#====================================
|
||||
# separate features and target
|
||||
#====================================
|
||||
x_features = ml_data.drop([target_colname, dst_colname], axis = 1)
|
||||
y_target = ml_data[target_colname]
|
||||
|
||||
# sanity check
|
||||
if not 'dst_mode' in x_features.columns:
|
||||
print('\nPASS: x_features has no target variable')
|
||||
x_ncols = len(x_features.columns)
|
||||
print('\nNo. of columns for x_features:', x_ncols)
|
||||
else:
|
||||
sys.exit('\nFAIL: x_features has target variable included. FIX it and rerun!')
|
||||
|
||||
#====================================
|
||||
# Train test split
|
||||
# with stratification
|
||||
#=====================================
|
||||
if split_type == '70_30':
|
||||
tts_test_size = 0.33
|
||||
if split_type == '80_20':
|
||||
tts_test_size = 0.2
|
||||
if split_type == 'sl':
|
||||
tts_test_size = 1/np.sqrt(x_ncols)
|
||||
train_sl = 1 - tts_test_size
|
||||
|
||||
#-------------------------
|
||||
# TTS split ~ split_type
|
||||
#-------------------------
|
||||
#x_train, x_test, y_train, y_test # traditional var_names
|
||||
# so my downstream code doesn't need to change
|
||||
X, X_bts, y, y_bts = train_test_split(x_features, y_target
|
||||
, test_size = tts_test_size
|
||||
, **rs
|
||||
, stratify = y_target)
|
||||
yc1 = Counter(y)
|
||||
yc1_ratio = yc1[0]/yc1[1]
|
||||
|
||||
yc2 = Counter(y_bts)
|
||||
yc2_ratio = yc2[0]/yc2[1]
|
||||
###############################################################################
|
||||
#======================================================
|
||||
# Determine categorical and numerical features
|
||||
#======================================================
|
||||
numerical_cols = X.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_cols
|
||||
categorical_cols = X.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_cols
|
||||
###############################################################################
|
||||
print('\n-------------------------------------------------------------'
|
||||
, '\nSuccessfully generated training and test data:'
|
||||
, '\nData used:' , data_type
|
||||
, '\nSplit type:', split_type
|
||||
|
||||
, '\n\nTotal no. of input features:' , len(X.columns)
|
||||
, '\n--------No. of numerical features:' , len(numerical_cols)
|
||||
, '\n--------No. of categorical features:', len(categorical_cols)
|
||||
|
||||
, '\n\nTotal data size:', len(X) + len(X_bts)
|
||||
|
||||
, '\n\nTrain data size:', X.shape
|
||||
, '\ny_train numbers:', yc1
|
||||
|
||||
, '\n\nTest data size:', X_bts.shape
|
||||
, '\ny_test_numbers:', yc2
|
||||
|
||||
, '\n\ny_train ratio:',yc1_ratio
|
||||
, '\ny_test ratio:', yc2_ratio
|
||||
, '\n-------------------------------------------------------------'
|
||||
)
|
||||
|
||||
if oversampling:
|
||||
|
||||
#######################################################################
|
||||
# RESAMPLING
|
||||
#######################################################################
|
||||
#------------------------------
|
||||
# Simple Random oversampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
print('\nSimple Random OverSampling\n', Counter(y_ros))
|
||||
print(X_ros.shape)
|
||||
|
||||
#------------------------------
|
||||
# Simple Random Undersampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rus, y_rus = undersample.fit_resample(X, y)
|
||||
print('\nSimple Random UnderSampling\n', Counter(y_rus))
|
||||
print(X_rus.shape)
|
||||
|
||||
#------------------------------
|
||||
# Simple combine ROS and RUS
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rouC, y_rouC = undersample.fit_resample(X_ros, y_ros)
|
||||
print('\nSimple Combined Over and UnderSampling\n', Counter(y_rouC))
|
||||
print(X_rouC.shape)
|
||||
|
||||
#------------------------------
|
||||
# SMOTE_NC: oversampling
|
||||
# [numerical + categorical]
|
||||
#https://stackoverflow.com/questions/47655813/oversampling-smote-for-binary-and-categorical-data-in-python
|
||||
#------------------------------
|
||||
# Determine categorical and numerical features
|
||||
numerical_ix = X.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_ix
|
||||
num_featuresL = list(numerical_ix)
|
||||
numerical_colind = X.columns.get_indexer(list(numerical_ix) )
|
||||
numerical_colind
|
||||
|
||||
categorical_ix = X.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_ix
|
||||
categorical_colind = X.columns.get_indexer(list(categorical_ix))
|
||||
categorical_colind
|
||||
|
||||
k_sm = 5 # default
|
||||
sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
|
||||
X_smnc, y_smnc = sm_nc.fit_resample(X, y)
|
||||
print('\nSMOTE_NC OverSampling\n', Counter(y_smnc))
|
||||
print(X_smnc.shape)
|
||||
|
||||
print('\nGenerated resampled data as below:'
|
||||
, '\n==========================='
|
||||
, '\nRandom oversampling:'
|
||||
, '\n==========================='
|
||||
|
||||
, '\n\nTrain data size:', X_ros.shape
|
||||
|
||||
, '\ny_train numbers:', y_ros
|
||||
, '\n\ny_train ratio:', Counter(y_ros)[0]/Counter(y_ros)[0]
|
||||
|
||||
, '\ny_test ratio:' , yc2_ratio
|
||||
|
||||
, '\n-------------------------------------------------------------'
|
||||
)
|
||||
|
||||
|
||||
# globals().update(locals()) # TROLOLOLOLOLOLS
|
||||
|
||||
#return()
|
||||
|
|
@ -603,19 +603,20 @@ def getmldata(gene, drug
|
|||
# training_df[drug].value_counts()
|
||||
# training_df['dst_mode'].value_counts()
|
||||
|
||||
all_training_df = my_df_ml[all_featuresN]
|
||||
#all_training_df = my_df_ml[all_featuresN]
|
||||
|
||||
# Getting the dst column as this will be required for tts_split()
|
||||
if 'dst' in my_df_ml:
|
||||
print('\ndst column exists')
|
||||
if my_df_ml['dst'].equals(my_df_ml[drug]):
|
||||
print('\nand this is identical to drug column:', drug)
|
||||
|
||||
all_featuresN2 = all_featuresN + ['dst', 'dst_mode']
|
||||
all_training_df = my_df_ml[all_featuresN2]
|
||||
|
||||
print('\nAll feature names:', all_featuresN2)
|
||||
####################################################################
|
||||
|
||||
print('\n#################################################################'
|
||||
, '\nSUCCESS: Extacted training data for gene:', gene.lower()
|
||||
, '\nDim of training_df:', all_training_df.shape)
|
||||
if use_or:
|
||||
print('\nThis includes Odds Ratio')
|
||||
else:
|
||||
print('\nThis EXCLUDES Odds Ratio'
|
||||
, '\n###############################################################')
|
||||
|
||||
#==========================================================================
|
||||
if write_maskfile:
|
||||
print('\nPASS: and now writing file to check masked columns and values:', outFile_mask_ml )
|
||||
|
|
@ -630,4 +631,15 @@ def getmldata(gene, drug
|
|||
else:
|
||||
print('\nPASS: But NOT writing processed file')
|
||||
#==========================================================================
|
||||
|
||||
print('\n#################################################################'
|
||||
, '\nSUCCESS: Extacted training data for gene:', gene.lower()
|
||||
, '\nDim of training_df:', all_training_df.shape)
|
||||
if use_or:
|
||||
print('\nThis includes Odds Ratio'
|
||||
, '\n###########################################################')
|
||||
else:
|
||||
print('\nThis EXCLUDES Odds Ratio'
|
||||
, '\n############################################################')
|
||||
|
||||
return(all_training_df)
|
||||
|
|
@ -753,6 +753,7 @@ def setvars(gene,drug):
|
|||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
|
||||
X_rouC, y_rouC = undersample.fit_resample(X_ros, y_ros)
|
||||
print('\nSimple Combined Over and UnderSampling\n', Counter(y_rouC))
|
||||
print(X_rouC.shape)
|
||||
|
|
|
|||
|
|
@ -67,7 +67,7 @@ print('\n#####################################################################\n
|
|||
#================
|
||||
# MultModelsCl: without formatted output
|
||||
#================
|
||||
mmD = MultModelsCl(input_df = X_smnc
|
||||
mmD = MultModelsCl_noBT(input_df = X_smnc
|
||||
, target = y_smnc
|
||||
, var_type = 'mixed'
|
||||
, tts_split_type = tts_split_7030
|
||||
|
|
@ -77,12 +77,13 @@ mmD = MultModelsCl(input_df = X_smnc
|
|||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True
|
||||
, run_blind_test = True
|
||||
, return_formatted_output = False)
|
||||
|
||||
#================
|
||||
# MultModelsCl: WITH formatted output
|
||||
#================
|
||||
mmDF3 = MultModelsCl(input_df = X_smnc
|
||||
mmDF3 = MultModelsCl_noBT(input_df = X_smnc
|
||||
, target = y_smnc
|
||||
, var_type = 'mixed'
|
||||
, tts_split_type = tts_split_7030
|
||||
|
|
@ -92,9 +93,21 @@ mmDF3 = MultModelsCl(input_df = X_smnc
|
|||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True
|
||||
, run_blind_test = True
|
||||
, return_formatted_output= True )
|
||||
|
||||
|
||||
mmDF9= MultModelsCl_noBT(input_df = X
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, tts_split_type = tts_split_7030
|
||||
, resampling_type = 'none'
|
||||
, skf_cv = None
|
||||
, blind_test_df = X_bts
|
||||
, blind_test_target = y_bts
|
||||
, add_cm = True
|
||||
, add_yn = True
|
||||
, run_blind_test = True
|
||||
, return_formatted_output= True )
|
||||
#=================
|
||||
# test function
|
||||
#=================
|
||||
|
|
|
|||
325
scripts/plotting/LINEAGE.R
Normal file
325
scripts/plotting/LINEAGE.R
Normal file
|
|
@ -0,0 +1,325 @@
|
|||
library(tidyverse)
|
||||
#install.packages("ggforce")
|
||||
library("ggforce")
|
||||
#install.packages("gginference")
|
||||
library(gginference)
|
||||
library(ggpubr)
|
||||
|
||||
#%% read data
|
||||
df = read.csv("/home/tanu/git/Data/pyrazinamide/output/pnca_merged_df2.csv")
|
||||
#df = read.csv("/home/tanu/git/Data/pyrazinamide/output/pnca_merged_df3.csv")
|
||||
|
||||
foo = as.data.frame(colnames(df))
|
||||
|
||||
my_df = df[ ,c('mutationinformation'
|
||||
, 'snp_frequency'
|
||||
, 'pos_count'
|
||||
, 'lineage'
|
||||
, 'lineage_multimode'
|
||||
, 'dst'
|
||||
, 'dst_mode')]
|
||||
|
||||
#%% create sensitivity column ~ dst_mode
|
||||
my_df$sensitivity = ifelse(my_df$dst_mode == 1, "R", "S")
|
||||
table(my_df$dst_mode)
|
||||
table(my_df$sensitivity)
|
||||
|
||||
test = my_df[my_df$mutationinformation=="A102P",]
|
||||
|
||||
|
||||
|
||||
|
||||
# fix the lineage_multimode labels
|
||||
my_df$lineage_multimode
|
||||
my_df$lineage_mm <- gsub("\\.0", "", my_df$lineage_multimode)
|
||||
my_df$lineage_mm
|
||||
|
||||
my_df$lineage_mm <- gsub("\\[|||]", "", my_df$lineage_mm)
|
||||
str(my_df$lineage_mm)
|
||||
table(my_df$lineage_mm)
|
||||
|
||||
my_dfF = separate_rows(my_df, lineage_mm, sep = ",")
|
||||
my_dfF = as.data.frame(my_dfF)
|
||||
|
||||
table(my_dfF$lineage_mm)
|
||||
my_dfF$lineage_mm <- gsub(" ", "", my_dfF$lineage_mm)
|
||||
table(my_dfF$lineage_mm)
|
||||
|
||||
# addd prefix L
|
||||
my_dfF$lineage_mm = paste0("L", my_dfF$lineage_mm)
|
||||
table(my_dfF$lineage_mm)
|
||||
|
||||
if (class(my_df) == class(my_dfF)){
|
||||
cat('\nPASS: separated lineage multimode label column')
|
||||
my_df = my_dfF
|
||||
} else{
|
||||
cat('\nFAIL: could not split lineage multimode column')
|
||||
}
|
||||
|
||||
# select only L1-L4 and LBOV
|
||||
sel_lineages = c("L1", "L2", "L3", "L4")
|
||||
table(my_df$lineage_mm)
|
||||
my_df2 = my_df[my_df$lineage_mm%in%sel_lineages,]
|
||||
table(my_df2$lineage)
|
||||
sum(table(my_df2$lineage_mm)) == nrow(my_df2)
|
||||
|
||||
|
||||
dup_rows = my_df2[duplicated(my_df2[c('mutationinformation')]), ]
|
||||
expected_nrows = nrow(my_df2) - nrow(dup_rows)
|
||||
my_df3 = my_df2[!duplicated(my_df2[c('mutationinformation')]), ]
|
||||
|
||||
if ( nrow(my_df3) == expected_nrows ) {
|
||||
cat('\nPASS: duplicated rows removed')
|
||||
}else{
|
||||
cat('\nFAIL: duplicated rows could not be removed')
|
||||
}
|
||||
|
||||
table(my_df3$lineage_mm)
|
||||
str(my_df3$lineage_mm)
|
||||
|
||||
# convert to factor
|
||||
str(my_df3)
|
||||
my_df3$lineage = as.factor(my_df3$lineage)
|
||||
my_df3$lineage_mm = as.factor(my_df3$lineage_mm)
|
||||
my_df3$sensitivity = as.factor(my_df3$sensitivity)
|
||||
|
||||
str(my_df3$lineage_mm)
|
||||
|
||||
#df2 = my_df2[1:100,]
|
||||
df2 = my_df3
|
||||
sum(table(df2$mutationinformation))
|
||||
|
||||
table(df2$lineage_mm)
|
||||
str(df2$lineage_mm)
|
||||
|
||||
#df3 = df2[na.omit(df2$dst)]
|
||||
#sum(is.na(df2$dst))
|
||||
df3 = df2[!is.na(df2$dst), ]
|
||||
nrow(df3)
|
||||
|
||||
#%% plot
|
||||
#============
|
||||
# facet wrap
|
||||
#============
|
||||
plot_data = df2
|
||||
plot_data = df3
|
||||
table(plot_data$mutationinformation, plot_data$lineage_mm, plot_data$dst)
|
||||
|
||||
test2 = my_df[1:500, ]
|
||||
test2 = my_df
|
||||
test2 = test2[test2$lineage%in%sel_lineages,]
|
||||
nrow(test2)
|
||||
|
||||
# stats
|
||||
f2 = test2[test2$mutationinformation == "Y95D",]
|
||||
h = table(f2$lineage, f2$dst); h
|
||||
h2 = table(f2$lineage, f2$dst_mode); h2
|
||||
length(h)
|
||||
length(h2)
|
||||
|
||||
|
||||
f2 = test2[test2$mutationinformation == "Y95D",]
|
||||
h = table(f2$lineage, f2$dst); h
|
||||
h2 = table(f2$lineage, f2$sensitivity); h2
|
||||
length(h)
|
||||
length(h2)
|
||||
|
||||
tm = "G97A" # 1
|
||||
tm = "L117R"
|
||||
tm = "D63G"
|
||||
tm = "A102P"
|
||||
tm = "F13L"
|
||||
tm = "E174G"
|
||||
tm = "L182S"
|
||||
tm = "L4S"
|
||||
|
||||
f3 = test2[test2$mutationinformation == tm,]
|
||||
h3 = table(f3$lineage, f3$sensitivity); h3
|
||||
print(h3)
|
||||
print(class(h3))
|
||||
print(dim(h3))
|
||||
dim(h3)[1] # >1
|
||||
dim(h3)[2] #>1
|
||||
#h3 = table(f3$lineage); h3
|
||||
length(h3)
|
||||
|
||||
h3v2 = table(f3$lineage, f3$sensitivity); h3v2
|
||||
length(h3v2)
|
||||
|
||||
#if length is > 2, then get these
|
||||
chisq.test(h3)
|
||||
chisq.test(h3)$p.value
|
||||
|
||||
#ggchisqtest(chisq.test(h3))
|
||||
|
||||
fisher.test(h3)
|
||||
fisher.test(h3)$p.value
|
||||
|
||||
#########################
|
||||
muts = unique(my_df2$mutationinformation)
|
||||
my_df = my_df2
|
||||
|
||||
# step1 : get muts with more than one lineage
|
||||
lin_muts = NULL
|
||||
for (i in muts) {
|
||||
print (i)
|
||||
s_mut = my_df[my_df$mutationinformation == i,]
|
||||
s_tab = table(s_mut$lineage, s_mut$sensitivity)
|
||||
#s_tab = table(s_mut$lineage)
|
||||
#print(s_tab)
|
||||
|
||||
#if (length(s_tab) > 1 ){
|
||||
# if (dim(s_tab)[1] > 1 ){
|
||||
# lin_muts = c(lin_muts, i)
|
||||
if (dim(s_tab)[1] > 1 && dim(s_tab)[2] > 1){
|
||||
lin_muts = c(lin_muts, i)
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
# # now from the above list, get only the ones that have both R and S
|
||||
# muts_var = NULL
|
||||
# for (i in lin_muts) {
|
||||
# print (i)
|
||||
# s_mut = my_df[my_df$mutationinformation == i,]
|
||||
# s_tab = table(s_mut$lineage, s_mut$sensitivity)
|
||||
# print(s_tab)
|
||||
# print(dim(s_tab)[2]) # if this is one, we are uninterested
|
||||
# if ( dim(s_tab)[2] > 1 ){
|
||||
# muts_var = c(muts_var, i)
|
||||
# }
|
||||
# }
|
||||
|
||||
|
||||
# now final check
|
||||
for (i in lin_muts) {
|
||||
print (i)
|
||||
s_mut = my_df[my_df$mutationinformation == i,]
|
||||
s_tab = table(s_mut$lineage, s_mut$sensitivity)
|
||||
print(s_tab)
|
||||
print(c(i, "FT:", fisher.test(s_tab)$p.value))
|
||||
# print(dim(s_tab)[2]) # if this is one, we are uninterested
|
||||
# if ( dim(s_tab)[2] > 1 ){
|
||||
# muts_var = c(muts_var, i)
|
||||
# }
|
||||
|
||||
}
|
||||
|
||||
plot_df = my_df[my_df$mutationinformation%in%lin_muts,]
|
||||
|
||||
#plot_df2 = plot_df[plot_df$lineage%in%sel_lineages,]
|
||||
|
||||
|
||||
|
||||
table(plot_df$lineage)
|
||||
length(unique(plot_df2$mutationinformation)) == length(lin_muts)
|
||||
|
||||
#muts_var
|
||||
lin_mutsL = plot_df$mutationinformation[plot_df$mutationinformation%in%lin_muts]
|
||||
|
||||
|
||||
plot_df$p.value = NULL
|
||||
|
||||
for (i in lin_muts) {
|
||||
print (i)
|
||||
s_mut = plot_df[plot_df$mutationinformation == i,]
|
||||
print(s_mut)
|
||||
s_tab = table(s_mut$lineage, s_mut$sensitivity)
|
||||
print(s_tab)
|
||||
ft_pvalue_i = round(fisher.test(s_tab)$p.value, 2)
|
||||
|
||||
print(ft_pvalue_i)
|
||||
|
||||
# #my_df[my_df['mutationinformation']==i,]['ft_pvalue']= ft_pvalue_i
|
||||
#plot_df[plot_df['mutationinformation']==i,]['p.value']= ft_pvalue_i
|
||||
|
||||
plot_df$p.value[plot_df$mutationinformation == i] <- ft_pvalue_i
|
||||
#print(s_tab)
|
||||
}
|
||||
|
||||
|
||||
|
||||
plot_df2 = my_df[my_df$mutationinformation == c("A102P"),]
|
||||
#https://stackoverflow.com/questions/72618364/how-to-use-geom-signif-from-ggpubr-with-a-chi-square-test
|
||||
|
||||
#########################
|
||||
library(grid)
|
||||
#sp2 + annotation_custom(grob)+facet_wrap(~cyl, scales="free")
|
||||
grob <- grobTree(textGrob("Scatter plot", x=0.1, y=0.95, hjust=0,
|
||||
gp=gpar(col="red", fontsize=5, fontface="italic")))
|
||||
|
||||
#############
|
||||
chi.test <- function(a, b) {
|
||||
return(chisq.test(cbind(a, b)))
|
||||
}
|
||||
|
||||
ggplot(plot_df, aes(x = lineage
|
||||
#, y = snp_frequency
|
||||
, fill = factor(sensitivity))) +
|
||||
geom_bar(
|
||||
stat = 'count'
|
||||
#stat = 'identity'
|
||||
, position = 'dodge') +
|
||||
facet_wrap(~mutationinformation
|
||||
, scales = 'free_y') +
|
||||
#coord_flip() +
|
||||
stat_count(aes(y=..count../sum(..count..), label=p.value), geom="text", hjust=0)
|
||||
|
||||
#geom_text(aes(label = p.value, x = -0.5, y = 1))
|
||||
|
||||
#geom_text(data = data.frame(lineage = c("L1", "L2", "L3", "L4"), p.value = "p.value" ))
|
||||
#geom_text(aes(label = p.value), stat = "count")
|
||||
|
||||
|
||||
#geom_text(aes(label=after_stat(count)), vjust=0, stat = "count") # shows numbers
|
||||
|
||||
#geom_signif(comparisons = list(c("L1", "L2", "L3", "L4")), test = "fisher.test", y = 1)
|
||||
|
||||
# geom_signif(data = data.frame(lineage = c("L1", "L2", "L3", "L4"),sensitivity = c("R", "S") )
|
||||
# , test = "fisher.test" )
|
||||
# , aes(y_position=c(5.3, 8.3), xmin=c(0.8, 0.8), xmax=c(1.2, 1.2))
|
||||
# )
|
||||
|
||||
|
||||
#geom_label(p.value)
|
||||
#coord_flip()
|
||||
# ggforce::facet_wrap_paginate(~mutationinformation
|
||||
# , ncol = 5
|
||||
# , nrow = 5
|
||||
# , page = 10
|
||||
# )
|
||||
|
||||
|
||||
|
||||
|
||||
# with coord flip
|
||||
ggplot(plot_data, aes(x = lineage_mm, fill = sensitivity)) +
|
||||
geom_bar(position = 'dodge') +
|
||||
facet_wrap(~mutationinformation) + coord_flip()
|
||||
|
||||
#============
|
||||
# facet grid
|
||||
#============
|
||||
ggplot(plot_data, aes(x = mutationinformation, fill = sensitivity)) +
|
||||
geom_bar(position = 'dodge') +
|
||||
facet_grid(~lineage_mm)
|
||||
|
||||
# with coord flip
|
||||
ggplot(plot_data, aes(x = mutationinformation, fill = sensitivity)) +
|
||||
geom_bar(position = 'dodge') +
|
||||
facet_grid(~lineage_mm)+ coord_flip()
|
||||
|
||||
##########################################
|
||||
#%% useful info
|
||||
# https://stackoverflow.com/questions/13773770/split-comma-separated-strings-in-a-column-into-separate-rows
|
||||
bardf = as.data.frame(bar)
|
||||
class(bardf) == class(my_df)
|
||||
|
||||
baz = my_df
|
||||
baz = baz %>%
|
||||
mutate(col2 = strsplit(as.character(col2), ",")) %>%
|
||||
unnest(col2)
|
||||
baz = as.data.frame(baz)
|
||||
class(baz) == class(bar)
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue