245 lines
No EOL
7.9 KiB
Python
Executable file
245 lines
No EOL
7.9 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Sun Mar 6 13:41:54 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
import os, sys
|
|
import pandas as pd
|
|
import numpy as np
|
|
import pprint as pp
|
|
from copy import deepcopy
|
|
from sklearn import linear_model
|
|
from sklearn.linear_model import LogisticRegression, LinearRegression
|
|
from sklearn.naive_bayes import BernoulliNB
|
|
from sklearn.neighbors import KNeighborsClassifier
|
|
from sklearn.svm import SVC
|
|
from sklearn.tree import DecisionTreeClassifier
|
|
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
|
|
from sklearn.ensemble import AdaBoostClassifier
|
|
from sklearn.ensemble import GradientBoostingClassifier
|
|
from sklearn.neural_network import MLPClassifier
|
|
from xgboost import XGBClassifier
|
|
from sklearn.naive_bayes import MultinomialNB
|
|
from sklearn.linear_model import SGDClassifier
|
|
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
|
|
|
|
from sklearn.compose import ColumnTransformer
|
|
from sklearn.compose import make_column_transformer
|
|
|
|
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
|
|
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef
|
|
from sklearn.metrics import jaccard_score
|
|
|
|
from sklearn.metrics import make_scorer
|
|
from sklearn.metrics import classification_report
|
|
|
|
from sklearn.metrics import average_precision_score
|
|
|
|
from sklearn.model_selection import cross_validate
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.model_selection import StratifiedKFold
|
|
|
|
from sklearn.pipeline import Pipeline
|
|
from sklearn.pipeline import make_pipeline
|
|
|
|
from sklearn.feature_selection import RFE
|
|
from sklearn.feature_selection import RFECV
|
|
import itertools
|
|
import seaborn as sns
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
print(np.__version__)
|
|
print(pd.__version__)
|
|
from statistics import mean, stdev, median, mode
|
|
|
|
from imblearn.over_sampling import RandomOverSampler
|
|
from imblearn.over_sampling import SMOTE
|
|
from imblearn.pipeline import Pipeline
|
|
#from sklearn.datasets import make_classification
|
|
from sklearn.model_selection import cross_validate, cross_val_score
|
|
from sklearn.model_selection import RepeatedStratifiedKFold
|
|
from sklearn.ensemble import AdaBoostClassifier
|
|
from imblearn.combine import SMOTEENN
|
|
from imblearn.under_sampling import EditedNearestNeighbours
|
|
|
|
from sklearn.model_selection import GridSearchCV
|
|
from sklearn.base import BaseEstimator
|
|
|
|
scoring_fn = ({'accuracy' : make_scorer(accuracy_score)
|
|
, 'fscore' : make_scorer(f1_score)
|
|
, 'mcc' : make_scorer(matthews_corrcoef)
|
|
, 'precision' : make_scorer(precision_score)
|
|
, 'recall' : make_scorer(recall_score)
|
|
, 'roc_auc' : make_scorer(roc_auc_score)
|
|
, 'jcc' : make_scorer(jaccard_score)
|
|
})
|
|
|
|
rs = {'random_state': 42}
|
|
njobs = {'n_jobs': 10}
|
|
skf_cv = StratifiedKFold(n_splits = 10
|
|
#, shuffle = False, random_state= None)
|
|
, shuffle = True,**rs)
|
|
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
|
, n_repeats=3
|
|
#, shuffle = False, random_state= None)
|
|
#, shuffle = True
|
|
,**rs)
|
|
#my_mcc = make_scorer({'mcc':make_scorer(matthews_corrcoef})
|
|
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
|
|
|
#%%
|
|
homedir = os.path.expanduser("~")
|
|
os.chdir(homedir + "/git/ML_AI_training/")
|
|
|
|
# my function
|
|
from MultClassPipe import MultClassPipeline
|
|
from MultClassPipe2 import MultClassPipeline2
|
|
from loopity_loop import MultClassPipeSKFLoop
|
|
from MultClassPipe3 import MultClassPipeSKFCV
|
|
|
|
#gene = 'pncA'
|
|
#drug = 'pyrazinamide'
|
|
|
|
#==============
|
|
# directories
|
|
#==============
|
|
datadir = homedir + '/git/Data/'
|
|
indir = datadir + drug + '/input/'
|
|
outdir = datadir + drug + '/output/'
|
|
|
|
#=======
|
|
# input
|
|
#=======
|
|
infile_ml1 = outdir + gene.lower() + '_merged_df3.csv'
|
|
#infile_ml2 = outdir + gene.lower() + '_merged_df2.csv'
|
|
|
|
my_df = pd.read_csv(infile_ml1)
|
|
my_df.dtypes
|
|
my_df_cols = my_df.columns
|
|
|
|
geneL_basic = ['pncA']
|
|
geneL_na = ['gid']
|
|
geneL_na_ppi2 = ['rpoB']
|
|
geneL_ppi2 = ['alr', 'embB', 'katG']
|
|
#%% get cols
|
|
mycols = my_df.columns
|
|
|
|
# change from numberic to
|
|
num_type = ['int64', 'float64']
|
|
cat_type = ['object', 'bool']
|
|
|
|
if my_df['active_aa_pos'].dtype in num_type:
|
|
my_df['active_aa_pos'] = my_df['active_aa_pos'].astype(object)
|
|
my_df['active_aa_pos'].dtype
|
|
|
|
# FIXME: if this is not structural, remove from source..
|
|
# 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)
|
|
|
|
# FIXME: either impute or remove!
|
|
# for embb (L114M, F115L, V123L, V125I, V131M) delete for now
|
|
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)
|
|
#%%============================================================================
|
|
|
|
# Target1: mutation_info_labels, convert to
|
|
dm_om_map = {'DM': 1, 'OM': 0} # pnca, OM is minority, other genes: DM is minority
|
|
my_df['mutation_class'] = my_df['mutation_info_labels'].map(dm_om_map)
|
|
my_df['mutation_class'].value_counts()
|
|
my_df['mutation_info_labels']. value_counts()
|
|
|
|
#%%
|
|
# GET X
|
|
common_cols_stabiltyN = ['ligand_distance'
|
|
, 'ligand_affinity_change'
|
|
, 'duet_stability_change'
|
|
, 'ddg_foldx'
|
|
, 'deepddg'
|
|
, 'ddg_dynamut2']
|
|
|
|
# Build stability columns ~ gene
|
|
if gene.lower() in geneL_basic:
|
|
x_stabilityN = common_cols_stabiltyN
|
|
|
|
if gene.lower() in geneL_ppi2:
|
|
x_stabilityN = common_cols_stabiltyN + ['mcsm_ppi2_affinity'
|
|
, 'interface_dist']
|
|
if gene.lower() in geneL_na:
|
|
x_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity']
|
|
|
|
if gene.lower() in geneL_na_ppi2:
|
|
x_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
|
|
|
X_strFN = ['asa'
|
|
, 'rsa'
|
|
, 'kd_values'
|
|
, 'rd_values']
|
|
|
|
X_evolFN = ['consurf_score'
|
|
, 'snap2_score'
|
|
, 'snap2_accuracy_pc']
|
|
|
|
# X_genomicFN = ['af'
|
|
# , 'or_mychisq'
|
|
# , 'or_logistic'
|
|
# , 'or_fisher'
|
|
# , 'pval_fisher']
|
|
|
|
#%% Construct numerical and categorical column names
|
|
numerical_FN = x_stabilityN + X_strFN + X_evolFN
|
|
|
|
# separate ones for foldx?
|
|
categorical_FN = ['ss_class'
|
|
, 'wt_prop_water'
|
|
# , 'lineage_labels' # misleading if using merged_df3
|
|
, 'mut_prop_water'
|
|
, 'wt_prop_polarity'
|
|
, 'mut_prop_polarity'
|
|
, 'wt_calcprop'
|
|
, 'mut_calcprop'
|
|
, 'active_aa_pos']
|
|
|
|
#%% extracting dfs based on numerical, categorical column names
|
|
#----------------------------------
|
|
# WITHOUT the target var included
|
|
#----------------------------------
|
|
num_df = my_df[numerical_FN]
|
|
num_df.shape
|
|
|
|
cat_df = my_df[categorical_FN]
|
|
cat_df.shape
|
|
|
|
all_df = my_df[numerical_FN + categorical_FN]
|
|
all_df.shape
|
|
|
|
#------------------------------
|
|
# WITH the target var included:
|
|
#'wtgt': with target
|
|
#------------------------------
|
|
num_df_wtgt = my_df[numerical_FN + ['mutation_class']]
|
|
num_df_wtgt.shape
|
|
|
|
cat_df_wtgt = my_df[categorical_FN + ['mutation_class']]
|
|
cat_df_wtgt.shape
|
|
|
|
all_df_wtgt = my_df[numerical_FN + categorical_FN + ['mutation_class']]
|
|
all_df_wtgt.shape
|
|
|
|
#%%
|
|
#%% Get train-test split and scoring functions
|
|
X = num_df_wtgt[numerical_FN]
|
|
y = num_df_wtgt['mutation_class']
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(X
|
|
,y
|
|
, test_size = 0.33
|
|
, random_state = 2
|
|
, shuffle = True
|
|
, stratify = y)
|
|
|