ML_AI_training/UQ_pnca_ML.py

333 lines
11 KiB
Python

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sun Mar 6 13:41:54 2022
@author: tanu
"""
#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 sklearn import linear_model
from sklearn import datasets
from collections import Counter
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.gaussian_process import GaussianProcessClassifier, kernels
from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from xgboost import XGBClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
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
from sklearn.feature_selection import RFE, RFECV
import itertools
import seaborn as sns
import matplotlib.pyplot as plt
from statistics import mean, stdev, median, mode
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.model_selection import GridSearchCV
from sklearn.base import BaseEstimator
import json
from sklearn.impute import KNNImputer as KNN
# My functions and globals
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
, **rs)
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
#%%
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
#from UQ_MultClassPipe4 import MultClassPipeSKFCV
from UQ_MultModelsCl import MultModelsCl
#gene = 'pncA'
#drug = 'pyrazinamide'
#gene = 'katG'
#drug = 'isoniazid'
#==============
# 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, index_col = 0)
my_df.dtypes
my_df_cols = my_df.columns
geneL_basic = ['pnca']
# -- CHECK script -- imports.py
#%% get cols
mycols = my_df.columns
mycols
# change from numberic to
num_type = ['int64', 'float64']
cat_type = ['object', 'bool']
# TODO:
# Treat active site aa pos as category and not numerical: This needs to be part of merged_df3!
#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
# -- CHECK script -- imports.py
#%%============================================================================
#%% IMPUTE values for OR [check script for exploration: UQ_or_imputer]
#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")
my_df[or_cols].isnull().sum()
my_dfI = pd.DataFrame(index = my_df['mutationinformation'] )
my_dfI = pd.DataFrame(KNN(n_neighbors= 5, 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()
# 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'])
#%% Combine mmCSM_lig Data
#%% Combine PROVEAN data
#%% Combine ED logo data
#%% Masking columns (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
# get logic from upstream!
my_df_ml = my_df.copy()
my_df_ml['mutationinformation'][my_df['ligand_distance']>10].value_counts()
my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>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), 'ligand_affinity_change'] = 0
(my_df_ml['ligand_affinity_change'] == 0).sum()
#%%============================================================================
# Separate blind test set
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
# Target1: dst
training_df[drug].value_counts()
training_df['dst_mode'].value_counts()
#%% Build X
common_cols_stabiltyN = ['ligand_distance'
, 'ligand_affinity_change'
, 'duet_stability_change'
, 'ddg_foldx'
, 'deepddg'
, 'ddg_dynamut2']
foldX_cols = ['contacts'
#, '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_strFN = ['rsa'
#, 'asa'
, 'kd_values'
, 'rd_values']
X_evolFN = ['consurf_score'
, 'snap2_score']
# quick inspection which lineage to use:
#foo = my_df_ml[['lineage', 'lineage_count_all', 'lineage_count_unique']]
X_genomicFN = ['maf'
# , 'or_mychisq'
# , 'or_logistic'
# , 'or_fisher'
# , 'pval_fisher'
#, 'lineage'
#, 'lineage_count_all'
#, 'lineage_count_unique'
]
#%% Construct numerical and categorical column names
# numerical feature names
numerical_FN = common_cols_stabiltyN + foldX_cols + X_strFN + X_evolFN + X_genomicFN
#categorical feature names
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 = training_df[numerical_FN]
num_df.shape
cat_df = training_df[categorical_FN]
cat_df.shape
all_df = training_df[numerical_FN + categorical_FN]
all_df.shape
#------------------------------
# WITH the target var included:
#'wtgt': with target
#------------------------------
# drug and dst_mode should be the same thing
num_df_wtgt = training_df[numerical_FN + ['dst_mode']]
num_df_wtgt.shape
cat_df_wtgt = training_df[categorical_FN + ['dst_mode']]
cat_df_wtgt.shape
all_df_wtgt = training_df[numerical_FN + categorical_FN + ['dst_mode']]
all_df_wtgt.shape
#%%================================================================
#%% Apply ML
#TODO: A
#%% Data
#------
# X
#------
X = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
X_bts = blind_test_df[numerical_FN + categorical_FN] # blind test data ALL
#X = all_df_wtgt[numerical_FN] # training numerical only
#X_bts = blind_test_df[numerical_FN] # blind test data numerical
#------
# y
#------
y = all_df_wtgt['dst_mode'] # training data y
y_bts = blind_test_df['dst_mode'] # blind data test y
#Blind test data {same format}
#X_bts = blind_test_df[numerical_FN]
#X_bts = blind_test_df[numerical_FN + categorical_FN]
#y_bts = blind_test_df['dst_mode']
X_bts_wt = blind_test_df[numerical_FN + ['dst_mode']]
# Quick check
(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
#%% MultClassPipeSKFCV: function call()
# mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
# , target = y
# , var_type = 'numerical'
# , skf_cv = skf_cv)
# mm_skf_scores_df_all = pd.DataFrame(mm_skf_scoresD)
# mm_skf_scores_df_all
# mm_skf_scores_df_test = mm_skf_scores_df_all.filter(like='test_', axis=0)
# mm_skf_scores_df_train = mm_skf_scores_df_all.filter(like='train_', axis=0) # helps to see if you trust the results
# print(mm_skf_scores_df_train)
# print(mm_skf_scores_df_test)