working on dissected model, testing diff feature groups
This commit is contained in:
parent
135efcee41
commit
e68a153883
4 changed files with 270 additions and 161 deletions
|
|
@ -417,125 +417,37 @@ else:
|
|||
#---------------------------------------
|
||||
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
|
||||
|
||||
#%%########################################################################
|
||||
#%% Data for ML ###############################################################
|
||||
#==========================
|
||||
# Data for ML
|
||||
#==========================
|
||||
my_df_ml = my_df.copy()
|
||||
|
||||
#%% Build X: input for ML
|
||||
common_cols_stabiltyN = ['ligand_distance'
|
||||
, 'ligand_affinity_change'
|
||||
, 'duet_stability_change'
|
||||
, 'ddg_foldx'
|
||||
, 'deepddg'
|
||||
, 'ddg_dynamut2'
|
||||
, 'mmcsm_lig'
|
||||
, 'contacts']
|
||||
|
||||
# Build stability columns ~ gene
|
||||
# Build column names to mask for affinity chanhes
|
||||
if gene.lower() in geneL_basic:
|
||||
X_stabilityN = common_cols_stabiltyN
|
||||
#X_stabilityN = common_cols_stabiltyN
|
||||
gene_affinity_colnames = []# not needed as its a common one
|
||||
cols_to_mask = ['ligand_affinity_change']
|
||||
|
||||
if gene.lower() in geneL_ppi2:
|
||||
# X_stabilityN = common_cols_stabiltyN + ['mcsm_ppi2_affinity' , 'interface_dist']
|
||||
geneL_ppi2_st_cols = ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
|
||||
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:
|
||||
# X_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity']
|
||||
geneL_na_st_cols = ['mcsm_na_affinity']
|
||||
X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
|
||||
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:
|
||||
# X_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
geneL_na_ppi2_st_cols = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist']
|
||||
X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
|
||||
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']
|
||||
|
||||
|
||||
X_foldX_cols = [ '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_str = ['rsa'
|
||||
#, 'asa'
|
||||
, 'kd_values'
|
||||
, 'rd_values']
|
||||
|
||||
X_ssFN = X_stabilityN + X_str + X_foldX_cols
|
||||
|
||||
X_evolFN = ['consurf_score'
|
||||
, 'snap2_score'
|
||||
, 'provean_score']
|
||||
|
||||
X_genomic_mafor = ['maf'
|
||||
, 'logorI'
|
||||
# , 'or_rawI'
|
||||
# , 'or_mychisq'
|
||||
# , 'or_logistic'
|
||||
# , 'or_fisher'
|
||||
# , 'pval_fisher'
|
||||
]
|
||||
|
||||
X_genomic_linegae = ['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_genomicFN = X_genomic_mafor + X_genomic_linegae
|
||||
|
||||
#X_aaindexFN = list(aa_df_cols)
|
||||
|
||||
#print('\nTotal no. of features for aaindex:', len(X_aaindexFN))
|
||||
|
||||
# numerical feature names [NO aa_index]
|
||||
numerical_FN = X_ssFN + X_evolFN + X_genomicFN
|
||||
|
||||
|
||||
# categorical feature names
|
||||
categorical_FN = ['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'
|
||||
, 'drtype_mode_labels' # beware then you can't use it to predict [USED it for uq_v1, not v2]
|
||||
, 'active_site' #[didn't use it for uq_v1]
|
||||
#, 'gene_name' # will be required for the combined stuff
|
||||
]
|
||||
#----------------------------------------------
|
||||
# count numerical and categorical features
|
||||
#----------------------------------------------
|
||||
|
||||
print('\nNo. of numerical features:', len(numerical_FN)
|
||||
, '\nNo. of categorical features:', len(categorical_FN))
|
||||
|
||||
###########################################################################
|
||||
#=======================
|
||||
# Masking columns:
|
||||
# (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
|
||||
#=======================
|
||||
# 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.loc[(my_df_ml['ligand_distance'] > 10), 'ligand_affinity_change'] = 0
|
||||
# (my_df_ml['ligand_affinity_change'] == 0).sum()
|
||||
|
||||
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()
|
||||
|
|
@ -546,16 +458,139 @@ my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask] = 0
|
|||
|
||||
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'
|
||||
, 'mmcsm_lig'
|
||||
, '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']
|
||||
|
||||
# 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_genomicFN = X_gn_mafor_Fnum + X_gn_linegae_Fnum + X_gn_Fcat
|
||||
###############################################################################
|
||||
# Feature groups further collaps:
|
||||
X_structural_FN = X_stability_FN + X_affinityFN + X_resprop_FN
|
||||
|
||||
all_featuresN = X_evolFN + X_structural_FN + X_genomicFN
|
||||
|
||||
###############################################################################
|
||||
#%% Define training and test data
|
||||
#======================================================
|
||||
# Training and BLIND test set [UQ]: actual vs imputed
|
||||
# No aa index but active_site included
|
||||
# dst with actual values : training set
|
||||
# dst with imputed values : blind test
|
||||
#==================================================
|
||||
#======================================================
|
||||
my_df_ml[drug].isna().sum() #'na' ones are the blind_test set
|
||||
|
||||
blind_test_df = my_df_ml[my_df_ml[drug].isna()]
|
||||
|
|
@ -567,6 +602,7 @@ training_df.shape
|
|||
# Target 1: dst_mode
|
||||
training_df[drug].value_counts()
|
||||
training_df['dst_mode'].value_counts()
|
||||
|
||||
####################################################################
|
||||
#============
|
||||
# ML data
|
||||
|
|
@ -574,8 +610,8 @@ training_df['dst_mode'].value_counts()
|
|||
#------
|
||||
# X: Training and Blind test (BTS)
|
||||
#------
|
||||
X = training_df[numerical_FN + categorical_FN]
|
||||
X_bts = blind_test_df[numerical_FN + categorical_FN]
|
||||
X = training_df[all_featuresN]
|
||||
X_bts = blind_test_df[all_featuresN]
|
||||
|
||||
#------
|
||||
# y
|
||||
|
|
@ -601,19 +637,67 @@ 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: UQ [no aa_index but active site included] training'
|
||||
, '\nSuccessfully split data: ALL features'
|
||||
, '\nactual values: training set'
|
||||
, '\nimputed values: blind test set'
|
||||
, '\nTrain data size:', X.shape
|
||||
, '\nTest data size:', X_bts.shape
|
||||
|
||||
, '\n\nTotal data size:', len(X) + len(X_bts)
|
||||
|
||||
, '\n\nTrain data size:', X.shape
|
||||
, '\ny_train numbers:', yc1
|
||||
, '\ny_train ratio:',yc1_ratio
|
||||
, '\n'
|
||||
|
||||
, '\n\nTest data size:', X_bts.shape
|
||||
, '\ny_test_numbers:', yc2
|
||||
|
||||
, '\n\ny_train ratio:',yc1_ratio
|
||||
, '\ny_test ratio:', yc2_ratio
|
||||
, '\n-------------------------------------------------------------'
|
||||
)
|
||||
|
||||
###########################################################################
|
||||
#%%
|
||||
###########################################################################
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue