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

added avg affinity and stability cols with mask for avg affinity

Browse source
This commit is contained in:
Tanushree Tunstall 2022-09-01 13:04:37 +01:00
parent e03ce277b7
commit 56b71c6ca2
2 changed files with 51 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

12
scripts/ml/ml_functions/GetMLData.py
View file

@ -436,7 +436,7 @@ def getmldata(gene, drug
if gene.lower() in geneL_basic: if gene.lower() in geneL_basic:
#X_stabilityN = common_cols_stabiltyN #X_stabilityN = common_cols_stabiltyN
gene_affinity_colnames = []# not needed as its the common ones gene_affinity_colnames = []# not needed as its the common ones
cols_to_mask = ['ligand_affinity_change'] cols_to_mask = ['ligand_affinity_change', 'avg_lig_affinity']
cols_to_mask_ppi2 = [] cols_to_mask_ppi2 = []
cols_to_mask_na = [] cols_to_mask_na = []
@ -444,7 +444,7 @@ def getmldata(gene, drug
gene_affinity_colnames = ['mcsm_ppi2_affinity', 'interface_dist'] gene_affinity_colnames = ['mcsm_ppi2_affinity', 'interface_dist']
#X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols #X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
#cols_to_mask = ['ligand_affinity_change', 'mcsm_ppi2_affinity'] #cols_to_mask = ['ligand_affinity_change', 'mcsm_ppi2_affinity']
cols_to_mask = ['ligand_affinity_change'] cols_to_mask = ['ligand_affinity_change', 'avg_lig_affinity']
cols_to_mask_ppi2 = ['mcsm_ppi2_affinity'] cols_to_mask_ppi2 = ['mcsm_ppi2_affinity']
cols_to_mask_na = [] cols_to_mask_na = []
@ -452,7 +452,7 @@ def getmldata(gene, drug
if gene.lower() in geneL_na: if gene.lower() in geneL_na:
gene_affinity_colnames = ['mcsm_na_affinity', 'nca_distance'] gene_affinity_colnames = ['mcsm_na_affinity', 'nca_distance']
#X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols #X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
cols_to_mask = ['ligand_affinity_change']#, 'mcsm_na_affinity'] cols_to_mask = ['ligand_affinity_change', 'avg_lig_affinity']
cols_to_mask_ppi2 = [] cols_to_mask_ppi2 = []
cols_to_mask_na = ['mcsm_na_affinity'] cols_to_mask_na = ['mcsm_na_affinity']
@ -461,7 +461,7 @@ def getmldata(gene, drug
gene_affinity_colnames = ['mcsm_na_affinity','nca_distance', 'mcsm_ppi2_affinity', 'interface_dist'] gene_affinity_colnames = ['mcsm_na_affinity','nca_distance', 'mcsm_ppi2_affinity', 'interface_dist']
#X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols #X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
#cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity'] #cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity']
cols_to_mask = ['ligand_affinity_change']#, 'mcsm_na_affinity'] cols_to_mask = ['ligand_affinity_change', 'avg_lig_affinity']
cols_to_mask_ppi2 = ['mcsm_ppi2_affinity'] cols_to_mask_ppi2 = ['mcsm_ppi2_affinity']
cols_to_mask_na = ['mcsm_na_affinity'] cols_to_mask_na = ['mcsm_na_affinity']
@ -530,6 +530,7 @@ def getmldata(gene, drug
, 'ddg_foldx' , 'ddg_foldx'
, 'deepddg' , 'deepddg'
, 'ddg_dynamut2' , 'ddg_dynamut2'
, 'avg_stability' # NEW
, 'contacts'] , 'contacts']
#-------- #--------
# FoldX # FoldX
@ -549,7 +550,8 @@ def getmldata(gene, drug
#=================== #===================
common_affinity_Fnum = ['ligand_distance' common_affinity_Fnum = ['ligand_distance'
, 'ligand_affinity_change' , 'ligand_affinity_change'
, 'mmcsm_lig'] , 'mmcsm_lig'
, 'avg_lig_affinity'] # NEW
# if gene.lower() in geneL_basic: # if gene.lower() in geneL_basic:
# X_affinityFN = common_affinity_Fnum # X_affinityFN = common_affinity_Fnum

44
scripts/ml/ml_functions/TEST_GetMLData.py
View file

@ -5,6 +5,33 @@ Created on Thu Sep 1 12:22:27 2022
@author: tanu @author: tanu
""" """
getmldata(gene = "alr"
, drug = "cycloserine"
, data_combined_model = False
, use_or = False
, omit_all_genomic_features = False
, write_maskfile = True
, write_outfile = False)
getmldata(gene = "embB"
, drug = "ethambutol"
, data_combined_model = False
, use_or = False
, omit_all_genomic_features = False
, write_maskfile = True
, write_outfile = False)
getmldata(gene = "gid"
, drug = "streptomycin"
, data_combined_model = False
, use_or = False
, omit_all_genomic_features = False
, write_maskfile = True
, write_outfile = False)
getmldata(gene = "katG" getmldata(gene = "katG"
, drug = "isoniazid" , drug = "isoniazid"
, data_combined_model = False , data_combined_model = False
@ -12,3 +39,20 @@ getmldata(gene = "katG"
, omit_all_genomic_features = False , omit_all_genomic_features = False
, write_maskfile = True , write_maskfile = True
, write_outfile = False) , write_outfile = False)
getmldata(gene = "rpoB"
, drug = "rifampicin"
, data_combined_model = False
, use_or = False
, omit_all_genomic_features = False
, write_maskfile = True
, write_outfile = False)
getmldata(gene = "pncA"
, drug = "pyrazinamide"
, data_combined_model = False
, use_or = False
, omit_all_genomic_features = False
, write_maskfile = True
, write_outfile = False)