added my_data4 after outputting merged_df3 for pnca to test the ml models

This commit is contained in:
Tanushree Tunstall 2022-03-03 13:35:05 +00:00
parent 25a55ac914
commit 04e0267dd1
11 changed files with 5918 additions and 377 deletions

108
ml_data/data_colnames.csv Normal file
View file

@ -0,0 +1,108 @@
"","x"
"1","mutationinformation"
"2","id"
"3","sample"
"4","lineage"
"5","sublineage"
"6","country_code"
"7","geographic_source"
"8","drtype"
"9","pyrazinamide"
"10","mutation"
"11","mutation_info"
"12","wild_type"
"13","mutant_type"
"14","position"
"15","wt_prop_water"
"16","mut_prop_water"
"17","wt_prop_polarity"
"18","mut_prop_polarity"
"19","wt_calcprop"
"20","mut_calcprop"
"21","chain"
"22","ligand_id"
"23","ligand_distance"
"24","duet_stability_change"
"25","duet_outcome"
"26","ligand_affinity_change"
"27","ligand_outcome"
"28","duet_scaled"
"29","affinity_scaled"
"30","wild_pos"
"31","wild_chain_pos"
"32","ddg_foldx"
"33","contacts"
"34","electro_rr"
"35","electro_mm"
"36","electro_sm"
"37","electro_ss"
"38","disulfide_rr"
"39","disulfide_mm"
"40","disulfide_sm"
"41","disulfide_ss"
"42","hbonds_rr"
"43","hbonds_mm"
"44","hbonds_sm"
"45","hbonds_ss"
"46","partcov_rr"
"47","partcov_mm"
"48","partcov_sm"
"49","partcov_ss"
"50","vdwclashes_rr"
"51","vdwclashes_mm"
"52","vdwclashes_sm"
"53","vdwclashes_ss"
"54","volumetric_rr"
"55","volumetric_mm"
"56","volumetric_sm"
"57","volumetric_ss"
"58","foldx_scaled"
"59","foldx_outcome"
"60","deepddg"
"61","deepddg_outcome"
"62","deepddg_scaled"
"63","asa"
"64","rsa"
"65","ss"
"66","ss_class"
"67","kd_values"
"68","rd_values"
"69","wt_3upper"
"70","consurf_score"
"71","consurf_scaled"
"72","consurf_colour"
"73","consurf_colour_rev"
"74","consurf_ci_upper"
"75","consurf_ci_lower"
"76","consurf_ci_colour"
"77","consurf_msa_data"
"78","consurf_aa_variety"
"79","snap2_score"
"80","snap2_scaled"
"81","snap2_accuracy_pc"
"82","snap2_outcome"
"83","af"
"84","beta_logistic"
"85","or_logistic"
"86","pval_logistic"
"87","se_logistic"
"88","zval_logistic"
"89","ci_low_logistic"
"90","ci_hi_logistic"
"91","or_mychisq"
"92","log10_or_mychisq"
"93","or_fisher"
"94","pval_fisher"
"95","neglog_pval_fisher"
"96","ci_low_fisher"
"97","ci_hi_fisher"
"98","est_chisq"
"99","pval_chisq"
"100","ddg_dynamut2"
"101","ddg_dynamut2_scaled"
"102","ddg_dynamut2_outcome"
"103","mut_3upper"
"104","seq_offset4pdb"
"105","pdb_file"
"106","mutation_info_labels"
"107","lineage_labels"
1 x
2 1 mutationinformation
3 2 id
4 3 sample
5 4 lineage
6 5 sublineage
7 6 country_code
8 7 geographic_source
9 8 drtype
10 9 pyrazinamide
11 10 mutation
12 11 mutation_info
13 12 wild_type
14 13 mutant_type
15 14 position
16 15 wt_prop_water
17 16 mut_prop_water
18 17 wt_prop_polarity
19 18 mut_prop_polarity
20 19 wt_calcprop
21 20 mut_calcprop
22 21 chain
23 22 ligand_id
24 23 ligand_distance
25 24 duet_stability_change
26 25 duet_outcome
27 26 ligand_affinity_change
28 27 ligand_outcome
29 28 duet_scaled
30 29 affinity_scaled
31 30 wild_pos
32 31 wild_chain_pos
33 32 ddg_foldx
34 33 contacts
35 34 electro_rr
36 35 electro_mm
37 36 electro_sm
38 37 electro_ss
39 38 disulfide_rr
40 39 disulfide_mm
41 40 disulfide_sm
42 41 disulfide_ss
43 42 hbonds_rr
44 43 hbonds_mm
45 44 hbonds_sm
46 45 hbonds_ss
47 46 partcov_rr
48 47 partcov_mm
49 48 partcov_sm
50 49 partcov_ss
51 50 vdwclashes_rr
52 51 vdwclashes_mm
53 52 vdwclashes_sm
54 53 vdwclashes_ss
55 54 volumetric_rr
56 55 volumetric_mm
57 56 volumetric_sm
58 57 volumetric_ss
59 58 foldx_scaled
60 59 foldx_outcome
61 60 deepddg
62 61 deepddg_outcome
63 62 deepddg_scaled
64 63 asa
65 64 rsa
66 65 ss
67 66 ss_class
68 67 kd_values
69 68 rd_values
70 69 wt_3upper
71 70 consurf_score
72 71 consurf_scaled
73 72 consurf_colour
74 73 consurf_colour_rev
75 74 consurf_ci_upper
76 75 consurf_ci_lower
77 76 consurf_ci_colour
78 77 consurf_msa_data
79 78 consurf_aa_variety
80 79 snap2_score
81 80 snap2_scaled
82 81 snap2_accuracy_pc
83 82 snap2_outcome
84 83 af
85 84 beta_logistic
86 85 or_logistic
87 86 pval_logistic
88 87 se_logistic
89 88 zval_logistic
90 89 ci_low_logistic
91 90 ci_hi_logistic
92 91 or_mychisq
93 92 log10_or_mychisq
94 93 or_fisher
95 94 pval_fisher
96 95 neglog_pval_fisher
97 96 ci_low_fisher
98 97 ci_hi_fisher
99 98 est_chisq
100 99 pval_chisq
101 100 ddg_dynamut2
102 101 ddg_dynamut2_scaled
103 102 ddg_dynamut2_outcome
104 103 mut_3upper
105 104 seq_offset4pdb
106 105 pdb_file
107 106 mutation_info_labels
108 107 lineage_labels