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

107
ml_data/colnames_order.csv Normal file
View file

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