Skip to content

Commit 8a1413d

Browse files
pizza6inchVghxv
authored andcommitted
no smote
1 parent a1e76ff commit 8a1413d

69 files changed

Lines changed: 54493 additions & 0 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

config/prostate.json

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
{
2+
"GDC_prostate_tissue": {
3+
"normal": 50,
4+
"tumor": 502,
5+
"sample_count": 2,
6+
"sample_type": "tissue",
7+
"file": "../prostate/champ_result/GDC_prostate_tissue/all_beta_normalized.csv",
8+
"split_test": 0.2,
9+
"random_state": 42
10+
},
11+
"GDC_prostate_tissue_80": {
12+
"normal": 40,
13+
"tumor": 401,
14+
"file": "../prostate/champ_result/GDC_prostate_tissue_80/all_beta_normalized.csv"
15+
},
16+
"GDC_prostate_tissue_20_test": {
17+
"normal": 10,
18+
"tumor": 101,
19+
"file": "../prostate/champ_result/GDC_prostate_tissue_20_test/all_beta_normalized.csv"
20+
},
21+
"GSE269244": {
22+
"normal": 118,
23+
"tumor": 120,
24+
"sample_count": 2,
25+
"sample_type": "tissue",
26+
"file": "../prostate/champ_result/GSE269244/all_beta_normalized.csv",
27+
"split_test": 0.2,
28+
"random_state": 42
29+
},
30+
"GSE269244_80": {
31+
"normal": 94,
32+
"tumor": 96,
33+
"file": "../prostate/champ_result/GSE269244_80/all_beta_normalized.csv"
34+
},
35+
"GSE269244_20_test": {
36+
"normal": 24,
37+
"tumor": 24,
38+
"file": "../prostate/champ_result/GSE269244_20_test/all_beta_normalized.csv"
39+
}
40+
}

config/prostate_plan_A.toml

Lines changed: 75 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,75 @@
1+
[init.hyper]
2+
df_file_1 = "../prostate/champ_result/GDC_prostate_tissue_80/all_beta_normalized.csv"
3+
df_file_2 = "../prostate/champ_result/GSE269244_80/all_beta_normalized.csv"
4+
dmp_file_1 = "../prostate/champ_result/GDC_prostate_tissue/DMP_result_TN.csv"
5+
dmp_file_2 = "../prostate/champ_result/GSE269244/DMP_result_TN.csv"
6+
majority_out_path_1 = "../prostate/planA/GDC_prostate_tissue/split80train"
7+
majority_out_path_2 = "../prostate/planA/GSE269244/split80train"
8+
joined_out_path = "../prostate/planA/joined"
9+
10+
[GO_distance_matrix.hyper]
11+
input_file = "prostate/planA/joined/section_2/dbeta_TSS_threshold_joined.csv"
12+
base_out_dir = "prostate/planA/joined/GO_distance_matrix"
13+
14+
[clustering_visual.hyper]
15+
result_prefix = "dbeta_TSS_threshold_joined"
16+
dbeta_file = "../prostate/planA/joined/section_2/dbeta_TSS_threshold_joined.csv"
17+
bp_file = "../prostate/planA/joined/GO_distance_matrix/distance_matrix_bp.csv"
18+
cc_file = "../prostate/planA/joined/GO_distance_matrix/distance_matrix_cc.csv"
19+
mf_file = "../prostate/planA/joined/GO_distance_matrix/distance_matrix_mf.csv"
20+
terms_count_file = "../prostate/planA/joined/GO_distance_matrix/terms_count.csv"
21+
result_out_path = "../prostate/planA/joined/section_5"
22+
23+
[simple_model.hyper]
24+
dbeta_file = "../prostate/planA/joined/section_5/dbeta_TSS_threshold_joined_consensus.csv"
25+
selected_feature_file = "../prostate/planA/GDC_prostate_tissue/split80train/section_3/rfe/selected_features.json"
26+
selected_feature_file_2 = "../prostate/planA/GSE269244/split80train/section_3/rfe/selected_features.json"
27+
train_out_path = "../prostate/planA/joined/split80train/section_6"
28+
validate_out_path = "../prostate/planA/joined/split20test/section_6"
29+
df_train_file = "../prostate/champ_result/GDC_prostate_tissue_80/all_beta_normalized.csv"
30+
df_test_file = "../prostate/champ_result/GDC_prostate_tissue_20_test/all_beta_normalized.csv"
31+
df_train_file_2 = "../prostate/champ_result/GSE269244_80/all_beta_normalized.csv"
32+
df_test_file_2 = "../prostate/champ_result/GSE269244_20_test/all_beta_normalized.csv"
33+
training_param_file = "../prostate/training_param.json"
34+
35+
[preprocess.filtering]
36+
threshold_TCGA = 0.36
37+
threshold_GEO = 0.21
38+
39+
[preprocess.dbeta]
40+
delta_beta_avg_feature_numTCGA = 373340
41+
NaN_dbeta_featureTCGA = []
42+
delta_beta_avg_feature_num_remove_NaNTCGA = 373340
43+
dmp_before_dropna_shape_featureTCGA = 286098
44+
dmp_after_dropna_shape_featureTCGA = 218741
45+
delta_beta_avg_feature_num_remove_NaN_join_dmpTCGA = 373340
46+
delta_beta_avg_feature_numGEO = 695602
47+
NaN_dbeta_featureGEO = []
48+
delta_beta_avg_feature_num_remove_NaNGEO = 695602
49+
dmp_before_dropna_shape_featureGEO = 188706
50+
dmp_after_dropna_shape_featureGEO = 136630
51+
delta_beta_avg_feature_num_remove_NaN_join_dmpGEO = 695602
52+
53+
[preprocess.filtering.hyper]
54+
avg_dbeta_lower_bound = 300
55+
avg_dbeta_upper_bound = 500
56+
57+
[feature_selection.rfe.hyper]
58+
train_out_path = "../prostate/planA/GDC_prostate_tissue/split80train/section_3/rfe"
59+
dbeta_info_file = "../prostate/planA/joined/section_5/dbeta_TSS_threshold_joined_consensus.csv"
60+
training_param_file = "../prostate/training_param.json"
61+
62+
[feature_selection.sfs.hyper]
63+
train_out_path = "../prostate/planA/GDC_prostate_tissue/split80train/section_3/sfs"
64+
dbeta_info_file = "../prostate/planA/joined/section_5/dbeta_TSS_threshold_joined_consensus.csv"
65+
training_param_file = "../prostate/training_param.json"
66+
67+
[feature_selection_2.rfe.hyper]
68+
train_out_path = "../prostate/planA/GSE269244/split80train/section_3/rfe"
69+
dbeta_info_file = "../prostate/planA/joined/section_5/dbeta_TSS_threshold_joined_consensus.csv"
70+
training_param_file = "../prostate/training_param.json"
71+
72+
[feature_selection_2.sfs.hyper]
73+
train_out_path = "../prostate/planA/GSE269244/split80train/section_3/sfs"
74+
dbeta_info_file = "../prostate/planA/joined/section_5/dbeta_TSS_threshold_joined_consensus.csv"
75+
training_param_file = "../prostate/training_param.json"

0 commit comments

Comments
 (0)