KIDS25-Team11/CAB empty dataframes.R at main · stjude-biohackathon/KIDS25-Team11 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
# CAB Epigenetics - CHIPSEQ, CutRUN, CutTag
epigenetics_chipseq_df <- data.frame(
  Type = character(),
  ID = character(),
  Group = character(),
  PkCallerUser = character(),
  INPUTUser = character(),
  LabID = character(),
  Species = character(),
  SRM_Order = character(),
  Description = character(),
  Project = character(),
  stringsAsFactors = FALSE
)

# CAB Epigenetics - ATACSEQ
epigenetics_atacseq_df <- data.frame(
  ID = character(),
  Group = character(),
  LabID = character(),
  Species = character(),
  SRM_Order = character(),
  Description = character(),
  Project = character(),
  stringsAsFactors = FALSE
)

# CAB Epigenetics - WGBS
epigenetics_wgbs_df <- data.frame(
  ID = character(),
  Group = character(),
  LabID = character(),
  Species = character(),
  SRM_Order = character(),
  Description = character(),
  Project = character(),
  stringsAsFactors = FALSE
)

# CAB Epigenetics - DiffPeak
epigenetics_diffpeak_df <- data.frame(
  ID = character(),
  LabID = character(),
  Project = character(),
  Group_Diff = character(),
  Group_Diff2 = character(),
  Target = character(),
  Control = character(),
  stringsAsFactors = FALSE
)

# CAB Epigenetics - HiC, HiCHIP, PLACSeq, CaptureC
epigenetics_hic_df <- data.frame(
  ID = character(),
  Group = character(),
  LabID = character(),
  Species = character(),
  Description = character(),
  Project = character(),
  Protocol_Enzyme = character(),
  stringsAsFactors = FALSE
)

# CAB Epigenetics - MethylationArray
epigenetics_methylation_df <- data.frame(
  Group = character(),
  LabID = character(),
  SRM_Order = character(),
  Project = character(),
  Sample_Name = character(),
  Sample_Type = character(),
  Sentrix_ID = character(),
  Array = character(),
  File_Location = character(),
  SJ_Tissue_Bank = character(),
  Sample_SJUID = character(),
  stringsAsFactors = FALSE
)

# CAB Transcriptomics - one variable
transcriptomics_one_var_df <- data.frame(
  LabID = character(),
  Species = character(),
  SRM_sample_number = character(),
  Genotype = character(),
  Hartwell_Center_SRM_order = character(),
  PDX = character(),
  Comparisons = character(),
  stringsAsFactors = FALSE
)

# CAB Transcriptomics - paired design
transcriptomics_paired_df <- data.frame(
  LabID = character(),
  Species = character(),
    SRM_sample_number = character(),
    Hartwell_Center_SRM_order = character(),
    PDX = character(),
    Comparisons = character(),
  Subject_ID = character(),
  Treatment = character(),
  stringsAsFactors = FALSE
)

# CAB Transcriptomics - multiple-Batch
transcriptomics_multi_batch_df <- data.frame(
  LabID = character(),
  Species = character(),
    SRM_sample_number = character(),
    Genotype = character(),
    Hartwell_Center_SRM_order = character(),
    PDX = character(),
    Comparisons = character(),
  Batch = character(),
  stringsAsFactors = FALSE
)

# CAB Transcriptomics - multi-factor
transcriptomics_multi_factor_df <- data.frame(
  LabID = character(),
  Species = character(),
    SRM_sample_number = character(),
    Genotype = character(),
    Hartwell_Center_SRM_order = character(),
    PDX = character(),
    Comparisons = character(),
  Condition = character(),
  stringsAsFactors = FALSE
)

# CAB Transcriptomics - longitudinal study
transcriptomics_longitudinal_df <- data.frame(
  LabID = character(),
  Species = character(),
    SRM_sample_number = character(),
    Genotype = character(),
    Hartwell_Center_SRM_order = character(),
    PDX = character(),
    Comparisons = character(),
  Subject_ID = character(),
  Hours = character(),
  stringsAsFactors = FALSE
)

# Print structure of each dataframe
cat("CHIPSEQ/CutRUN/CutTag columns:\n")
print(names(epigenetics_chipseq_df))

cat("\nATACSEQ columns:\n")
print(names(epigenetics_atacseq_df))

cat("\nWGBS columns:\n")
print(names(epigenetics_wgbs_df))

cat("\nDiffPeak columns:\n")
print(names(epigenetics_diffpeak_df))

cat("\nHiC/HiCHIP/PLACSeq/CaptureC columns:\n")
print(names(epigenetics_hic_df))

cat("\nMethylationArray columns:\n")
print(names(epigenetics_methylation_df))

cat("\nTranscriptomics (one variable) columns:\n")
print(names(transcriptomics_one_var_df))

cat("\nTranscriptomics (paired design) columns:\n")
print(names(transcriptomics_paired_df))

cat("\nTranscriptomics (multiple-Batch) columns:\n")
print(names(transcriptomics_multi_batch_df))

cat("\nTranscriptomics (multi-factor) columns:\n")
print(names(transcriptomics_multi_factor_df))

cat("\nTranscriptomics (longitudinal study) columns:\n")
print(names(transcriptomics_longitudinal_df))