-
Notifications
You must be signed in to change notification settings - Fork 0
/
data_load.R
339 lines (259 loc) · 12.3 KB
/
data_load.R
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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
# references:
# https://uw-gac.github.io/primed_example_notebooks/terra_workspace.nb.html
# https://bioconductor.org/packages/release/bioc/vignettes/AnVIL/inst/doc/Introduction.html#using-av-to-work-with-anvil-tables-and-data
#
# goals:
# - load .tsv files from workspace to tibbles
# - modify the tibbles and make data tables from them in workspace
# - attempt to do the same in a different workspace
# - if possible, load all example files in example workspaces
# get the latest version of AnVIL from github
# remotes::install_github("Bioconductor/AnVIL")
library(AnVIL)
library(tidyverse)
project <- avworkspace_namespace()
workspace <- avworkspace_name()
bucket <- avbucket()
# list files in workspace (bucket), then copy to compute node
#system(paste0("gsutil ls ",bucket), intern=TRUE)
gsutil_ls(bucket)
## participant table
participant_file_name <- "demo notebook RC 1 GRU - participant.tsv"
participant_file_path <- file.path(bucket, participant_file_name)
gsutil_cp(participant_file_path, "./")
participant_table <- read_tsv(participant_file_name)
# rename the id column and load the tibble into a workspace data table
modified_participant_table <-
participant_table %>%
rename("entity:participant_id" = participant_id) %>%
avtable_import()
## biosample table
biosample_file_name <- "demo notebook RC 1 GRU - biosample.tsv"
biosample_file_path <- file.path(bucket, biosample_file_name)
gsutil_cp(biosample_file_path, "./")
biosample_table <- read_tsv(biosample_file_name)
# rename the id column and load the tibble into a workspace data table
modified_biosample_table <-
biosample_table %>%
rename("entity:biosample_id" = biosample_id) %>%
avtable_import()
## phenotype table
phenotype_file_name <- "demo notebook RC 1 GRU - phenotype.tsv"
phenotype_file_path <- file.path(bucket, phenotype_file_name)
gsutil_cp(phenotype_file_path, "./")
phenotype_table <- read_tsv(phenotype_file_name)
# rename the id column and load the tibble into a workspace data table
# NOTE: this isn't really how we'd want to make phenotype row IDs...
modified_phenotypoe_table <-
phenotype_table %>%
mutate("entity:phenotype_id" =
paste0(participant_id, seq(1:length(phenotype_table))),
.before = "participant_id") %>%
avtable_import()
## experiment table
experiment_file_name <- "demo notebook RC 1 GRU - experiment.tsv"
experiment_file_path <- file.path(bucket, experiment_file_name)
gsutil_cp(experiment_file_path, "./")
experiment_table <- read_tsv(experiment_file_name)
# rename the id column and load the tibble into a workspace data table
modified_experiment_table <-
experiment_table %>%
rename("entity:experiment_id" = experiment_id) %>%
avtable_import()
## aligned_short_reads table
aligned_short_reads_file_name <- "demo notebook RC 1 GRU - aligned_short_reads.tsv"
aligned_short_reads_file_path <- file.path(bucket, aligned_short_reads_file_name)
gsutil_cp(aligned_short_reads_file_path, "./")
aligned_short_reads_table <- read_tsv(aligned_short_reads_file_name)
# rename the id column and load the tibble into a workspace data table
modified_aligned_short_reads_table <-
aligned_short_reads_table %>%
mutate("entity:aligned_short_reads_id" = "a_made_up_md5_0123", .before = "experiment_id") %>%
avtable_import()
# Copy this script into the bucket
gsutil_cp("./data_load.R", bucket)
# can I do the same thing for a different bucket from this workspace?
project <- avworkspace_namespace()
workspace <- "GREGoR_DCC_RC2_GRU_demo"
bucket <- avbucket(project, name = workspace)
gsutil_ls(bucket)
## participant table
participant_file_name <- "demo notebook RC 2 GRU - participant.tsv"
participant_file_path <- file.path(bucket, participant_file_name)
gsutil_cp(participant_file_path, "./")
participant_table <- read_tsv(participant_file_name)
# rename the id column and load the tibble into a workspace data table
modified_participant_table <-
participant_table %>%
rename("entity:participant_id" = participant_id) %>%
avtable_import(namespace = project, name = workspace)
# checking at https://app.terra.bio/#workspaces/GREGoR-ben/GREGoR_DCC_RC2_GRU_demo/data - it worked!
## biosample table
biosample_file_name <- "demo notebook RC 2 GRU - biosample.tsv"
biosample_file_path <- file.path(bucket, biosample_file_name)
gsutil_cp(biosample_file_path, "./")
biosample_table <- read_tsv(biosample_file_name)
# rename the id column and load the tibble into a workspace data table
modified_biosample_table <-
biosample_table %>%
rename("entity:biosample_id" = biosample_id) %>%
avtable_import(namespace = project, name = workspace)
## phenotype table
phenotype_file_name <- "demo notebook RC 2 GRU - phenotype.tsv"
phenotype_file_path <- file.path(bucket, phenotype_file_name)
gsutil_cp(phenotype_file_path, "./")
phenotype_table <- read_tsv(phenotype_file_name)
# rename the id column and load the tibble into a workspace data table
# NOTE: this isn't really how we'd want to make phenotype row IDs...
modified_phenotype_table <-
phenotype_table %>%
mutate("entity:phenotype_id" =
paste0(participant_id, seq(1:length(phenotype_table))),
.before = "participant_id") %>%
avtable_import(namespace = project, name = workspace)
## experiment table
experiment_file_name <- "demo notebook RC 2 GRU - experiment.tsv"
experiment_file_path <- file.path(bucket, experiment_file_name)
gsutil_cp(experiment_file_path, "./")
experiment_table <- read_tsv(experiment_file_name)
# rename the id column and load the tibble into a workspace data table
modified_experiment_table <-
experiment_table %>%
rename("entity:experiment_id" = experiment_id) %>%
avtable_import(namespace = project, name = workspace)
## aligned_short_reads table
aligned_short_reads_file_name <- "demo notebook RC 2 GRU - aligned_short_reads.tsv"
aligned_short_reads_file_path <- file.path(bucket, aligned_short_reads_file_name)
gsutil_cp(aligned_short_reads_file_path, "./")
aligned_short_reads_table <- read_tsv(aligned_short_reads_file_name)
# rename the id column and load the tibble into a workspace data table
modified_aligned_short_reads_table <-
aligned_short_reads_table %>%
mutate("entity:aligned_short_reads_id" = "a_made_up_md5_0456", .before = "experiment_id") %>%
avtable_import(namespace = project, name = workspace)
# Copy this script into the bucket
gsutil_cp("./data_load.R", bucket)
## do again for HMB data from RC 1:
# can I do the same thing for a different bucket from this workspace?
project <- avworkspace_namespace()
workspace <- "GREGoR_DCC_RC1_HMB_demo"
bucket <- avbucket(project, name = workspace)
gsutil_ls(bucket)
## participant table
participant_file_name <- "demo notebook RC 1 HMB - participant.tsv"
participant_file_path <- file.path(bucket, participant_file_name)
gsutil_cp(participant_file_path, "./")
participant_table <- read_tsv(participant_file_name)
# rename the id column and load the tibble into a workspace data table
modified_participant_table <-
participant_table %>%
rename("entity:participant_id" = participant_id) %>%
avtable_import(namespace = project, name = workspace)
# checking at https://app.terra.bio/#workspaces/GREGoR-ben/GREGoR_DCC_RC2_GRU_demo/data - it worked!
## biosample table
biosample_file_name <- "demo notebook RC 1 HMB - biosample.tsv"
biosample_file_path <- file.path(bucket, biosample_file_name)
gsutil_cp(biosample_file_path, "./")
biosample_table <- read_tsv(biosample_file_name)
# rename the id column and load the tibble into a workspace data table
modified_biosample_table <-
biosample_table %>%
rename("entity:biosample_id" = biosample_id) %>%
avtable_import(namespace = project, name = workspace)
## phenotype table
phenotype_file_name <- "demo notebook RC 1 HMB - phenotype.tsv"
phenotype_file_path <- file.path(bucket, phenotype_file_name)
gsutil_cp(phenotype_file_path, "./")
phenotype_table <- read_tsv(phenotype_file_name)
# rename the id column and load the tibble into a workspace data table
# NOTE: this isn't really how we'd want to make phenotype row IDs...
modified_phenotype_table <-
phenotype_table %>%
mutate("entity:phenotype_id" =
paste0(participant_id, seq(1:length(phenotype_table))),
.before = "participant_id") %>%
avtable_import(namespace = project, name = workspace)
## experiment table
experiment_file_name <- "demo notebook RC 1 HMB - experiment.tsv"
experiment_file_path <- file.path(bucket, experiment_file_name)
gsutil_cp(experiment_file_path, "./")
experiment_table <- read_tsv(experiment_file_name)
# rename the id column and load the tibble into a workspace data table
modified_experiment_table <-
experiment_table %>%
rename("entity:experiment_id" = experiment_id) %>%
avtable_import(namespace = project, name = workspace)
## aligned_short_reads table
aligned_short_reads_file_name <- "demo notebook RC 1 HMB - aligned_short_reads.tsv"
aligned_short_reads_file_path <- file.path(bucket, aligned_short_reads_file_name)
gsutil_cp(aligned_short_reads_file_path, "./")
aligned_short_reads_table <- read_tsv(aligned_short_reads_file_name)
# rename the id column and load the tibble into a workspace data table
modified_aligned_short_reads_table <-
aligned_short_reads_table %>%
mutate("entity:aligned_short_reads_id" = "a_made_up_md5_0789", .before = "experiment_id") %>%
avtable_import(namespace = project, name = workspace)
# Copy this script into the bucket
gsutil_cp("./data_load.R", bucket)
## do again for HMB data from RC 2:
# can I do the same thing for a different bucket from this workspace?
project <- avworkspace_namespace()
workspace <- "GREGoR_DCC_RC2_HMB_demo"
bucket <- avbucket(project, name = workspace)
gsutil_ls(bucket)
## participant table
participant_file_name <- "demo notebook RC 2 HMB - participant.tsv"
participant_file_path <- file.path(bucket, participant_file_name)
gsutil_cp(participant_file_path, "./")
participant_table <- read_tsv(participant_file_name)
# rename the id column and load the tibble into a workspace data table
modified_participant_table <-
participant_table %>%
rename("entity:participant_id" = participant_id) %>%
avtable_import(namespace = project, name = workspace)
# checking at https://app.terra.bio/#workspaces/GREGoR-ben/GREGoR_DCC_RC2_GRU_demo/data - it worked!
## biosample table
biosample_file_name <- "demo notebook RC 2 HMB - biosample.tsv"
biosample_file_path <- file.path(bucket, biosample_file_name)
gsutil_cp(biosample_file_path, "./")
biosample_table <- read_tsv(biosample_file_name)
# rename the id column and load the tibble into a workspace data table
modified_biosample_table <-
biosample_table %>%
rename("entity:biosample_id" = biosample_id) %>%
avtable_import(namespace = project, name = workspace)
## phenotype table
phenotype_file_name <- "demo notebook RC 2 HMB - phenotype.tsv"
phenotype_file_path <- file.path(bucket, phenotype_file_name)
gsutil_cp(phenotype_file_path, "./")
phenotype_table <- read_tsv(phenotype_file_name)
# rename the id column and load the tibble into a workspace data table
# NOTE: this isn't really how we'd want to make phenotype row IDs...
modified_phenotype_table <-
phenotype_table %>%
mutate("entity:phenotype_id" =
paste0(participant_id, seq(1:length(phenotype_table))),
.before = "participant_id") %>%
avtable_import(namespace = project, name = workspace)
## experiment table
experiment_file_name <- "demo notebook RC 2 HMB - experiment.tsv"
experiment_file_path <- file.path(bucket, experiment_file_name)
gsutil_cp(experiment_file_path, "./")
experiment_table <- read_tsv(experiment_file_name)
# rename the id column and load the tibble into a workspace data table
modified_experiment_table <-
experiment_table %>%
rename("entity:experiment_id" = experiment_id) %>%
avtable_import(namespace = project, name = workspace)
## aligned_short_reads table
aligned_short_reads_file_name <- "demo notebook RC 2 HMB - aligned_short_reads.tsv"
aligned_short_reads_file_path <- file.path(bucket, aligned_short_reads_file_name)
gsutil_cp(aligned_short_reads_file_path, "./")
aligned_short_reads_table <- read_tsv(aligned_short_reads_file_name)
# rename the id column and load the tibble into a workspace data table
modified_aligned_short_reads_table <-
aligned_short_reads_table %>%
mutate("entity:aligned_short_reads_id" = "a_made_up_md5_1011", .before = "experiment_id") %>%
avtable_import(namespace = project, name = workspace)
# Copy this script into the bucket
gsutil_cp("./data_load.R", bucket)