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
339
340
341
342
343
344
345
346
347
348 | def consortiumToPublic(
syn,
processingDate,
genie_version,
releaseId,
databaseSynIdMappingDf,
publicReleaseCutOff=365,
):
cna_path = os.path.join(database_to_staging.GENIE_RELEASE_DIR, "data_CNA.txt")
clinical_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR, "data_clinical.txt"
)
clinical_sample_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR,
"data_clinical_sample.txt",
)
clinicl_patient_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR,
"data_clinical_patient.txt",
)
data_gene_panel_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR, "data_gene_matrix.txt"
)
mutations_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR,
"data_mutations_extended.txt",
)
seg_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR,
"data_cna_hg19.seg",
)
combined_bed_path = os.path.join(
database_to_staging.GENIE_RELEASE_DIR, "genie_combined.bed"
)
if not os.path.exists(database_to_staging.GENIE_RELEASE_DIR):
os.mkdir(database_to_staging.GENIE_RELEASE_DIR)
if not os.path.exists(database_to_staging.CASE_LIST_PATH):
os.mkdir(database_to_staging.CASE_LIST_PATH)
# public release preview
public_release_preview = databaseSynIdMappingDf["Id"][
databaseSynIdMappingDf["Database"] == "public"
].values[0]
public_release_preview_caselist = database_to_staging.search_or_create_folder(
syn=syn, parentid=public_release_preview, folder_name="case_lists"
)
#######################################################################
# Sponsored projects filter
#######################################################################
# if before release date -> go into staging consortium
# if after date -> go into public
# sponsoredReleaseDate = syn.tableQuery('SELECT * FROM syn8545108')
# sponsoredReleaseDateDf = sponsoredReleaseDate.asDataFrame()
# sponsoredProjectSamples = syn.tableQuery('SELECT * FROM syn8545106')
# sponsoredProjectSamplesDf = sponsoredProjectSamples.asDataFrame()
# sponsoredProjectsDf = sponsoredProjectSamplesDf.merge(
# sponsoredReleaseDateDf, left_on="sponsoredProject",
# right_on="sponsoredProjects")
# dates = sponsoredProjectsDf['releaseDate'].apply(
# lambda date: datetime.datetime.strptime(date, '%b-%Y'))
# publicReleaseSamples = sponsoredProjectsDf['genieSampleId'][
# dates < processingDate]
#######################################################################
# SEQ_DATE filter
# Jun-2015, given processing date (today) -> public release
# (processing date - Jun-2015 > 12 months)
consortiumReleaseWalk = synapseutils.walk(syn, releaseId)
consortiumRelease = next(consortiumReleaseWalk)
for filename, synid in consortiumRelease[2]:
if filename == "data_clinical.txt":
clinical = syn.get(synid, followLink=True)
elif filename == "data_gene_matrix.txt":
gene_matrix = syn.get(synid, followLink=True)
elif filename == "assay_information.txt":
assay_info = syn.get(synid, followLink=True)
clinicalDf = pd.read_csv(clinical.path, sep="\t", comment="#")
gene_matrixdf = pd.read_csv(gene_matrix.path, sep="\t")
removeForPublicSamples = process_functions.seqDateFilter(
clinicalDf, processingDate, publicReleaseCutOff
)
logger.info("SAMPLE CLASS FILTER")
remove_sc_samples = database_to_staging.sample_class_filter(clinical_df=clinicalDf)
removeForPublicSamples = list(set(removeForPublicSamples).union(remove_sc_samples))
# comment back in when public release filter back on
# publicReleaseSamples = publicReleaseSamples.append(keepForPublicSamples)
# Make sure all null oncotree codes are removed
clinicalDf = clinicalDf[~clinicalDf["ONCOTREE_CODE"].isnull()]
publicReleaseSamples = clinicalDf.SAMPLE_ID[
~clinicalDf.SAMPLE_ID.isin(removeForPublicSamples)
]
existing_seq_dates = clinicalDf.SEQ_DATE[
clinicalDf.SAMPLE_ID.isin(publicReleaseSamples)
]
logger.info(
"SEQ_DATES for public release: "
+ ", ".join(set(existing_seq_dates.astype(str)))
)
# Clinical release scope filter
clinical_tier_release_scope_synid = databaseSynIdMappingDf["Id"][
databaseSynIdMappingDf["Database"] == "clinical_tier_release_scope"
][0]
publicRelease = extract.get_syntabledf(
syn=syn,
query_string=f"SELECT * FROM {clinical_tier_release_scope_synid} where releaseScope = 'public'",
)
allClin = clinicalDf[clinicalDf["SAMPLE_ID"].isin(publicReleaseSamples)]
allClin.to_csv(clinical_path, sep="\t", index=False)
gene_matrixdf = gene_matrixdf[gene_matrixdf["SAMPLE_ID"].isin(publicReleaseSamples)]
gene_matrixdf.to_csv(data_gene_panel_path, sep="\t", index=False)
load.store_file(
syn=syn,
filepath=data_gene_panel_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_gene_matrix.txt",
)
load.store_file(
syn=syn,
filepath=clinical_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_clinical.txt",
)
create_case_lists.main(
clinical_path,
assay_info.path,
database_to_staging.CASE_LIST_PATH,
"genie_public",
)
caseListFiles = os.listdir(database_to_staging.CASE_LIST_PATH)
caseListEntities = []
for casePath in caseListFiles:
casePath = os.path.join(database_to_staging.CASE_LIST_PATH, casePath)
caseListEntities.append(
load.store_file(
syn=syn,
filepath=casePath,
parentid=public_release_preview_caselist,
version_comment=genie_version,
)
)
# Grab mapping table to fill in clinical headers
clinical_code_to_desc_map_synid = databaseSynIdMappingDf["Id"][
databaseSynIdMappingDf["Database"] == "clinical_code_to_desc_map"
][0]
mapping = extract.get_syntabledf(
syn=syn, query_string=f"SELECT * FROM {clinical_code_to_desc_map_synid}"
)
genePanelEntities = []
for entName, entId in consortiumRelease[2]:
is_deprecated_file = entName in ["data_fusions.txt"]
# skip files to convert
if (
entName.startswith("data_linear")
or "meta_" in entName
or entName.endswith(".html")
or entName
in [
"data_clinical_sample.txt",
"data_gene_matrix.txt",
"data_clinical_patient.txt",
"data_guide.pdf",
"release_notes.pdf",
"samples_to_retract.csv",
"non_somatic.csv",
"snv_as_dnp.csv",
"snv_as_onp.csv",
"duplicated_variants.csv",
]
or is_deprecated_file
):
# data_gene_matrix was processed above because it had to be
# used for generating caselists
continue
if entName == "data_clinical.txt":
patientCols = publicRelease["fieldName"][
publicRelease["level"] == "patient"
].tolist()
sampleCols = ["PATIENT_ID"]
sampleCols.extend(
publicRelease["fieldName"][publicRelease["level"] == "sample"].tolist()
)
# clinicalDf is defined on line 127
clinicalDf = clinicalDf[clinicalDf["SAMPLE_ID"].isin(publicReleaseSamples)]
# Delete columns that are private scope
# for private in privateRelease:
# del clinicalDf[private]
process_functions.addClinicalHeaders(
clinicalDf,
mapping,
patientCols,
sampleCols,
clinical_sample_path,
clinicl_patient_path,
)
load.store_file(
syn=syn,
filepath=clinical_sample_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_clinical_sample.txt",
)
load.store_file(
syn=syn,
filepath=clinicl_patient_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_clinical_patient.txt",
)
elif "mutation" in entName:
mutation = syn.get(entId, followLink=True)
mutationDf = pd.read_csv(mutation.path, sep="\t", comment="#")
# mutationDf = commonVariantFilter(mutationDf)
mutationDf["FILTER"] = "PASS"
mutationDf = mutationDf[
mutationDf["Tumor_Sample_Barcode"].isin(publicReleaseSamples)
]
text = process_functions.removeFloat(mutationDf)
with open(mutations_path, "w") as f:
f.write(text)
load.store_file(
syn=syn,
filepath=mutations_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_mutations_extended.txt",
)
elif "CNA" in entName:
cna = syn.get(entId, followLink=True)
cnaDf = pd.read_csv(cna.path, sep="\t")
cna_columns = pd.concat([publicReleaseSamples, pd.Series("Hugo_Symbol")])
# parse out the CNA columns to keep
cnaDf = cnaDf[cnaDf.columns[cnaDf.columns.isin(cna_columns)]]
text = process_functions.removeFloat(cnaDf)
text = (
text.replace("\t\t", "\tNA\t")
.replace("\t\t", "\tNA\t")
.replace("\t\n", "\tNA\n")
)
with open(cna_path, "w") as cnaFile:
cnaFile.write(text)
load.store_file(
syn=syn,
filepath=cna_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_CNA.txt",
)
elif entName.endswith(".seg"):
seg = syn.get(entId, followLink=True)
segDf = pd.read_csv(seg.path, sep="\t")
segDf = segDf[segDf["ID"].isin(publicReleaseSamples)]
text = process_functions.removeFloat(segDf)
with open(seg_path, "w") as segFile:
segFile.write(text)
load.store_file(
syn=syn,
filepath=seg_path,
parentid=public_release_preview,
version_comment=genie_version,
name="data_cna_hg19.seg",
)
elif entName == "genomic_information.txt":
bed = syn.get(entId, followLink=True)
bedDf = pd.read_csv(bed.path, sep="\t")
bedDf = bedDf[bedDf.SEQ_ASSAY_ID.isin(allClin.SEQ_ASSAY_ID)]
bedDf.to_csv(combined_bed_path, sep="\t", index=False)
load.store_file(
syn=syn,
filepath=combined_bed_path,
parentid=public_release_preview,
version_comment=genie_version,
name="genomic_information.txt",
)
else:
ent = syn.get(entId, followLink=True, downloadFile=False)
copiedId = synapseutils.copy(
syn,
ent,
public_release_preview,
version=ent.versionNumber,
updateExisting=True,
setProvenance=None,
skipCopyAnnotations=True,
)
copiedEnt = syn.get(copiedId[ent.id], downloadFile=False)
# Set version comment
copiedEnt.versionComment = genie_version
copiedEnt = syn.store(copiedEnt, forceVersion=False)
# There was a time when gene panel files had to be renamed
# with an appended genie version. But... GEN-76
# No longer appending genie verison to release files
# So just need to track gene panel entities
if entName.startswith("data_gene_panel"):
genePanelEntities.append(copiedEnt)
return caseListEntities, genePanelEntities
|