forked from transmart/tranSMART-ETL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathSNP.properties
276 lines (219 loc) · 11 KB
/
SNP.properties
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
###########################################################################
# tranSMART - translational medicine data mart
#
# Copyright 2008-2012 Janssen Research & Development, LLC.
#
# This product includes software developed at Janssen Research & Development, LLC.
#
# This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License
# as published by the Free Software * Foundation, either version 3 of the License, or (at your option) any later version, along with the following terms:
# 1. You may convey a work based on this program in accordance with section 5, provided that you retain the above notices.
# 2. You may convey verbatim copies of this program code as you receive it, in any medium, provided that you retain the above notices.
#
# This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS * FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along with this program. If not, see <http://www.gnu.org/licenses/>.
#
#
##########################################################################
# **********************************************************************
# PLINK program's absolute path and is used to transform PLINK files
# **********************************************************************
plink=C:/software/plink/plink.exe
cut=C:/Program Files (x86)/GnuWin32/bin/cut.exe
# *********************************************************************************
# this is the genotyping data file from Affymetrix GenomeWideSNP_6 platform
# and usually generated by Affymetrix's APT (apt-probeset-genotype program)
# *********************************************************************************
genotype_source_file=C:/SNP/CCLE/GT/birdseed-v2.calls.txt
# *********************************************************************************
# this parameter define the size of buffer for holding the number of processed
# probes
# *********************************************************************************
buffer_size=1000
# *********************************************************************************
# this is copy number data files from Affymetrix GenomeWideSNP_6 platform,
# usually generated by Affymetrix's CNAT (apt-copynumber-workflow program),
# and each sample has one *.CN5.CNCHP.txt file
# *********************************************************************************
copy_number_source_directory=C:/SNP/CCLE/CN
copy_number_file_pattern=.CN5.CNCHP.txt
# ***********************************************************
# Study name is used for generating output filenames
# ***********************************************************
study_name=CCLE
# **************************************************
# A directory used for storing output files
# **************************************************
output_directory=C:/SNP/CCLE/output1
# **************************************************
# output filename for CN probe's copy number data
# **************************************************
cn_copy_number_output=CCLE_CN.cn
# *********************************************************************************
# Columns in Affymetrix GenomeWideSNP_6's CopyNumber files are:
# 0. ProbeSetName
# 1. Chromosome
# 2. Position
# 3. CNState
# 4. Log2Ratio
# 5. SmoothSignal
# 6. LOH Allele Difference
#
# The first three columns are picked up by default, the value of parameter is used as
# CopyNumber, can be set as the column name, such as SmoothSignal (Millenium's choice),
# CNState (default), or column number (starting with 0), such as 3 (CNState),
# 5 (SmoothSignal)
# *********************************************************************************
copy_number_coulmn=SmoothSignal
#copy_number_coulmn=5
# **************************************************************************************
# parameters for loading SNP related
#
# GPL13314: Illumina HumanOmni2.5-Quad BeadChip;
# GPL6984: Illumina Human1M-Duov3 DNA Analysis BeadChip (Human1M-Duov3_B)
# GPL2004: [Mapping50K_Hind240] Affymetrix Human Mapping 50K Hind240 SNP Array
# GPL2005: [Mapping50K_Xba240] Affymetrix Human Mapping 50K Xba240 SNP Array
# GPL3718: [Mapping250K_Nsp] Affymetrix Mapping 250K Nsp SNP Array
# GPL3720: [Mapping250K_Sty] Affymetrix Mapping 250K Sty SNP Array
# GPL6801: [GenomeWideSNP_6] Affymetrix Genome-Wide Human SNP 6.0 Array
# ***************************************************************************************
#**************************************************************
# parameters for CCLE
#
# the following 4 parameters are used for DE_GPL_INFO:
#**************************************************************
organism=Homo sapiens
marker_type=SNP
platform=GenomeWideSNP_6
title=Affymetrix Genome-Wide Human SNP 6.0 Array
#**************************************************************
# used for deapp.de_subject_sample_mapping's platform
#**************************************************************
platform_type=SNP
#***************************************************************
# parameters used for identifying subject-sample mapping file
#***************************************************************
#source_directory=C:/Customers/MPI/CCLE
#subject_sample_mapping=CCLE_SNP_Subject_Sample_Mapping.txt
source_directory=C:/Customers/Pfizer
subject_sample_mapping=cards_subject_sample_map.txt
#**************************************************************
# used to check/add patient_num in PATIENT_DIMENSION
#**************************************************************
source_system_prefix=CARDS
#********************************************************************************
# parameters for creating i2b2 SNP nodes:
# snp_node = snp_base_node + "\" + platform_name
# and used in tables: I2B2, I2B2_SECURE, CONCEPT_DIMENSION and CONCEPT_COUNTS
#********************************************************************************
#platform_name=GenomeWideSNP_6
platform_name=Perlegen_600k
snp_base_node=/Bio Bank/CARDS_Genotyping_Study/Biomarker Data/Genotyping
#****************************************
# parameters for GSE14860
#****************************************
# RICERCA: \\sanofi\\Oncology:Empirical\\BSI-201_Ricerca_cell_line_sensitivity_screening\\Data\\SNP_Profiling
# GSE14860: \\sanofi\\Oncology:pan-PI3K inhibition\\Endometrial_Cancer_Salvesen_GSE14860\\Data\\SNP_Profiling
#source_system_prefix=GSE14860
#study_name=GSE14860
#source_directory=C:/Customers/Sanofi/SNP/GSE14860
#subject_sample_mapping=GSE14860_subject_sample_mapping.txt
#platform_id=GPL2004_2005
#platform_name=Affymetrix Human Mapping 50K Hind240 and 50K Xba240 SNP Array
#snp_base_node=/sanofi/Oncology:pan-PI3K inhibition/Endometrial_Cancer_Salvesen_GSE14860/Data/SNP profiling
#****************************************
# parameters for RICERCA
#****************************************
#source_system_prefix=RICERCACL
#study_name=RICERCACL
#source_directory=C:/Customers/MPI/Ricerca
#subject_sample_mapping=RICERCACL_SNP_Subject_Sample_Mapping.txt
#platform_id=GPL3718_3720
#platform_name=Affymetrix Mapping 250K Nsp and Sty SNP Array
#snp_base_node=/Millennium Studies/MLN4924/Pre-Clinical Studies/Ricerca/Biomarker Data
#****************************************
# parameters for GKS300
#****************************************
#source_system_prefix=GSKCL
#study_name=GSKCL
#source_directory=C:/Customers/MPI/GSK300
#subject_sample_mapping=GSK300_SNP_Subject_Sample_Mapping.txt
#platform_id=GPL3718_3720
#platform_name=Affymetrix Mapping 250K Nsp and Sty SNP Array
#snp_base_node=/Public Studies/GSK 300/Biomarker Data
#****************************************
# parameters for Oncotest
#****************************************
#source_system_prefix=ONCOTEST_001
#study_name=ONCOTEST_001
#source_directory=C:/Customers/MPI/Oncotest
#subject_sample_mapping=Oncotest_tumor_cells_Subject_Sample_Mapping.txt
#subject_sample_mapping=Oncotest_cell_lines_Subject_Sample_Mapping.txt
#platform_id=GenomeWideSNP_6
#platform_name=Affymetrix Genome-Wide Human SNP Array 6.0
#snp_base_node=/Millennium Studies/MLN4924/Pre-Clinical Studies/Oncotest/Biomarker Data/Cell Lines
#snp_base_node=/Millennium Studies/MLN4924/Pre-Clinical Studies/Oncotest/Biomarker Data/Tumor Cells
# ************************************************************************************
# remap Copy Number file's sample id to patient number from patient_dimension
# ************************************************************************************
skip_reformat_copy_number=yes
# ************************************************************************************
# remap CN probe's Copy Number file's sample id to patient number from patient_dimension
# ************************************************************************************
skip_reformat_cn_copy_number=no
# ************************************************************************************
# remap genotyping file's sample id to patient number from patient_dimension
# ************************************************************************************
skip_reformat_genetype=yes
# ************************************************************************************
# whether to create PLINK *.fam file and data is queried from patient_dimension
# ************************************************************************************
skip_plink_fam=yes
# ************************************************************************************
# whether to create binary PLINK file and PLINK files for each chromosomes
# ************************************************************************************
skip_plink_file_creation=yes
# ***********************************
# loading flags for i2b2 metadata
# ***********************************
skip_i2b2=no
skip_i2b2_secure=no
skip_patient_dimension=no
skip_concept_dimension=no
skip_concept_counts=no
skip_observation_fact=no
skip_de_subject_sample_mapping=no
skip_de_gpl_info=no
#*******************************************
# loading flags for SEARCHAPP tables
#*******************************************
skip_search_keyword=yes
skip_search_keyword_term=yes
#*******************************************
# loading flags for SNP annotation tables
#*******************************************
skip_de_snp_info=no
skip_de_snp_probe=no
skip_snp_gene_map=no
skip_de_gpl_info=no
chromosome_prefix=chr
start_chr=1
end_chr=2
#end_chr=24
#********************************************************
# fine tuning SNP data loading to table level
#********************************************************
skip_snp_dataset=yes
skip_snp_probe_sorted_def=yes
skip_snp_subject_sorted_def=yes
skip_snp_copy_number=yes
skip_snp_calls_by_gsm=yes
skip_snp_data_by_patient=yes
skip_snp_data_by_probe=no
#*******************************************
# loading flags for BIOMART tables
#*******************************************
skip_bio_content=yes
skip_bio_content_reference=yes
skip_bio_content_repository=yes