-
Notifications
You must be signed in to change notification settings - Fork 4
/
pgstoolkit.config
executable file
·331 lines (331 loc) · 25 KB
/
pgstoolkit.config
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
### CONFIGURATION FILE FOR PRSTOOLKIT ###
# Set the directory variables and parameters, the order doesn't matter.
#
# Note:
# - In addition to this configuration file, the SLURM settings of the main file (prstoolkit.sh) need to be manually configured as well.
# This includes the settings for mail events.
# - Precede your comments with a #-sign.
# - Don't end the directory variables with '/' (forward-slash)!
# - Please leave the "" if you would like to leave a parameter empty.
#
# =================================================================================================================================================================
# =----------------------------------------------------------- GENERAL -----------------------------------------------------------=
# =================================================================================================================================================================
### REQUIRED: indicate what method to use [PLINK/RAPIDOPGS/PRSCS/PRSICE/LDPRED/MANUAL/NONE]
# PLINK -- use PLINK to calculate PGS from posterior SNP effect sizes
# RAPIDOPGS -- use RapidoPGS to calculate PGS from GWAS summary statistics without requiring an external LD panel
# PRSCS -- use PRS-CS to calculate PGS by inferring posterior SNP effect sizes under continuous shrinkage priors
# PRSICE -- use PRSice to calculate PGS, GWAS summary statistics will be LD-pruned using P-value thresholds
# LDPRED -- use LDpred to LD-correct GWAS summary statistics and calculate polygenic scores *not implemented yet*
# MANUAL -- use an in-house developed Rscript to calculate a polygenic score using a limited set of variants *not implemented yet*
# NONE -- don't perform PRS, instead only peform quality control (if QC is turned on)
PRSMETHOD="PLINK"
#
### REQUIRED: Name of the project.
PROJECTNAME="EXAMPLE_PGS"
#
### REQUIRED: Directory settings
# PROJECT_DIR -- path to where the main analysis directory resides
# OUTPUT_DIRNAME -- name of the output directory within the PROJECT_DIR directory
# SUBPROJECT_DIR_NAME -- name of (sub)project -- this will be used to create subfolders within the OUTPUTDIR
# MAIN_WORKDIR_NAME -- name of the working directory within the main analysis directory, used for temporary files
# LOG_DIRNAME -- name of the subdirectory of the PROJECT_DIR directory used for storing log files
PROJECT_DIR="/hpc/dhl_ec/USERNAME/projects/EXAMPLE_PGS"
OUTPUT_DIRNAME="PGS"
SUBPROJECT_DIR_NAME="NORMAL_EXAMPLE"
MAIN_WORKDIR_NAME="PGS_TMP_EXAMPLE"
LOG_DIRNAME="PGS_LOGS_EXAMPLE"
#
### REQUIRED: quality control settings
# QC -- indicate whether quality control should be applied according to the specs below [YES/NO]
# MAF -- minimum minor allele frequency to keep variants, e.g. "0.005"
# INFO -- minimum imputation quality score to keep variants, e.g. "0.3"
QC="NO"
MAF="0.01"
INFO="0.8"
#
### REQUIRED: keep the files temporarily generated by the PGSToolKit at the end of a job [TRUE/FALSE]
KEEP_TEMP_FILES="TRUE"
#
### REQUIRED: [TRUE/FALSE] whether to save a copy of this configuration file along with the results
SAVE_CONFIG="TRUE"
#
# =================================================================================================================================================================
# =----------------------------------------------------------- SOFTWARE -----------------------------------------------------------=
# =================================================================================================================================================================
# REQUIRED: path to where the software resides on the server
SOFTWARE="/hpc/local/Rocky8/dhl_ec/software"
#
RSCRIPT="/hpc/local/Rocky8/dhl_ec/software/R-4.3.1/bin/Rscript"
PYTHONPATH="/hpc/local/Rocky8/dhl_ec/software/mambaforge3/envs/pgstoolkit/python"
#
# REQUIRED: path to where PRSTOOLKIT resides on the server
PRSTOOLKITDIR="${SOFTWARE}/PGSToolKit"
PRSTOOLKITSCRIPTS="${PRSTOOLKITDIR}/SCRIPTS"
#
# REQUIRED: paths to PRS method executables
PRSICE2_R="${SOFTWARE}/PRSice_linux_235/PRSice.R"
PRSICE2_SH="${SOFTWARE}/PRSice_linux_235/PRSice_linux"
PLINK="${SOFTWARE}/plink2_linux_x86_64_20240105_alpha_5_10/plink2"
PRSCS="${SOFTWARE}/PRScs_04Jan2021/PRScs.py"
#
# =================================================================================================================================================================
# =----------------------------------------------------------- DATA -----------------------------------------------------------=
# =================================================================================================================================================================
### REQUIRED: base file format
# Different methods require different data. R stands for required, O for optional. _______________________________________________
# | RAPIDOPGS | PLINK | PRSCS | LDPRED | PRSICE |
# BASEDATA -- path to the base file containing the GWAS summary data, | R | R | R | | R |
# preferably .gz compressed but plain text should also work | | | | | |
# BF_BUILD -- build of the base file, e.g. "hg19" or "hg38" | R | | | | |
# BF_ID_COL -- name of the SNP ID column in the base file | R | R | R | | R |
# BF_CHR_COL -- name of the chromosome column in the base file | R | | | | R |
# BF_POS_COL -- name of the position column in the base file | R | | | | R |
# BF_EFFECT_COL -- name of the effect allele column in the base file | R | R | R | | R |
# BF_NON_EFFECT_COL -- name of the non-effect allele column in the base file | R | | R | | R |
# BF_STAT -- type of measure in the BF_STAT_COL, either "beta" or "or" | | | R | | R |
# *it is unknown whether RapidoPGS supports odds ratios | | | | | |
# BF_STAT_COL -- name of the beta/OR/effect size column in the base file | R | R | R | | R |
# BF_FRQ_COL -- name of the effect allele frequency column in the base file | R/O | | | | |
# *required for Rapido for quantative traits only | | | | | |
# BF_SE_COL -- name of the column of the standard error of the beta/OR value | R | | | | |
# BF_PVALUE_COL -- name of the column containing the P-values of the assocation test | R | | R | | R |
# BF_SBJ_COL -- name of the column containing the sample size for each variant | R/O | | | | |
# *for quantative traits using Rapido, provide either BF_SBJ_COL or BF_SAMPLE_SIZE | | | | | |
# BF_SAMPLE_SIZE -- sample size of the GWAS, *required for Rapido for quantitative traits only | R/O | | R | | |
# BF_TARGET_TYPE -- "cc" for a case control trait, "quant" for a quantative trait | R | | | | |
#
# Below an example on b37. This is the first part of a score created by Inouye et al.
# The variantIDs were modified to accomodate the genetic data used.
#
# CAD score; https://pubmed.ncbi.nlm.nih.gov/30309464/
# Inouye_bioRxiv_2018/metaGRS_hg19_20180205.txt.gz | head
# chr position rsid allele1 allele2 effect_allele beta
# 1 2245570 rs2843152 C G G -2.76009e-02
# 1 22132518 rs35465346 A G G 2.39340e-02
# 1 38386727 rs28470722 A G G -1.74935e-02
#
# Inouye_bioRxiv_2018/metaGRS_hg19_20180205.4PGSTK.txt.gz | head
# variantid rsid rsid_aegs chr position effect_allele other_allele beta P_ukbb
# 1:2245570 rs2843152 rs2843152 1 2245570 G C -2.76009e-02 1.34e-05
# 1:22132518 rs35465346 rs35465346 1 22132518 G A 2.39340e-02 5.91e-06
# 1:38386727 rs28470722 rs28470722 1 38386727 G A -1.74935e-02 7.37e-06
# 1:55496039 rs11206510 rs11206510 1 55496039 T C 2.93005e-02 3.68e-08
#
BASEDATA="/hpc/dhl_ec/svanderlaan/projects/polygenicscores/Inouye_bioRxiv_2018/metaGRS_hg19_20180205.4PGSTK.txt"
BF_BUILD="hg19"
BF_ID_COL="rsid_aegs"
BF_CHR_COL="chr"
BF_POS_COL="position"
BF_EFFECT_COL="effect_allele"
BF_NON_EFFECT_COL="other_allele"
BF_STAT="P"
BF_STAT_COL="beta"
BF_FRQ_COL=""
BF_SE_COL=""
BF_PVALUE_COL=""
BF_SBJ_COL=""
BF_SAMPLE_SIZE=""
BF_TARGET_TYPE=""
#
# REQUIRED: path to where the LD reference data resides.
# - RapidoPGS and PLINK: no reference data is used
# - PRS-CS: developer recommends to use either the reference material from the 1000 genomes project or from the UK biobank.
# You can find the links to these files at the GitHub page of PRS-CS: https://github.com/getian107/PRScs.
# For PRS-CS, please supply the path to the folder containing the map and .hdf5 files, e.g. "/data/ldblk_1kg_eur".
# - PRSice: reference data is optional, must be in .bed format https://www.cog-genomics.org/plink2/formats#bed.
# If no reference data is provided, PRSice will use the target genotype for LD calculation.
# For PRSice, please supply the path and prefix of the .bed files, e.g. "/data/1000Gp3v5.20130502.EUR.chr".
LDDATA=""
#
# REQUIRED: validation dataset name and format.
# The only accepted format for the validation data is .bgen: https://www.well.ox.ac.uk/~gav/bgen_format/.
# VALIDATIONDATA -- path to the directory containing the validation data, e.g.:
# b38: "/hpc/dhl_ec/data/DATA_QC_imputation_2023/aegscombo/_topmed_r3_f10_b38"
# b37: "/hpc/dhl_ec/data/DATA_COMBINED_EAGLE2_1000Gp3v5HRCr11"
# VALIDATIONPREFIX -- prefix of the validation files excluding the chr-number and extension, e.g.:
# b38: ""
# b37: "data.qc.1kgp3hrcr11.idfix.rsid.8bit.chr"
# VAL_REF_POS -- position of the reference allele in the .bgen file relative to the alternative allele, "ref-first" (default), "ref-last" or "ref-unknown",
# required for RapidoPGS, PLINK and PRS-CS
### b38 -- TOPMed imputed
VALIDATIONDATA="/hpc/dhl_ec/data/DATA_imputation_2023/aegscombo/_topmed_r3_f10_b38"
VALIDATIONPREFIX="data.topmed_r3_f10_b38.split_norm_af_filter.8bit.chr"
### b37 version -- deprecated
### VALIDATIONDATA="/hpc/dhl_ec/data/DATA_COMBINED_EAGLE2_1000Gp3v5HRCr11"
### VALIDATIONPREFIX="data.qc.1kgp3hrcr11.idfix.rsid.8bit.chr"
VAL_REF_POS="ref-first"
#
# REQUIRED: sample file
# Should be in this format: https://www.well.ox.ac.uk/~gav/qctool_v2/documentation/sample_file_formats.html.
# The sample file is only required for retrieving the sample IDs. Phenotypes and covariates are not required,
# except for by PRSice, which requires a single phenotype (PRSICE_PHENOTYPE) to fit the PGS to. Note that the samples in the sample file
# should have the same order as the samples in the bgen files, some methods (PRSice at least) will otherwise return an error.
# SAMPLE_FILE -- path to the sample file, e.g.:
# b38: "/hpc/dhl_ec/data/DATA_COMBINED_EAGLE2_1000Gp3v5HRCr11/data.qc.1kgp3hrcr11.idfix.rsid.8bit.sample"
# b37: "/hpc/dhl_ec/data/DATA_imputation_2023/aegscombo/_topmed_r3_f10_b38/data.topmed_r3_f10_b38.split_norm_af_filter.8bit.sample"
# This file looks like this - note that the 'sex' column can be empty:
ID_1 ID_2 missing sex
0 0 0 D
0 SampleID1 0 M
0 SampleID2 0 NA
0 SampleID3 0 F
#
# PRSICE_PHENOTYPE -- phenotype for which PRSice will compute a set of risk scores, this phenotype must be present in the sample file (PRSice only)
# and must have at least 2 distinct values
# PRSICE_PHENOTYPE_BINARY -- [TRUE/FALSE] indicating whether PRSICE_PHENOTYPE contains a binary phenotype
### b38
SAMPLE_FILE="/hpc/dhl_ec/data/DATA_QC_imputation_2023/aegscombo/_topmed_r3_f10_b38/data.topmed_r3_f10_b38.split_norm_af_filter.8bit.sample"
### b37 version -- deprecated
### SAMPLE_FILE="/hpc/dhl_ec/data/DATA_COMBINED_EAGLE2_1000Gp3v5HRCr11/data.qc.1kgp3hrcr11.idfix.rsid.8bit.sample"
PRSICE_PHENOTYPE=""
PRSICE_PHENOTYPE_BINARY=""
#
### OPTIONAL: stats file used for quality control
# Note that quality control can only be performed if the variant ID columns in the stats file (STATS_ID_COL) and in the base file (BF_ID_COL) match.
# The stats file must be .gz compressed, white space delimited and the first line must be the header.
# STATS_FILE -- path to the stats file
# STATS_ID_COL -- name of the stats file column containing the SNP IDs
# STATS_MAF_COL -- name of the stats file column containing the minor allele frequency
# STATS_INFO_COL -- name of the stats file column containing the imputation score
STATS_FILE=""
STATS_ID_COL=""
STATS_MAF_COL=""
STATS_INFO_COL=""
#
# =================================================================================================================================================================
# =----------------------------------------------------------- PERFORMANCE -----------------------------------------------------------=
# =================================================================================================================================================================
#
### REQUIRED: run-time [days-hours:minutes:seconds] dedicated to each sub-job
RUNTIME_QC="12:00:00"
RUNTIME_PLINKSCORE="12:00:00"
RUNTIME_PLINKSUM="12:00:00"
RUNTIME_RAPIDO="120:00:00"
RUNTIME_PRSICE="12:00:00"
RUNTIME_PRSCS="120:00:00"
RUNTIME_PRSCS_format="12:00:00"
#
### REQUIRED: memory [K|M|G|T] dedicated to each sub-job
MEMORY_QC="10G"
MEMORY_PLINKSCORE="40G"
MEMORY_PLINKSUM="40G"
MEMORY_RAPIDO="60G"
MEMORY_PRSICE="40G"
MEMORY_PRSCS="120G"
MEMORY_PRSCS_format="40G"
#
### REQUIRED: CPUs, some PRS methods support multithreading, some do not, and for some is has not been implemented yet
PRSICE_CPUS="12"
PRSCS_CPUS="12"
#
# =================================================================================================================================================================
# =----------------------------------------------------------- METHOD SPECIFIC SETTINGS -----------------------------------------------------------=
# =================================================================================================================================================================
# +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+ PRSICE settings +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+
# PRSice calculates the PRS for all individuals in the target population for a given phenotype.
# For more on PRSice parameters go here: https://www.prsice.info/command_detail/.
# PRSICE_EXTRACT -- file containing SNPs to be included in the analysis, PRSice will return an error if it runs into duplicate SNPs, in this case it will
# write the non-duplicate SNPs to a file in the working directory, put the path to the generated file in this parameter to avoid this error
# PRSICE_EXCLUDE -- file containing SNPs to be excluded from the analysis
# PRSICE_CLUMP_KB -- distance for clumping in kb, the default is "250"
# PRSICE_CLUMP_P -- P-value threshold used for clumping, default is "1"
# PRSICE_CLUMP_R2 -- r2 threshold for clumping, default is "0.1"
# PRSICE_PERM -- number of permutations to perform, default is "10000"
# PRSICE_THREADS -- number of threads to use, e.g. "20", if set to "max" the number of threads will be derived from the amount of dedicated CPUs (PRSICE_CPUS)
# PRSICE_SETTINGS -- some (not all) additional settings for PRSice, e.g. PRSICE_SETTINGS="--no-clump --print-snp --extract PRSice.valid --score sum --missing center"
# --score -- method to calculate the polygenic score [avg/std/con-std/sum], e.g. "--score sum"
# avg - take the average effect size (default)
# std - standardize the effect size
# con-std - standardize the effect size using mean and SD derived from control samples
# sum - direct summation of the effect size
# --missing -- way to handle missing genotypes
# mean_impute - missing genotypes contribute an amount proportional to imputed frequency (default)
# set_zero - throw out missing observations
# center - shift all scores to mean zero
# --no-clump -- don't use clump if you already filtered the data; in case of most GWAS results you do want to use clumping
# --print-snp -- print a list of SNPs used at the end in the modeling
# --all-score -- print out all the calculated scores for each P-value threshold, handy if you want to do some offline modeling down the road,
# this will generate a huge file
# --seed [seed] -- random number used for permutation, e.g. "91149214", usefull for when you would like
# to be able to generate identical results when providing the same input
# --no-default -- remove all default options, including the default behaviour of PRSice of searching for MAF and info columns in the base file and
# using those to filter SNPs
# --allow-inter -- allow the generation of a large intermediate file to speed up the calculation
# --fastscore -- only calculate the PRS for threshold(s) set within the bar level
# --all-score -- gives the PRS for each individual at all thresholds specified by --bar-levels, instead of only the PRS for each individual
# that explains most of the variation in the phenotype
# --bar-levels [levels] -- level(s) of barchart to be plotted, e.g. "0.05,0.1"
PRSICE_EXTRACT=""
PRSICE_EXCLUDE=""
PRSICE_CLUMP_KB="250"
PRSICE_CLUMP_P="1"
PRSICE_CLUMP_R2="0.1"
PRSICE_PERM="10000"
PRSICE_THREADS="max"
PRSICE_SETTINGS="--score sum --seed 91149214 --no-default --allow-inter --missing center --bar-levels 0.000000005,0.00000005,0.0000005,0.000005,0.00005,0.0005,0.005,0.05,0.1,0.2,0.3,0.4,0.5,1 --fastscore"
#
# +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+ LDpred settings +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+
# Parameters for LDpred *currently not implemented*
# LDPREDDIR -- where the LDpred directory resides
# LDPREDSYNC -- python script to synchronise files
# LDPRED -- python script that implements the LDpred LD-correction of GWAS summary statistics
# LDPREDPRS -- python script to calculate polygenic scores
# LDPREDDIR="${SOFTWARE}/ldpred"
# LDPREDSYNC="${LDPREDDIR}/ldpred/coord_genotypes.py"
# LDPRED="${LDPREDDIR}/ldpred/LDpred.py"
# LDPREDPRS="${LDPREDDIR}/ldpred/validate.py"
#
# +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+ PLINK settings +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+
# Below the parameters for the PLINK allelic scoring function. This function is also used by RapidoPGS and PRS-CS as those are only able to compute effect sizes.
# Note that within this toolkit, PLINK is set to calculate the sum of the allele scores instead of the default average allele score. The reason behind this is
# that if we were to calculate the average for each chromosome, we would not be able to take the sum of all chromosomes.
# More on PLINK --score parameters: https://www.cog-genomics.org/plink/2.0/score
# PLINK_SETTINGS -- optional settings of PLINK, e.g. "center no-mean-imputation se zs"
# Dosage modifiers -- modify the default allelic dosages (you can only pick one)
# center - translates all dosages to mean zero
# variance-standardize - transforms each variant's dosage vector to have mean zero, variance 1
# dominant - causes dosages greater than 1 to be treated as 1
# recessive - uses max(dosage-1,0) on diploid chromosomes
# no-mean-imputation -- throw out missing observations (default is to apply mean-imputation - similar to PRSice2 [https://choishingwan.github.io/PRSice/command_detail/])
# se -- causes the input coefficients to be treated as independent standard errors
# ignore-dup-ids -- don't throw an error when variant IDs occur multiple times in the input file (still prints warning)
# list variants[-zs] -- write the variant IDs used for scoring to 'plink2.sscore.vars[.zst]'
PLINK_SETTINGS=""
#
# +=+==+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+ RAPIDOPGS settings +=+=+=+=++=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+
# More on RapidoPGS parameters: https://rdrr.io/github/GRealesM/RapidoPGS/man/rapidopgs_single.html
# RP_filt_threshold -- scalar indicating the ppi threshold (if filt_threshold < 1) or the number of top SNPs by absolute weights (if filt_threshold >= 1)
# to filter the dataset after PGS computation. If NULL (DEFAULT), no thresholding will be applied
# RP_recalc -- logical [TRUE/FALSE] indicating if weights should be recalculated after thresholding, only relevant if filt_threshold is defined
# RP_ppi -- scalar representing the prior probability, default is "1e-04"
# RP_prior -- the prior specifies that BETA at causal SNPs follows a centred normal distribution with standard deviation sd.prior,
# sensible and widely used DEFAULTs are 0.2 for case control traits, and 0.15 * var(trait) for quantitative (selected if trait == "quant")
# RP_REF -- path to the reference file the SNPs should be filtered and aligned to, this file should have 5 columns (CHR, BP, SNPID, REF and ALT)
# and should be in the same build as the summary statistics
RP_filt_threshold="0.5"
RP_recalc="FALSE"
RP_ppi="1e-04"
RP_prior="0.2"
RP_REF=""
#
# +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+ PRS-CS settings +=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=++=+=+=+=+
# For a more detailed description of PRS-CS parameters go to https://github.com/getian107/PRScs.
# PRSCS_THREADS -- maximum amount of threads, when empty, PRS-CS uses the maximum amount of threads of the CPUS dedicated to the job
# BIM_FILE_AVAILABLE -- [YES/NO] indicating if a .bim file is already available, in this case BIM_FILE_PATH should also be specified, a .bim file can be
# retrieved from the tmp files of a previous run (https://www.cog-genomics.org/plink/2.0/formats#bim) and is specific to the validation dataset
# BIM_FILE_PATH -- path to the .bim file
# PRSCS_SETTINGS -- optional settings of PRS-CS (e.g. PRSCS_SETTINGS="--a 1 --b 0.5 --chrom 1,3,5")
# --a [value] -- parameter a in the gamma-gamma prior, default is 1
# --b [value] -- parameter b in the gamma-gamma prior, default is 0.5
# --phi [value] -- global shrinkage parameter, e.g. "1e-6", if not specified phi will be learned from the data
# --n_iter [int] -- total number of MCMC iterations, default is 1000
# --n_burnin [int] -- number of burnin iterations, default is 500
# --thin [int] -- thinning factor of the Markov chain, default is 5
# --chrom [list] -- the chromosome(s) on which the model is fitted, separated by comma, e.g. 1,3,5, default is iterating through chromosomes 1-22
# --beta_std [bool] -- [True/False] whether to return standardized posterior SNP effect sizes, default is False
# --seed [int] -- non-negative integer which seeds the random number generator
PRSCS_THREADS=""
BIM_FILE_AVAILABLE="NO"
BIM_FILE_PATH=""
PRSCS_SETTINGS=""