Signed-off-by: Mehmet <[email protected]>

high_ld/high_ld_hg19.txt

@@ -0,0 +1,31 @@
+#https://genome.sph.umich.edu/wiki/Regions_of_high_linkage_disequilibrium_(LD)
+#There are regions of long-range, high linkage diequilibrium in the human genome. These regions should be excluded when performing certain analyses such as principal component analysis on genotype data. 
+#Here is a list of positions for GRCH Build 37
+#You can remove these regions from a PED file using the following PLINK commands.
+#plink --file mydata --make-set high-ld.txt --write-set --out hild
+#plink --file mydata --exclude hild.set --recode --out mydatatrimmed
+#Chr	Start	Stop
+1	48000000	52000000
+2	86000000	100500000
+2	134500000	138000000
+2	183000000	190000000
+3	47500000	50000000
+3	83500000	87000000
+3	89000000	97500000
+5	44500000	50500000
+5	98000000	100500000
+5	129000000	132000000
+5	135500000	138500000
+6	25000000	35000000
+6	57000000	64000000
+6	140000000	142500000
+7	55000000	66000000
+8	7000000	13000000
+8	43000000	50000000
+8	112000000	115000000
+10	37000000	43000000
+11	46000000	57000000
+11	87500000	90500000
+12	33000000	40000000
+12	109500000	112000000
+20	32000000	34500000

high_ld/high_ld_hg38.txt

@@ -0,0 +1,50 @@
+#https://genome.sph.umich.edu/wiki/Regions_of_high_linkage_disequilibrium_(LD)
+#There are regions of long-range, high linkage diequilibrium in the human genome. These regions should be excluded when performing certain analyses such as principal component analysis on genotype data. 
+#Here is a list of positions for GRCH Build 38
+#You can remove these regions from a PED file using the following PLINK commands.
+#plink --file mydata --make-set high-ld.txt --write-set --out hild
+#plink --file mydata --exclude hild.set --recode --out mydatatrimmed
+#Chr	Start	Stop
+1	47761740	51761740
+1	125169943	125170022
+1	144106678	144106709
+1	181955019	181955047
+2	85919365	100517106
+2	87416141	87416186
+2	87417804	87417863
+2	87418924	87418981
+2	89917298	89917322
+2	135275091	135275210
+2	182427027	189427029
+2	207609786	207609808
+3	47483505	49987563
+3	83368158	86868160
+5	44464140	51168409
+5	129636407	132636409
+6	25391792	33424245
+6	26726947	26726981
+6	57788603	58453888
+6	61109122	61357029
+6	61424410	61424451
+6	139637169	142137170
+7	54964812	66897578
+7	62182500	62277073
+8	8105067	12105082
+8	43025699	48924888
+8	47303500	47317337
+8	110918594	113918595
+9	40365644	40365693
+9	64198500	64200392
+9	88958735	88959017
+10	36671065	43184546
+10	41693521	41885273
+11	88127183	91127184
+12	32955798	41319931
+12	34639034	34639084
+14	87391719	87391996
+14	94658026	94658080
+17	43159541	43159574
+20	4031884	4032441
+20	33948532	36438183
+22	30060084	30060162
+22	42980497	42980522

main.py

@@ -0,0 +1,126 @@
+# -*- coding: utf-8 -*-
+
+import sys, os
+import argparse
+import time
+from multiprocessing import cpu_count
+import wbbc
+
+sys.path.append(os.path.dirname(__file__))
+
+
+def arguments():
+    # argument parser
+    parser = argparse.ArgumentParser()
+
+    # TSV raw data file
+    parser.add_argument(
+        "-tf",
+        "--tsvFile",
+        nargs="?",
+        required=False,
+        help="file name of TSV raw data",
+    )
+
+    # TSV raw data path
+    parser.add_argument(
+        "-tp",
+        "--tsvPath",
+        nargs="?",
+        required=False,
+        help="path of TSV raw data",
+    )
+
+    # filename of allele frequency without extension
+    parser.add_argument(
+        "-af",
+        "--alleleFrqFile",
+        nargs="?",
+        default="wbbc_{}".format(time.strftime("%Y-%m-%d", time.localtime())),
+        help="file name of allele frequency without extension",
+    )
+
+    # decimal digits of alleles frequency
+    parser.add_argument(
+        "-ad",
+        "--afDigits",
+        nargs="?",
+        type=int,
+        default=6,
+        help="decimal digits of alleles frequency",
+    )
+
+    # threshold of standard deviation of alleles frequency
+    parser.add_argument(
+        "-sd",
+        "--stdev",
+        nargs="?",
+        type=float,
+        default=0.03,
+        help="threshold of standard deviation of alleles frequency",
+    )
+
+    # filename of regions of High Linkage Disequilibrium
+    parser.add_argument(
+        "-hld",
+        "--highLD",
+        nargs="?",
+        default="",
+        help="filename of regions of High Linkage Disequilibrium. Refer to: https://genome.sph.umich.edu/wiki/Regions_of_high_linkage_disequilibrium_(LD)",
+    )
+
+    # threshold of standard deviation of alleles frequency
+    parser.add_argument(
+        "-th",
+        "--thread",
+        nargs="?",
+        type=int,
+        default=cpu_count() if cpu_count() > 0 else 4,
+        help="threads count for concurrency",
+    )
+
+    return parser.parse_args()
+
+
+# 基于基因芯片的TSV数据，从WBBC的VCF中筛选出符合条件的突变和频率数据，生成alleles和frequency文件作为祖源计算器的参考数据集
+def main():
+    # get arguments
+    args = arguments()
+
+    # TSV文件集合
+    tsvFiles = []
+
+    # 指定TSV文件
+    if args.tsvFile != None:
+        tsvFiles.extend(args.tsvFile.strip().split())
+
+    # 指定TSV目录
+    if args.tsvPath != None:
+        tsvPath = args.tsvPath.strip()
+        for file in os.listdir(tsvPath):
+            if os.path.isfile(os.path.join(tsvPath, file)):
+                tsvFiles.append(os.path.join(tsvPath, file))
+
+    if len(tsvFiles) > 0:
+        isTsvExist = True
+        for file in tsvFiles:
+            if not os.access(file, os.F_OK):
+                print("TSV file {} is not available.".format(file))
+                isTsvExist = False
+    else:
+        print("Please set one more TSV files or path.")
+        isTsvExist = False
+
+    if isTsvExist:
+        wbbc.make_allele_frq(
+            tsvFiles,
+            args.highLD,
+            args.alleleFrqFile,
+            args.afDigits,
+            args.stdev,
+            args.thread,
+        )
+
+
+if __name__ == "__main__":
+    main()