offtracker 2.10.10__zip → 2.11.0__zip

{offtracker-2.10.10/offtracker.egg-info → offtracker-2.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.10.10
+Version: 2.11.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.10.10 → offtracker-2.11.0}/offtracker/X_offplot.py

@@ -5,10 +5,21 @@ import matplotlib.pyplot as plt
 import matplotlib.patches as patches
 from matplotlib import rcParams
 # 和用 plt.rcParams or matplotlib.rcParams 是一样的
-dict_rc = {
-    'pdf.fonttype': 42,
-    'font.family': ['Arial']
-}
+import sys
+if sys.platform[:3] == 'win':
+    dict_rc = {
+        'pdf.fonttype': 42,
+        'font.family': ['Arial']
+    }
+elif sys.platform[:5] == 'linux':
+    dict_rc = {
+        'pdf.fonttype': 42,
+        'font.family': ['Arial']
+    }
+else:
+    dict_rc = {
+        'pdf.fonttype': 42,
+    }
 rcParams.update(dict_rc)
 
 # 2024.06.03. offtable 添加 threshold 分界线，默认为 None，常用的是 2

{offtracker-2.10.10 → offtracker-2.11.0}/offtracker/_version.py

@@ -1,4 +1,4 @@
-__version__ = "2.10.10"
+__version__ = "2.11.0"
 # 2023.08.11. v1.1.0	adding a option for not normalizing the bw file
 # 2023.10.26. v1.9.0	prerelease for v2.0
 # 2023.10.27. v2.0.0	大更新，还没微调
@@ -36,4 +36,6 @@ __version__ = "2.10.10"
 # 2025.06.17. v2.10.7   修复翻新代码结构导致的bug
 # 2025.06.27. v2.10.8   将 chmod 放在了 setup.py 里
 # 2025.06.28. v2.10.9   现在 pip 都是从 wheel 安装，不再运行 setup.py，所以增加一个 offtracker_init.py
-# 2025.06.28. v2.10.10  直接塞 script 里试试
+# 2025.06.28. v2.10.10  直接塞 script 里试试
+# 2025.06.28. v2.10.11  回滚到2.10.9外加修正
+# 2025.07.02. v2.11.0  基于 blast 的缺陷更新 candidates

{offtracker-2.10.10 → offtracker-2.11.0/offtracker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: offtracker
-Version: 2.10.10
+Version: 2.11.0
 Summary: Tracking-seq data analysis
 Home-page: https://github.com/Lan-lab/offtracker
 Author: Runda Xu

{offtracker-2.10.10 → offtracker-2.11.0}/offtracker.egg-info/SOURCES.txt

@@ -12,7 +12,6 @@ offtracker.egg-info/SOURCES.txt
 offtracker.egg-info/dependency_links.txt
 offtracker.egg-info/requires.txt
 offtracker.egg-info/top_level.txt
-offtracker/utility/bedGraphToBigWig
 offtracker/snakefile/Snakefile_QC.smk
 offtracker/snakefile/Snakefile_offtracker.smk
 offtracker/utility/1.1_bed2fr.py

{offtracker-2.10.10 → offtracker-2.11.0}/offtracker.egg-info/requires.txt

@@ -1,4 +1,5 @@
 pandas
+polars>=1.19.0
 numpy
 biopython<=1.85
 pybedtools

{offtracker-2.10.10 → offtracker-2.11.0}/scripts/offtracker_candidates.py

@@ -20,6 +20,7 @@ script_folder= os.path.join(script_dir, 'utility')
 
 import argparse
 import pandas as pd
+import polars as pl
 import pybedtools
 import multiprocessing as mp
 from Bio.Blast.Applications import NcbiblastnCommandline 
@@ -89,18 +90,20 @@ def main():
     #########
     # BLAST #
     #########
+    # 2025.07.02 基于 blast 的缺陷更新
+
     if os.path.isfile(dir_sgRNA_blast):
         print(f'{dir_sgRNA_blast} exists, skipped.')
     else:
         if quick_mode:
             print('Using quick mode for BLAST')
             blastx_cline = NcbiblastnCommandline(query=dir_sgRNA_fasta, task='blastn-short',out=dir_sgRNA_blast,
-                                                db=blast_db, evalue=10000,outfmt=6, num_threads=n_threads,
-                                                gapopen=4, gapextend=2, reward=2, word_size=5, dust='no', soft_masking=False)
+                                                db=blast_db, evalue=100000,outfmt=6, num_threads=n_threads,
+                                                gapopen=4, gapextend=2, reward=2, word_size=6, dust='no', soft_masking=False)
         else:
             blastx_cline = NcbiblastnCommandline(query=dir_sgRNA_fasta, task='blastn-short',out=dir_sgRNA_blast,
-                                                db=blast_db, evalue=10000,outfmt=6, num_threads=n_threads,
-                                                gapopen=4, gapextend=2, reward=2, word_size=4, dust='no', soft_masking=False)   
+                                                db=blast_db, evalue=100000,outfmt=6, num_threads=n_threads,
+                                                gapopen=4, gapextend=2, reward=2, word_size=5, dust='no', soft_masking=False)   
         print(f'BLAST for candidate off-target sites of {sgRNA_name}.')
         blastx_cline()
         print(f'BLAST finished.')
@@ -109,33 +112,39 @@ def main():
     # Output bed #
     ##############
     
-    blast_regions = pd.read_csv(dir_sgRNA_blast, sep='\t',header=None)
+    # 2025.07.02 基于 blast 的缺陷更新
+    len_sgRNA = len(sgRNA_seq)
+    blast_regions = pl.read_csv(dir_sgRNA_blast, separator='\t',has_header=False)
     blast_regions.columns = ['query acc.','chr','% identity','alignment length','mismatches','gap opens','q. start','q. end','st','ed','evalue','bit score']
-    blast_regions = blast_regions[blast_regions.evalue<10000]
-    
-    # reverse strand 
-    blast_regions['reverse'] = (blast_regions['st']>blast_regions['ed']).astype(int)
-    blast_regions_f = blast_regions[blast_regions.reverse==0].copy()
-    blast_regions_r = blast_regions[blast_regions.reverse==1].copy()
-    temp = blast_regions_r['st'].copy()
-    blast_regions_r['st'] = blast_regions_r['ed']
-    blast_regions_r['ed'] = temp
-    blast_regions = pd.concat([blast_regions_f, blast_regions_r])
-    # sort and add location
-    blast_regions = blast_regions.sort_values('evalue').reset_index(drop=True)
-    blast_regions['location']=blast_regions['chr'].str[:] + ':' + blast_regions['st'].astype(str).str[:] + '-' + blast_regions['ed'].astype(str).str[:]
-    blast_regions = blast_regions.drop_duplicates(subset='location').copy()
-    
-    # alignment length 筛选
-    len_sgRNA=len(sgRNA_seq)
-    min_len = len_sgRNA-8
-    blast_regions = blast_regions[blast_regions['alignment length']>=min_len].copy().reset_index(drop=True)
-    blast_regions = blast_regions.reindex(columns = ['chr', 'st', 'ed' , 'query acc.', '% identity', 'alignment length', 'mismatches',
-        'gap opens', 'q. start', 'q. end', 'evalue', 'bit score', 'reverse', 'location'] )
-    
+
+    # reverse strand
+    blast_regions = blast_regions.with_columns((pl.col('st') > pl.col('ed')).cast(pl.Int8).alias('reverse'))
+    blast_regions_f = blast_regions.filter(pl.col('reverse') == 0)
+    blast_regions_r = blast_regions.filter(pl.col('reverse') == 1)
+    blast_regions_r = blast_regions_r.with_columns([
+        pl.col('ed').alias('st'),
+        pl.col('st').alias('ed')
+    ])
+    blast_regions = pl.concat([blast_regions_f, blast_regions_r])
+
+    # add location 
+    blast_regions = blast_regions.with_column(
+        (pl.col('chr') + ':' + pl.col('st').cast(str) + '-' + pl.col('ed').cast(str)).alias('location')
+    )
+    # filter, sort, dedup
+    blast_regions = blast_regions.with_columns(mis=(len_sgRNA - 1 - pl.col('q. end')+pl.col('q. start')+pl.col('mismatches')+pl.col('gap opens')).cast(pl.Int8))
+    blast_regions = blast_regions.with_columns(mis2=(len_sgRNA - pl.col('alignment length')*pl.col('% identity')/100).round().cast(pl.Int8))
+    blast_regions = blast_regions.filter((pl.col('mis')<8)|(pl.col('mis2')<8))
+    blast_regions = blast_regions.sort('mis').unique('location',keep='first', maintain_order=True)
+    blast_regions = blast_regions.select([
+        'chr', 'st', 'ed', 'query acc.', '% identity', 'alignment length', 'mismatches',
+        'gap opens', 'q. start', 'q. end', 'evalue', 'bit score', 'reverse', 'location', 'mis', 'mis2'
+    ])
+
     # 输出 bed 用于后续 alignment score 计算
-    blast_regions_bed = blast_regions[['chr','st','ed']]
-    xseq.write_bed(blast_regions_bed, dir_sgRNA_bed)
+    blast_regions_bed = blast_regions.select(['chr', 'st', 'ed'])
+    blast_regions_bed.write_csv(dir_sgRNA_bed, separator='\t', has_header=False)
+
     # 对 bed 进行排序但不合并
     a = pybedtools.BedTool(dir_sgRNA_bed)
     a.sort(g=dir_chrom_sizes).saveas( dir_sgRNA_bed )
@@ -155,10 +164,10 @@ def main():
     bed_short = xseq.X_readbed(dir_sgRNA_bed)
     bed_short = bed_short[bed_short['chr'].isin(common_chr)].copy()
     bed_short['midpoint'] = ((bed_short['st'] + bed_short['ed'])/2).astype(int)
-    bed_short['st'] = bed_short['midpoint'] - half_width 
+    bed_short['st'] = bed_short['midpoint'] - half_width
     bed_short['ed'] = bed_short['midpoint'] + half_width
     bed_short.loc[bed_short['st']<0,'st']=0
-    bed_short = bed_short.drop_duplicates()        
+    bed_short = bed_short.drop_duplicates()
 
     #########
     # 根据 bed_f 位点 ed 前后 half_width 取基因组序列

offtracker-2.11.0/scripts/offtracker_config.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# 2023.08.11. adding a option for not normalizing the bw file
+# 2025.05.22. refine the structure
+# 2025.06.05. 增加 ignore_chr 选项，默认只取 common chromosomes，用于 1.1_bed2fr.py
+
+import argparse
+import os, glob, yaml
+import pandas as pd
+import shutil, re
+import offtracker
+import offtracker.X_sequence as xseq
+script_dir = os.path.abspath(os.path.dirname(offtracker.__file__))
+utility_dir = os.path.join(script_dir, 'utility')
+file_path = os.path.join(utility_dir, 'bedGraphToBigWig')
+file_stat = os.stat(file_path)
+file_mode = oct(file_stat.st_mode & 0o777)
+if file_mode != '0o755':
+    try:
+        os.chmod( os.path.join(utility_dir, 'bedGraphToBigWig'), 0o755)
+    except:
+        print('offtracker may be installed in root but not initialized. Please run "offtracker_init.py" with root permission first.')
+
+###
+def main():
+    parser = argparse.ArgumentParser()
+    parser.description='Mapping fastq files of Tracking-seq.'
+    parser.add_argument('-f','--folder', type=str, required=True,  help='Directory of the input folder' )
+    parser.add_argument('-r','--ref'   , type=str, required=True,  help='The fasta file of reference genome')
+    parser.add_argument('-i','--index' , type=str, required=True,  help='The index file of chromap')
+    parser.add_argument('-g','--genome', type=str, required=True,  help='File of chromosome sizes, or "hg38", "mm10" ')
+    parser.add_argument('-o','--outdir', type=str, default='same', help='The output folder')
+    parser.add_argument('--subfolder'  , type=int, default=0,      help='subfolder level')
+    parser.add_argument('-t','--thread', type=int, default=4,      help='Number of threads to be used')
+    parser.add_argument('--blacklist'  , type=str, default='same', help='Blacklist of genome regions in bed format. "none" for no filter')
+    parser.add_argument('--binsize'    , type=str, default=100,    help='Bin size for calculating bw residue')
+    parser.add_argument('--normalize'  , type=str, default='True', help='Whether to normalize the BigWig file. "True" or "False"')
+    parser.add_argument('--ignore_chr' , action='store_true', help='If not set, only chr1-chr22, chrX, chrY, chrM will be analyzed.')
+
+
+    args = parser.parse_args()
+
+    if (args.genome == 'hg38') or (args.genome == 'mm10'):
+        dir_chrom_sizes = os.path.join(utility_dir, f'{args.genome}.chrom.sizes')
+    else:
+        dir_chrom_sizes = args.genome
+
+    if (args.normalize != 'True') & (args.normalize != 'False'):
+        raise ValueError('Please provide "True" or "False" for "--normalize"')
+
+    if args.blacklist == 'same':
+        assert ((args.genome == 'hg38') or (args.genome == 'mm10')), 'Please provide blacklist file, or "--blacklist none" to skip'
+        args.blacklist = args.genome
+        
+    if (args.blacklist == 'hg38') or (args.blacklist == 'mm10'):
+        blacklist = os.path.join(utility_dir, f'offtracker_blacklist_{args.blacklist}.merged.bed')
+    else:
+        blacklist = args.blacklist
+
+    if args.outdir == 'same':
+        args.outdir = args.folder
+    else:
+        if not os.path.exists(args.outdir):
+            os.makedirs(args.outdir)
+
+    if args.ignore_chr:
+        args.ignore_chr = '--ignore_chr'
+    else:
+        args.ignore_chr = ''
+
+    # 搜索 folder 的 n级子目录下的所有 fastq/fastq.gz/fq/fq.gz 文件
+    sample_names, files_R1, files_R2 = xseq.detect_fastq(args.folder, n_subfolder=args.subfolder)
+
+    assert not isinstance(sample_names, str), 'No fastq file is detected!'
+
+    dict_yaml = {
+        # fastq 信息
+        'files_R1':dict(zip(sample_names,files_R1)),
+        'files_R2':dict(zip(sample_names,files_R2)), # 单端 files_R2=[] 结果会自动为 {}
+        # 输入输出文件夹
+        'input_dir':args.folder,
+        'output_dir':args.outdir,
+        # 运行参数
+        'thread':args.thread,
+        'index':args.index,
+        'fasta':args.ref,
+        'binsize':args.binsize,
+        'blacklist':blacklist,
+        'genomelen':dir_chrom_sizes,
+        'normalize':args.normalize,
+        'utility_dir':utility_dir,
+        'ignore_chr':args.ignore_chr,
+        }
+
+    with open( os.path.join(args.outdir,'config.yaml'), 'w') as outfile:
+        yaml.dump(dict_yaml, outfile, default_flow_style=False)
+
+    snakefile = os.path.join(script_dir, 'snakefile/Snakefile_offtracker.smk')
+    shutil.copy(snakefile, os.path.join(args.outdir,'Snakefile'))
+
+    return 'config_main finished'
+
+if __name__ == '__main__' :
+    result = main()
+    print(result)
+

offtracker-2.11.0/scripts/offtracker_qc.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+THIS_VERSION = '0.4.1'
+
+import argparse
+import os, glob, yaml
+import pandas as pd
+import shutil, re
+import offtracker
+import offtracker.X_sequence as xseq
+
+script_dir = os.path.abspath(os.path.dirname(offtracker.__file__))
+utility_dir = os.path.join(script_dir, 'utility')
+file_path = os.path.join(utility_dir, 'bedGraphToBigWig')
+file_stat = os.stat(file_path)
+file_mode = oct(file_stat.st_mode & 0o777)
+if file_mode != '0o755':
+    try:
+        os.chmod( os.path.join(utility_dir, 'bedGraphToBigWig'), 0o755)
+    except:
+        print('offtracker may be installed in root but not initialized. Please run "offtracker_init.py" with root permission first.')
+
+###
+def main():
+    parser = argparse.ArgumentParser()
+    parser.description=f'xbulk_qc v{THIS_VERSION}. QC and trim fastq files.'
+    parser.add_argument('-f','--folder', type=str, required=True,        help='Directory of the input folder' )
+    parser.add_argument('-o','--outdir', type=str, default='same',       help='The output folder')
+    parser.add_argument('--subfolder'  , type=int, default=0,            help='subfolder level')
+    parser.add_argument('-t','--thread', type=int, default=8,            help='Number of threads to be used')
+
+    args = parser.parse_args()
+
+    # 自动化的参数调整和报错
+    if args.outdir == 'same':
+        args.outdir = os.path.join(args.folder,'Trimmed_data')
+        if not os.path.exists( args.outdir ):
+            os.makedirs( args.outdir )
+    else:
+        if not os.path.exists(args.outdir):
+            os.makedirs(args.outdir)
+
+    # 搜索 folder 的 n级子目录下的所有 fastq/fastq.gz/fq/fq.gz 文件
+    sample_names, files_R1, files_R2 = xseq.detect_fastq(args.folder, n_subfolder=args.subfolder)
+
+    assert not isinstance(sample_names, str), 'No fastq file is detected!'
+
+    dict_yaml = {
+        # fastq 信息
+        'files_R1':dict(zip(sample_names,files_R1)),
+        'files_R2':dict(zip(sample_names,files_R2)), # 单端 files_R2=[] 结果会自动为 {}
+        # 输入输出文件夹
+        'input_dir':args.folder,
+        'output_dir':args.outdir,
+        # 运行参数
+        'thread':args.thread,
+        'utility_dir':utility_dir
+        }
+
+
+    with open( os.path.join(args.outdir,'config.yaml'), 'w', encoding='utf-8') as outfile:
+        yaml.dump(dict_yaml, outfile, default_flow_style=False)
+
+    snakefile = os.path.join(script_dir, 'snakefile/Snakefile_QC.smk')
+    shutil.copy(snakefile, os.path.join(args.outdir,'Snakefile'))
+
+    return 'config_qc finished'
+
+if __name__ == '__main__' :
+    result = main()
+    print(result)
+

{offtracker-2.10.10 → offtracker-2.11.0}/setup.py

@@ -26,7 +26,7 @@ with open(os.path.join(here, package_folder, '_version.py'),'r',encoding='utf-8'
 
 # requirements
 REQUIRED = [
-   'pandas', 'numpy', 'biopython<=1.85', 'pybedtools', 'pyyaml', 
+   'pandas', 'polars>=1.19.0', 'numpy', 'biopython<=1.85', 'pybedtools', 'pyyaml', 
 ]
 ## pybedtools may be not supported in Windows
 
@@ -49,8 +49,7 @@ setup(
     python_requires=REQUIRES_PYTHON,
     packages=['offtracker'],
     package_data={'offtracker': ['snakefile/*','utility/*']},
-    scripts = [ 'offtracker/utility/bedGraphToBigWig',
-                'scripts/offtracker_init.py',
+    scripts = [ 'scripts/offtracker_init.py',
                 'scripts/offtracker_qc.py',
                 'scripts/offtracker_config.py',
                 'scripts/offtracker_candidates.py',

offtracker-2.10.10/scripts/offtracker_config.py

@@ -1,97 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-# 2023.08.11. adding a option for not normalizing the bw file
-# 2025.05.22. refine the structure
-# 2025.06.05. 增加 ignore_chr 选项，默认只取 common chromosomes，用于 1.1_bed2fr.py
-
-import argparse
-import os, glob, yaml
-import pandas as pd
-import shutil, re
-import offtracker
-import offtracker.X_sequence as xseq
-script_dir = os.path.abspath(os.path.dirname(offtracker.__file__))
-utility_dir = os.path.join(script_dir, 'utility')
-# try:
-#     os.chmod( os.path.join(utility_dir, 'bedGraphToBigWig'), 0o755)
-# except:
-#     print('offtracker may be installed in root but not initialized. Please run "offtracker_init.py" with root permission first.')
-
-###
-parser = argparse.ArgumentParser()
-parser.description='Mapping fastq files of Tracking-seq.'
-parser.add_argument('-f','--folder', type=str, required=True,  help='Directory of the input folder' )
-parser.add_argument('-r','--ref'   , type=str, required=True,  help='The fasta file of reference genome')
-parser.add_argument('-i','--index' , type=str, required=True,  help='The index file of chromap')
-parser.add_argument('-g','--genome', type=str, required=True,  help='File of chromosome sizes, or "hg38", "mm10" ')
-parser.add_argument('-o','--outdir', type=str, default='same', help='The output folder')
-parser.add_argument('--subfolder'  , type=int, default=0,      help='subfolder level')
-parser.add_argument('-t','--thread', type=int, default=4,      help='Number of threads to be used')
-parser.add_argument('--blacklist'  , type=str, default='same', help='Blacklist of genome regions in bed format. "none" for no filter')
-parser.add_argument('--binsize'    , type=str, default=100,    help='Bin size for calculating bw residue')
-parser.add_argument('--normalize'  , type=str, default='True', help='Whether to normalize the BigWig file. "True" or "False"')
-parser.add_argument('--ignore_chr' , action='store_true', help='If not set, only chr1-chr22, chrX, chrY, chrM will be analyzed.')
-
-
-args = parser.parse_args()
-
-if (args.genome == 'hg38') or (args.genome == 'mm10'):
-    dir_chrom_sizes = os.path.join(utility_dir, f'{args.genome}.chrom.sizes')
-else:
-    dir_chrom_sizes = args.genome
-
-if (args.normalize != 'True') & (args.normalize != 'False'):
-    raise ValueError('Please provide "True" or "False" for "--normalize"')
-
-if args.blacklist == 'same':
-    assert ((args.genome == 'hg38') or (args.genome == 'mm10')), 'Please provide blacklist file, or "--blacklist none" to skip'
-    args.blacklist = args.genome
-    
-if (args.blacklist == 'hg38') or (args.blacklist == 'mm10'):
-    blacklist = os.path.join(utility_dir, f'offtracker_blacklist_{args.blacklist}.merged.bed')
-else:
-    blacklist = args.blacklist
-
-if args.outdir == 'same':
-    args.outdir = args.folder
-else:
-    if not os.path.exists(args.outdir):
-        os.makedirs(args.outdir)
-
-if args.ignore_chr:
-    args.ignore_chr = '--ignore_chr'
-else:
-    args.ignore_chr = ''
-
-# 搜索 folder 的 n级子目录下的所有 fastq/fastq.gz/fq/fq.gz 文件
-sample_names, files_R1, files_R2 = xseq.detect_fastq(args.folder, n_subfolder=args.subfolder)
-
-assert not isinstance(sample_names, str), 'No fastq file is detected!'
-
-dict_yaml = {
-    # fastq 信息
-    'files_R1':dict(zip(sample_names,files_R1)),
-    'files_R2':dict(zip(sample_names,files_R2)), # 单端 files_R2=[] 结果会自动为 {}
-    # 输入输出文件夹
-    'input_dir':args.folder,
-    'output_dir':args.outdir,
-    # 运行参数
-    'thread':args.thread,
-    'index':args.index,
-    'fasta':args.ref,
-    'binsize':args.binsize,
-    'blacklist':blacklist,
-    'genomelen':dir_chrom_sizes,
-    'normalize':args.normalize,
-    'utility_dir':utility_dir,
-    'ignore_chr':args.ignore_chr,
-    }
-
-with open( os.path.join(args.outdir,'config.yaml'), 'w') as outfile:
-    yaml.dump(dict_yaml, outfile, default_flow_style=False)
-
-snakefile = os.path.join(script_dir, 'snakefile/Snakefile_offtracker.smk')
-shutil.copy(snakefile, os.path.join(args.outdir,'Snakefile'))
-
-

offtracker-2.10.10/scripts/offtracker_qc.py

@@ -1,63 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-THIS_VERSION = '0.4.1'
-
-import argparse
-import os, glob, yaml
-import pandas as pd
-import shutil, re
-import offtracker
-import offtracker.X_sequence as xseq
-
-script_dir = os.path.abspath(os.path.dirname(offtracker.__file__))
-utility_dir = os.path.join(script_dir, 'utility')
-# try:
-#     os.chmod( os.path.join(utility_dir, 'bedGraphToBigWig'), 0o755)
-# except:
-#     print('offtracker may be installed in root but not initialized. Please run "offtracker_init.py" with root permission first.')
-
-###
-parser = argparse.ArgumentParser()
-parser.description=f'xbulk_qc v{THIS_VERSION}. QC and trim fastq files.'
-parser.add_argument('-f','--folder', type=str, required=True,        help='Directory of the input folder' )
-parser.add_argument('-o','--outdir', type=str, default='same',       help='The output folder')
-parser.add_argument('--subfolder'  , type=int, default=0,            help='subfolder level')
-parser.add_argument('-t','--thread', type=int, default=8,            help='Number of threads to be used')
-
-args = parser.parse_args()
-
-# 自动化的参数调整和报错
-if args.outdir == 'same':
-    args.outdir = os.path.join(args.folder,'Trimmed_data')
-    if not os.path.exists( args.outdir ):
-        os.makedirs( args.outdir )
-else:
-    if not os.path.exists(args.outdir):
-        os.makedirs(args.outdir)
-
-# 搜索 folder 的 n级子目录下的所有 fastq/fastq.gz/fq/fq.gz 文件
-sample_names, files_R1, files_R2 = xseq.detect_fastq(args.folder, n_subfolder=args.subfolder)
-
-assert not isinstance(sample_names, str), 'No fastq file is detected!'
-
-dict_yaml = {
-    # fastq 信息
-    'files_R1':dict(zip(sample_names,files_R1)),
-    'files_R2':dict(zip(sample_names,files_R2)), # 单端 files_R2=[] 结果会自动为 {}
-    # 输入输出文件夹
-    'input_dir':args.folder,
-    'output_dir':args.outdir,
-    # 运行参数
-    'thread':args.thread,
-    'utility_dir':utility_dir
-    }
-
-
-with open( os.path.join(args.outdir,'config.yaml'), 'w', encoding='utf-8') as outfile:
-    yaml.dump(dict_yaml, outfile, default_flow_style=False)
-
-snakefile = os.path.join(script_dir, 'snakefile/Snakefile_QC.smk')
-shutil.copy(snakefile, os.path.join(args.outdir,'Snakefile'))
-
-