offtracker 2.7.10__zip → 2.10.0__zip

offtracker-2.10.0/scripts/offtracker_candidates.py

@@ -0,0 +1,318 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# 2023.10.27. v2.0: 2.0以target_location midpoint为中心，因此取消 pct 计算
+# 2023.12.06. v2.1: 2.1增加 cleavage_site 推测, 修正 deletion 错位, 以 cleavage_site 为中心
+# 2025.04.25. 修正大小写问题
+# 2025.06.11. 调整跳过已存在的candidates的代码顺序
+
+import os,sys,re,time
+from itertools import product, permutations
+
+if sys.version_info < (3,0):
+    import platform
+    raise Exception(f'python3 is needed, while running {platform.python_version()} now')
+
+import offtracker
+import offtracker.X_sequence as xseq
+script_dir = os.path.abspath(os.path.dirname(offtracker.__file__))
+script_folder= os.path.join(script_dir, 'mapping')
+
+import argparse
+import pandas as pd
+import pybedtools
+import multiprocessing as mp
+from Bio.Blast.Applications import NcbiblastnCommandline 
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.description='Generate candidate regions by sgRNA sequence'
+    parser.add_argument('--sgrna' ,       type=str, required=True, help='One sgRNA sequence without PAM' )
+    parser.add_argument('--pam'   ,       type=str, required=True, help='The protospacer adjacent motif' )
+    parser.add_argument('--pam_location', type=str, default='downstream', help='Upstream or downstream, default is downstream (Cas9)' )
+    parser.add_argument('--name'  ,       type=str, required=True, help='custom name of the sgRNA' )
+    parser.add_argument('-r','--ref'    , type=str, required=True, help='The fasta file of reference genome')
+    parser.add_argument('-b','--blastdb', type=str, required=True, help='blast database')
+    parser.add_argument('-o','--outdir' , type=str, required=True, help='The output folder')
+    parser.add_argument('-g','--genome' , type=str, default='hg38', help='File of chromosome sizes, or "hg38", "mm10" ')
+    parser.add_argument('-t','--thread' , type=int, default=4,     help='Number of threads for parallel computing')
+    parser.add_argument('--quick_mode'  , action='store_true',  help='BLAST faster but less candidates.')
+
+    args = parser.parse_args()
+    
+    
+    if (args.genome == 'hg38') or (args.genome == 'mm10'):
+        dir_chrom_sizes = os.path.join(script_folder, f'{args.genome}.chrom.sizes')
+    else:
+        dir_chrom_sizes = args.genome
+    
+    sgRNA_name = args.name
+    sgRNA_seq  = args.sgrna
+    PAM = args.pam
+    PAM_loc = args.pam_location.lower()
+    n_threads  = args.thread
+    dir_output = args.outdir
+    if not os.path.exists(dir_output):
+        os.makedirs(dir_output)
+    dir_ref_fa = args.ref
+    blast_db   = args.blastdb
+    quick_mode = args.quick_mode
+    
+    # parameters for alignment
+    half_width = 100
+    pct_params = 1.0
+    frag_len= half_width*2
+    dir_df_candidate = os.path.join(dir_output, f'df_candidate_{sgRNA_name}.csv')
+    if os.path.isfile(dir_df_candidate):
+        print(f'{dir_df_candidate} exists, skipped.') 
+        return 'skipped'
+    
+    sgRNA_seq = sgRNA_seq.upper()
+    PAM = PAM.upper()
+    dir_sgRNA_fasta = os.path.join(dir_output, f'{sgRNA_name}_PAM.fasta')
+    dir_sgRNA_blast = os.path.join(dir_output, f'{sgRNA_name}_PAM.blast')
+    dir_sgRNA_bed   = os.path.join(dir_output, f'{sgRNA_name}_PAM.bed')
+    
+    if PAM_loc == 'downstream':
+        possible_sgRNA_PAM = list(product([sgRNA_seq],xseq.possible_seq(PAM)))
+    elif PAM_loc == 'upstream':
+        possible_sgRNA_PAM = list(product(xseq.possible_seq(PAM),[sgRNA_seq]))
+    else:
+        raise Exception(f'PAM_location should be "upstream" or "downstream", while {PAM_loc} is given.')
+    possible_sgRNA_PAM = [''.join(combination) for combination in possible_sgRNA_PAM]
+    n_seq = len(possible_sgRNA_PAM)
+    
+    ID = pd.Series(['seq']*n_seq) + pd.Series(range(1,n_seq+1)).astype(str)
+    df_sgRNA_PAM = pd.DataFrame({'ID':ID,'sequence':possible_sgRNA_PAM})
+    xseq.write_fasta(df_sgRNA_PAM, dir_sgRNA_fasta)
+    
+    #########
+    # BLAST #
+    #########
+    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)
+        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)   
+        print(f'BLAST for candidate off-target sites of {sgRNA_name}.')
+        blastx_cline()
+        print(f'BLAST finished.')
+    
+    ##############
+    # Output bed #
+    ##############
+    
+    blast_regions = pd.read_csv(dir_sgRNA_blast, sep='\t',header=None)
+    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'] )
+    
+    # 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)
+    # 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 )
+    print(f'Output {sgRNA_name}_PAM.bed')
+    
+    
+    ###################
+    # alignment score #
+    ###################
+
+    #########
+    # 读取 blast bed
+    #########
+    common_chr = pd.Series(['chr']*23).str[:] + pd.Series(range(23)).astype(str).str[:]
+    common_chr = pd.concat([common_chr, pd.Series(['chrX','chrY'])]).to_numpy()
+
+    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['ed'] = bed_short['midpoint'] + half_width
+    bed_short.loc[bed_short['st']<0,'st']=0
+    bed_short = bed_short.drop_duplicates()        
+
+    #########
+    # 根据 bed_f 位点 ed 前后 half_width 取基因组序列
+    #########
+
+    temp_bed = os.path.join(dir_output, 'temp.bed')
+    xseq.write_bed(bed_short.iloc[:,:3], temp_bed)
+    a = pybedtools.BedTool(temp_bed)
+    fasta = pybedtools.example_filename(dir_ref_fa)
+    a = a.sequence(fi=fasta)
+    with open(a.seqfn) as f:
+        fasta = {} 
+        for line in f:
+            line = line.strip() # 去除末尾换行符
+            if line[0] == '>':
+                header = line[1:]
+            else:
+                sequence = line
+                fasta[header] = fasta.get(header,'') + sequence
+
+    # pybedtools 得到位置 chrA:X-Y 时，X数字会往左多1bp
+
+    #########
+    # local alignment
+    #########
+    # 生成 DNA_matrix
+    mismatch_score = 0.01
+    base_codes = list(xseq.ambiguous_nt.keys())
+    all_base_pairs = list(permutations(base_codes,2)) + [(x,x) for x in base_codes]
+    DNA_matrix = {x : xseq.get_base_score(*x, mismatch_score=mismatch_score) for x in all_base_pairs}
+    # 添加 PAM
+    if PAM_loc == 'downstream':
+        sgRNA_PAM_fw = sgRNA_seq + PAM
+    else:
+        sgRNA_PAM_fw = PAM + sgRNA_seq
+
+    sgRNA_PAM_rv = xseq.reverse_complement(sgRNA_PAM_fw)
+
+    list_args_fw=[]
+    list_args_rv=[]
+    for a_key, a_seq in fasta.items():
+        # 2025.04.25 修正大小写问题
+        a_seq = re.sub('[^ATCG]','N',a_seq.upper())
+        list_args_fw.append( [a_key, sgRNA_PAM_fw, a_seq, frag_len, DNA_matrix, mismatch_score] )
+        list_args_rv.append( [a_key, sgRNA_PAM_rv, a_seq, frag_len, DNA_matrix, mismatch_score] )
+    st = time.time()
+    with mp.Pool(n_threads) as p:
+        list_align_forward = p.starmap(xseq.sgRNA_alignment, list_args_fw)
+    ed = time.time()
+    print('align_forward:{:.2f}'.format(ed-st))
+    st = time.time()
+    with mp.Pool(n_threads) as p:
+        list_align_reverse = p.starmap(xseq.sgRNA_alignment, list_args_rv)
+    ed = time.time()
+    print('align_reverse:{:.2f}'.format(ed-st))
+    #
+    df_align_forward = pd.DataFrame(list_align_forward, columns= ['fw_score','fw_pct','fw_target','fw_location','fw_deletion','fw_insertion','fw_mismatch'])
+    df_align_reverse = pd.DataFrame(list_align_reverse, columns= ['rv_score','rv_pct','rv_target','rv_location','rv_deletion','rv_insertion','rv_mismatch'])
+    df_align_reverse['rv_target'] = df_align_reverse['rv_target'].apply(xseq.reverse_complement)
+    df_candidate = pd.concat([df_align_forward,df_align_reverse],axis=1)
+    df_candidate['location'] = fasta.keys()
+    df_candidate['alignment_score'] = df_candidate[['fw_score','rv_score']].max(axis=1)
+    #df_candidate['fw_score_2'] = df_candidate['fw_score']*(pct_params-df_candidate['fw_pct'].abs())
+    #df_candidate['rv_score_2'] = df_candidate['rv_score']*(pct_params-df_candidate['rv_pct'].abs())
+    #df_candidate['best_seq_score'] = df_candidate[['fw_score_2', 'rv_score_2']].max(axis=1)
+    #df_candidate['best_strand'] = df_candidate[['fw_score_2', 'rv_score_2']].idxmax(axis='columns').replace({'fw_score_2':'+', 'rv_score_2':'-'})
+    #df_candidate.loc[df_candidate['fw_score_2']==df_candidate['rv_score_2'],'best_strand']='equal_score'
+    df_candidate['best_seq_score'] = df_candidate[['fw_score', 'rv_score']].max(axis=1)
+    df_candidate['best_strand'] = df_candidate[['fw_score', 'rv_score']].idxmax(axis='columns').replace({'fw_score':'+', 'rv_score':'-'})
+    df_candidate.loc[df_candidate['fw_score']==df_candidate['rv_score'],'best_strand']='equal_score'
+            
+    # GG check
+    # 2023.12.05 增加 cleavage_site 推测
+    list_best_target = []
+    list_best_location = []
+    list_cleavage_site = []
+    list_delete = []
+    list_insert = []
+    list_mismat = []
+    list_GG = []
+    for a_row in df_candidate.iterrows():
+        if a_row[1]['best_strand']=='+':
+            list_best_target.append(a_row[1]['fw_target'])
+            list_best_location.append(a_row[1]['fw_location'])
+            list_cleavage_site.append(int(a_row[1]['fw_location'].split('-')[1]) - 6)
+            list_delete.append(a_row[1]['fw_deletion'])
+            list_insert.append(a_row[1]['fw_insertion'])
+            list_mismat.append(a_row[1]['fw_mismatch'])
+            if a_row[1]['fw_target'][-2:]=='GG':
+                list_GG.append('OK')
+            else:
+                list_GG.append('NO')                     
+        elif a_row[1]['best_strand']=='-':
+            list_best_target.append(a_row[1]['rv_target'])
+            list_best_location.append(a_row[1]['rv_location'])
+            list_cleavage_site.append(int(a_row[1]['rv_location'].split('-')[0].split(':')[1]) + 5)
+            list_delete.append(a_row[1]['rv_deletion'])
+            list_insert.append(a_row[1]['rv_insertion'])
+            list_mismat.append(a_row[1]['rv_mismatch'])
+            if a_row[1]['rv_target'][-2:]=='GG':
+                list_GG.append('OK')
+            else:
+                list_GG.append('NO')  
+        else:
+            if a_row[1]['fw_target'][-2:]=='GG':
+                list_best_target.append(a_row[1]['fw_target'])
+                list_best_location.append(a_row[1]['fw_location'])
+                list_cleavage_site.append(int(a_row[1]['fw_location'].split('-')[1]) - 6)
+                list_delete.append(a_row[1]['fw_deletion'])
+                list_insert.append(a_row[1]['fw_insertion'])
+                list_mismat.append(a_row[1]['fw_mismatch'])
+                list_GG.append('OK_same_score')
+            # 发现没有 GG 则看 RC
+            elif a_row[1]['rv_target'][-2:]=='GG':
+                list_best_target.append(a_row[1]['rv_target'])
+                list_best_location.append(a_row[1]['rv_location'])
+                list_cleavage_site.append(int(a_row[1]['rv_location'].split('-')[0].split(':')[1]) + 5)
+                list_delete.append(a_row[1]['rv_deletion'])
+                list_insert.append(a_row[1]['rv_insertion'])
+                list_mismat.append(a_row[1]['rv_mismatch'])
+                list_GG.append('OK_same_score')
+            else:
+                list_best_target.append(a_row[1]['fw_target'])
+                list_best_location.append(a_row[1]['fw_location'])
+                list_cleavage_site.append(int(a_row[1]['fw_location'].split('-')[1]) - 6)
+                list_delete.append(a_row[1]['fw_deletion'])
+                list_insert.append(a_row[1]['fw_insertion'])
+                list_mismat.append(a_row[1]['fw_mismatch'])                    
+                list_GG.append('NO_same_score')
+    # 记入 df_candidate
+    df_candidate['deletion'] = list_delete
+    df_candidate['insertion'] = list_insert
+    df_candidate['mismatch'] = list_mismat
+    df_candidate['GG'] = list_GG
+    df_candidate['best_target'] = list_best_target
+    df_candidate['target_location'] = list_best_location
+    df_candidate['cleavage_site'] = list_cleavage_site
+
+    # 2.0 更新一下格式
+    df_candidate = df_candidate.drop_duplicates(subset=['target_location']).reset_index(drop=True)
+    df_candidate = pd.concat([xseq.bedfmt(df_candidate['target_location']), df_candidate],axis=1)
+    # df_candidate['midpoint'] = ((df_candidate['ed'] + df_candidate['st'])/2).astype(int)
+    df_candidate = xseq.add_ID(df_candidate, midpoint='cleavage_site')
+
+    df_candidate.to_csv(dir_df_candidate)
+    print(f'Output df_candidate_{sgRNA_name}.csv')
+    os.remove(temp_bed)
+
+    return 'Done!'
+    
+
+if __name__ == '__main__' :
+    result = main()
+    print(result)
+
+
+

{offtracker-2.7.10 → offtracker-2.10.0}/scripts/offtracker_config.py

@@ -1,20 +1,22 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# 2023.08.11. v1.1	adding a option for not normalizing the bw file
+# 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__))
-script_folder= os.path.join(script_dir, 'mapping')
-os.chmod( os.path.join(script_folder, 'bedGraphToBigWig'), 0o755)
+utility_dir = os.path.join(script_dir, 'utility')
 
 ###
 parser = argparse.ArgumentParser()
-parser.description='Mapping fastq files of Track-seq.'
+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')
@@ -25,12 +27,13 @@ parser.add_argument('-t','--thread', type=int, default=4,      help='Number of t
 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()
 
+args = parser.parse_args()
 
 if (args.genome == 'hg38') or (args.genome == 'mm10'):
-    dir_chrom_sizes = os.path.join(script_folder, f'{args.genome}.chrom.sizes')
+    dir_chrom_sizes = os.path.join(utility_dir, f'{args.genome}.chrom.sizes')
 else:
     dir_chrom_sizes = args.genome
 
@@ -42,7 +45,7 @@ if args.blacklist == 'same':
     args.blacklist = args.genome
     
 if (args.blacklist == 'hg38') or (args.blacklist == 'mm10'):
-    blacklist = os.path.join(script_folder, f'offtracker_blacklist_{args.blacklist}.merged.bed')
+    blacklist = os.path.join(utility_dir, f'offtracker_blacklist_{args.blacklist}.merged.bed')
 else:
     blacklist = args.blacklist
 
@@ -52,59 +55,40 @@ else:
     if not os.path.exists(args.outdir):
         os.makedirs(args.outdir)
 
-gz_R2 = []
-for fastq in ['*2.*fq','*2.*fastq','*2.*fq.gz','*2.*fastq.gz']:
-    fq_files = glob.glob( os.path.join(args.folder, args.subfolder*'*/', fastq ) )
-    print('{} {} samples detected'.format( len(fq_files), fastq[4:] ) )
-    gz_R2.extend( fq_files )
-
-gz_R2.sort()
-gz_R2 = pd.Series(gz_R2)
-suffix = gz_R2.str.extract('(fastq.*|fq.*)',expand=False)
-prefix = gz_R2.str.extract('(.*)(?:.fq|.fastq)',expand=False)
-
-nametype = None
-for a_type in ['_trimmed_2', '_2_val_2','_R2_val_2','_R2','_2']:
-    len_type = len(a_type)
-    if prefix[0][-len_type:] == a_type:
-        nametype = a_type
-        sample_dir = prefix.str[:-len_type]
-        break
-
-if nametype is None:
-    # pattern 搜索模式，可能会出 bug
-    # find "_R2." or "_2." in prefix[0]
-    pattern = re.compile(r'(_R2\.|_2\.)')
-    m = pattern.search(prefix[0])
-    if m:
-        nametype = prefix[0][m.span()[0]:]
-        len_type = len(nametype)
-        sample_dir = prefix.str[:-len_type]
-
-assert nametype is not None, 'No fastq detected or the file name is invaild!'
-
-sample_name = sample_dir.apply(os.path.basename)
+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, NGS_type=args.NGS_type)
+
+assert not isinstance(sample_names, str), 'No fastq file is detected!'
 
 dict_yaml = {
-    'suffix':suffix[0],
-    'sample':dict(zip(sample_name,sample_dir)),
+    # 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 {}
+    'NGS_type':args.NGS_type,
+    # 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,
-    'nametype':nametype,
     'genomelen':dir_chrom_sizes,
     'normalize':args.normalize,
-    'script_folder':script_folder
+    '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, 'mapping/Snakefile_offtracker')
+snakefile = os.path.join(script_dir, 'snakefile/Snakefile_offtracker.smk')
 shutil.copy(snakefile, os.path.join(args.outdir,'Snakefile'))
 
 

offtracker-2.10.0/scripts/offtracker_qc.py

@@ -0,0 +1,62 @@
+#!/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')
+os.chmod( os.path.join(utility_dir, 'bedGraphToBigWig'), 0o755)
+
+###
+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')
+parser.add_argument('--NGS_type'   , type=str, default='paired-end', help='paired-end or single-end')
+
+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, NGS_type=args.NGS_type)
+
+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 {}
+    'NGS_type':args.NGS_type,
+    # 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'))
+
+

{offtracker-2.7.10 → offtracker-2.10.0}/setup.py

@@ -11,7 +11,7 @@ from setuptools import find_packages, setup, Command
 NAME = 'offtracker'
 DESCRIPTION = 'Tracking-seq data analysis'
 AUTHOR = 'Runda Xu'
-EMAIL = 'runda.xu@foxmail.com'
+EMAIL = 'xrd18@tsinghua.org.cn'
 URL = 'https://github.com/Lan-lab/offtracker'
 REQUIRES_PYTHON = '>=3.6.0'
 
@@ -47,9 +47,10 @@ setup(
     author_email=EMAIL,
     url=URL,
     python_requires=REQUIRES_PYTHON,
-    packages=find_packages(),
-    package_data={'offtracker': ['mapping/*']},
-    scripts = ['scripts/offtracker_config.py',
+    packages=['offtracker'],
+    package_data={'offtracker': ['snakefile/*','utility/*']},
+    scripts = ['scripts/offtracker_qc.py',
+               'scripts/offtracker_config.py',
                'scripts/offtracker_candidates.py',
                'scripts/offtracker_analysis.py',
                'scripts/offtracker_plot.py'],