-
Notifications
You must be signed in to change notification settings - Fork 17
/
Copy pathgala
executable file
·222 lines (219 loc) · 11.2 KB
/
gala
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
#!/usr/bin/env python3
################################################################
# This file part of GALA Gap-free Long-reads Assembler #
# Auther: Mohamed awad #
# Company: Xiangchao Gan lab (MPIPZ) #
# Released under the (MIT) license (see LICENSE file) #
################################################################
import os
import sys
scr='src'
path=os.path.dirname(os.path.abspath(__file__))
absolute=os.path.join(path,scr)
sys.path.insert(0, absolute)
from comp_generator import comp_generator
from cut_gathering import cut_gathering
from new_genome import genomes
from scaffolding import scaffolding
from bam_seprator import bam_seprator
from read_extract import read_extract
import argparse
parser = argparse.ArgumentParser(prog="gala",usage='%(prog)s -h [options] <draft_names & paths> <fa/fq> <reads> <platform>',description='GALA Gap-free Long-reads Assembler')
parser.add_argument("draft_names",nargs=1,type=str,help='Draft names and paths\t[required]')
parser.add_argument("input_file",nargs=1,type=str,help='input type (fq/fa) \t[required]')
parser.add_argument("reads",nargs=1,type=str,help='raw/corrected reads\t[required]')
parser.add_argument("sequencing_platform",nargs=1,type=str,help='\n\tpacbio-raw\n\tpacbio-corrected\n\tnanopore-raw\n\tnanopore-corrected\n\t\t[required]')
parser.add_argument("-a",nargs='*', type=str, default=['canu'], help='Chr-by_Chr assembler (canu flye miniasm) \t [default canu]',dest="assembler")
parser.add_argument("-b",nargs=1, type=int, default=[5000], metavar='Alignment block length\t [default 5000]',dest="block")
parser.add_argument("-p",nargs=1, type=int, default=[70], metavar='Alignment identity percentage\t [default 70%]',dest="percent")
parser.add_argument("-l",nargs=1, type=int, default=[1], metavar='lowest number of misassemblies indecator\t [default 1]',dest="lowest")
parser.add_argument("-c",nargs=1, type=int, default=[5000], metavar='Shortest contig length\t [default 5000]',dest="contig")
parser.add_argument("-k",nargs=1, type=int, default=[175], metavar='Mis-assembly block\t [default 175]\n\t\t\tIt is better to extend the misassembly block in case of\n\t\t\tunpolished assemblies or expected mis-assemblies\n\t\t\tin highly repetative regions (5000-10000)',dest="cutblock")
parser.add_argument("-q",nargs=1, type=int, default=[20], metavar='Mapping quality\t [default 20]',dest="qty")
parser.add_argument("-f",nargs=1, type=str, default=['gathering'], metavar='Output files name\t[default gathering]',dest="name")
parser.add_argument("-t",nargs=1, type=str, default=['False'], metavar='cut on a threshold passed by -u\t[default False]',dest="threshold")
parser.add_argument("-u",nargs=1, type=int, default=[3], metavar='threshold cut value\t[default 3]',dest="threshold_value")
parser.add_argument("--cut1",nargs=1, type=int, default=[50000], metavar='The length of the smallest discordance on contigs of length >= 1000000 \t[default 50000]\n\t\t Be very careful with this parameter',dest="diff_1")
parser.add_argument("--cut2",nargs=1, type=int, default=[25000], metavar='The length of the smallest discordance on contigs of length >= 100000 \t[default 25000]\n\t\t Be very careful with this parameter',dest="diff_2")
parser.add_argument("--cut3",nargs=1, type=int, default=[15000], metavar='The length of the smallest discordance on contigs of length >= 5000 \t[default 15000]\n\t\t Be very careful with this parameter',dest="diff_3")
parser.add_argument("-o",nargs=1, type=str, default=[os.getcwd()], metavar='output files path\t[default current directory]',dest="output")
parser.add_argument('-v','--version', action='version', version='%(prog)s 1.0.0')
args = parser.parse_args()
draft_names=args.draft_names[0]
draft_names=os.path.abspath(draft_names)
reads=args.reads[0]
reads=os.path.abspath(reads)
input_file=args.input_file[0]
platform=args.sequencing_platform[0]
block=args.block[0]
threshold_value=args.threshold_value[0]
threshold=args.threshold[0]
if threshold in ('False','false','FALSE','F','f'):
theshold=False
elif threshold in ('True','true','TRUE','T','t'):
theshold=True
cutblock=args.cutblock[0]
percent=args.percent[0]
qty=args.qty[0]
output=args.output[0]
output=os.path.abspath(output)
name=args.name[0]
contig=args.contig[0]
diff_1=args.diff_1[0]
diff_2=args.diff_2[0]
diff_3=args.diff_3[0]
assembler=args.assembler
try:
os.chdir(output)
except:
os.mkdir(output)
os.chdir(output)
try:
os.mkdir('gala_results')
except:
pass
new_dir=os.path.join(output,'gala_results')
os.chdir(new_dir)
workdir=os.getcwd()
comp_generator(genomes=draft_names,output=workdir)
op=''.join(list(open('draft_comp.sh')))
op=op.replace('comparison','preliminary_comparison')
om=open('draft_comp.sh','w')
om.writelines(op)
om.close()
os.system('sh draft_comp.sh')
path_to_paf='preliminary_comparison'
number_of_drafts=''.join(list(open(draft_names))).count('=')
cut_gathering(path=path_to_paf,number_of_drafts=number_of_drafts,block=block,percentage=percent,shortage_contig=contig,quality=qty,out_file=True,out_name=name,out_path=workdir,cut_block=cutblock,threshold=threshold,threshold_value=threshold_value,diff_1=diff_1,diff_2=diff_2,diff_3=diff_3)
try:
os.mkdir('new_genomes')
except:
pass
genomes(genomes=draft_names,gathering=os.path.join(workdir,name),gathering_name=name,outpath=workdir+'/new_genomes')
new_path=workdir+'/'+'new_genomes/'
try:
os.mkdir('gap_free_comp')
except:
pass
outpath=workdir+'/gap_free_comp'
comp_generator(genomes=new_path+'new_draft_names_paths.txt',output=outpath)
new_path=outpath
os.chdir(outpath)
os.system('sh draft_comp.sh')
path_to_drafts='comparison'
scaffolding(path='comparison',number_of_drafts=number_of_drafts,block=block,percentage=percent,shortage_contig=contig,quality=qty,out_file=True,output_name=name,output=outpath,diff_1=diff_1,diff_2=diff_2,diff_3=diff_3)
new_path=output+'/'+'new_genomes/'
os.chdir(workdir+'/new_genomes')
os.system('for i in *.fa; do bwa index $i;done')
os.chdir(workdir)
try:
os.mkdir('mapping')
except:
pass
mapping=list(open('new_genomes/new_draft_names_paths.txt'))
for i in mapping:
dirname=i.split('=')[0]
os.system('mkdir -p mapping/'+dirname)
for i in mapping:
dirname=i.split('=')[0]
genomdir=i.split('=')[1].replace('\n','')
os.system('bwa mem '+genomdir+' '+reads+'| samtools sort | samtools view -Sb > mapping/'+dirname+'/mapping.bam')
os.system('samtools index mapping/'+dirname+'/mapping.bam')
new_path=workdir+'/'+'mapping/'
os.chdir(workdir+'/mapping')
for i in mapping:
dirname=i.split('=')[0]
os.chdir(new_path+dirname)
os.system('samtools view -H mapping.bam| grep SQ|cut -f 2|cut -d : -f 2 > contig_names')
for i in mapping:
dirname=i.split('=')[0]
bam_seprator(contig_name=new_path+dirname+'/contig_names',bam_file=new_path+dirname+'/mapping.bam',out_put_path=new_path+dirname)
os.chdir(new_path+dirname)
os.system('sh bam_seprator.sh')
os.chdir(new_path+dirname+'/bams')
os.system('for i in *; do samtools view $i | cut -f 1 > $i.read_names;done;')
dirnames=[]
for i in mapping:
dirnames.append(i.split('=')[0])
scaffs=os.path.join(outpath,name)
li=os.listdir(scaffs)
ok={}
for i in dirnames:
ok[i]={}
for base in dirnames:
op=list(open(scaffs+'/'+name+'_'+base+'.scaff'))
oa=open(new_path+base+'/scaffolds','w')
oa.writelines('cd bams\n')
nn=1
for bas in op:
if bas[:6]=='scaff_':
rr=bas.split('\t')
rmn=rr[-2]
rr=rr[:-2]
rr='\t'.join(rr[1:]).replace('\n','')
rr=rr.replace('\t','.bam.read_names ')
rr='cat '+rr+'.bam.read_names > ../scaffold_'+str(nn)+'.read_names\n'
ok[base]['scaffold_'+str(nn)]=str(rmn).replace('\n','')
oa.writelines(rr)
nn=nn+1
oa.close()
for i in dirnames:
os.chdir(os.path.join(new_path,i))
os.system('sh scaffolds')
mm=list(open('scaffolds'))[1:]
for base in mm:
mn=base.split(' > ../')[-1].replace('\n','')
read_extract(reads,mn,input_file)
if 'canu' in assembler:
for i in dirnames:
rmn=open(new_path+i+'/assembly_c.sh','w')
os.chdir(os.path.join(new_path,i))
mm=list(open('scaffolds'))[1:]
for base in mm:
mn=base.split(' > ../')[-1].replace('.read_names\n','.read.fq')
rmn.writelines('canu -p canu_'+mn.replace('.read.fq','')+ ' -d canu_'+mn.replace('.read.fq','')+' genomeSize='+str(int(ok[i][mn.replace('.read.fq','')])/1000000)+ 'm -' +platform+' '+new_path+i+'/'+mn+'\n')
if 'flye' in assembler:
for i in dirnames:
rmn=open(new_path+i+'/assembly_f.sh','w')
os.chdir(os.path.join(new_path,i))
mm=list(open('scaffolds'))[1:]
for base in mm:
mn=base.split(' > ../')[-1].replace('.read_names\n','.read.fq')
rmn.writelines('cd '+workdir+'/chr_by_chr/'+i+'\n')
rmn.writelines('mkdir -p flye_'+mn.replace('.read.fq','\ncd flye_')+mn.replace('.read.fq','\n'))
rmn.writelines('flye --out-dir flye_'+mn.replace('.read.fq','')+' --genome-size '+str(int(ok[i][mn.replace('.read.fq','')])/1000000)+ 'm --' +platform.replace('nanopore','nano').replace('corrected','corr')+' '+new_path+i+'/'+mn+'\n')
if 'miniasm' in assembler:
for i in dirnames:
rmn=open(new_path+i+'/assembly_m.sh','w')
os.chdir(os.path.join(new_path,i))
mm=list(open('scaffolds'))[1:]
for base in mm:
mn=base.split(' > ../')[-1].replace('.read_names\n','.read.fq')
rmn.writelines('cd '+workdir+'/chr_by_chr/'+i+'\n')
rmn.writelines('mkdir -p miniasm_'+mn.replace('.read.fq','\ncd miniasm_')+mn.replace('.read.fq','\n'))
if 'pacbio' in platform:
rmn.writelines('minimap2 -x ava-pb '+new_path+i+'/'+mn+' '+new_path+i+'/'+mn+' | gzip -1 > '+mn.replace('.read.fq','')+'.paf.gz\n')
rmn.writelines('miniasm -f '+new_path+i+'/'+mn+' '+mn.replace('.read.fq','')+'.paf.gz > '+mn.replace('.read.fq','.gfa\n'))
rmn.writelines("awk "+"'/^S/{print "+'">"$2"\\n"$3}'+"' "+mn.replace('.read.fq','.gfa ')+ '> '+mn.replace('.read.fq','.fa\n'))
rmn.writelines('flye --polish-target '+mn.replace('.read.fq','.fa') +' --out-dir . -'+platform.replace('corrected','corr')+' '+new_path+i+'/'+mn+' --iterations 3'+'\n')
elif 'nanopore' in platform:
rmn.writelines('minimap2 -x ava-ont '+new_path+i+'/'+mn+' '+new_path+i+'/'+mn+' | gzip -1 > '+mn.replace('.read.fq','')+'.paf.gz\n')
rmn.writelines('miniasm -f '+new_path+i+'/'+mn+' '+mn.replace('.read.fq','')+'.paf.gz > '+mn.replace('.read.fq','.gfa\n'))
rmn.writelines("awk "+"'/^S/{print "+'">"$2"\\n"$3}'+"' "+mn.replace('.read.fq','.gfa ')+ '> '+mn.replace('.read.fq','.fa\n'))
rmn.writelines('flye --polish-target '+mn.replace('.read.fq','.fa') +' --out-dir . --'+platform.replace('corrected','corr').replace('nanopore','nano')+' '+new_path+i+'/'+mn+' --iterations 3'+'\n')
os.chdir(workdir)
try:
os.mkdir('chr_by_chr')
except:
pass
os.chdir(workdir+'/chr_by_chr')
for i in mapping:
dirname=i.split('=')[0]
try:
os.mkdir(workdir+'/chr_by_chr/'+dirname)
except:
pass
os.chdir(workdir+'/chr_by_chr/'+dirname)
os.system('sh '+new_path+dirname+'/assembly_*.sh')
if '-v':
parser.parse_args(['-v'])