-
Notifications
You must be signed in to change notification settings - Fork 0
/
EcoliWrapper.py
173 lines (123 loc) · 6.04 KB
/
EcoliWrapper.py
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
import os
import argparse
import logging
import Bio.SeqIO as SeqIO
import glob
import csv
#Setup
#Create the result folder
os.system('mkdir $HOME/Results/')
#Setup Logging
filename = 'miniproject.log'
path = os.path.expanduser('~')
path = path + '/Results/'
log = logging.getLogger()
log.setLevel(logging.DEBUG)
handler = logging.FileHandler(path+filename, 'w', 'utf-8')
handler.setFormatter(logging.Formatter('%(message)s'))
log.addHandler(handler)
#Retrieve the Illumina reads for the resequencing of K-12 project from NCBI:
os.system('prefetch -v SRR8185310 --output-directory $HOME/Results/')
#Convert the sra file into fastq format
os.system('fastq-dump $HOME/Results/SRR8185310/SRR8185310.sra --outdir $HOME/Results/SRR8185310/')
#Assembly
#Using SPAdes to assemble the genome
os.system('spades.py -k 55,77,99,127 -s $HOME/Results/SRR8185310/SRR8185310.fastq -t 2 --only-assembler -o $HOME/Results/spade_result/')
#Logging command used
log.info('SPAdes was run with the following command to assemble the K12 genome - SRR8185310:')
log.info('spades.py -k 55,77,99,127 -s $HOME/Results/SRR8185310/SRR8185310.fastq -t 2 --only-assembler -o $HOME/Results/spade_result/')
log.info(' ')
#Calculate the number of contigs with a length > 1000, calculate the length of the assembly,
#and write the long contigs into a new file as long.fasta
long = []
count = 0
length = 0
for contig in SeqIO.parse(path+'spade_result/contigs.fasta', 'fasta'):
if len(contig.seq) > 1000:
count += 1
length += len(contig.seq)
long.append(contig)
SeqIO.write(long, path+'long.fasta', "fasta")
#Logging the number of long contigs found
log.info('There are ' + str(count) + ' contigs > 1000 in the assembly.')
log.info(' ')
#Logging the length of the assembly with only long contigs
log.info('There are ' + str(length) + ' bp in the assembly.')
log.info(' ')
#Annotation
#Use Prokka to annotate this assembly with Prokka default Escherichia genus database.
os.system('prokka --genus Escherichia --outdir $HOME/Results/prokka_results/ $HOME/Results/long.fasta')
#Logging command used
log.info('Prokka was run with following command for annotation:')
log.info('prokka --genus Escherichia --outdir $HOME/Results/prokka_results/ $HOME/Results/long.fasta')
log.info(' ')
#Logging prokka's results
log.info('The Prokka analysis summary is list as following: ')
log.info(' ')
#Locate the txt file under Prokka
prokka_txt = glob.glob(path+'prokka_results/*.txt')
prokka_txt = ''.join(prokka_txt)
#Open input file text, read input file as a string, remove the empty line at the end and split the input file by line
input_string = open(prokka_txt, 'r').read().rstrip().split('\n')
for line in input_string:
log.info(line)
if line.startswith('tRNA'):
trna = line
trna = trna.split(': ')[1]
elif line.startswith('CDS: '):
cds = line
cds = cds.split(': ')[1]
log.info(' ')
#Calculate the discrepancty found by Prokka to RefSeq for E. coli K-12 (NC_000913), which has 4140 CDS and 89 tRNAs annotated.
trna = int(trna) - 89
cds = int(cds) - 4140
##Logging discrepancy
if trna < 0 and cds < 0:
log.info('Prokka found ' + str(abs(cds)) + ' less CDS and ' + str(abs(trna)) + ' less tRNA than the RefSeq.')
elif trna > 0 and cds < 0:
log.info('Prokka found ' + str(abs(cds)) + ' less CDS and ' + str(abs(trna)) + ' addtional tRNA than the RefSeq.')
elif trna < 0 and cds > 0:
log.info('Prokka found ' + str(abs(cds)) + ' addtional CDS and ' + str(abs(trna)) + ' less tRNA than the RefSeq.')
else:
log.info('Prokka found ' + str(abs(cds)) + ' addtional CDS and ' + str(abs(trna)) + ' additional tRNA than the RefSeq.')
log.info(' ')
#Mapping
#Download data from RefSeq E. coli K-12 (NC_000913) for building indexes
os.system('wget ftp://ftp.ncbi.nlm.nih.gov/genomes/archive/old_refseq/Bacteria/Escherichia_coli_K_12_substr__MG1655_uid57779/NC_000913.fna -P $HOME/Results/NC_000913/')
#Use bowtie2 to build index with prefix - 'EcoliK12'
os.system('bowtie2-build --threads 2 -q $HOME/Results/NC_000913/NC_000913.fna EcoliK12')
#Make a new folder under Result to keep all indexes generated
os.system('mkdir $HOME/Results/EcoliK12_index')
os.system('mv EcoliK12*.bt2 $HOME/Results/EcoliK12_index/')
#Download data from the E. coli transcriptome project of a K-12 derivative BW38028
#SRR1411276: https://www.ncbi.nlm.nih.gov/sra/SRX604287
os.system('prefetch -v SRR1411276 --output-directory $HOME/Results/')
##Convert the sra file into fastq format
os.system('fastq-dump $HOME/Results/SRR1411276/SRR1411276.sra --outdir $HOME/Results/SRR1411276/')
#Use Tophat to map reads from SRR1411276 to index, and save the results to 'Results/tophat_out/'
os.system('tophat2 -o $HOME/Results/tophat_out/ --no-novel-juncs $HOME/Results/EcoliK12_index/EcoliK12 $HOME/Results/SRR1411276/SRR1411276.fastq')
#Quantification
#Use Cufflinks to quantify transcriptomic expression and save the output to 'Results/Cufflinks_out/'
os.system('cufflinks -q -p 2 -o $HOME/Results/Cufflinks_out/ $HOME/Results/tophat_out/accepted_hits.bam')
#Rewrite the quantified transciptomic expression generated from Crufflinks to 'transcriptome_data.fpkm', which is a
#csv format file with seqname, start, end, strand and FPKM for each record.
fpkm = open(path+'transcriptome_data.fpkm', 'w')
writer = csv.writer(fpkm, delimiter = ',')
with open(path+'Cufflinks_out/transcripts.gtf') as handle:
reader = csv.reader(handle, delimiter = '\t')
for row in reader:
#Split the last column of attributes
temp = row[-1].split('; ')
#Save the record of FPKM
for att in temp:
if att.startswith('FPKM '):
f = att[6:-1]
#Write the information into 'transcriptome_data.fpkm'
new = []
new.append(row[0])
new.append(row[3])
new.append(row[4])
new.append(row[6])
new.append(f)
writer.writerow(new)
fpkm.close()