I'm fairly new with Biopython. Right now, I'm trying to compute protein parameters from several protein sequences (more than 100) in fasta format. However, I've found difficult to parse the sequences correctly.
This is the code im using:
from Bio import SeqIO
from Bio.SeqUtils.ProtParam import ProteinAnalysis
input_file = open ("/Users/matias/Documents/Python/DOE.fasta", "r")
for record in SeqIO.parse(input_file, "fasta"):
my_seq = str(record.seq)
analyse = ProteinAnalysis(my_seq)
print(analyse.molecular_weight())
But I'm getting this error message:
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site- packages/Bio/SeqUtils/__init__.py", line 438, in molecular_weight
weight = sum(weight_table[x] for x in seq) - (len(seq) - 1) * water
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/Bio/SeqUtils/__init__.py", line 438, in <genexpr>
weight = sum(weight_table[x] for x in seq) - (len(seq) - 1) * water
KeyError: '\\'
Printing each sequence as string shows me every seq has a "\" at the end, but so far I haven't been able to remove it. Any ideas would be very appreciated.
That really shouldn't be there in your file, but if you can't get a clean input file, you can use my_seq = str(record.seq).rstrip('\\') to remove it at runtime.
Related
Hi I am running this python script to remove over-representative sequences from my fastq files, but I keep getting the error. I am new to bioinfomatics and have been following a fixed set of pipeline for sequence assembly. I wanted to remove over-representative sequences with this script
python /home/TranscriptomeAssemblyTools/RemoveFastqcOverrepSequenceReads.py -1 R1_1.fq -2 R1_2.fq
**Here is the error
Traceback (most recent call last):
File "TranscriptomeAssemblyTools/RemoveFastqcOverrepSequenceReads.py", line 46, in
leftseqs=ParseFastqcLog(opts.l_fastqc)
File "TranscriptomeAssemblyTools/RemoveFastqcOverrepSequenceReads.py", line 33, in ParseFastqcLog
with open(fastqclog) as fp:
TypeError: coercing to Unicode: need string or buffer, NoneType found**
Here is the script :
import sys
import gzip
from os.path import basename
import argparse
import re
from itertools import izip,izip_longest
def seqsmatch(overreplist,read):
flag=False
if overreplist!=[]:
for seq in overreplist:
if seq in read:
flag=True
break
return flag
def get_input_streams(r1file,r2file):
if r1file[-2:]=='gz':
r1handle=gzip.open(r1file,'rb')
r2handle=gzip.open(r2file,'rb')
else:
r1handle=open(r1file,'r')
r2handle=open(r2file,'r')
return r1handle,r2handle
def FastqIterate(iterable,fillvalue=None):
"Grab one 4-line fastq read at a time"
args = [iter(iterable)] * 4
return izip_longest(fillvalue=fillvalue, *args)
def ParseFastqcLog(fastqclog):
with open(fastqclog) as fp:
for result in re.findall('Overrepresented sequences(.*?)END_MODULE', fp.read(), re.S):
seqs=([i.split('\t')[0] for i in result.split('\n')[2:-1]])
return seqs
if __name__=="__main__":
parser = argparse.ArgumentParser(description="options for removing reads with over-represented sequences")
parser.add_argument('-1','--left_reads',dest='leftreads',type=str,help='R1 fastq file')
parser.add_argument('-2','--right_reads',dest='rightreads',type=str,help='R2 fastq file')
parser.add_argument('-fql','--fastqc_left',dest='l_fastqc',type=str,help='fastqc text file for R1')
parser.add_argument('-fqr','--fastqc_right',dest='r_fastqc',type=str,help='fastqc text file for R2')
opts = parser.parse_args()
leftseqs=ParseFastqcLog(opts.l_fastqc)
rightseqs=ParseFastqcLog(opts.r_fastqc)
r1_out=open('rmoverrep_'+basename(opts.leftreads).replace('.gz',''),'w')
r2_out=open('rmoverrep_'+basename(opts.rightreads).replace('.gz',''),'w')
r1_stream,r2_stream=get_input_streams(opts.leftreads,opts.rightreads)
counter=0
failcounter=0
with r1_stream as f1, r2_stream as f2:
R1=FastqIterate(f1)
R2=FastqIterate(f2)
for entry in R1:
counter+=1
if counter%100000==0:
print "%s reads processed" % counter
head1,seq1,placeholder1,qual1=[i.strip() for i in entry]
head2,seq2,placeholder2,qual2=[j.strip() for j in R2.next()]
flagleft,flagright=seqsmatch(leftseqs,seq1),seqsmatch(rightseqs,seq2)
if True not in (flagleft,flagright):
r1_out.write('%s\n' % '\n'.join([head1,seq1,'+',qual1]))
r2_out.write('%s\n' % '\n'.join([head2,seq2,'+',qual2]))
else:
failcounter+=1
print 'total # of reads evaluated = %s' % counter
print 'number of reads retained = %s' % (counter-failcounter)
print 'number of PE reads filtered = %s' % failcounter
r1_out.close()
r2_out.close()
Maybe you already solved it, I had the same error but now is running well.
Hope this help
(1) Files we need:
usage: RemoveFastqcOverrepSequenceReads.py [-h] [-1 LEFTREADS] [-2 RIGHTREADS] [-fql L_FASTQC] [-fqr R_FASTQC
(2) Specify fastqc_data.text files that are in the fastqc output, unzip the output directory
'-fql','--fastqc_left',dest='l_fastqc',type=str,help='fastqc text file for R1'
'-fqr','--fastqc_right',dest='r_fastqc',type=str,help='fastqc text file for R2'
(3) Keep the reads and the fastqc_data text in the same directory
(4) Specify the path location before each file
python RemoveFastqcOverrepSequenceReads.py
-1 ./bicho.fq.1.gz -2./bicho.fq.2.gz
-fql ./fastqc_data_bicho_1.txt -fqr ./fastqc_data_bicho_2.txt
(5) run! :)
This is my python code. I have an excel file named test.csv with some data in it.
import numpy as np
import os
f=open('test.csv')
data=f.read()
f.close()
lines=data.split('\n')
header=lines[0].split(',')
lines=lines[1:]
print(header)
float_data=np.zeros((len(lines),len(header)-1))
for i,line in enumerate (lines):
values=[float(x) for x in line.split(',')[1:]]
float_data[i,:]=values
This is my excel data
Everytime i run, i get this error "Cannot copy sequence with size 0 to array with dimension 5."
A likely cause:
In [76]: y=np.zeros((3,5))
In [77]: y[0,:]=[]
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-77-e62a2beed947> in <module>()
----> 1 y[0,:]=[]
ValueError: cannot copy sequence with size 0 to array axis with dimension 5
For some line, values is an empty list. Maybe a blank line?
[float(x) for x in ''.split(',')[1:]]
I'm new to python and this site so thank-you in advance for your... understanding. This is my first attempt at a python script.
I'm having what I think is a performance issue trying to solve this problem which is causing me to not get any data back.
This code works on a small text file of a couple pages but when I try to use it on my 35MB real data text file it just hits the CPU and hasn't returned any data (>24 hours now).
Here's a snippet of the real data from the 35MB text file:
D)dddld
d00d90d
dd
ddd
vsddfgsdfgsf
dfsdfdsf
aAAAAAa
221546
29806916295
Meowing
fs:/mod/umbapp/umb/sentbox/221546.pdu
2013:10:4:22:11:31:4
sadfsdfsdf
sdfff
ff
f
29806916295
What's your cat doing?
fs:/mod/umbapp/umb/sentbox/10955.pdu
2013:10:4:22:10:15:4
aaa
aaa
aaaaa
What I'm trying to copy into a new file:
29806916295
Meowing
fs:/mod/umbapp/umb/sentbox/221546.pdu
2013:10:4:22:11:31:4
29806916295
What's your cat doing?
fs:/mod/umbapp/umb/sentbox/10955.pdu
2013:10:4:22:10:15:4
My Python code is:
import re
with open('testdata.txt') as myfile:
content = myfile.read()
text = re.search(r'\d{11}.*\n.*\n.*(\d{4})\D+(\d{2})\D+(\d{1})\D+(\d{2})\D+(\d{2})\D+\d{2}\D+\d{1}', content, re.DOTALL).group()
with open("result.txt", "w") as myfile2:
myfile2.write(text)
Regex isn't the fastest way to search a string. You also compounded the problem by having a very big string (35MB). Reading an entire file into memory is generally not recommended because you may run into memory issues.
Judging from your regex pattern, it seems like you want to capture 4-line groups that start with an 11-digit string and end with some time-line string. Try this code:
import re
start_pattern = re.compile(r'^\d{11}$')
end_pattern = re.compile(r'^\d{4}\D+\d{2}\D+\d{1}\D+\d{2}\D+\d{2}\D+\d{2}\D+\d{1}$')
capturing = 0
capture = ''
with open('output.txt', 'w') as output_file:
with open('input.txt', 'r') as input_file:
for line in input_file:
if capturing > 0 and capturing <= 4:
capturing += 1
capture += line
elif start_pattern.match(line):
capturing = 1
capture = line
if capturing == 4:
if end_pattern.match(line):
output_file.write(capture + '\n')
else:
capturing = 0
It iterates over the input file, line by line. If it finds a line matching the start_pattern, it will read in 3 more. If the 4th line matches the end_pattern, it will write the whole group to the output file.
I have written a python script that calls unix sort using subprocess module. I am trying to sort a table based on two columns(2 and 6). Here is what I have done
sort_bt=open("sort_blast.txt",'w+')
sort_file_cmd="sort -k2,2 -k6,6n {0}".format(tab.name)
subprocess.call(sort_file_cmd,stdout=sort_bt,shell=True)
The output file however contains an incomplete line which produces an error when I parse the table but when I checked the entry in the input file given to sort the line looks perfect. I guess there is some problem when sort tries to write the result to the file specified but I am not sure how to solve it though.
The line looks like this in the input file
gi|191252805|ref|NM_001128633.1| Homo sapiens RIMS binding protein 3C (RIMBP3C), mRNA gnl|BL_ORD_ID|4614 gi|124487059|ref|NP_001074857.1| RIMS-binding protein 2 [Mus musculus] 103 2877 3176 846 941 1.0102e-07 138.0
In output file however only gi|19125 is printed. How do I solve this?
Any help will be appreciated.
Ram
Using subprocess to call an external sorting tool seems quite silly considering that python has a built in method for sorting items.
Looking at your sample data, it appears to be structured data, with a | delimiter. Here's how you could open that file, and iterate over the results in python in a sorted manner:
def custom_sorter(first, second):
""" A Custom Sort function which compares items
based on the value in the 2nd and 6th columns. """
# First, we break the line into a list
first_items, second_items = first.split(u'|'), second.split(u'|') # Split on the pipe character.
if len(first_items) >= 6 and len(second_items) >= 6:
# We have enough items to compare
if (first_items[1], first_items[5]) > (second_items[1], second_items[5]):
return 1
elif (first_items[1], first_items[5]) < (second_items[1], second_items[5]):
return -1
else: # They are the same
return 0 # Order doesn't matter then
else:
return 0
with open(src_file_path, 'r') as src_file:
data = src_file.read() # Read in the src file all at once. Hope the file isn't too big!
with open(dst_sorted_file_path, 'w+') as dst_sorted_file:
for line in sorted(data.splitlines(), cmp = custom_sorter): # Sort the data on the fly
dst_sorted_file.write(line) # Write the line to the dst_file.
FYI, this code may need some jiggling. I didn't test it too well.
What you see is probably the result of trying to write to the file from multiple processes simultaneously.
To emulate: sort -k2,2 -k6,6n ${tabname} > sort_blast.txt command in Python:
from subprocess import check_call
with open("sort_blast.txt",'wb') as output_file:
check_call("sort -k2,2 -k6,6n".split() + [tab.name], stdout=output_file)
You can write it in pure Python e.g., for a small input file:
def custom_key(line):
fields = line.split() # split line on any whitespace
return fields[1], float(fields[5]) # Python uses zero-based indexing
with open(tab.name) as input_file, open("sort_blast.txt", 'w') as output_file:
L = input_file.read().splitlines() # read from the input file
L.sort(key=custom_key) # sort it
output_file.write("\n".join(L)) # write to the output file
If you need to sort a file that does not fit in memory; see Sorting text file by using Python
I am currently making my first python effort, a modification of some code written by a friend. I am using python 2.6.6. The original piece of code, which works, extracts information from a log file of data from donations made by credit card to my nonprofit. My new version, should it one day work, will perform the same task for donations that were made by paypal. The log files are similar, but have different field names and other differences.
The error messages I'm getting are:
Traceback (most recent call last):
File "../logparse-paypal-1.py", line 196, in
convert_log(sys.argv[1], sys.argv[2], access_ids)
File "../logparse-paypal-1.py", line 170, in convert_log
output = [f(record, access_ids) for f in output_fns]
TypeError: 'str' object is not callable
I've read some of the posts on this forum related to this error message, but so far I'm still at sea. I can't find any consequential differences between the portions of my code that related to the likely problem object (access_ids) and the code that I started with. All I did related to the access_ids table was to remove some lines that printed problems the script finds with the table that caused it to ignore some data. Perhaps I changed a character or something while doing that, but I've looked and so far can't find anything.
The portion of the code that is producing these error messages is the following:
# Use the output functions configured above to convert the
# transaction record into a list of outputs to be emitted to
# the CSV output file.
print "Converting %s at %s to CSV" % (record["type"], record["time"])
output = [f(record, access_ids) for f in output_fns]
j = 0
while j < len(output):
os.write(csv_fd, output[j])
if j < len(output) - 1:
os.write(csv_fd, ",")
else:
os.write(csv_fd, "\n")
j += 1
convert_count += 1
print "Converted %d approved transactions to CSV format, skipped %d non-approved transactions" % (convert_count, skip_count)
if __name__ == '__main__':
if len(sys.argv) < 3:
print "Usage: logparse.py INPUT_FILE OUTPUT_FILE [ACCESS_IDS_FILE]"
print
print " INPUT_FILE Silent post log containing transaction records (must exist)"
print " OUTPUT_FILE Filename for the CSV file to be created (must not exist, will be created)"
print " ACCESS_IDS_FILE List of Access IDs and email addresses (optional, must exist if specified)"
sys.exit(-1)
access_ids = {}
if len(sys.argv) > 3:
access_ids = load_access_ids(sys.argv[3])
convert_log(sys.argv[1], sys.argv[2], access_ids)
Line 170 is this one:
output = [f(record, access_ids) for f in output_fns]
and line 196 is this one:
convert_log(sys.argv[1], sys.argv[2], access_ids)
The access_ids definition, possibly related to the problem, is this:
def access_id_fn(record, access_ids):
if "payer_email" in record and len(record["payer_email"]) > 0:
if record["payer_email"] in access_ids:
return '"' + access_ids[record["payer_email"]] + '"'
else:
return ""
else:
return ""
AND
def load_access_ids(filename):
print "Loading Access IDs from %s..." % filename
access_ids = {}
for line in open(filename, "r"):
line = line.rstrip()
access_id, email = [s.strip() for s in line.split(None, 1)]
if not email_address.match(email):
continue
if email in access_ids:
access_ids[string.strip(email)] = string.strip(access_id)
return access_ids
Thanks in advance for any advice with this.
Dave
I'm not seeing anything right off hand, but you did mention that the log files were similar and I take that to mean that there are differences between the two.
Can you post a line from each?
I would double check the data in the log files and make sure what you think is being read in is correct. This definitely appears to me like a piece of data is being read in, but somewhere it is breaking what the code is expecting.