Save output from biopython object into a file? - python

Here i have a code written to extract "locus_tag" of gene using "id". How can i save the output from this into a file in a tab seperated format????code adopted and modified https://www.biostars.org/p/110284/
from Bio import SeqIO
foo = open("geneid.txt")
lines = foo.read().splitlines()
genbank_file = open("example.gbk")
for record in SeqIO.parse(genbank_file, "genbank"):
for f in record.features:
if f.type == "CDS" and "protein_id" in f.qualifiers:
protein_id = f.qualifiers["protein_id"][0]
if protein_id in lines:
print f.qualifiers["protein_id"][0],f.qualifiers["locus_tag"][0]

Try adding something like this -- but you will need to make certain the indentations are correct with the code that you have already written.
with open(your_outputFileName, 'w') as outputFile:
string = '\t'.join([f.qualifiers['protein_id'][0],f.qualifiers['locus_tag'][0]])
outputFile.write(string + '\n')
You should also consider opening your initial file using "with". This will automatically close the file when you are done with it -- otherwise -- be certain to close the file (e.g., foo.close()).
for record in SeqIO.parse(genbank_file, 'genbank'):
for f in record.features:
if f.type == 'CDS' and 'protein_id' in f.qualifiers:
protein_id = f.qualifiers['protein_id'][0]
if protein_id in lines:
print f.qualifiers['protein_id'][0],f.qualifiers['locus_tag'][0]
with open('your_outputFileName', 'w') as outputFile:
string = '\t'.join([f.qualifiers['protein_id'][0],f.qualifiers['locus_tag'][0]]) + '\n'
outputFile.write(string)

Related

Rename fasta file according to a dataframe in python

Hello I have huge file such as :
>Seq1.1
AAAGGAGAATAGA
>Seq2.2
AGGAGCTTCTCAC
>Seq3.1
CGTACTACGAGA
>Seq5.2
CGAGATATA
>Seq3.1
CGTACTACGAGA
>Seq2
AGGAGAT
and a dataframe such as :
tab
query New_query
Seq1.1 Seq1.1
Seq2.2 Seq2.2
Seq3.1 Seq3.1_0
Seq5.2 Seq5.2_3
Seq3.1 Seq3.1_1
and the idea is to rename the >Seqname according to the tab.
Then for each Seqname, if tab['query'] != tab['New_query'], then rename the Seqname as tab['New_query']
Ps: All the >Seqname are not present in the tab, if it is the case then I do nothing.
I should then get a new fasta file such as :
>Seq1.1
AAAGGAGAATAGA
>Seq2.2
AGGAGCTTCTCAC
>Seq3.1_0
CGTACTACGAGA
>Seq5.2_3
CGAGATATA
>Seq3.1_1
CGTACTACGAGA
>Seq2
AGGAGAT
I tried this code :
records = SeqIO.parse("My_fasta_file.aa", 'fasta')
for record in records:
subtab=tab[tab['query']==record.id]
subtab=subtab.drop_duplicates(subset ="New_query",keep = "first")
if subtab.empty == True: #it means that the seq was not in the tab, so I do not rename the sequence.
continue
else:
if subtab['query'].iloc[0] != subtab['New_query'].iloc[0]:
record.id = subtab['New_query']
record.description = subtab['New_query']
else:
continue
it works but it takes to much time ...
You can create a mapper dictionary from the dataframe and then read the fasta file line by line, substituting the lines which starts with >:
mapper = tab.set_index('query').to_dict()['New_query']
with open('My_fasta_file.aa', 'r') as f_in, open('output.txt', 'w') as f_out:
for line in map(str.strip, f_in):
if line.startswith('>'):
v = line.split('>')[-1]
line = '>{}'.format(mapper.get(v, v))
print(line, file=f_out)
Creates output.txt:
>Seq1.1
AAAGGAGAATAGA
>Seq2.2
AGGAGCTTCTCAC
>Seq3.1_1
CGTACTACGAGA
>Seq5.2_3
CGAGATATA
>Seq3.1_1
CGTACTACGAGA
>Seq2
AGGAGAT
The solution by #Andrej using a dictionary is indeed the way to go.. Since you are already using biopython, below is a way to use it, and I think it might be good because it does handle fasta files properly..
Your data.frame is:
tab = pd.DataFrame({'query':['Seq1.1','Seq2.2','Seq3.1','Seq5.2','Seq3.1'],
'New_query':['Seq1.1','Seq2.2','Seq3.1_0','Seq5.2_3','Seq3.1_1']})
Same dictionary as Andrej:
mapper = tab.set_index('query').to_dict()['New_query']
Then similar to what you have done, we just change the header (by updating id and description, thanks to #Chris_Rands):
records = list(SeqIO.parse("My_fasta_file.aa", "fasta"))
for i in records:
i.id = mapper.get(i.id,i.id)
i.description = mapper.get(i.description,i.description)
Now write the file:
with open("new.fasta", "w") as output_handle:
SeqIO.write(records, output_handle, "fasta")

How do I replace a text file's contents with another if they are different?

I am looking to replace one text file with the contents of another if they are not the same.
Whenever I run this script, "['" and "']" are added on to the old_text.txt file, which means it will never match with new_text.txt file.
How do I remove these characters so the .txt files have the exact same contents after running this script?
old_text = open('old_text.txt', 'r+')
new_text = open('new_text.txt', 'r+')
old_text_compare = str(old_text.readlines())
new_text_compare = str(new_text.readlines())
if old_text_compare != new_text_compare:
print("difference")
old_text = open('old_text.txt', 'w')
old_text.write(str(new_text_compare))
else:
print("no difference")
If you want to compare file contents directly, use .read() rather than .readlines()
with open('old_text.txt', 'r+') as f1, open('new_text.txt', 'r+') as f2:
old = f1.read()
new = f2.read()
if old != new:
with open('new_text.txt', 'w') as f1:
f1.write(old)
else:
print("no difference")
You want to compare the list of lines directly, like so:
if old_text.readlines() != new_text.readlines():
...

replace line if found or append - python

I have text that is key-value pairs separated by '='. I would like to replace the line if the key matches. if not, i would like to append it at the bottom. I've tried several ways, including:
def split_command_key_and_value(command):
if '=' in command:
command2 = command.split('=')
return command2
def test(command, path):
command2 = split_command_key_and_value(command)
pattern = command2[0]
myfile = open(path,'r') # open file handle for read
# use r'', you don't need to replace '\' with '/'
result = open(path, 'w') # open file handle for write
for line in myfile:
line = line.strip() # it's always a good behave to strip what you read from files
if pattern in line:
line = command # if match, replace line
result.write(line) # write every line
myfile.close() # don't forget to close file handle
result.close()
I know the above is just to replace text, but it deletes the text in the file, and I can't see why. Could someone point me in the right direction?
Thanks
Update:
I'm almost there, but some of my lines have similar keys, so mutiple lines are matching when only 1 should. I've tried to incorporate a regex boundary in my loop with no luck. My code is below. Does anyone have a suggestion?
There is some text in the file that isn't key-value, so I would like to skip that.
def modify(self, name, value):
comb = name + ' ' + '=' + ' ' + value + '\n'
with open('/file/', 'w') as tmpstream:
with open('/file/', 'r') as stream:
for line in stream:
if setting_name in line:
tmpstream.write(comb)
else:
tmpstream.write(line)
I think I got it. See code below.
def modify(self, name, value):
comb = name + ' ' + '=' + ' ' + value + '\n'
mylist = []
with open('/file/', 'w') as tmpstream:
with open('/file/', 'r') as stream:
for line in stream:
a = line.split()
b = re.compile('\\b'+name+'\\b')
if len(a) > 0:
if b.search(a[0]):
tmpstream.write(comb)
else:
tmpstream.write(line)
I spoke too soon. It stops at the key-value I provide. So, it only writes one line, and doesn't write the lines that don't match.
def modify(name, value):
comb = name + ' ' + '=' + ' ' + value + '\n'
mylist = []
with open('/file1', 'w') as tmpstream:
with open('/file2', 'r') as stream:
for line in stream:
a = line.split()
b = re.compile('\\b'+name+'\\b')
if len(a) > 0:
if b.search(a[0]):
tmpstream.write(comb)
else:
tmpstream.write(line)
Can anyone see the issue?
Because when you open file for writing
result = open(path, 'w') # open file handle for write
you just erase it content. Try to write in different file and after all work done replace old file with new one. Or read all data into memory and then process it and write to file.
with open(path) as f:
data = f.read()
with open(path, 'w') as f:
for l in data:
# make job here
first of all you are reading an writing the same file ...
you could first read it all and the write line by line
with open(path,'r') as f:
myfile = f.read() # read everything in the variable "myfile"
result = open(path, 'w') # open file handle for write
for line in myfile.splitlines(): # process the original file content 1 line at a time
# as before
I strongly recommend reading python's documentation on how to read and write files.
If you open an existing file in write-mode open(path, 'w'), its content will be erased:
mode can be (...) 'w' for only writing (an existing file with the same name will be erased)
To replace a line in python you can have a look at this: Search and replace a line in a file in Python
Here is one the solutions provided there adapted to your context (tested for python3):
from tempfile import mkstemp
from shutil import move
from os import close
def test(filepath, command):
# Split command into key/value
key, _ = command.split('=')
matched_key = False
# Create a temporary file
fh, tmp_absolute_path = mkstemp()
with open(tmp_absolute_path, 'w') as tmp_stream:
with open(filepath, 'r') as stream:
for line in stream:
if key in line:
matched_key = True
tmp_stream.write(command + '\n')
else:
tmp_stream.write(line)
if not matched_key:
tmp_stream.write(command + '\n')
close(fh)
move(tmp_absolute_path, filepath)
Note that with the code above every line that matches key (key=blob or blob=key) will be replaced.

How should I replace parts from a text file through Python?

Okay, so here's the deal, folks:
I've been experimenting with Python(3.3), trying to create a python program capable of generating random names for weapons in a game and replacing their old names, which are located inside a text file. Here's my function:
def ModifyFile(shareddottxt):
global name
a = open(str(shareddottxt) , 'r')
b = a.read()
namefix1 = '''SWEP.PrintName = "'''
namefix2 = '''" //sgaardname'''
name1 = b.find(namefix1) + len(namefix1)
name2 = b.find(namefix2, name1)
name = name + b[name1:name2] ## We got our weapon's name! Let's add the suffix.
c = open((shareddottxt + ".lua"), 'r+')
for line in b:
c.write(line.replace(name, (name + namesuffix)))
c.close()
a.close
As you can see, I first open my text file to find the weapon's name. After that, I try to create a new file and copy the contents from the old one, while replacing the weapon's name for (name + namesuffix). However, after calling the function, I get nothing. No file whatsoever. And even if I DO add the file to the folder manually, it does not change. At all.
Namesuffix is generated through another function early on. It is saved as a global var.
Also, my text file is huge, but the bit I'm trying to edit is:
SWEP.PrintName = "KI Stinger 9mm" //sgaardname
The expected result:
SWEP.PrintName = "KI Stinger 9mm NAMESUFFIX" //sgaardname
Where did I mess up, guys?
Something like this is more pythonic.
def replace_in_file(filename, oldtext, newtext):
with open(filename, 'r+') as file:
lines = file.read()
new_lines = lines.replace(oldtext, newtext)
file.seek(0)
file.write(new_lines)
If you don't want to replace that file
def replace_in_file(filename, oldtext, newtext):
with open(filename, 'r') as file, open(filename + ".temp", 'w') as temp:
lines = file.read()
new_lines = lines.replace(oldtext, newtext)
temp.write(new_lines)

How to search and replace text in a file?

How do I search and replace text in a file using Python 3?
Here is my code:
import os
import sys
import fileinput
print ("Text to search for:")
textToSearch = input( "> " )
print ("Text to replace it with:")
textToReplace = input( "> " )
print ("File to perform Search-Replace on:")
fileToSearch = input( "> " )
#fileToSearch = 'D:\dummy1.txt'
tempFile = open( fileToSearch, 'r+' )
for line in fileinput.input( fileToSearch ):
if textToSearch in line :
print('Match Found')
else:
print('Match Not Found!!')
tempFile.write( line.replace( textToSearch, textToReplace ) )
tempFile.close()
input( '\n\n Press Enter to exit...' )
Input file:
hi this is abcd hi this is abcd
This is dummy text file.
This is how search and replace works abcd
When I search and replace 'ram' by 'abcd' in above input file, it works as a charm. But when I do it vice-versa i.e. replacing 'abcd' by 'ram', some junk characters are left at the end.
Replacing 'abcd' by 'ram'
hi this is ram hi this is ram
This is dummy text file.
This is how search and replace works rambcd
As pointed out by michaelb958, you cannot replace in place with data of a different length because this will put the rest of the sections out of place. I disagree with the other posters suggesting you read from one file and write to another. Instead, I would read the file into memory, fix the data up, and then write it out to the same file in a separate step.
# Read in the file
with open('file.txt', 'r') as file :
filedata = file.read()
# Replace the target string
filedata = filedata.replace('abcd', 'ram')
# Write the file out again
with open('file.txt', 'w') as file:
file.write(filedata)
Unless you've got a massive file to work with which is too big to load into memory in one go, or you are concerned about potential data loss if the process is interrupted during the second step in which you write data to the file.
fileinput already supports inplace editing. It redirects stdout to the file in this case:
#!/usr/bin/env python3
import fileinput
with fileinput.FileInput(filename, inplace=True, backup='.bak') as file:
for line in file:
print(line.replace(text_to_search, replacement_text), end='')
As Jack Aidley had posted and J.F. Sebastian pointed out, this code will not work:
# Read in the file
filedata = None
with file = open('file.txt', 'r') :
filedata = file.read()
# Replace the target string
filedata.replace('ram', 'abcd')
# Write the file out again
with file = open('file.txt', 'w') :
file.write(filedata)`
But this code WILL work (I've tested it):
f = open(filein,'r')
filedata = f.read()
f.close()
newdata = filedata.replace("old data","new data")
f = open(fileout,'w')
f.write(newdata)
f.close()
Using this method, filein and fileout can be the same file, because Python 3.3 will overwrite the file upon opening for write.
You can do the replacement like this
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'w')
for line in f1:
f2.write(line.replace('old_text', 'new_text'))
f1.close()
f2.close()
You can also use pathlib.
from pathlib2 import Path
path = Path(file_to_search)
text = path.read_text()
text = text.replace(text_to_search, replacement_text)
path.write_text(text)
(pip install python-util)
from pyutil import filereplace
filereplace("somefile.txt","abcd","ram")
Will replace all occurences of "abcd" with "ram".
The function also supports regex by specifying regex=True
from pyutil import filereplace
filereplace("somefile.txt","\\w+","ram",regex=True)
Disclaimer: I'm the author (https://github.com/MisterL2/python-util)
Open the file in read mode. Read the file in string format. Replace the text as intended. Close the file. Again open the file in write mode. Finally, write the replaced text to the same file.
try:
with open("file_name", "r+") as text_file:
texts = text_file.read()
texts = texts.replace("to_replace", "replace_string")
with open(file_name, "w") as text_file:
text_file.write(texts)
except FileNotFoundError as f:
print("Could not find the file you are trying to read.")
Late answer, but this is what I use to find and replace inside a text file:
with open("test.txt") as r:
text = r.read().replace("THIS", "THAT")
with open("test.txt", "w") as w:
w.write(text)
DEMO
With a single with block, you can search and replace your text:
with open('file.txt','r+') as f:
filedata = f.read()
filedata = filedata.replace('abc','xyz')
f.truncate(0)
f.write(filedata)
Your problem stems from reading from and writing to the same file. Rather than opening fileToSearch for writing, open an actual temporary file and then after you're done and have closed tempFile, use os.rename to move the new file over fileToSearch.
My variant, one word at a time on the entire file.
I read it into memory.
def replace_word(infile,old_word,new_word):
if not os.path.isfile(infile):
print ("Error on replace_word, not a regular file: "+infile)
sys.exit(1)
f1=open(infile,'r').read()
f2=open(infile,'w')
m=f1.replace(old_word,new_word)
f2.write(m)
Using re.subn it is possible to have more control on the substitution process, such as word splitted over two lines, case-(in)sensitive match. Further, it returns the amount of matches which can be used to avoid waste of resources if the string is not found.
import re
file = # path to file
# they can be also raw string and regex
textToSearch = r'Ha.*O' # here an example with a regex
textToReplace = 'hallo'
# read and replace
with open(file, 'r') as fd:
# sample case-insensitive find-and-replace
text, counter = re.subn(textToSearch, textToReplace, fd.read(), re.I)
# check if there is at least a match
if counter > 0:
# edit the file
with open(file, 'w') as fd:
fd.write(text)
# summary result
print(f'{counter} occurence of "{textToSearch}" were replaced with "{textToReplace}".')
Some regex:
add the re.I flag, short form of re.IGNORECASE, for a case-insensitive match
for multi-line replacement re.subn(r'\n*'.join(textToSearch), textToReplace, fd.read()), depending on the data also '\n{,1}'. Notice that for this case textToSearch must be a pure string, not a regex!
Besides the answers already mentioned, here is an explanation of why you have some random characters at the end:
You are opening the file in r+ mode, not w mode. The key difference is that w mode clears the contents of the file as soon as you open it, whereas r+ doesn't.
This means that if your file content is "123456789" and you write "www" to it, you get "www456789". It overwrites the characters with the new input, but leaves any remaining input untouched.
You can clear a section of the file contents by using truncate(<startPosition>), but you are probably best off saving the updated file content to a string first, then doing truncate(0) and writing it all at once.
Or you can use my library :D
I got the same issue. The problem is that when you load a .txt in a variable you use it like an array of string while it's an array of character.
swapString = []
with open(filepath) as f:
s = f.read()
for each in s:
swapString.append(str(each).replace('this','that'))
s = swapString
print(s)
I tried this and used readlines instead of read
with open('dummy.txt','r') as file:
list = file.readlines()
print(f'before removal {list}')
for i in list[:]:
list.remove(i)
print(f'After removal {list}')
with open('dummy.txt','w+') as f:
for i in list:
f.write(i)
you can use sed or awk or grep in python (with some restrictions). Here is a very simple example. It changes banana to bananatoothpaste in the file. You can edit and use it. ( I tested it worked...note: if you are testing under windows you should install "sed" command and set the path first)
import os
file="a.txt"
oldtext="Banana"
newtext=" BananaToothpaste"
os.system('sed -i "s/{}/{}/g" {}'.format(oldtext,newtext,file))
#print(f'sed -i "s/{oldtext}/{newtext}/g" {file}')
print('This command was applied: sed -i "s/{}/{}/g" {}'.format(oldtext,newtext,file))
if you want to see results on the file directly apply: "type" for windows/ "cat" for linux:
####FOR WINDOWS:
os.popen("type " + file).read()
####FOR LINUX:
os.popen("cat " + file).read()
I have done this:
#!/usr/bin/env python3
import fileinput
import os
Dir = input ("Source directory: ")
os.chdir(Dir)
Filelist = os.listdir()
print('File list: ',Filelist)
NomeFile = input ("Insert file name: ")
CarOr = input ("Text to search: ")
CarNew = input ("New text: ")
with fileinput.FileInput(NomeFile, inplace=True, backup='.bak') as file:
for line in file:
print(line.replace(CarOr, CarNew), end='')
file.close ()
I modified Jayram Singh's post slightly in order to replace every instance of a '!' character to a number which I wanted to increment with each instance. Thought it might be helpful to someone who wanted to modify a character that occurred more than once per line and wanted to iterate. Hope that helps someone. PS- I'm very new at coding so apologies if my post is inappropriate in any way, but this worked for me.
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'w')
n = 1
# if word=='!'replace w/ [n] & increment n; else append same word to
# file2
for line in f1:
for word in line:
if word == '!':
f2.write(word.replace('!', f'[{n}]'))
n += 1
else:
f2.write(word)
f1.close()
f2.close()
def word_replace(filename,old,new):
c=0
with open(filename,'r+',encoding ='utf-8') as f:
a=f.read()
b=a.split()
for i in range(0,len(b)):
if b[i]==old:
c=c+1
old=old.center(len(old)+2)
new=new.center(len(new)+2)
d=a.replace(old,new,c)
f.truncate(0)
f.seek(0)
f.write(d)
print('All words have been replaced!!!')
I have worked this out as an exercise of a course: open file, find and replace string and write to a new file.
class Letter:
def __init__(self):
with open("./Input/Names/invited_names.txt", "r") as file:
# read the list of names
list_names = [line.rstrip() for line in file]
with open("./Input/Letters/starting_letter.docx", "r") as f:
# read letter
file_source = f.read()
for name in list_names:
with open(f"./Output/ReadyToSend/LetterTo{name}.docx", "w") as f:
# replace [name] with name of the list in the file
replace_string = file_source.replace('[name]', name)
# write to a new file
f.write(replace_string)
brief = Letter()
Like so:
def find_and_replace(file, word, replacement):
with open(file, 'r+') as f:
text = f.read()
f.write(text.replace(word, replacement))
def findReplace(find, replace):
import os
src = os.path.join(os.getcwd(), os.pardir)
for path, dirs, files in os.walk(os.path.abspath(src)):
for name in files:
if name.endswith('.py'):
filepath = os.path.join(path, name)
with open(filepath) as f:
s = f.read()
s = s.replace(find, replace)
with open(filepath, "w") as f:
f.write(s)

Categories