tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

tidy kd_df script

Browse source
This commit is contained in:
Tanushree Tunstall 2020-04-07 17:42:06 +01:00
parent ae541ca16a
commit 73ae22e8a2
1 changed files with 23 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

40
scripts/kd_df.py
View file

@ -78,7 +78,8 @@ print('Output filename:', out_filename
, '\n=============================================================') , '\n=============================================================')
#%% end of variable assignment for input and output files #%% end of variable assignment for input and output files
#======================================================================= #=======================================================================
def kd_to_csv(inputfasta, outputkdcsv, windowsize): #%% kd values from fasta file and output csv
def kd_to_csv(inputfasta, outputkdcsv, windowsize, plot=False):
""" """
Calculate kd (hydropathy values) from input fasta file Calculate kd (hydropathy values) from input fasta file
@ -181,17 +182,14 @@ def kd_to_csv(inputfasta, outputkdcsv, windowsize):
#=============== #===============
# writing file # writing file
#=============== #===============
print('Writing file:', out_filename print('Writing file:'
, '\nFilename:', out_filename , '\nFilename:', outputkdcsv
, '\nPath:', outdir # , '\nPath:', outdir
, '\nExpected no. of rows:', len(kd_df)
, '\nExpected no. of cols:', len(kd_df.columns)
, '\n=============================================================') , '\n=============================================================')
kd_df.to_csv(outfile, header = True, index = True) kd_df.to_csv(outputkdcsv, header = True, index = True)
print('Finished writing:', out_filename
, '\nNo. of rows:', len(kd_df)
, '\nNo. of cols:', len(kd_df.columns)
, '\n=============================================================')
#=============== #===============
# plot: optional! # plot: optional!
@ -201,12 +199,14 @@ def kd_to_csv(inputfasta, outputkdcsv, windowsize):
# FIXME: save fig # FIXME: save fig
# extract just pdb if from 'id' to pass to title of plot # extract just pdb if from 'id' to pass to title of plot
# foo = re.match(r'(^[0-9]{1}\w{3})', id).groups(1) # foo = re.match(r'(^[0-9]{1}\w{3})', id).groups(1)
plot(kd_values, linewidth = 1.0) if plot:
#axis(xmin = 1, xmax = num_residues) plot(kd_values, linewidth = 1.0)
xlabel('Residue Number') #axis(xmin = 1, xmax = num_residues)
ylabel('Hydrophobicity') xlabel('Residue Number')
title('K&D Hydrophobicity for ' + id) ylabel('Hydrophobicity')
show() title('K&D Hydrophobicity for ' + id)
show()
#%% end of function #%% end of function
#======================================================================= #=======================================================================
#%% call function #%% call function
@ -214,7 +214,13 @@ def kd_to_csv(inputfasta, outputkdcsv, windowsize):
#======================================================================= #=======================================================================
def main(): def main():
print('Running hydropathy calcs', in_filename, 'output csv:', out_filename) print('Running hydropathy calcs', in_filename, 'output csv:', out_filename)
kd_to_csv(infile, outfile, windowsize = 3) kd_to_csv(infile, outfile, 3)
print('Finished writing file:'
, '\nFilename:', outfile
, '\nPath:', outdir
# , '\nNo. of rows:', ''
# , '\nNo. of cols:', ''
, '\n=============================================================')
if __name__ == '__main__': if __name__ == '__main__':
main() main()