def get_all_atoms():
# read in a pdb file
file = bpd().read_pdb('nuc_with_5FC.pdb')
# create a dataframe that contains all atoms
atoms = file.df['ATOM']
atoms
hetatm = file.df['HETATM']
hetatm
all_atoms = atoms.append(hetatm)
all_atoms
all_atoms.head(50)
all_atoms.tail(50)
# clean up the order - make sure atom numbers are nicely ascending
all_atoms = all_atoms.sort_values(['atom_number'], ascending=[True])
all_atoms
all_atoms.head(50)
all_atoms.tail(50)
return (all_atoms)
# set working directory to where your input pdb file is
import sys, os
os.chdir('C:\Kotryna\Python\Lab projects\pdb file handling\Input_Output_files')
cwd = os.getcwd()
print("cwd is: ", cwd)
# import tools you'll need
import pandas as pd
from biopandas.pdb import PandasPdb as bpd
import numpy as np
# read in a pdb file
file1 = bpd().read_pdb('nuc_with_hydrogens.pdb')
# create a dataframe that contains all atoms
atoms = file1.df['ATOM']
atoms
# write atoms out to csv for reference
#atoms.to_csv("../Output_files/original_atoms.csv", encoding='utf-8', index=False)
# what are the column names
atoms.columns
#############################################
# part 2 = specific DNA chain
# get the cytosines & their C5 atoms
"""
# set working directory to where your input pdb file is
import sys, os
os.chdir('C:\Kotryna\Python\Lab projects\pdb file handling\Input_Output_files')
cwd = os.getcwd()
print("cwd is: ", cwd)
# import tools you'll need
import pandas as pd
from biopandas.pdb import PandasPdb as bpd
import numpy as np
### make a dictionary to match atom numbers to atom names
# open pdb snippet that contains the relevant atom names & numbers
file = bpd().read_pdb('pdb_snippet_for_conect.txt')
# create a dataframe that contains all atoms
atoms = file.df['ATOM']
atoms
hetatm = file.df['HETATM']
hetatm
all_atoms = atoms.append(hetatm)
all_atoms
# extract atom numbers & names into lists
atom_numbers = all_atoms.atom_number.tolist()
atom_names = all_atoms.atom_name.tolist()
length = len(atom_numbers)
# set working directory to where your input pdb file is
import sys, os
os.chdir('C:\Kotryna\Python\Lab projects\pdb file handling\Input_Output_files')
cwd = os.getcwd()
print("cwd is: ", cwd)
# import tools you'll need
import pandas as pd
from biopandas.pdb import PandasPdb as bpd
import numpy as np
# read in a pdb file
file = bpd().read_pdb('pdb_with_5FC.pdb')
# create a dataframe that contains all atoms
atoms = file.df['ATOM']
atoms
hetatm = file.df['HETATM']
hetatm
all_atoms = atoms.append(hetatm)
all_atoms
all_atoms.tail(50)
## write atoms out to csv for reference