def calcDistances(pdb_name, input_file, output_dir):
p = PDBParser()
structure = p.get_structure("X", input_file)
resnam = [] # A list containing all Residue Names
resnum = [] # A list containing all Residue Numbers
reschain = [] # A list containing the chain name in which the residues lie
crdCA = []
crdSC = []
sizeSC = []
for residue in structure.get_residues():
resnam.append(residue.resname)
resnum.append(residue.get_full_id()[3][1])
reschain.append(residue.get_full_id()[2])
noSC = True
noCA = True
rescrd_SC = (
[]
) # A list containing the coordinates of all side chain atoms of the current residue. Will be used to calculate the COM of the side chain.
for atom in structure.get_atoms():
# atom.name is equivalent to atom.get_id()
if atom.parent.id == residue.id and atom.name == "CA":
noCA = False
crdCA.append(atom.get_coord())
elif atom.parent.id == residue.id and atom.name not in ["C", "CA", "O", "N"]:
noSC = False
rescrd_SC.append(atom.get_coord())
if noCA:
print(
"\nERROR: ",
pdb_name,
"has a missing alpha carbon at residue ",
resnum[-1],
". Please manually check PDB file for extraneous structural information (e.g. partially resolved"
"residues, bound DNA or ligands, etc.). Distances cannot be calculated.\n",
)
sys.exit()
if noSC:
print("Missing side chain in residue: ", resnum[-1], resnam[-1], ", possibly a GLY:", pdb_name)
crdSC.append(crdCA[-1])
sizeSC.append(0)
else:
# Calculate side chain properties:
sizeSC.append(len(rescrd_SC))
crdSC.append(sum(rescrd_SC) / float(sizeSC[-1]))
single_letter_aa = ph.convert_to_one_letter_code(resnam)
distSC = [["PDB_AA"] + [str(res.get_id()[1]) + resdict[res.get_resname()] for res in structure.get_residues()]]
for i in range(len(resnam)):
dist_sc_per_aa = [single_letter_aa[i]]
for j in range(len(single_letter_aa)):
distSCi = 0.0
if crdSC[i][0] == "NA" or crdSC[j][0] == "NA":
dist_sc_per_aa.append("NA")
continue
if i != j:
distSCi = math.sqrt(
(crdSC[i][0] - crdSC[j][0]) ** 2
+ (crdSC[i][1] - crdSC[j][1]) ** 2
+ (crdSC[i][2] - crdSC[j][2]) ** 2
)
dist_sc_per_aa.append(distSCi)
distSC.append(dist_sc_per_aa)
with open(output_dir + "/" + pdb_name + "_dist.csv", "wb") as output_file:
csv_writer = csv.writer(output_file, delimiter=",")
csv_writer.writerows(distSC)
def merge_df_by_aa(all_dfs, col_list, retain_gaps=False):
align_outfile = "temp.txt"
all_seqs = []
all_headers = []
# We'll use this later for looping through all the dataframes/files
df_range = xrange(len(all_dfs))
for i in df_range:
# Read in CSV files as dataframes
seq_list = all_dfs[i][col_list[i]].values
# print seq_list
# Grab AA sequence from column
if len(seq_list[0]) == 3:
seq = ''.join(ph.convert_to_one_letter_code(seq_list))
elif len(seq_list[0]) == 1:
seq = ''.join(seq_list)
else:
raise "Could not recognized amino acid column in dataframe."
# Append sequences and filenames to list for maaft processing
all_seqs.append(seq)
all_headers.append('>AA_' + str(i))
# Align sequences with mafft
align_seqs_mafft(all_seqs, all_headers, align_outfile)
# Extract the sequences from the aligned file
(seqs, headers) = ph.get_sequences(align_outfile)
# Now go backwards and build a dataframe with the sequences aligned
# Column headers are file names and rows are each AA in sequence.
aligned_seqs = dict()
for i in df_range:
aligned_seqs[headers[i][1:]] = list(seqs[i])
aligned_df = pd.DataFrame(data=aligned_seqs)
# Initialize list for storing newly constructed dataframes which will eventually be merged
# with aligned_df.
partial_dfs = []
# Loop through file list and append rows to a new dataframe corresponding to the aligned
# sequences. This is where the core functionality of this script happens.
for s in df_range:
j = 0
# How many rows in the original CSV?
row_length = len(all_dfs[s].index)
current_col = all_headers[s][1:]
# Initialize dict to store new rows. We will convert this back to a dataframe later.
# Building a dictionary of lists first and then converting to a DF, rather than appending rows
# to an existing DF is MUCH, MUCH faster.
new_df_dict = dict()
for index, row in aligned_df[current_col].iteritems():
# If the sequence in the alignment is not blank, and we haven't reached the end of
# the original CSV sequence length...
if j >= row_length:
break
if row != '-':
# Append rows from original CSV to our new dictionary
new_df_dict[index] = all_dfs[s].iloc[j, :].values
j += 1
# Append newly generated dataframe to a list to concatenate later
new_df = pd.DataFrame.from_dict(new_df_dict, orient='index')
# Add back in appropriate column names
new_df.columns = all_dfs[s].columns
partial_dfs.append(new_df)
# Insert aligned_df to the beginning of the list of new dataframes
partial_dfs.insert(0, aligned_df)
# Concatenate dataframes together by column (i.e., like cbind in R)
aligned_df = pd.concat(partial_dfs, axis=1)
# Remove any rows containing NaN
if retain_gaps is False:
aligned_df = aligned_df.dropna()
return aligned_df
