Delete utils_convert.py
Browse files- utils_convert.py +0 -82
utils_convert.py
DELETED
|
@@ -1,82 +0,0 @@
|
|
| 1 |
-
import numpy as np
|
| 2 |
-
from biopandas.pdb import PandasPdb
|
| 3 |
-
|
| 4 |
-
pdb_order = [
|
| 5 |
-
"record_name",
|
| 6 |
-
"atom_number",
|
| 7 |
-
"blank_1",
|
| 8 |
-
"atom_name",
|
| 9 |
-
"alt_loc",
|
| 10 |
-
"residue_name",
|
| 11 |
-
"blank_2",
|
| 12 |
-
"chain_id",
|
| 13 |
-
"residue_number",
|
| 14 |
-
"insertion",
|
| 15 |
-
"blank_3",
|
| 16 |
-
"x_coord",
|
| 17 |
-
"y_coord",
|
| 18 |
-
"z_coord",
|
| 19 |
-
"occupancy",
|
| 20 |
-
"b_factor",
|
| 21 |
-
"blank_4",
|
| 22 |
-
"segment_id",
|
| 23 |
-
"element_symbol",
|
| 24 |
-
"charge",
|
| 25 |
-
"line_idx",
|
| 26 |
-
]
|
| 27 |
-
mmcif_read = {
|
| 28 |
-
"group_PDB": "record_name",
|
| 29 |
-
"id": "atom_number",
|
| 30 |
-
"auth_atom_id": "atom_name",
|
| 31 |
-
"auth_comp_id": "residue_name",
|
| 32 |
-
"auth_asym_id": "chain_id",
|
| 33 |
-
"auth_seq_id": "residue_number",
|
| 34 |
-
"Cartn_x": "x_coord",
|
| 35 |
-
"Cartn_y": "y_coord",
|
| 36 |
-
"Cartn_z": "z_coord",
|
| 37 |
-
"occupancy": "occupancy",
|
| 38 |
-
"B_iso_or_equiv": "b_factor",
|
| 39 |
-
"type_symbol": "element_symbol",
|
| 40 |
-
}
|
| 41 |
-
|
| 42 |
-
nonefields = [
|
| 43 |
-
"blank_1",
|
| 44 |
-
"alt_loc",
|
| 45 |
-
"blank_2",
|
| 46 |
-
"insertion",
|
| 47 |
-
"blank_3",
|
| 48 |
-
"blank_4",
|
| 49 |
-
"segment_id",
|
| 50 |
-
"charge",
|
| 51 |
-
"line_idx",
|
| 52 |
-
]
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
def biopandas_mmcif2pdb(pandasmmcif, model_index = 1):
|
| 56 |
-
"""
|
| 57 |
-
Converts the ATOM and HETATM dataframes of PandasMmcif() to PandasPdb() format.
|
| 58 |
-
"""
|
| 59 |
-
pandaspdb = PandasPdb()
|
| 60 |
-
for a in ["ATOM", "HETATM"]:
|
| 61 |
-
dfa = pandasmmcif.df[a]
|
| 62 |
-
dfa = dfa.loc[dfa.pdbx_PDB_model_num == model_index]
|
| 63 |
-
if a =='ATOM':
|
| 64 |
-
if len(dfa) == 0:
|
| 65 |
-
raise ValueError(f"No model found for index: {model_index}")
|
| 66 |
-
# keep only those fields found in pdb
|
| 67 |
-
dfa = dfa[mmcif_read.keys()]
|
| 68 |
-
# rename fields
|
| 69 |
-
dfa = dfa.rename(columns=mmcif_read)
|
| 70 |
-
# add empty fields
|
| 71 |
-
for i in nonefields:
|
| 72 |
-
dfa[i] = ""
|
| 73 |
-
dfa["charge"] = np.nan
|
| 74 |
-
# reorder columns to PandasPdb order
|
| 75 |
-
dfa = dfa[pdb_order]
|
| 76 |
-
pandaspdb.df[a] = dfa
|
| 77 |
-
|
| 78 |
-
# update line_idx
|
| 79 |
-
pandaspdb.df["ATOM"]["line_idx"] = pandaspdb.df["ATOM"].index.values
|
| 80 |
-
pandaspdb.df["HETATM"]["line_idx"] = pandaspdb.df["HETATM"].index
|
| 81 |
-
|
| 82 |
-
return pandaspdb
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|