Spaces:
Sleeping
Sleeping
Commit
·
b9d0e9c
1
Parent(s):
298b080
Update code/add_3Dalignment.py
Browse files- code/add_3Dalignment.py +68 -6
code/add_3Dalignment.py
CHANGED
|
@@ -11,6 +11,35 @@ import gzip
|
|
| 11 |
from pathlib import Path
|
| 12 |
from Bio.Align import substitution_matrices
|
| 13 |
aligner = Align.PairwiseAligner()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
def distance(x1, y1, z1, x2, y2, z2):
|
| 16 |
d = math.sqrt(math.pow(x2 - x1, 2) +
|
|
@@ -186,7 +215,40 @@ def get_coords(annot, alignments, coords, resnums_for_sasa, mode):
|
|
| 186 |
|
| 187 |
|
| 188 |
def get_alignments_3D(identifier, model_num, pdb_path, pdbSequence, source, chain, pdbID, mode, path_3D_alignment,file_format = 'gzip'):
|
|
|
|
|
|
|
|
|
|
| 189 |
if mode == 1:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
atomSequence = ''
|
| 191 |
coords = []
|
| 192 |
resnums_for_sasa = []
|
|
@@ -206,7 +268,7 @@ def get_alignments_3D(identifier, model_num, pdb_path, pdbSequence, source, chai
|
|
| 206 |
atomSequence += threeToOne(line[17:20].strip())
|
| 207 |
coords.append([line[31:38].strip(), line[39:46].strip(), line[47:54].strip()])
|
| 208 |
resnums_for_sasa.append(line[22:26].strip())
|
| 209 |
-
|
| 210 |
#f = open(Path(path_3D_alignment / f'{identifier}_{pdbID}_{str(chain)}_alignment.txt'),"w")
|
| 211 |
|
| 212 |
aligner.mode = 'local'
|
|
@@ -249,15 +311,15 @@ def get_alignments_3D(identifier, model_num, pdb_path, pdbSequence, source, chai
|
|
| 249 |
atomSequence += threeToOne(line[17:20].strip())
|
| 250 |
coords.append([line[31:38].strip(), line[39:46].strip(), line[47:54].strip()])
|
| 251 |
resnums_for_sasa.append(line[22:26].strip())
|
| 252 |
-
f = open(Path(path_3D_alignment / f'{identifier}_{str(model_num)}_3Dalignment.txt'),"w")
|
| 253 |
aligner.mode = 'local'
|
| 254 |
aligner.substitution_matrix = substitution_matrices.load("BLOSUM62")
|
| 255 |
aligner.open_gap_score = -11
|
| 256 |
aligner.extend_gap_score = -1
|
| 257 |
alignments = aligner.align(pdbSequence, atomSequence)
|
| 258 |
alignments = (list(alignments))
|
| 259 |
-
for alignment in alignments:
|
| 260 |
-
|
| 261 |
-
|
| 262 |
-
|
| 263 |
return alignments, coords, resnums_for_sasa
|
|
|
|
| 11 |
from pathlib import Path
|
| 12 |
from Bio.Align import substitution_matrices
|
| 13 |
aligner = Align.PairwiseAligner()
|
| 14 |
+
import requests
|
| 15 |
+
from Bio.PDB import PDBParser, PPBuilder
|
| 16 |
+
from io import StringIO
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
from Bio.PDB.Polypeptide import *
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
def convert_non_standard_amino_acids(sequence):
|
| 23 |
+
"""
|
| 24 |
+
Convert non-standard or ambiguous amino acid codes to their closest relatives.
|
| 25 |
+
"""
|
| 26 |
+
|
| 27 |
+
# Define a dictionary to map non-standard codes to standard amino acids
|
| 28 |
+
conversion_dict = {
|
| 29 |
+
'B': 'D', # Aspartic Acid (D) is often used for B (Asx)
|
| 30 |
+
'Z': 'E', # Glutamic Acid (E) is often used for Z (Glx)
|
| 31 |
+
'X': 'A', # Alanine (A) is a common placeholder for unknown/ambiguous
|
| 32 |
+
'U': 'C', # Cysteine (C) is often used for Selenocysteine (U)
|
| 33 |
+
'J': 'L', # Leucine (L) is often used for J (Leu/Ile)
|
| 34 |
+
'O': 'K', # Lysine (K) is often used for O (Pyrrolysine)
|
| 35 |
+
# '*' or 'Stop' represents a stop codon; you may replace with '' to remove
|
| 36 |
+
'*': '',
|
| 37 |
+
}
|
| 38 |
+
|
| 39 |
+
# Replace non-standard codes with their closest relatives
|
| 40 |
+
converted_sequence = ''.join([conversion_dict.get(aa, aa) for aa in sequence])
|
| 41 |
+
|
| 42 |
+
return converted_sequence
|
| 43 |
|
| 44 |
def distance(x1, y1, z1, x2, y2, z2):
|
| 45 |
d = math.sqrt(math.pow(x2 - x1, 2) +
|
|
|
|
| 215 |
|
| 216 |
|
| 217 |
def get_alignments_3D(identifier, model_num, pdb_path, pdbSequence, source, chain, pdbID, mode, path_3D_alignment,file_format = 'gzip'):
|
| 218 |
+
st.write('I am here get alignments 3D')
|
| 219 |
+
uniprotSequence = convert_non_standard_amino_acids(uniprotSequence)
|
| 220 |
+
pdbSequence = convert_non_standard_amino_acids(pdbSequence)
|
| 221 |
if mode == 1:
|
| 222 |
+
if source != 'modbase':
|
| 223 |
+
|
| 224 |
+
# Step 1: Fetch the PDB file
|
| 225 |
+
pdb_url = f"https://files.rcsb.org/download/{pdbID}.pdb"
|
| 226 |
+
|
| 227 |
+
response = requests.get(pdb_url)
|
| 228 |
+
response.raise_for_status() # Check for a successful response
|
| 229 |
+
|
| 230 |
+
# Step 2: Parse the PDB file from memory
|
| 231 |
+
atoms = [i for i in response.text.split('\n') if i.startswith('ATOM')]
|
| 232 |
+
atoms = [i.split() for i in atoms]
|
| 233 |
+
atoms = [i for i in atoms if (i[2] == 'CA' and i[4] == chain)]
|
| 234 |
+
atomSequence = ''.join([three_to_one(i[3]) for i in atoms])
|
| 235 |
+
coords = [[i[6] ,i[7] ,i[8]] for i in atoms]
|
| 236 |
+
resnums_for_sasa = [i[5] for i in atoms]
|
| 237 |
+
else:
|
| 238 |
+
pdb_url = f"https://files.rcsb.org/download/{pdb_code}.pdb"
|
| 239 |
+
|
| 240 |
+
response = requests.get(pdbID)
|
| 241 |
+
response.raise_for_status() # Check for a successful response
|
| 242 |
+
|
| 243 |
+
# Step 2: Parse the PDB file from memory
|
| 244 |
+
atoms = [i for i in response.text.split('\n') if i.startswith('ATOM')]
|
| 245 |
+
atoms = [i.split() for i in atoms]
|
| 246 |
+
atoms = [i for i in atoms if i[2] == 'CA']
|
| 247 |
+
atomSequence = ''.join([three_to_one(i[3]) for i in atoms])
|
| 248 |
+
coords = [[i[6] ,i[7] ,i[8]] for i in atoms]
|
| 249 |
+
resnums_for_sasa = [i[5] for i in atoms]
|
| 250 |
+
|
| 251 |
+
"""
|
| 252 |
atomSequence = ''
|
| 253 |
coords = []
|
| 254 |
resnums_for_sasa = []
|
|
|
|
| 268 |
atomSequence += threeToOne(line[17:20].strip())
|
| 269 |
coords.append([line[31:38].strip(), line[39:46].strip(), line[47:54].strip()])
|
| 270 |
resnums_for_sasa.append(line[22:26].strip())
|
| 271 |
+
"""
|
| 272 |
#f = open(Path(path_3D_alignment / f'{identifier}_{pdbID}_{str(chain)}_alignment.txt'),"w")
|
| 273 |
|
| 274 |
aligner.mode = 'local'
|
|
|
|
| 311 |
atomSequence += threeToOne(line[17:20].strip())
|
| 312 |
coords.append([line[31:38].strip(), line[39:46].strip(), line[47:54].strip()])
|
| 313 |
resnums_for_sasa.append(line[22:26].strip())
|
| 314 |
+
#f = open(Path(path_3D_alignment / f'{identifier}_{str(model_num)}_3Dalignment.txt'),"w")
|
| 315 |
aligner.mode = 'local'
|
| 316 |
aligner.substitution_matrix = substitution_matrices.load("BLOSUM62")
|
| 317 |
aligner.open_gap_score = -11
|
| 318 |
aligner.extend_gap_score = -1
|
| 319 |
alignments = aligner.align(pdbSequence, atomSequence)
|
| 320 |
alignments = (list(alignments))
|
| 321 |
+
#for alignment in alignments:
|
| 322 |
+
# f.write(str(alignment))
|
| 323 |
+
# f.write('\n')
|
| 324 |
+
# f.write('\n')
|
| 325 |
return alignments, coords, resnums_for_sasa
|