| 1 |
""" |
| 2 |
VASCO Chemical Shift format parser. |
| 3 |
""" |
| 4 |
|
| 5 |
import csb.core |
| 6 |
|
| 7 |
|
| 8 |
class ShiftInfo(object): |
| 9 |
|
| 10 |
def __init__(self, residue_id, amino_acid, nucleus, |
| 11 |
shift, element, secondary_structure): |
| 12 |
|
| 13 |
self.residue_id = residue_id |
| 14 |
self.nucleus = nucleus |
| 15 |
self.element = element |
| 16 |
self.amino_acid = amino_acid |
| 17 |
self.shift = shift |
| 18 |
self.secondary_structure = secondary_structure |
| 19 |
|
| 20 |
def __str__(self): |
| 21 |
return '{0.amino_acid} {0.nucleus} {0.shift}'.format(self) |
| 22 |
|
| 23 |
__repr__ = __str__ |
| 24 |
|
| 25 |
|
| 26 |
class ChemicalShiftContainer(csb.core.DictionaryContainer): |
| 27 |
|
| 28 |
def __init__(self, bmrb_id='', pdb_id='', sequence='', |
| 29 |
chain='', exptype=''): |
| 30 |
|
| 31 |
self.bmrb_id = bmrb_id |
| 32 |
self.pdb_id = pdb_id |
| 33 |
self.sequence = sequence |
| 34 |
self.chain = chain |
| 35 |
self.exptype = exptype |
| 36 |
|
| 37 |
super(ChemicalShiftContainer, self).__init__() |
| 38 |
|
| 39 |
class VascoStructureParser(object): |
| 40 |
""" |
| 41 |
Simple Vasco Parser |
| 42 |
""" |
| 43 |
|
| 44 |
def __init__(self): |
| 45 |
self._stream = None |
| 46 |
|
| 47 |
def parse(self, file_name, ignore_outliers=True): |
| 48 |
""" |
| 49 |
@param file_name: source file to parse |
| 50 |
@type file_name: str |
| 51 |
@return: a L{ChemicalShiftContainer} of L{ShiftInfo} objects |
| 52 |
@rtype: dict |
| 53 |
""" |
| 54 |
self._stream = open(file_name) |
| 55 |
shifts = self._parse_header() |
| 56 |
|
| 57 |
self._parse_shifts(shifts, ignore_outliers=ignore_outliers) |
| 58 |
self._stream.close() |
| 59 |
|
| 60 |
return shifts |
| 61 |
|
| 62 |
def _parse_header(self): |
| 63 |
|
| 64 |
bmrb_id = '' |
| 65 |
pdb_id = '' |
| 66 |
sequence = '' |
| 67 |
chain = '' |
| 68 |
exptype = '' |
| 69 |
self._stream.seek(0) |
| 70 |
|
| 71 |
while True: |
| 72 |
try: |
| 73 |
line = next(self._stream) |
| 74 |
except StopIteration : |
| 75 |
break |
| 76 |
|
| 77 |
if line.startswith('#'): |
| 78 |
if line[2:].startswith('BMRB ORIGIN'): |
| 79 |
bmrb_id = line[20:].strip() |
| 80 |
elif line[2:].startswith('PDB ORIGIN'): |
| 81 |
pdb_id = line[20:].strip() |
| 82 |
elif line[2:].startswith('SEQUENCE PDB'): |
| 83 |
sequence = line[20:].strip() |
| 84 |
chain = line[17] |
| 85 |
elif line[2:].startswith('PDB EXPTYPE'): |
| 86 |
exptype = line[20:].strip() |
| 87 |
else: |
| 88 |
break |
| 89 |
|
| 90 |
|
| 91 |
return ChemicalShiftContainer(bmrb_id, pdb_id, chain, |
| 92 |
sequence, exptype ) |
| 93 |
|
| 94 |
|
| 95 |
def _parse_shifts(self, data, ignore_outliers=True): |
| 96 |
|
| 97 |
while True: |
| 98 |
try: |
| 99 |
line = next(self._stream) |
| 100 |
except StopIteration: |
| 101 |
break |
| 102 |
|
| 103 |
if ignore_outliers and "Shift outlier" in line: |
| 104 |
continue |
| 105 |
|
| 106 |
chain_id = line[7] |
| 107 |
res_code = line[9:14].strip() |
| 108 |
res_label = line[16:19].strip() |
| 109 |
res_ss = line[21] |
| 110 |
nucleus_name = line[23:28].strip() |
| 111 |
nucleus_element = line[41] |
| 112 |
shift = float(line[43:52]) |
| 113 |
|
| 114 |
info = ShiftInfo(res_code, res_label, |
| 115 |
nucleus_name, shift, |
| 116 |
nucleus_element, res_ss) |
| 117 |
|
| 118 |
if not chain_id in data: |
| 119 |
data.append(chain_id, csb.core.OrderedDict()) |
| 120 |
|
| 121 |
if not res_code in data[chain_id]: |
| 122 |
data[chain_id][res_code] = {} |
| 123 |
|
| 124 |
|
| 125 |
data[chain_id][res_code][nucleus_name] = info |
| 126 |
|
| 127 |
|