def setUp(self):
logger.debug('SETUP TESTS...')
in_file_lst = [
r'../test/TestInput/test_crosscheck.xlsx',
r'test/TestInput/test_crosscheck.xlsx',
r'../TestInput/test_crosscheck.xlsx',
r'TestInput/test_crosscheck.xlsx',
]
in_file = ''
for f in in_file_lst:
if os.path.isfile(f):
in_file = os.path.abspath(f)
break
logger.info(f'Input file {in_file}')
bad_in_file = r'test/TestInput/test_crosscheck_x.txt'
out_folder_lst = [
r'../test/TestOutput/',
r'test/TestOutput/',
r'../TestOutput/',
r'TestOutput/',
]
out_folder = ''
for p in out_folder_lst:
if os.path.isdir(p):
out_folder = os.path.abspath(p)
break
out_file = os.path.join(out_folder, 'test_crosscheck_output.csv')
logger.info(f'Out put file will be: {out_file}')
self.pass_params = ['-i', in_file, '-o', out_file]
self.fail_input_params = ['-i', bad_in_file, '-o', out_file]
def load_file(file: str) -> dict:
if os.path.isfile(file):
if file.lower().endswith('.xlsx'):
abbr_df = pd.read_excel(file)
elif file.lower().endswith('.csv'):
abbr_df = pd.read_csv(file)
elif file.lower().endswith('.tsv'):
abbr_df = pd.read_csv(file, sep='\t')
else:
abbr_df = pd.DataFrame()
logger.error(f'Can Not load file: {file}')
else:
raise FileNotFoundError
abbr_df.fillna('', inplace=True)
groups_lst = abbr_df.columns.tolist()
logger.info(
f'Input {len(groups_lst)} abbreviation groups: {", ".join(groups_lst)}'
)
abbr_dct = {}
if not abbr_df.empty:
for g in groups_lst:
col_abbr_lst = abbr_df[g].unique().tolist()
try:
col_abbr_lst.remove('')
except ValueError:
pass
abbr_dct[g] = col_abbr_lst
return abbr_dct
def main(argv):
"""
:param argv: -i <input epiLION abbreviation file in .txt format>
"""
in_file = ''
out_file = ''
is_output = False
try:
opts, args = getopt.getopt(argv, "hi:o:", ["infile=", "outfile="])
logger.debug(f'User input: {opts}, {args}')
except getopt.GetoptError:
logger.info('epiLION.py -i <input_file> -o <output_file>')
return is_output
for opt, arg in opts:
if opt == '-h':
logger.info('epiLION.py -i <input_file> -o <output_file>')
return is_output
elif opt in ("-i", "--infile"):
in_file = arg
elif opt in ("-o", "--outfile"):
out_file = arg
if os.path.isfile(in_file):
logger.info(f'Load input file: {in_file}')
with open(in_file, 'r') as in_obj:
in_lst = in_obj.readlines()
epilion2sdf(in_lst, out_file)
logger.info(f'Save output file: {out_file}')
logger.info('FINISHED')
is_output = True
else:
logger.error(f'Can NOT open input file:')
logger.error(in_file)
logger.error('!!! FAILED to PROCESS !!!')
return is_output
def parse_epilion(abbr: str) -> dict:
fa_decoder = ParserFA()
pl_decoder = ParserPL()
info_dct = {}
converter = Converter(abbr_cfg_path)
epilion_id = converter.convert_abbr(abbr)
if fa_decoder.is_fa(epilion_id):
smi = fa_decoder.get_smi_fa(epilion_id)
logger.info(epilion_id + ': ' + smi)
elif pl_decoder.is_pl(epilion_id):
smi = pl_decoder.get_smi_pl(epilion_id)
logger.info(epilion_id + ': ' + smi)
else:
logger.info(f'Can NOT parse abbreviation: {epilion_id}')
try:
mol = Chem.MolFromSmiles(smi)
AllChem.Compute2DCoords(mol)
# m_mass = Descriptors.MolWt(mol)
m_exactmass = rdMolDescriptors.CalcExactMolWt(mol)
m_formula = rdMolDescriptors.CalcMolFormula(mol)
img = Draw.MolToImage(mol, size=(600, 400))
img_io = BytesIO()
img.save(img_io, format='png')
img_io.seek(0)
img.save(img_io, format='png')
img_data = base64.b64encode(img_io.getbuffer())
img_data_url = r'data:image/png;base64,' + img_data.decode("utf-8")
info_dct['id'] = epilion_id
info_dct['formula'] = m_formula
info_dct['exactmass'] = '%.4f' % m_exactmass
info_dct['img'] = img_data_url
except Exception as e:
logger.error(f'! FAILED: {epilion_id}')
logger.error(f'! FAILED to generate structure from SMILES: {smi}')
logger.error(e)
return info_dct
return epilion_lst
def convert_text(self, input_text: str) -> (dict, list):
usr_abbr_lst = input_text.split('\n')
epilion_dct = {}
bad_input_lst = []
for abbr in usr_abbr_lst:
epilion_id = self.convert_abbr(abbr)
if epilion_id:
epilion_dct[abbr] = epilion_id
else:
bad_input_lst.append(abbr)
return epilion_dct, bad_input_lst
if __name__ == '__main__':
test_in_file = r'../test/TestInput/test_crosscheck.xlsx'
test_out_file = r'../test/TestOutput/test_crosscheck_output.xlsx'
cfg_file = r'../configurations/LinearFA_abbreviations.xlsx'
converter = Converter(cfg_file)
converter.convert_table(test_in_file, test_out_file)
logger.info('epiLion converter finished.')
def epilion2sdf(abbr_lst, save_sdf):
if isinstance(abbr_lst, str):
try:
if os.path.isfile(abbr_lst):
logger.info(f'Try to open file: {abbr_lst}')
with open(abbr_lst, 'r') as infile_obj:
abbr_lst = infile_obj.readlines()
else:
logger.error(f'Can NOT load input: {abbr_lst}')
logger.info('!! END PROCESSING !!')
exit()
except Exception as e:
logger.error(f'Can NOT load input: {abbr_lst}')
logger.error(e)
fa_decoder = ParserFA()
pl_decoder = ParserPL()
info_dct = {}
for abbr in abbr_lst:
logger.info(abbr)
if fa_decoder.is_fa(abbr):
smi = fa_decoder.get_smi_fa(abbr)
logger.info(abbr + ': ' + smi)
info_dct[abbr] = smi
elif pl_decoder.is_pl(abbr):
smi = pl_decoder.get_smi_pl(abbr)
logger.info(abbr + ': ' + smi)
info_dct[abbr] = smi
else:
logger.info(f'Can NOT parse abbreviation: {abbr}')
sdf_writer = Chem.SDWriter(open(save_sdf, mode='w'))
for m in abbr_lst:
if m in info_dct:
smi = info_dct[m]
try:
mol = Chem.MolFromSmiles(smi)
AllChem.Compute2DCoords(mol)
mol.SetProp('_Name', m)
m_mass = Descriptors.MolWt(mol)
m_exactmass = rdMolDescriptors.CalcExactMolWt(mol)
m_formula = rdMolDescriptors.CalcMolFormula(mol)
mol.SetProp('EXACT_MASS', '%.6f' % m_exactmass)
mol.SetProp('NOMINAL_MASS', '%.3f' % m_mass)
mol.SetProp('FORMULA', m_formula)
sdf_writer.write(mol)
except Exception as e:
logger.error(f'! FAILED: {m}')
logger.error(
f'! FAILED to generate structure from SMILES: {smi}')
logger.error(e)
else:
logger.warning(f'!! Can NOT parse: {m}')
mol.SetProp('_Name', m)
m_mass = Descriptors.MolWt(mol)
m_exactmass = rdMolDescriptors.CalcExactMolWt(mol)
m_formula = rdMolDescriptors.CalcMolFormula(mol)
mol.SetProp('EXACT_MASS', '%.6f' % m_exactmass)
mol.SetProp('NOMINAL_MASS', '%.3f' % m_mass)
mol.SetProp('FORMULA', m_formula)
sdf_writer.write(mol)
except Exception as e:
logger.error(f'! FAILED: {m}')
logger.error(
f'! FAILED to generate structure from SMILES: {smi}')
logger.error(e)
else:
logger.warning(f'!! Can NOT parse: {m}')
if __name__ == '__main__':
test_file = r'../../test/TestInput/test_names.txt'
output_file = r'../../test/TestOutput/test_names_sdf.sdf'
with open(test_file, 'r') as input_obj:
input_lst = input_obj.readlines()
epilion2sdf(input_lst, output_file)
epilion2sdf(test_file, output_file)
epilion2sdf(input_lst, output_file)
logger.info('FINISHED!')
raise Exception('test bad parameter... Failed')
def test_epiLION_Converter_bad_input(self):
logger.debug('test bad input...')
result = convLION.main(self.fail_input_params)
if result is False:
logger.debug('test bad input... PASSED')
else:
raise Exception('test bad input... Failed')
def test_epiLION_Converter_good_input(self):
logger.debug('test sample data...')
result = convLION.main(self.pass_params)
if result is True:
logger.debug('test sample data... PASSED')
else:
raise Exception('test sample data... Failed')
def tearDown(self):
logger.debug('TEST END!')
if __name__ == '__main__':
# python convLION.py -i test/TestInput/test_crosscheck.xlsx -o test/TestOutput/test_crosscheck_output.xlsx
epiLION_Path = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, epiLION_Path + '/../')
unittest.main()
logger.info('TESTS FINISHED!')
def main(argv):
"""
:param argv: -i <input epiLION abbreviation file in .txt format>
"""
in_file = ''
out_file = ''
is_output = False
try:
opts, args = getopt.getopt(argv, "hi:o:", ["infile=", "outfile="])
logger.debug(f'User input: {opts}, {args}')
except getopt.GetoptError:
logger.info('epiLIONConverter.py -i <input_file> -o <output_file>')
return is_output
for opt, arg in opts:
if opt == '-h':
logger.info('epiLIONConverter.py -i <input_file> -o <output_file>')
return is_output
elif opt in ("-i", "--infile"):
in_file = arg
elif opt in ("-o", "--outfile"):
out_file = arg
if os.path.isfile(in_file):
logger.info(f'Load input file: {in_file}')
converter = Converter(abbr_cfg_path)
converter.convert_table(in_file, out_file)
logger.info(f'Save output file: {out_file}')
logger.info('FINISHED')
is_output = True
logger.info(f'is_output {is_output}')
else:
logger.error(f'Can NOT open input file:')
logger.error(in_file)
logger.error('!!! FAILED to PROCESS !!!')
return is_output
def get_smi_fa(self, abbr: str) -> str:
smi = None
fa_info_dct = self.decode_fa(abbr)
if fa_info_dct['NUM_C']:
c_chain_lst = [''] + ['C'] * int(fa_info_dct['NUM_C'])
c_term_lst = []
if fa_info_dct['LINK']:
if fa_info_dct['LINK'] == 'O-':
c_chain_lst[0] = 'O'
elif fa_info_dct['LINK'] == 'P-':
c_chain_lst[0] = r'O'
c_chain_lst[1] = r'\C='
c_chain_lst[2] = r'C/'
else:
c_chain_lst[0] = 'O'
c_chain_lst[1] = 'C('
c_term_lst.append(')=O')
else:
c_chain_lst[0] = 'O'
c_chain_lst[1] = 'C('
c_term_lst.append(')=O')
c_idx_lst = list(range(3, int(fa_info_dct['NUM_C']) + 1))
if int(fa_info_dct['NUM_DB']
) > 0 and fa_info_dct['MOD_INFO'] is None:
fa_info_dct['MOD'] = [{
'NUM': fa_info_dct['NUM_DB'],
'MOD': 'DB',
'SITE_INFO': None,
'SITE': None
}]
logger.info(fa_info_dct['MOD'])
for _mod in fa_info_dct['MOD']:
_mod_code = _mod['MOD']
if _mod['SITE']:
for _site in _mod['SITE']:
_idx = int(_site['SITE'])
site_code = mod_cfg_df.loc[_mod_code, 'SMI_SITE']
site_post_code = mod_cfg_df.loc[_mod_code, 'SMI_POST']
site_term_code = mod_cfg_df.loc[_mod_code,
'SMI_TERMINAL']
if isinstance(site_code, str):
c_chain_lst[_idx] = site_code
if isinstance(site_post_code, str):
c_chain_lst[_idx + 1] = site_post_code
if isinstance(site_term_code, str):
c_term_lst.append(site_term_code)
else:
if _mod_code in ['DB', 'Ep']:
site_code = mod_cfg_df.loc[_mod_code, 'SMI_SITE']
site_post_code = mod_cfg_df.loc[_mod_code, 'SMI_POST']
_mod_count = int(_mod['NUM'])
_used_idx_lst = []
c_mod_idx = c_idx_lst[0]
_counter = 1
c_shift = 3
if c_shift * _mod_count > int(
fa_info_dct['NUM_C']) - 2:
c_shift = 2 # if more C=C in chain and no bis-allylic position
logger.info(
'Too many C=C, try to remove bis-allylic positions'
)
while _counter <= _mod_count:
if c_mod_idx in c_idx_lst and c_mod_idx + 1 in c_idx_lst:
logger.info(c_mod_idx)
c_chain_lst[c_mod_idx] = site_code
c_chain_lst[c_mod_idx + 1] = site_post_code
_used_idx_lst.extend(
[c_mod_idx, c_mod_idx + 1])
c_idx_lst = [
x for x in c_idx_lst
if x not in _used_idx_lst
]
c_mod_idx += c_shift
_counter += 1
else:
c_mod_idx += 1
else:
site_code = mod_cfg_df.loc[_mod_code, 'SMI_SITE']
site_term_code = mod_cfg_df.loc[_mod_code,
'SMI_TERMINAL']
_mod_count = int(_mod['NUM'])
_used_idx_lst = []
c_mod_idx = c_idx_lst[0]
_counter = 1
while _counter <= _mod_count:
if c_mod_idx in c_idx_lst:
c_chain_lst[c_mod_idx] = site_code
if isinstance(site_term_code, str):
c_term_lst.append(site_term_code)
c_idx_lst.remove(c_mod_idx)
_counter += 1
else:
c_mod_idx += 1
else:
c_chain_lst = []
c_term_lst = []
if c_term_lst:
c_chain_lst.extend(sorted(c_term_lst, reverse=True))
if c_chain_lst:
smi = ''.join(c_chain_lst)
smi = re.sub(r'\\/', r'\\', smi)
smi = re.sub(r'/\\', r'/', smi)
return smi
fa_lst = [
'FA18:0',
'18:1',
'O-16:0',
'P-18:0',
'20:4[4DB,2OH,1Ke]',
'20:4[4DB{5,9,12,15},2OH{8,11},1Ke{14}]',
'20:4[4DB{5Z,9E,12E,15E},2OH{8S,11R},1Ke{14}]',
'20:4[4DB{5Z,9E,11Z,14Z},1OH{8S}]',
'9:0<CHO{@9C}>',
# '20:1[PGA{8a,12b},1DB{13Z},1OH{15S}]'
]
for _abbr in fa_lst:
fa = fa_decoder.decode_fa(_abbr)
logger.info(fa)
_smi = fa_decoder.get_smi_fa(_abbr)
logger.info(_abbr + ': ' + _smi)
pl_lst = [
r'PC(O-16:0/18:1)',
r'PC(P-16:0_18:1)',
r'PC(P-16:0/18:1)',
'PC(16:0/20:4[4DB,2OH,1Ke])',
'PC(16:0/20:4[4DB{5,9,12,15},2OH{8,11},1Ke{14}])',
'PC(16:0/20:4[4DB{5Z,9E,12E,15E},2OH{8S,11R},1Ke{14}])',
]
for _abbr in pl_lst:
logger.info(_abbr)
pl = pl_decoder.decode_pl(_abbr)