def seekRank(df, mode):
# inchi.inchikey_from_inchi
# usage : the same way in html_report.generate_candidate_html
assert mode in {0, 1}
lst = []
for index, row in df.iterrows():
target_inchikey = ''
if pd.isnull(row['parameters.inchi']) | \
len(str(row['parameters.inchi']).strip()) == 0:
if 'parameters.inchikey' not in row.index:
lst.append(
(row['parameters.db_molecule_name'], 'No inchi/inchikey'))
continue
else:
target_inchikey = row['parameters.inchikey']
else:
inchi = 'InChI=1S/%s' % row['parameters.inchi']
target_inchikey = inchikey_from_inchi(inchi)
content = row['peaks'][0]
annotations = []
if 'annotations' in content.keys():
annotations = content['annotations'][0]
else:
if mode == 1:
lst.append(
(row['parameters.db_molecule_name'], 'No annotations'))
elif mode == 0:
lst.append((target_inchikey, 'No annotations'))
continue
candidates = annotations['mol_candidates']
indice = 0
i = 0
for c in candidates:
inchi = 'InChI=1S/%s' % c['InChI']
inchikey = inchikey_from_inchi(inchi)
i += 1
if target_inchikey == inchikey:
indice = i
break
if mode == 1:
lst.append((row['parameters.db_molecule_name'], indice))
elif mode == 0:
lst.append((target_inchikey, indice))
return lst
def save_inchi(peaklist, outdir, mode):
if mode == 1:
outpath = '%s/positive' % outdir
else:
outpath = '%s/negative' % outdir
if not os.path.exists(outpath):
os.makedirs(outpath)
print(outpath)
for i in range(len(peaklist)):
peak = peaklist[i]
with open('%s/%s.inchi' % (outpath, i), 'w') as fout:
inchi = peak.parent_spectrum.parameters['inchi']
inchikey = inchikey_from_inchi(inchi)
fout.write('%s\t%s\n' % (inchi, inchikey))
def _get_next_raw_record(self):
if self.currentfile=='':
self.currentfile=os.path.join(self.database_path, self.db_name, self.subf,
str(self.mzcurrent//1000),
str(self.mzcurrent%1000//100),
str(self.mzcurrent%100//10),
'%s.st2'%str(self.mzcurrent%10));
while (not os.path.isfile(self.currentfile)) and (self.mzcurrent<=self.mzmax_int):
self.mzcurrent+=1;
self.currentfile=os.path.join(self.database_path, self.db_name, self.subf,
str(self.mzcurrent//1000),
str(self.mzcurrent%1000//100),
str(self.mzcurrent%100//10),
'%s.st2'%str(self.mzcurrent%10));
if self.mzcurrent<=self.mzmax_int:
self.datafile=open(self.currentfile,'r');
self.record_index=-1;
else:
raise StopIteration();
s=self.datafile.readline();
self.record_index+=1;
while s=='':
self.datafile.close();
self.mzcurrent+=1;
self.currentfile=os.path.join(self.database_path, self.db_name, self.subf,
str(self.mzcurrent//1000),
str(self.mzcurrent%1000//100),
str(self.mzcurrent%100//10),
'%s.st2'%str(self.mzcurrent%10));
while (not os.path.isfile(self.currentfile)) and (self.mzcurrent<=self.mzmax_int):
self.mzcurrent+=1;
self.currentfile=os.path.join(self.database_path, self.db_name, self.subf,
str(self.mzcurrent//1000),
str(self.mzcurrent%1000//100),
str(self.mzcurrent%100//10),
'%s.st2'%str(self.mzcurrent%10));
if self.mzcurrent<=self.mzmax_int:
self.datafile=open(self.currentfile,'r');
self.record_index=-1;
else:
raise StopIteration();
s=self.datafile.readline();
self.record_index+=1;
s=s.rstrip('\n').split('\t');
record=MolecularRecord();
record['MZ']=float(s[0]);
if self.charged:
record['Mass']=float(s[1]);
record['Charge']=float(s[2]);
else:
record['Mass']=record['MZ'];
record['Charge']=0;
if 'ShortInChI' in self.required_fields:
record['ShortInChI']=parse_inchi(s[2+self.offs])[0];
if 'InChI' in self.required_fields:
record['InChI']=s[2+self.offs];
if 'SMILES' in self.required_fields:
record['SMILES']=s[3+self.offs];
if 'IDs' in self.required_fields:
record['IDs']=s[4+self.offs];
if 'FPT' in self.required_fields:
record['FPT']=decode_from_base64(s[5+self.offs]);
# Mask FPT here !
if 'Frag' in self.required_fields:
record['Frag']=s[6+self.offs];
if self.charged:
record['FragCharge']=s[9];
if 'InChIKeyValues' in self.required_fields:
record['InChIKeyValues']=inchikeyvalues_from_inchi(s[2+self.offs]);
if 'InChIKey' in self.required_fields:
record['InChIKey']=inchikey_from_inchi(s[2+self.offs]);
if ('Formula' in self.required_fields) or ('ElementVector' in self.required_fields) or ('FormulaVector' in self.required_fields):
fla=parse_formula(s[1+self.offs].split('/')[0]);
if 'Formula' in self.required_fields:
record['Formula']=fla;
if 'ElementVector' in self.required_fields:
record['ElementVector']=formula_to_element_vector(fla);
if 'FormulaVector' in self.required_fields:
record['FormulaVector']=encode_formula_to_array(fla);
return record;
def loadresults(peaks, data_path):
fname = data_path + '/fpt_mask.default';
with open(fname,'rb') as finp:
fpt_mask = np.fromfile(finp, dtype=np.uint8);
print(fpt_mask.shape);
fpt_mask = encode_to_base64(fpt_mask);
print(len(fpt_mask))
print(fpt_mask)
time.sleep(15)
pred_test = np.loadtxt(data_path + '/pred_test.txt')
pred_train = np.loadtxt(data_path + '/pred_train.txt')
inchi_test = [];
formulas_test = [];
scores_test = [];
inchi_train = [];
formulas_train = [];
scores_train = [];
fname = data_path + '/train_inchi.txt';
with open(fname,'r') as finp:
for s in finp:
inchi_train.append(inchikey_from_inchi(s.rstrip('\n')).split('-')[0]);
fname = data_path + '/train_formulas.txt';
with open(fname,'r') as finp:
for s in finp:
formulas_train.append(s.rstrip('\n'));
fname = data_path + '/train_formula_scores.txt';
with open(fname,'r') as finp:
for s in finp:
scores_train.append(float(s.rstrip('\n')));
fname = data_path + '/test_inchi.txt';
with open(fname,'r') as finp:
for s in finp:
inchi_test.append(inchikey_from_inchi(s.rstrip('\n')).split('-')[0]);
fname = data_path + '/test_formulas.txt';
with open(fname,'r') as finp:
for s in finp:
formulas_test.append(s.rstrip('\n'));
fname = data_path + '/test_formula_scores.txt';
with open(fname,'r') as finp:
for s in finp:
scores_test.append(float(s.rstrip('\n')));
print(len(pred_test))
print(len(inchi_test))
print(len(formulas_test))
print(len(scores_test))
print(len(pred_train))
print(len(inchi_train))
print(len(formulas_train))
print(len(scores_train))
if len(pred_test)!=len(inchi_test) or len(inchi_test) != len(formulas_test) or len(formulas_test) != len(scores_test):
raise ValueError('Unequal test sizes!');
if len(pred_train)!=len(inchi_train) or len(inchi_train) != len(formulas_train) or len(formulas_train) != len(scores_train):
raise ValueError('Unequal train sizes!');
inchiindex = {};
for i in range(len(peaks)):
pi = peaks[i].parent_spectrum.parameters['inchi'];
pi = inchikey_from_inchi(pi).split('-')[0]
inchiindex[pi] = i;
#with open(data_path + '/listinchi.txt', 'w') as fout:
# for key in inchiindex.keys():
# fout.write('%s\n'%key)
inchi = inchi_test + inchi_train
formulas = formulas_test + formulas_train
scores = scores_test + scores_train
pred = np.vstack((pred_test, pred_train))
lost_count = 0;
for i in range(len(inchi)):
if inchi[i] in inchiindex:
j = inchiindex[inchi[i]];
peak = peaks[j];
if 'csifingerid_count' in peak.parameters:
peak.parameters['csifingerid_count'] += 1;
else:
peak.parameters['csifingerid_count'] = 1;
subi = peak.parameters['csifingerid_count'];
p = pred[i, :].tolist();
for k in range(len(p)):
p[k] = str(p[k])
peak.parameters['csifingerid_predfpt_%s'%subi] = ','.join(p);
peak.parameters['csifingerid_fptmask_%s'%subi] = fpt_mask;
peak.parameters['csifingerid_formula_%s'%subi] = formulas[i];
peak.parameters['csifingerid_score_%s'%subi] = scores[i];
else:
print('Error! Inchi not found! %s'%inchi[i]);
lost_count += 1;
print('Total Missing: %s'%lost_count)
notpresent_count = len(peaks);
for peak in peaks:
if 'csifingerid_count' in peak.parameters:
notpresent_count -= 1;
return lost_count, notpresent_count
def generate_candidate_html(mainHTML,
candidate,
outpath,
index,
subpath,
merged=False):
if 'Annotation' in candidate:
if candidate['Annotation'] == 'Correct':
mainHTML.write('<tr><td bgcolor="#ccffcc">\n')
else:
mainHTML.write('<tr><td bgcolor="#e0e0e0">\n')
else:
mainHTML.write('<tr><td>\n')
if 'SMILES' in candidate:
smiles = candidate['SMILES']
has_image = False
if smiles != '':
fname = os.path.join(outpath, 'candidate_%s.png' % index)
if generate_candidate_image(fname, smiles):
has_image = True
if has_image:
mainHTML.write(
'<table><tr><td><img src="%s/candidate_%s.png"></td><td>\n' %
(subpath, index))
mainHTML.write('<b>Total Score:</b> %s\n' % candidate['TotalScore'])
mainHTML.write('<br><b>Individual Scores:</b>\n')
for score in candidate['Scores']:
mainHTML.write('<br><b>%s:</b> %s\n' %
(score, candidate['Scores'][score]))
mainHTML.write('<br><b>Mass:</b> %s, <b>Charge:</b> %s' %
(candidate['Mass'], candidate['Charge']))
smiles = ''
inchi = ''
formula = ''
if 'Formula' in candidate:
formula = candidate['Formula'].formula_to_string()
elif 'FormulaVector' in candidate:
formula = decode_formula_from_array(
candidate['FormulaVector']).formula_to_string()
if formula != '':
mainHTML.write(', <b>Formula:</b> %s' % formula)
if merged:
adduct = ''
isotope = ''
if 'Adduct' in candidate:
adduct = candidate['Adduct']
if 'Isotope' in candidate:
isotope = candidate['Isotope']
mainHTML.write('<br><b>Adduct:</b> %s, <b>Isotope:</b> %s\n' %
(adduct, isotope))
if 'SMILES' in candidate:
mainHTML.write('<br><b>SMILES:</b> %s\n' % candidate['SMILES'])
if 'InChI' in candidate:
mainHTML.write('<br><b>InChI</b>=1S/%s\n' % candidate['InChI'])
inchi = 'InChI=1S/%s' % candidate['InChI']
inchikey = inchikey_from_inchi(inchi)
mainHTML.write('<br><b>InChIKey:</b> %s\n' % inchikey)
mainHTML.write(
'<br><button onclick="CallPubChem(this.id)" id="%s">PubChem</button><br>\n'
% (inchikey))
if has_image:
mainHTML.write('</td></tr></table>\n')
mainHTML.write('</td></tr>\n')