def add_to_all_mapping(dataframe, mapping):
for other_id, mnx_id in dataframe[['XREF', 'MNX_ID']].values:
cleaned_key = _apply_sanitize_rules(
_apply_sanitize_rules(other_id,
REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION)
mapping[cleaned_key] = mnx_id
def add_to_bigg_mapping(xref, bigg2mnx, mnx2bigg):
bigg_selection = xref[['bigg' in blub for blub in xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(_apply_sanitize_rules(id, REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION) for id in bigg_selection.XREF]
bigg2mnx.update(dict(zip(sanitized_XREF, bigg_selection.MNX_ID)))
mnx2bigg.update(dict(zip(bigg_selection.MNX_ID, sanitized_XREF)))
def add_to_bigg_mapping(xref, bigg2mnx, mnx2bigg):
bigg_selection = xref[['bigg' in blub for blub in xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(_apply_sanitize_rules(id, REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION) for id in bigg_selection.XREF]
bigg2mnx.update(dict(zip(sanitized_XREF, bigg_selection.MNX_ID)))
mnx2bigg.update(dict(zip(bigg_selection.MNX_ID, sanitized_XREF)))
reac_xref.columns = [name.replace('#', '') for name in reac_xref.columns]
reac_prop = read_table('../data/metanetx/reac_prop.tsv.gz', skiprows=107, compression='gzip', index_col=0)
reac_prop.columns = [name.replace('#', '') for name in reac_prop.columns]
chem_prop = read_table('../data/metanetx/chem_prop.tsv.gz', skiprows=125, compression='gzip', index_col=0,
names=['name', 'formula', 'charge', 'mass', 'InChI', 'SMILES', 'source'])
# replace NaN with None
chem_prop = chem_prop.where((notnull(chem_prop)), "")
REVERSE_ID_SANITIZE_RULES_SIMPHENY = [(value, key) for key, value in ID_SANITIZE_RULES_SIMPHENY]
metanetx = dict()
# Metabolites
bigg_selection = chem_xref[['bigg' in blub for blub in chem_xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(_apply_sanitize_rules(id.replace('bigg:', ''), REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION) for id in bigg_selection.XREF]
bigg2mnx = dict(zip(sanitized_XREF, bigg_selection.MNX_ID))
mnx2bigg = dict(zip(bigg_selection.MNX_ID, sanitized_XREF))
# Reactions
bigg_selection = reac_xref[['bigg' in blub for blub in reac_xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(_apply_sanitize_rules(id.replace('bigg:', ''), REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION) for id in bigg_selection.XREF]
bigg2mnx.update(dict(zip(sanitized_XREF, bigg_selection.MNX_ID)))
mnx2bigg.update(dict(zip(bigg_selection.MNX_ID, sanitized_XREF)))
# put into final result dict
metanetx['bigg2mnx'] = bigg2mnx
metanetx['mnx2bigg'] = mnx2bigg
reac_xref.columns = [name.replace('#', '') for name in reac_xref.columns]
reac_prop = read_table('../data/metanetx/reac_prop.tsv.gz', skiprows=107, compression='gzip', index_col=0)
reac_prop.columns = [name.replace('#', '') for name in reac_prop.columns]
chem_prop = read_table('../data/metanetx/chem_prop.tsv.gz', skiprows=125, compression='gzip', index_col=0,
names=['name', 'formula', 'charge', 'mass', 'InChI', 'SMILES', 'source'])
# replace NaN with None
chem_prop = chem_prop.where((notnull(chem_prop)), None)
REVERSE_ID_SANITIZE_RULES_SIMPHENY = [(value, key) for key, value in ID_SANITIZE_RULES_SIMPHENY]
metanetx = dict()
# Metabolites
bigg_selection = chem_xref[['bigg' in blub for blub in chem_xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(_apply_sanitize_rules(id.replace('bigg:', ''), REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION) for id in bigg_selection.XREF]
bigg2mnx = dict(zip(sanitized_XREF, bigg_selection.MNX_ID))
mnx2bigg = dict(zip(bigg_selection.MNX_ID, sanitized_XREF))
# Reactions
bigg_selection = reac_xref[['bigg' in blub for blub in reac_xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(_apply_sanitize_rules(id.replace('bigg:', ''), REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION) for id in bigg_selection.XREF]
bigg2mnx.update(dict(zip(sanitized_XREF, bigg_selection.MNX_ID)))
mnx2bigg.update(dict(zip(bigg_selection.MNX_ID, sanitized_XREF)))
# put into final result dict
metanetx['bigg2mnx'] = bigg2mnx
metanetx['mnx2bigg'] = mnx2bigg
def add_to_all_mapping(dataframe, mapping):
for other_id, mnx_id in dataframe[['XREF', 'MNX_ID']].values:
cleaned_key = _apply_sanitize_rules(
_apply_sanitize_rules(other_id, REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION)
mapping[cleaned_key] = mnx_id
compression="gzip",
index_col=0,
names=["name", "formula", "charge", "mass", "InChI", "SMILES", "source"],
)
# replace NaN with None
chem_prop = chem_prop.where((notnull(chem_prop)), None)
REVERSE_ID_SANITIZE_RULES_SIMPHENY = [(value, key) for key, value in ID_SANITIZE_RULES_SIMPHENY]
metanetx = dict()
# Metabolites
bigg_selection = chem_xref[["bigg" in blub for blub in chem_xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(
_apply_sanitize_rules(id.replace("bigg:", ""), REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION,
)
for id in bigg_selection.XREF
]
bigg2mnx = dict(zip(sanitized_XREF, bigg_selection.MNX_ID))
mnx2bigg = dict(zip(bigg_selection.MNX_ID, sanitized_XREF))
# Reactions
bigg_selection = reac_xref[["bigg" in blub for blub in reac_xref.XREF]]
sanitized_XREF = [
_apply_sanitize_rules(
_apply_sanitize_rules(id.replace("bigg:", ""), REVERSE_ID_SANITIZE_RULES_SIMPHENY),
ID_SANITIZE_RULES_TAB_COMPLETION,
)
for id in bigg_selection.XREF
]