def pull_unichem():
# declare the unichem ids for the target data
target_uc_url: str = get_latest_unichem_url()
xref_file = pull_via_urllib(target_uc_url,
'UC_XREF.txt.gz',
decompress=False,
subpath='UNICHEM')
struct_file = pull_via_urllib(target_uc_url,
'UC_STRUCTURE.txt.gz',
subpath='UNICHEM')
def pull_smpdb():
dname = pull_via_urllib('http://smpdb.ca/downloads/',
'smpdb_pathways.csv.zip',
decompress=False,
subpath='SMPDB')
ddir = path.dirname(dname)
with ZipFile(dname, 'r') as zipObj:
zipObj.extractall(ddir)
def pull_mods():
for mod in mods:
subp = modmap[mod]
origname = pull_via_urllib('https://fms.alliancegenome.org/download/',
f'GENE-DESCRIPTION-JSON_{mod}.json.gz',
subpath=subp)
#This should be fine. But for the makefile it's nice if the directory in which this goes is the same as the {mod} in the filename.
# And we'd like it to be the names of the prefixes
if mod != modmap[mod]:
newname = origname.replace(mod, modmap[mod])
os.rename(origname, newname)
def pull_unii():
for (pullfile,originalprefix,finalname) in [('UNIIs.zip','UNII_Names','Latest_UNII_Names.txt'),
('UNII_Data.zip','UNII_Records','Latest_UNII_Records.txt')]:
dname = pull_via_urllib('https://fdasis.nlm.nih.gov/srs/download/srs/',pullfile,decompress=False,subpath='UNII')
ddir = path.dirname(dname)
with ZipFile(dname, 'r') as zipObj:
zipObj.extractall(ddir)
#this zip file unzips into a readme and a file named something like "UNII_Names_<date>.txt" and we need to rename it for make
files = listdir(ddir)
for filename in files:
if filename.startswith(originalprefix):
original = path.join(ddir,filename)
final = path.join(ddir,finalname)
rename(original,final)
def pull_omim():
pull_via_urllib('https://www.omim.org/static/omim/data/',
'mim2gene.txt',
subpath='OMIM',
decompress=False)
def pull_orphanet():
pull_via_urllib('http://www.orphadata.org/data/RD-CODE/Packs/',
'Orphanet_Nomenclature_Pack_EN.zip',
subpath='Orphanet',
decompress=False)
def pull_one_uniprotkb(which):
pull_via_urllib('ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/',f'uniprot_{which}.fasta.gz',subpath='UniProtKB')
def pull_uniprotkb():
pull_via_urllib('ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/',f'idmapping.dat.gz',subpath='UniProtKB')
for which in ['sprot','trembl']:
pull_via_urllib('ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/',f'uniprot_{which}.fasta.gz',subpath='UniProtKB')
def pull_doid():
pull_via_urllib('https://raw.githubusercontent.com/DiseaseOntology/HumanDiseaseOntology/main/src/ontology/','doid.json', subpath='DOID', decompress=False)
def pull_drugcentral():
dname = pull_via_urllib('https://unmtid-shinyapps.net/download/','structures.smiles.tsv',decompress=False,subpath='DRUGCENTRAL')
def pull_ncit():
#Currently, just pull a mapping we need.
pull_via_urllib('https://evs.nci.nih.gov/ftp1/NCI_Thesaurus/Mappings/',
f'NCIt-SwissProt_Mapping.txt',
subpath='NCIT',
decompress=False)
def pull_rhea():
outputfile = pull_via_urllib('https://ftp.expasy.org/databases/rhea/rdf/',
'rhea.rdf.gz',
subpath='RHEA',
decompress=True)
def pull_hmdb():
dname = pull_via_urllib('https://hmdb.ca/system/downloads/current/','hmdb_metabolites.zip',decompress=False,subpath='HMDB')
ddir = path.dirname(dname)
with ZipFile(dname, 'r') as zipObj:
zipObj.extractall(ddir)
def pull_gtopdb_ligands():
pull_via_urllib('https://www.guidetopharmacology.org/DATA/','ligands.tsv',decompress=False,subpath='GTOPDB')