def download_pfam_descriptions(output_dir='.', verbose=True):
pfam_hmm_dat = path.join(output_dir, 'Pfam-A.hmm.dat.gz')
download_file(
'ftp://ftp.ebi.ac.uk/pub/databases/Pfam/current_release/Pfam-A.hmm.dat.gz',
pfam_hmm_dat,
verbose=verbose)
return pfam_hmm_dat
def download_and_process_viral_refseq(merged_viral_faas=None,
output_dir='.',
viral_files=2,
threads=10,
verbose=True):
"""Can only download newest version"""
# download all of the viral protein files, need to know the number of files
# TODO: Make it so that you don't need to know number of viral files in refseq viral
if merged_viral_faas is None: # download database if not provided
faa_base_name = 'viral.%s.protein.faa.gz'
viral_faa_glob = path.join(output_dir, faa_base_name % '*')
for number in range(viral_files):
number += 1
refseq_url = 'ftp://ftp.ncbi.nlm.nih.gov/refseq/release/viral/viral.%s.protein.faa.gz' % number
refseq_faa = path.join(output_dir, faa_base_name % number)
download_file(refseq_url, refseq_faa, verbose=verbose)
# then merge files from above
merged_viral_faas = path.join(output_dir,
'viral.merged.protein.faa.gz')
run_process([
'cat %s > %s' % (' '.join(glob(viral_faa_glob)), merged_viral_faas)
],
shell=True)
# make mmseqs database
refseq_viral_mmseqs_db = path.join(
output_dir, 'refseq_viral.%s.mmsdb' % get_iso_date())
make_mmseqs_db(merged_viral_faas,
refseq_viral_mmseqs_db,
create_index=True,
threads=threads,
verbose=verbose)
return refseq_viral_mmseqs_db
def download_vog_annotations(output_dir, vogdb_version='latest', verbose=True):
vog_annotations = path.join(output_dir,
'vog_annotations_%s.tsv.gz' % vogdb_version)
download_file(
'http://fileshare.csb.univie.ac.at/vog/%s/vog.annotations.tsv.gz' %
vogdb_version,
vog_annotations,
verbose=verbose)
return vog_annotations
def download_and_process_amg_database(output_dir,
branch='master',
verbose=True):
amg_database = path.join(output_dir,
'amg_database.%s.tsv' % get_iso_date())
download_file(
'https://raw.githubusercontent.com/shafferm/DRAM/%s/data/amg_database.tsv'
% branch,
amg_database,
verbose=verbose)
return amg_database
def download_and_process_function_heatmap_form(output_dir,
branch='master',
verbose=True):
function_heatmap_form = path.join(
output_dir, 'function_heatmap_form.%s.tsv' % get_iso_date())
download_file(
'https://raw.githubusercontent.com/shafferm/DRAM/%s/data/function_heatmap_form.tsv'
% branch,
function_heatmap_form,
verbose=verbose)
return function_heatmap_form
def download_and_process_genome_summary_form(output_dir,
branch='master',
verbose=True):
genome_summary_form = path.join(
output_dir, 'genome_summary_form.%s.tsv' % get_iso_date())
download_file(
'https://raw.githubusercontent.com/shafferm/DRAM/%s/data/genome_summary_form.tsv'
% branch,
genome_summary_form,
verbose=verbose)
return genome_summary_form
def download_dbcan_descriptions(output_dir='.',
upload_date='07302020',
verbose=True):
dbcan_fam_activities = path.join(
output_dir, 'CAZyDB.%s.fam-activities.txt' % upload_date)
download_file(
'http://bcb.unl.edu/dbCAN2/download/Databases/CAZyDB.%s.fam-activities.txt'
% upload_date,
dbcan_fam_activities,
verbose=verbose)
return dbcan_fam_activities
def download_and_process_kofam_ko_list(kofam_ko_list_gz=None,
output_dir='.',
verbose=False):
if kofam_ko_list_gz is None:
kofam_ko_list_gz = path.join(output_dir, 'kofam_ko_list.tsv.gz')
download_file('ftp://ftp.genome.jp/pub/db/kofam/ko_list.gz',
kofam_ko_list_gz,
verbose=verbose)
# TODO: fix this so that it is gunzipped to the path
kofam_ko_list = path.join(output_dir, 'kofam_ko_list.tsv')
run_process(['gunzip', kofam_ko_list_gz], verbose=verbose)
return kofam_ko_list
def download_and_process_pfam(pfam_full_zipped=None,
output_dir='.',
threads=10,
verbose=True):
if pfam_full_zipped is None: # download database if not provided
pfam_full_zipped = path.join(output_dir, 'Pfam-A.full.gz')
download_file(
'ftp://ftp.ebi.ac.uk/pub/databases/Pfam/current_release/Pfam-A.full.gz',
pfam_full_zipped,
verbose=verbose)
pfam_profile = process_mmspro(pfam_full_zipped, output_dir, 'pfam',
threads, verbose)
return pfam_profile
def download_and_process_dbcan(dbcan_hmm=None,
output_dir='.',
dbcan_release='8',
verbose=True):
if dbcan_hmm is None: # download database if not provided
dbcan_hmm = path.join(output_dir,
'dbCAN-HMMdb-V%s.txt' % dbcan_release)
download_file(
'http://bcb.unl.edu/dbCAN2/download/Databases/dbCAN-HMMdb-V%s.txt'
% dbcan_release,
dbcan_hmm,
verbose=verbose)
run_process(['hmmpress', '-f', dbcan_hmm], verbose=verbose)
return dbcan_hmm
def download_and_process_vogdb(vog_hmm_targz=None,
output_dir='.',
vogdb_release='latest',
verbose=True):
if vog_hmm_targz is None:
vog_hmm_targz = path.join(output_dir, 'vog.hmm.tar.gz')
vogdb_url = 'http://fileshare.csb.univie.ac.at/vog/%s/vog.hmm.tar.gz' % vogdb_release
download_file(vogdb_url, vog_hmm_targz, verbose=verbose)
hmm_dir = path.join(output_dir, 'vogdb_hmms')
mkdir(hmm_dir)
vogdb_targz = tarfile.open(vog_hmm_targz)
vogdb_targz.extractall(hmm_dir)
vog_hmms = path.join(output_dir, 'vog_%s_hmms.txt' % vogdb_release)
merge_files(glob(path.join(hmm_dir, 'VOG*.hmm')), vog_hmms)
run_process(['hmmpress', '-f', vog_hmms], verbose=verbose)
return vog_hmms
def download_and_process_merops_peptidases(peptidase_faa=None,
output_dir='.',
threads=10,
verbose=True):
if peptidase_faa is None: # download database if not provided
peptidase_faa = path.join(output_dir, 'merops_peptidases_nr.faa')
merops_url = 'ftp://ftp.ebi.ac.uk/pub/databases/merops/current_release/pepunit.lib'
download_file(merops_url, peptidase_faa, verbose=verbose)
peptidase_mmseqs_db = path.join(output_dir,
'peptidases.%s.mmsdb' % get_iso_date())
make_mmseqs_db(peptidase_faa,
peptidase_mmseqs_db,
create_index=True,
threads=threads,
verbose=verbose)
return peptidase_mmseqs_db
def download_and_process_kofam_hmms(kofam_profile_tar_gz=None,
output_dir='.',
verbose=False):
if kofam_profile_tar_gz is None:
kofam_profile_tar_gz = path.join(output_dir, 'kofam_profiles.tar.gz')
download_file('ftp://ftp.genome.jp/pub/db/kofam/profiles.tar.gz',
kofam_profile_tar_gz,
verbose=verbose)
kofam_profiles = path.join(output_dir, 'kofam_profiles')
mkdir(kofam_profiles)
run_process(['tar', '-xzf', kofam_profile_tar_gz, '-C', kofam_profiles],
verbose=verbose)
merged_kofam_profiles = path.join(output_dir, 'kofam_profiles.hmm')
merge_files(glob(path.join(kofam_profiles, 'profiles', '*.hmm')),
merged_kofam_profiles)
run_process(['hmmpress', '-f', merged_kofam_profiles], verbose=verbose)
return merged_kofam_profiles
def download_and_process_uniref(uniref_fasta_zipped=None,
output_dir='.',
uniref_version='90',
threads=10,
verbose=True):
""""""
if uniref_fasta_zipped is None: # download database if not provided
uniref_fasta_zipped = path.join(output_dir,
'uniref%s.fasta.gz' % uniref_version)
uniref_url = 'ftp://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref%s/uniref%s.fasta.gz' % \
(uniref_version, uniref_version)
download_file(uniref_url, uniref_fasta_zipped, verbose=verbose)
uniref_mmseqs_db = path.join(
output_dir, 'uniref%s.%s.mmsdb' % (uniref_version, get_iso_date()))
make_mmseqs_db(uniref_fasta_zipped,
uniref_mmseqs_db,
create_index=True,
threads=threads,
verbose=verbose)
return uniref_mmseqs_db
