def rebuild_references(annotations: Dict) -> Dict[str, List[Reference]]:
""" Rebuilds the SeqRecord 'references' annotation from JSON """
bases = annotations["references"]
refs = []
for ref in bases:
new_reference = Reference()
new_reference.__dict__ = ref
new_reference.location = [location_from_string(loc) for loc in ref["location"]]
refs.append(new_reference)
annotations["references"] = refs
return annotations
def start_li(self, attrs):
if self._state == 'references':
self._reference_state = 'pubmed_id'
self._flush_text()
if (self._current_reference != ''):
self._references.append(self._current_reference)
self._current_reference = Reference()
def reset(self):
sgmllib.SGMLParser.reset(self)
self.ndb_dict = Record()
self.text = ''
self._space_group = ''
self._state = 'id'
self._reference_state = 'authors'
self._current_reference = Reference()
def __init__(self):
self['Id'] = ''
self['Features'] = ''
self['Name'] = ''
self['Sequence'] = Crystal({})
self['Citation'] = Reference()
self['Space Group'] = ''
self['Cell Constants'] = {}
self['Crystallization Conditions'] = []
self['Refinement'] = ''
self['Coordinates'] = ''
def reference_number(self, line):
"""RN line, reference number (start of new reference)."""
from Bio.SeqFeature import Reference
# if we have a current reference that hasn't been added to
# the list of references, add it.
if self._current_ref is not None:
self.data.annotations['references'].append(self._current_ref)
else:
self.data.annotations['references'] = []
self._current_ref = Reference()
def reference_number(self, line):
rn = line[5:].rstrip()
assert rn[0] == '[' and rn[-1] == ']', "Missing brackets %s" % rn
ref = Reference()
ref.number = int(rn[1:-1])
self.data.references.append(ref)
f.qualifiers["label"].remove(color)
f.qualifiers["label"].append("color: #ff8eff")
# sort features by start location, source always first
gb_archive.features.sort(
key=lambda f: (-len(gb.seq)) * (f.type == "source") + f.location.start
)
# translate color from notes to ApEinfo
for feature in gb_archive.features:
translate_color(feature)
# Fix the direct submission reference
if gb_archive.annotations["references"][-1].title == "Direct Submission":
ref = gb_archive.annotations["references"][-1]
else:
ref = Reference()
ref.title = "Direct Submission"
gb_archive.annotations.append(ref)
ref.authors = "Larralde M"
ref.journal = "Distributed with the MoClo Python library\nhttps://github.com/althonos/moclo"
# write the final record
dst_dir = os.path.abspath(
os.path.join(__file__, "..", "..", "moclo-plant", "registry", "plant")
)
with fs.open_fs(os.path.join(__file__, "..", ".."), create=True) as dst_fs:
dir_fs = dst_fs.makedirs(fs.path.join("moclo-plant", "registry", "plant"), recreate=True)
with dir_fs.open("{}.gb".format(info["id"]), "w") as dst_file:
write(gb_archive, dst_file, "gb")
def to_seq_record(self) -> SeqRecord:
"""Convert the cluster to a single record.
Annotations of the source sequence are kept intact if they don't
overlap with the cluster boundaries. Component genes are added on the
record as *CDS* features. Annotated protein domains are added as
*misc_feature*.
"""
# store time of record creation
now = datetime.datetime.now()
# NB(@althonos): we use inclusive 1-based ranges in the data model
# but slicing expects 0-based ranges with exclusive ends
bgc = self.source[self.start - 1:self.end]
bgc.id = bgc.name = self.id
# copy sequence annotations
bgc.annotations = self.source.annotations.copy()
bgc.annotations["topology"] = "linear"
bgc.annotations["molecule_type"] = "DNA"
with patch_locale("C"):
bgc.annotations['date'] = now.strftime("%d-%b-%Y").upper()
biopython_version = tuple(map(int, Bio.__version__.split(".")))
if biopython_version < (1, 77):
from Bio import Alphabet
bgc.seq.alphabet = Alphabet.generic_dna
# add GECCO preprint as a reference
ref = Reference()
ref.title = "Accurate de novo identification of biosynthetic gene clusters with GECCO"
ref.journal = "bioRxiv (2021.05.03.442509)"
ref.comment = "doi:10.1101/2021.05.03.442509"
ref.authors = ", ".join([
"Laura M Carroll", "Martin Larralde", "Jonas Simon Fleck",
"Ruby Ponnudurai", "Alessio Milanese", "Elisa Cappio Barazzone",
"Georg Zeller"
])
bgc.annotations.setdefault("references", []).append(ref)
# add GECCO-specific annotations as a structured comment
structured_comment = bgc.annotations.setdefault(
"structured_comment", OrderedDict())
structured_comment['GECCO-Data'] = {
"version":
f"GECCO v{__version__}",
"creation_date":
now.isoformat(),
"biosyn_class":
",".join(ty.name for ty in self.type.unpack()),
"alkaloid_probability":
self.type_probabilities.get(ProductType.Alkaloid, 0.0),
"polyketide_probability":
self.type_probabilities.get(ProductType.Polyketide, 0.0),
"ripp_probability":
self.type_probabilities.get(ProductType.RiPP, 0.0),
"saccharide_probability":
self.type_probabilities.get(ProductType.Saccharide, 0.0),
"terpene_probability":
self.type_probabilities.get(ProductType.Terpene, 0.0),
"nrp_probability":
self.type_probabilities.get(ProductType.NRP, 0.0),
"other_probability":
self.type_probabilities.get(ProductType.Other, 0.0),
}
# add proteins as CDS features
for gene in self.genes:
# write gene as a /cds GenBank record
cds = gene.to_seq_feature()
cds.location += -self.start
bgc.features.append(cds)
# write domains as /misc_feature annotations
for domain in gene.protein.domains:
misc = domain.to_seq_feature(protein_coordinates=False)
misc.location += cds.location.start
bgc.features.append(misc)
# return the complete BGC
return bgc
RN [1] ok
RA Submitter, A.; ok
RT "Bacullis sp. strain XYZ genome annotated using Prokka."; ok
RL Submitted (18-Apr-2016) to the INSDC. ok
XX
'''
record.id = "XXX"
record.name = 'XXX'
contig_name = record.description.split('Contig ')[1].split(' ')[0]
contig_list.append(contig_name)
record.description = args.description
record.dbxrefs.append("Project:%s" % args.project)
record.annotations['accessions'] = ['XXX', 'contig']
record.annotations["data_file_division"] = 'XXX'
record.annotations["references"] = [Reference()]
record.annotations["references"][0].authors = 'XXX'
record.annotations["references"][0].location = [
FeatureLocation(0, len(record))
]
record.annotations["references"][0].title = ''
record.annotations["references"][
0].journal = 'Submitted (%s) to the INSDC.' % today.strftime(
'%d-%b-%Y')
new_features = []
for i in range(0, len(record.features)):
type_list.append(record.features[i].type)
if record.features[i].type == 'source':
del record.features[i].qualifiers['project']
del record.features[i].qualifiers['genome_md5']
del record.features[i].qualifiers['genome_id']
nargs='?',
type=argparse.FileType('w'),
default=sys.stdout)
args = parser.parse_args()
# First get the lineage (and fail now if not found)
lineage = get_lineage(args.species, args.email)
if not lineage:
raise RuntimeError(
"Could not find lineage information on NCBI for species '%s'" %
args.species)
print('Found lineage: %s' % lineage)
# Prepare the bibliographic reference
ref = Reference()
if args.ref_pubmed_id:
ref.pubmed_id = args.ref_pubmed_id
if args.ref_consortium:
ref.consrtm = args.ref_consortium
if args.ref_authors:
ref.authors = args.ref_authors
if args.ref_title:
ref.title = args.ref_title
if args.ref_journal:
ref.journal = args.ref_journal
else:
now = datetime.datetime.now()
ref_date = now.strftime("%m-%b-%Y").upper()
# Temp switch to C to get english month abbr
saved = locale.setlocale(locale.LC_TIME)
def reference_number(self, line):
rn = line[5:].rstrip()
assert rn[0] == '[' and rn[-1] == ']', "Missing brackets %s" % rn
ref = Reference()
ref.number = int(rn[1:-1])
self.data.references.append(ref)
def create_reference(author_string=None):
"""Returns mock Reference data."""
reference = Reference()
reference.authors = author_string
return reference
def doConvert(embl_file, dep_file, contact, project, genome_project_id, organism_name, strain, locus_tag, taxon_id, dna_source, authors, comment, ac, clean=False):
record = SeqIO.read(open(embl_file), "embl")
# ----------------------------------------
# HEADER
# ----------------------------------------
# remove accession
if 'accession' in record.annotations.keys():
del record.annotations['accession']
record.annotations['accession'] = [ac]
# ID line
record.id = "XXX"
record.name = "XXX"
record.annotations['data_file_division'] = 'PRO'
record.annotations['data_file_class'] = 'WGS'
# PR line
record.dbxrefs = ["Project:%s" % genome_project_id]
# OS line
record.annotations["organism"] = "%s %s" % (organism_name, strain)
# DE line
if project == 'metahit':
record.description = "%s %s draft genome." % (organism_name, strain)
else:
record.description = "%s %s genome." % (organism_name, strain)
# RN & RL lines
if dna_source == 'GHP':
dna_source = 'Rowett Institute of Nutrition and Health, University of Aberdeen -- http://www.rowett.ac.uk/divisions/ghp/'
authors = 'Pajon A., Turner K., Parkhill J., Duncan S., Flint H.'
elif dna_source == 'INRA':
dna_source = 'INRA Clermont-Ferrand-Theix -- http://www.clermont.inra.fr/'
authors = 'Pajon A., Turner K., Parkhill J., Bernalier A.'
elif dna_source == 'HCIR':
dna_source = 'Helmholtz Centre for Infection Research -- http://www.helmholtz-hzi.de/'
authors = 'Pajon A., Turner K., Parkhill J., Timmis K., Oxley A., Wurdemann D.'
elif dna_source == 'DSMZ':
dna_source = 'German Collection of Microorganisms and Cell Cultures -- http://www.dsmz.de/'
authors = 'Pajon A., Turner K., Parkhill J.'
elif dna_source == 'NCTC':
dna_source = 'Health Protection Agency\'s National Collection of Type Cultures -- http://www.hpacultures.org.uk/'
authors = 'Pajon A., Turner K., Parkhill J.'
elif dna_source == 'DPM':
dna_source = 'Departments of Periodontology and Microbiology, King\'s College London -- http://www.kcl.ac.uk/'
authors = 'Pajon A., Turner K., Parkhill J., Wade W., Vartoukian S.'
else:
dna_source = dna_source
authors = authors
ref_journal = Reference()
ref_journal.journal = 'Unpublished.'
if project == 'metahit':
ref_journal.consrtm = "metaHIT consortium -- http://www.metahit.eu/"
ref_journal.title = 'The genome sequence of %s %s' % (organism_name, strain)
ref_journal.authors = authors
ref_dep = Reference()
ref_dep.authors = CONTACTS[contact]['author']
today = date.today()
ref_dep.journal = "Submitted (%s) to the EMBL/GenBank/DDBJ databases. Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SA, United Kingdom." % today.strftime("%d-%b-%Y")
ref_dep.title = 'Direct submission'
record.annotations['references'] = [ref_journal, ref_dep]
# CC line
record.annotations['comment'] = ['Data release policy http://www.sanger.ac.uk/legal/#t_2',
'DNA source: %s' % dna_source,
'%s' % comment]
# ----------------------------------------
# GAP FEATURE (only with clean option)
# ----------------------------------------
# Add FT gap
seq = record.seq
in_N = False
gap_features = []
if clean:
# TODO - Cope with a sequence which ends with N
if seq[-1] != "N":
print "WARNING: sequence ends with N"
for i in range(len(seq)):
if seq[i] == 'N' and not in_N:
start_N = i
in_N = True
if in_N and not seq[i+1] == 'N':
end_N = i + 1
length = end_N - start_N
assert length > 0
assert str(seq[start_N:end_N]) == "N"*length
# do not create FT for 1bp gap
if length > 1:
gap_feature = SeqFeature(FeatureLocation(start_N,end_N), strand=1, type="gap")
gap_feature.qualifiers['estimated_length'] = [length]
gap_features.append(gap_feature)
in_N = False
# ----------------------------------------
# OTHER FEATURE (only with clean option)
# ----------------------------------------
new_features = []
first_source = True
has_source = False
removed_cds = 0
for i in range(len(record.features)):
feature = record.features[i]
# Add strain into FT source
if feature.type == 'source' and first_source:
has_source = True
feature.location.end.position = len(record.seq)
feature.qualifiers['organism'] = ["%s %s" % (organism_name, strain)]
feature.qualifiers['strain'] = [strain]
# Remove qualifier /note & /translation
if clean:
if 'note' in feature.qualifiers.keys():
del feature.qualifiers['note']
#if 'translation' in feature.qualifiers.keys():
# del feature.qualifiers['translation']
# Rename locus_tag
if clean:
if 'locus_tag' in feature.qualifiers.keys():
feature.qualifiers['locus_tag'] = [getLocusTag(feature.qualifiers['locus_tag'][0], locus_tag, feature.type)]
# Check /EC_number="5.3.1.25" or /EC_number="1.1.2.-"
if clean:
if 'EC_number' in feature.qualifiers.keys():
for i in range(len(feature.qualifiers['EC_number'])):
feature.qualifiers['EC_number'][i] = getEcNumber(feature.qualifiers['EC_number'][i])
# Remove (EC 2.1.2.3) in /product and /function
if 'product' in feature.qualifiers.keys():
for i in range(len(feature.qualifiers['product'])):
(feature.qualifiers['product'][i], ec_list) = getValueWithoutEc(feature.qualifiers['product'][i], feature)
if ec_list:
for ec in ec_list:
if 'EC_number' not in feature.qualifiers.keys():
feature.qualifiers['EC_number'] = [ec]
else:
feature.qualifiers['EC_number'].append(ec)
# Remove tRNA /product (not only when containing ???)
if clean:
if feature.type == 'tRNA' and 'product' in feature.qualifiers.keys():
del feature.qualifiers['product']
#for i in range(len(feature.qualifiers['product'])):
# if feature.qualifiers['product'][i].count('?') > 1:
# del feature.qualifiers['product'][i]
if 'function' in feature.qualifiers.keys():
for i in range(len(feature.qualifiers['function'])):
(feature.qualifiers['function'][i], ec_list) = getValueWithoutEc(feature.qualifiers['function'][i], feature)
if ec_list:
for ec in ec_list:
if 'EC_number' not in feature.qualifiers.keys():
feature.qualifiers['EC_number'] = [ec]
else:
feature.qualifiers['EC_number'].append(ec)
# Remove FT gene & keep only one FT source per record & remove some CDS
if clean:
if not feature.type == 'gene':
if feature.type == 'source':
if first_source:
new_features.append(feature)
first_source = False
# Remove CDS that are not valid
# CDS -- translation must start with M, nucleotide sequence without N's & no overlap with gap feature
# CDS -- must not have internal stop codons
# CDS -- must end with stop codons (TAG, TAA, or TGA) or add '<' or '>' e.g. complement(<1..174); 1399953..>1401221
elif feature.type == 'CDS':
if not 'transl_table' in feature.qualifiers.keys():
feature.qualifiers['transl_table'] = 11
if feature.strand == 1:
stop_codon = record.seq[feature.location.nofuzzy_end-3:feature.location.nofuzzy_end]
if not str(stop_codon) in ['TAG', 'TAA', 'TGA']:
feature.location = FeatureLocation(ExactPosition(feature.location.nofuzzy_start), AfterPosition(feature.location.nofuzzy_end))
if feature.strand == -1:
stop_codon = record.seq[feature.location.nofuzzy_start:feature.location.nofuzzy_start+3]
if not str(stop_codon) in ['CTA', 'TTA', 'TCA']:
feature.location = FeatureLocation(BeforePosition(feature.location.nofuzzy_start), ExactPosition(feature.location.nofuzzy_end))
translation = feature.extract(record.seq).translate(table=11)
if 'translation' in feature.qualifiers.keys():
if translation[-1] == '*':
if not len(translation) - 1 == len(feature.qualifiers['translation'][0]):
print 'WARNING: CDS %s translation length of different size' % feature.location
print translation
print feature.qualifiers['translation'][0]
else:
if not str(translation[:-1]) == str(feature.qualifiers['translation'][0]):
print 'WARNING: CDS %s translation not identical' % feature.location
print translation[:-1]
print feature.qualifiers['translation'][0]
else:
if not len(translation) == len(feature.qualifiers['translation'][0]):
print 'WARNING: CDS %s translation length of different size' % feature.translation
print translation
print feature.qualifiers['translation'][0]
else:
if not str(translation) == str(feature.qualifiers['translation'][0]):
print 'WARNING: CDS %s translation not identical' % feature.location
print translation
print feature.qualifiers['translation'][0]
#feature.qualifiers['translation'] = [translation]
if translation.startswith('M') and record.seq[feature.location.nofuzzy_start:feature.location.nofuzzy_end].count('N') == 0:
if translation[:-1].count('*') >= 1:
print 'WARNING: CDS %s with internal stop codon' % feature.location
print translation
else:
new_features.append(feature)
else:
print 'WARNING: CDS %s does not start with M' % feature.location
print translation
removed_cds = removed_cds + 1
else:
new_features.append(feature)
if not clean:
new_features.append(feature)
# Add source feature
if not has_source:
feature = SeqFeature(FeatureLocation(0,len(record.seq)), type="source")
feature.qualifiers['organism'] = ["%s %s" % (organism_name, strain)]
feature.qualifiers['strain'] = [strain]
feature.qualifiers['db_xref'] = ["taxon:%s" % taxon_id]
feature.qualifiers['mol_type'] = getMolType(embl_file)
new_features.append(feature)
if clean:
print 'WARNING: %s CDSs have been removed' % removed_cds
else:
print "Only adding header, use '--clean' for cleaning features"
new_features.extend(gap_features)
new_features.sort(feature_compare)
record.features = new_features
# Write out new embl file
SeqIO.write([record], open(dep_file, "w"), "embl")
# if any(f.location is None for f in gb.features):
# continue
for f in gb.features:
if f.location is None:
print(gb, f)
# sort features by start location, source always first
gb.features.sort(key=lambda f: (-len(gb.seq)) *
(f.type == "source") + f.location.start)
# translate color from notes to ApEinfo
for feature in gb.features:
translate_color(feature)
# Add an EcoFlex article reference
ref = Reference()
ref.authors = 'Moore SJ, Lai HE, Kelwick RJ, Chee SM, Bell DJ, Polizzi KM, Freemont PS.'
ref.title = 'EcoFlex: A Multifunctional MoClo Kit for E. coli Synthetic Biology.'
ref.journal = 'ACS Synth Biol 2016;5:1059-1069.'
ref.pubmed_id = '27096716'
gb.annotations['references'].append(ref)
# Fix the direct submission reference
ref = Reference()
# ref = gb.annotations["references"][-1]
ref.authors = "Larralde M"
ref.title = "Direct Submission"
ref.journal = "Distributed with the MoClo Python library\nhttps://github.com/althonos/moclo"
gb.annotations['references'].append(ref)
# write the final record
def reformat_gbk(gbk_file,
study,
publication_title,
publication_authors,
publication_journal,
locus_tag_prefix,
taxon_id,
scaffold_prefix,
strain,
plasmid=False,
locus_count_start=1):
'''
- remove protein_id
- split scaffolds into contigs ==> name contigs contig_XXX
- generate agp file
:param gbk_file:
:param study:
:param publication:
:param locus_tag_prefix:
:param plasmid:
:return:
'''
source, taxonomy, organism = taxon_id2taxonomy(taxon_id)
print(source)
print()
print(taxonomy)
print()
new_records = []
from Bio import SeqIO
import copy
import copy
from Bio.SeqFeature import Reference
from Bio.SeqFeature import FeatureLocation
with open(gbk_file, 'r') as f:
records = [i for i in SeqIO.parse(f, 'genbank')]
#locus_count=1
contig_records = []
contig_count = 1
for new_record in records:
start = 0
end = len(new_record.seq)
print(dir(new_record))
for feature in new_record.features:
'''
if feature.type == 'assembly_gap':
print 'GAP-------'
print feature
contig = new_record[start:int(feature.location.start)]
# update start location
start = int(feature.location.end)
# rename contig record LOCUS
contig.id = "contig_%s" % contig_count
contig.name = "contig_%s" % contig_count
contig_records.append(contig)
contig_count += 1
'''
contig = new_record[start:end]
contig.id = "%s_%02d" % (scaffold_prefix, contig_count)
contig.name = "%s_%02d" % (scaffold_prefix, contig_count)
contig_records.append(contig)
contig_count += 1
for n, record in enumerate(contig_records):
ref = Reference()
ref.authors = publication_authors
ref.journal = publication_journal
ref.title = publication_title
'''
ref_seq = Refserence()
ref.authors = "Trestan Pillonel"
ref.journal = "RL Submitted (09-APRIL-2019) to the INSDC."
'''
#print record
#print dir(record)
#print "id", record.id
#print "name", record.name
#print record.annotations
#print record.description
#print record.dbxrefs
#record.id = ''
record.annotations['source'] = source
record.annotations['taxonomy'] = taxonomy
record.annotations['organism'] = organism
record.description = '%s %s scaffold_%s' % (organism, strain,
n + 1)
if record.features[0].type != 'source':
print('NOT SOURCE-------------------')
record.features = [copy.copy(record.features[0])
] + record.features
record.features[0].qualifiers = {}
record.features[0].type = 'source'
record.features[0].location = FeatureLocation(
0, len(record.seq))
else:
print('SOURCE!!!!!!!!!!!!!!!!')
record.features[0].qualifiers['db_xref'] = ["taxon:%s" % taxon_id]
record.features[0].qualifiers['mol_type'] = ["genomic DNA"]
record.features[0].qualifiers['organism'] = ["%s" % organism]
record.features[0].qualifiers['strain'] = ["%s" % strain]
if plasmid:
# /mol_type="genomic DNA"
# /organism="Klebsiella pneumoniae"
# /strain="KpGe"
#record.features[0].type = "source"
#record.features[0].qualifiers['organism'] = ["Klebsiella pneumoniae"]
#record.features[0].qualifiers['strain'] = ["KpGe"]
record.features[0].qualifiers['plasmid'] = ["p%s" % strain]
record.annotations['mol_type'] = ["genomic DNA"]
ref.location = [record.features[0].location]
#print 'location!', ref.location
record.annotations['references'] = [ref]
record.dbxrefs = ['BioProject:%s' % study]
for i, feature in enumerate(record.features):
if "protein_id" in feature.qualifiers:
del feature.qualifiers['protein_id']
if feature.type == 'gene':
'''
if not plasmid:
locus = "%s_%05d" % (locus_tag_prefix, locus_count)
else:
print 'rename locus!', locus_tag_prefix
locus = "%s_p%04d" % (locus_tag_prefix, locus_count)
'''
locus = "%s_%05d" % (locus_tag_prefix, locus_count_start)
locus_count_start += 1
feature.qualifiers['locus_tag'] = locus
record.features[i + 1].qualifiers['locus_tag'] = locus
new_records.append(record)
return new_records
