def missing_species_names(names):
"""returns a Table of missing species names, or None"""
missing = []
for name in names:
n = Species.get_species_name(name)
if n == "None":
missing.append([name])
if missing:
result = make_table(header=["MISSING SPECIES"], data=missing)
else:
result = None
return result
def get_chrom_names(ref_species, compara):
"""returns the list of chromosome names"""
genome_db = compara.ComparaDb.get_table("genome_db")
dnafrag = compara.ComparaDb.get_table("dnafrag")
joined = genome_db.join(
dnafrag, onclause=genome_db.c.genome_db_id == dnafrag.c.genome_db_id)
condition = sql.and_(
dnafrag.c.coord_system_name == "chromosome",
genome_db.c.name == Species.get_ensembl_db_prefix(ref_species),
dnafrag.c.is_reference == 1,
)
query = sql.select([dnafrag.c.name], condition).select_from(joined)
chroms = [r[0] for r in query.execute()]
return chroms
def renamed_seqs(aln):
"""renames sequences to be just species common name"""
new = []
names = Counter()
for seq in aln.seqs:
latin = get_latin_from_label(seq.name)
common = Species.get_common_name(latin)
names[common] += 1
seq.name = common
new.append((seq.name, seq))
if max(list(names.values())) > 1:
# a species occures more than once
return None
return make_aligned_seqs(data=new, moltype=DNA, array_align=False)
def display_available_dbs(account, release=None):
"""displays the available Ensembl databases at the nominated host"""
db_list = get_db_name(account=account, db_type="core", release=release)
db_list += get_db_name(account=account, db_type="compara", release=release)
rows = []
for db_name in db_list:
species_name = db_name.species
if species_name:
common_name = Species.get_common_name(db_name.species, level="ignore")
if "compara" in db_name.name:
species_name = common_name = "-"
rows.append([db_name.release, db_name.name, species_name, common_name])
table = make_table(
header=["Release", "Db Name", "Species", "Common Name"], data=rows, space=2
)
table = table.sorted(["Release", "Db Name"])
table.legend = (
"Values of 'None' indicate cogent does not have a value for that database name."
)
return table
def get_one2one_orthologs(
compara, ref_genes, outpath, not_strict, force_overwrite, test
):
"""writes one-to-one orthologs of protein coding genes to outpath"""
species = Counter(compara.species)
written = 0
records = []
with click.progressbar(ref_genes, label="Finding 1to1 orthologs") as ids:
for gene in ids:
outfile_name = os.path.join(outpath, "%s.fa.gz" % gene)
if os.path.exists(outfile_name) and not force_overwrite:
written += 1
continue
syntenic = list(
compara.get_related_genes(
stableid=gene, relationship="ortholog_one2one"
)
)
if len(syntenic) != 1:
continue
syntenic = syntenic[0]
if not not_strict and (
syntenic is None or Counter(syntenic.get_species_set()) != species
):
# skipping, not all species had a 1to1 ortholog for this gene
continue
seqs = []
for m in syntenic.members:
records.append([gene, m.stableid, m.location, m.description])
name = Species.get_common_name(m.genome.species)
cds = m.canonical_transcript.cds.trim_stop_codon(allow_partial=True)
cds.name = name
seqs.append([name, cds])
seqs = make_unaligned_seqs(data=seqs)
if test:
print()
print(gene)
print(seqs.to_fasta())
else:
with gzip.open(outfile_name, "wt") as outfile:
outfile.write(seqs.to_fasta() + "\n")
LOGGER.output_file(outfile_name)
written += 1
if test:
msg = "Would have written %d files to %s" % (written, outpath)
else:
msg = "Wrote %d files to %s" % (written, outpath)
click.echo(msg)
if written > 0:
metadata = make_table(
header=["refid", "stableid", "location", "description"], rows=records
)
metadata.write(os.path.join(outpath, "metadata.tsv"))
return