def insert_proteomes(p_entries: str, p_proteins: str, p_proteomes: str,
p_structures: str, p_uniprot2ida: str,
p_uniprot2matches: str, p_uniprot2proteome: str,
stg_url: str):
logger.info("preparing data")
proteomes = loadobj(p_proteomes)
uniprot2pdbe = {}
for pdb_id, entry in loadobj(p_structures).items():
for uniprot_acc in entry["proteins"]:
try:
uniprot2pdbe[uniprot_acc].add(pdb_id)
except KeyError:
uniprot2pdbe[uniprot_acc] = {pdb_id}
# Init all proteomes
xrefs = {}
for proteome_id in proteomes:
xrefs[proteome_id] = {
"domain_architectures": set(),
"entries": {},
"proteins": 0,
"sets": set(),
"structures": set(),
"taxa": set()
}
entries = loadobj(p_entries)
proteins = Store(p_proteins)
u2ida = Store(p_uniprot2ida)
u2matches = Store(p_uniprot2matches)
u2proteome = Store(p_uniprot2proteome)
logger.info("starting")
i = 0
for uniprot_acc, proteome_id in u2proteome.items():
proteome = xrefs[proteome_id]
proteome["proteins"] += 1
info = proteins[uniprot_acc]
proteome["taxa"].add(info["taxid"])
try:
dom_members, dom_arch, dom_arch_id = u2ida[uniprot_acc]
except KeyError:
pass
else:
proteome["domain_architectures"].add(dom_arch_id)
for entry_acc in u2matches.get(uniprot_acc, []):
entry = entries[entry_acc]
try:
proteome["entries"][entry.database].add(entry_acc)
except KeyError:
proteome["entries"][entry.database] = {entry_acc}
if entry.clan:
proteome["sets"].add(entry.clan["accession"])
try:
pdb_ids = uniprot2pdbe[uniprot_acc]
except KeyError:
pass
else:
proteome["structures"] |= pdb_ids
i += 1
if not i % 10000000:
logger.info(f"{i:>12,}")
logger.info(f"{i:>12,}")
proteins.close()
u2ida.close()
u2matches.close()
u2proteome.close()
con = MySQLdb.connect(**url2dict(stg_url), charset="utf8mb4")
cur = con.cursor()
cur.execute("DROP TABLE IF EXISTS webfront_proteome")
cur.execute("""
CREATE TABLE webfront_proteome
(
accession VARCHAR(20) PRIMARY KEY NOT NULL,
name VARCHAR(215) NOT NULL,
is_reference TINYINT NOT NULL,
strain VARCHAR(512),
assembly VARCHAR(512),
taxonomy_id VARCHAR(20) NOT NULL,
counts LONGTEXT NOT NULL
) CHARSET=utf8mb4 DEFAULT COLLATE=utf8mb4_unicode_ci
""")
cur.close()
sql = """
INSERT INTO webfront_proteome VALUES (%s, %s, %s, %s, %s, %s, %s)
"""
with Table(con, sql) as table:
for proteome_id, info in proteomes.items():
counts = reduce(xrefs[proteome_id])
counts["entries"]["total"] = sum(counts["entries"].values())
table.insert(
(proteome_id, info["name"], 1 if info["is_reference"] else 0,
info["strain"], info["assembly"], info["taxon_id"],
jsonify(counts)))
con.commit()
con.close()
logger.info("complete")
def insert_structures(p_entries: str, p_proteins: str, p_structures: str,
p_uniprot2ida: str, p_uniprot2matches: str,
p_uniprot2proteome: str, stg_url: str):
logger.info("preparing data")
entries = {}
for entry in loadobj(p_entries).values():
entries[entry.accession] = (entry.database, entry.clan)
uniprot2pdbe = {}
xrefs = {}
for pdb_id, entry in loadobj(p_structures).items():
for uniprot_acc, chains in entry["proteins"].items():
try:
uniprot2pdbe[uniprot_acc][pdb_id] = chains
except KeyError:
uniprot2pdbe[uniprot_acc] = {pdb_id: chains}
xrefs[pdb_id] = {
"domain_architectures": set(),
"entries": {},
"proteomes": set(),
"proteins": 0,
"sets": set(),
"taxa": set()
}
proteins = Store(p_proteins)
u2ida = Store(p_uniprot2ida)
u2matches = Store(p_uniprot2matches)
u2proteome = Store(p_uniprot2proteome)
logger.info("starting")
i = 0
for uniprot_acc in sorted(uniprot2pdbe):
info = proteins[uniprot_acc]
try:
dom_members, dom_arch, dom_arch_id = u2ida[uniprot_acc]
except KeyError:
dom_arch_id = None
proteome_id = u2proteome.get(uniprot_acc)
matches = u2matches.get(uniprot_acc, {})
for pdb_id, chains in uniprot2pdbe[uniprot_acc].items():
_xrefs = xrefs[pdb_id]
if dom_arch_id:
_xrefs["domain_architectures"].add(dom_arch_id)
if proteome_id:
_xrefs["proteomes"].add(proteome_id)
_xrefs["proteins"] += 1
_xrefs["taxa"].add(info["taxid"])
for entry_acc, locations in matches.items():
database, clan = entries[entry_acc]
for chain_id, segments in chains.items():
if overlaps_pdb_chain(locations, segments):
try:
_xrefs["entries"][database].add(entry_acc)
except KeyError:
_xrefs["entries"][database] = {entry_acc}
if clan:
_xrefs["sets"].add(clan["accession"])
break # Skip other chains
i += 1
if not i % 10000:
logger.info(f"{i:>12,}")
logger.info(f"{i:>12,}")
proteins.close()
u2ida.close()
u2matches.close()
u2proteome.close()
con = MySQLdb.connect(**url2dict(stg_url), charset="utf8mb4")
cur = con.cursor()
cur.execute("DROP TABLE IF EXISTS webfront_structure")
cur.execute("""
CREATE TABLE webfront_structure
(
accession VARCHAR(4) PRIMARY KEY NOT NULL,
name VARCHAR(512) NOT NULL,
source_database VARCHAR(10) NOT NULL,
experiment_type VARCHAR(16) NOT NULL,
release_date DATETIME NOT NULL,
resolution FLOAT,
literature LONGTEXT,
chains LONGTEXT NOT NULL,
proteins LONGTEXT NOT NULL,
secondary_structures LONGTEXT,
counts LONGTEXT NOT NULL
) CHARSET=utf8mb4 DEFAULT COLLATE=utf8mb4_unicode_ci
""")
cur.close()
sql = """
INSERT INTO webfront_structure
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
"""
with Table(con, sql) as table:
for pdb_id, info in loadobj(p_structures).items():
counts = reduce(xrefs[pdb_id])
counts["entries"]["total"] = sum(counts["entries"].values())
table.insert((
pdb_id,
info["name"],
"pdb",
info["evidence"],
info["date"],
info["resolution"],
jsonify(info["citations"]),
# Sorted list of unique chain (e.g. 'A', 'B', ...)
jsonify(sorted({
chain_id
for chains in info["proteins"].values()
for chain_id in chains
}),
nullable=False),
jsonify(info["proteins"], nullable=False),
jsonify(info["secondary_structures"]),
jsonify(counts)))
con.commit()
con.close()
logger.info("complete")
def insert_proteins(p_entries: str, p_proteins: str, p_structures: str,
p_taxonomy: str, p_uniprot2comments: str,
p_uniprot2name: str, p_uniprot2evidences: str,
p_uniprot2ida: str, p_uniprot2matches: str,
p_uniprot2proteome: str, p_uniprot2sequence: str,
pro_url: str, stg_url: str):
logger.info("loading CATH/SCOP domains")
uniprot2cath = pdbe.get_cath_domains(pro_url)
uniprot2scop = pdbe.get_scop_domains(pro_url)
logger.info("preparing data")
proteins = Store(p_proteins)
u2comments = Store(p_uniprot2comments)
u2descriptions = Store(p_uniprot2name)
u2evidences = Store(p_uniprot2evidences)
u2ida = Store(p_uniprot2ida)
u2matches = Store(p_uniprot2matches)
u2proteome = Store(p_uniprot2proteome)
u2sequence = Store(p_uniprot2sequence)
taxonomy = {}
for taxid, info in loadobj(p_taxonomy).items():
taxonomy[taxid] = jsonify({
"taxId": taxid,
"scientificName": info["sci_name"],
"fullName": info["full_name"]
})
uniprot2pdbe = {}
for pdb_id, entry in loadobj(p_structures).items():
for uniprot_acc in entry["proteins"]:
try:
uniprot2pdbe[uniprot_acc].append(pdb_id)
except KeyError:
uniprot2pdbe[uniprot_acc] = [pdb_id]
logger.info("counting proteins/IDA")
ida_count = {}
for dom_members, dom_arch, dom_arch_id in u2ida.values():
try:
ida_count[dom_arch_id] += 1
except KeyError:
ida_count[dom_arch_id] = 1
logger.info("inserting proteins")
entries = loadobj(p_entries)
con = MySQLdb.connect(**url2dict(stg_url), charset="utf8mb4")
cur = con.cursor()
cur.execute("""
SELECT protein_acc, COUNT(*)
FROM webfront_varsplic
GROUP BY protein_acc
""")
isoforms = dict(cur.fetchall())
cur.execute("DROP TABLE IF EXISTS webfront_protein")
cur.execute("""
CREATE TABLE webfront_protein
(
accession VARCHAR(15) PRIMARY KEY NOT NULL,
identifier VARCHAR(16) NOT NULL,
organism LONGTEXT NOT NULL,
name VARCHAR(255) NOT NULL,
description LONGTEXT,
sequence LONGBLOB NOT NULL,
length INT(11) NOT NULL,
proteome VARCHAR(20),
gene VARCHAR(70),
go_terms LONGTEXT,
evidence_code INT(11) NOT NULL,
source_database VARCHAR(10) NOT NULL,
is_fragment TINYINT NOT NULL,
structure LONGTEXT,
tax_id VARCHAR(20) NOT NULL,
ida_id VARCHAR(40),
ida TEXT,
counts LONGTEXT NOT NULL
) CHARSET=utf8mb4 DEFAULT COLLATE=utf8mb4_unicode_ci
""")
cur.close()
i = 0
sql = """
INSERT into webfront_protein
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)
"""
with Table(con, sql) as table:
for uniprot_acc, protein_info in proteins.items():
taxid = protein_info["taxid"]
try:
taxon = taxonomy[taxid]
except KeyError:
table.close()
con.close()
raise RuntimeError(f"{uniprot_acc}: invalid taxon {taxid}")
try:
name = u2descriptions[uniprot_acc]
except KeyError:
table.close()
con.close()
raise RuntimeError(f"{uniprot_acc}: missing name")
try:
evidence, gene = u2evidences[uniprot_acc]
except KeyError:
table.close()
con.close()
raise RuntimeError(f"{uniprot_acc}: missing evidence")
try:
sequence = u2sequence[uniprot_acc]
except KeyError:
table.close()
con.close()
raise RuntimeError(f"{uniprot_acc}: missing sequence")
proteome_id = u2proteome.get(uniprot_acc)
clans = []
databases = {}
go_terms = {}
for entry_acc in u2matches.get(uniprot_acc, []):
entry = entries[entry_acc]
try:
databases[entry.database] += 1
except KeyError:
databases[entry.database] = 1
if entry.clan:
clans.append(entry.clan["accession"])
for term in entry.go_terms:
go_terms[term["identifier"]] = term
protein_structures = {}
domains = uniprot2cath.get(uniprot_acc)
if domains:
protein_structures["cath"] = {}
for dom in domains.values():
dom_id = dom["id"]
protein_structures["cath"][dom_id] = {
"domain_id": dom["superfamily"]["id"],
"coordinates": dom["locations"]
}
domains = uniprot2scop.get(uniprot_acc)
if domains:
protein_structures["scop"] = {}
for dom in domains.values():
dom_id = dom["id"]
protein_structures["scop"][dom_id] = {
"domain_id": dom["superfamily"]["id"],
"coordinates": dom["locations"]
}
try:
dom_members, dom_arch, dom_arch_id = u2ida[uniprot_acc]
except KeyError:
dom_arch = dom_arch_id = None
dom_count = 0
else:
dom_count = ida_count[dom_arch_id]
table.insert(
(uniprot_acc, protein_info["identifier"], taxon, name,
jsonify(u2comments.get(uniprot_acc)),
gzip.compress(sequence.encode("utf-8")),
protein_info["length"], proteome_id, gene,
jsonify(list(go_terms.values())), evidence,
"reviewed" if protein_info["reviewed"] else "unreviewed",
1 if protein_info["fragment"] else 0,
jsonify(protein_structures), protein_info["taxid"],
dom_arch_id, dom_arch,
jsonify({
"domain_architectures": dom_count,
"entries": databases,
"isoforms": isoforms.get(uniprot_acc, 0),
"proteomes": 1 if proteome_id else 0,
"sets": len(set(clans)),
"structures": len(uniprot2pdbe.get(uniprot_acc, [])),
"taxa": 1
})))
i += 1
if not i % 10000000:
logger.info(f"{i:>12,}")
logger.info(f"{i:>12,}")
con.commit()
proteins.close()
u2comments.close()
u2descriptions.close()
u2evidences.close()
u2ida.close()
u2matches.close()
u2proteome.close()
u2sequence.close()
logger.info("indexing")
cur = con.cursor()
cur.execute("""
CREATE UNIQUE INDEX ui_protein_identifier
ON webfront_protein (identifier)
""")
cur.execute("""
CREATE INDEX i_protein_proteome
ON webfront_protein (proteome)
""")
cur.execute("""
CREATE INDEX i_protein_database
ON webfront_protein (source_database)
""")
cur.execute("""
CREATE INDEX i_protein_taxon
ON webfront_protein (tax_id)
""")
cur.execute("""
CREATE INDEX i_protein_ida
ON webfront_protein (ida_id)
""")
cur.execute("""
CREATE INDEX i_protein_fragment
ON webfront_protein (is_fragment)
""")
cur.close()
con.close()
logger.info("complete")
def insert_taxonomy(p_entries: str,
p_proteins: str,
p_structures: str,
p_taxonomy: str,
p_uniprot2matches: str,
p_uniprot2proteome: str,
stg_url: str,
p_interpro2taxonomy: str,
tmpdir: Optional[str] = None):
logger.info("preparing data")
dt = DirectoryTree(tmpdir)
entries = loadobj(p_entries)
taxonomy = loadobj(p_taxonomy)
uniprot2pdbe = {}
for pdb_id, entry in loadobj(p_structures).items():
for uniprot_acc, chains in entry["proteins"].items():
try:
uniprot2pdbe[uniprot_acc][pdb_id] = chains
except KeyError:
uniprot2pdbe[uniprot_acc] = {pdb_id: chains}
proteins = Store(p_proteins)
u2matches = Store(p_uniprot2matches)
u2proteome = Store(p_uniprot2proteome)
logger.info("starting")
i = 0
xrefs = {}
files = []
for uniprot_acc, info in proteins.items():
taxon_id = info["taxid"]
try:
taxon = xrefs[taxon_id]
except KeyError:
taxon = xrefs[taxon_id] = init_xrefs()
try:
proteome_id = u2proteome[uniprot_acc]
except KeyError:
pass
else:
taxon["proteomes"].add(proteome_id)
taxon["proteins"]["all"] += 1
protein_structures = uniprot2pdbe.get(uniprot_acc, {})
# Add structures to taxon, regardless of entry matches
taxon["structures"]["all"] |= set(protein_structures.keys())
databases = set()
for entry_acc, locations in u2matches.get(uniprot_acc, {}).items():
entry = entries[entry_acc]
database = entry.database
try:
taxon["entries"][database].add(entry_acc)
except KeyError:
taxon["entries"][database] = {entry_acc}
if database not in databases:
# Counting the protein *once* per database
databases.add(database)
try:
taxon["proteins"]["databases"][database] += 1
except KeyError:
taxon["proteins"]["databases"][database] = 1
try:
taxon["proteins"]["entries"][entry_acc] += 1
except KeyError:
taxon["proteins"]["entries"][entry_acc] = 1
for pdb_id, chains in protein_structures.items():
for chain_id, segments in chains.items():
if overlaps_pdb_chain(locations, segments):
try:
taxon["structures"]["entries"][entry_acc].add(
pdb_id)
except KeyError:
taxon["structures"]["entries"][entry_acc] = {
pdb_id
}
break # Skip other chains
i += 1
if not i % 1000000:
output = dt.mktemp()
dump_xrefs(xrefs, taxonomy, output)
files.append(output)
xrefs = {}
if not i % 10000000:
logger.info(f"{i:>12,}")
if xrefs:
output = dt.mktemp()
dump_xrefs(xrefs, taxonomy, output)
files.append(output)
xrefs = {}
logger.info(f"{i:>12,}")
logger.info(f"temporary files: "
f"{sum(map(os.path.getsize, files))/1024/1024:.0f} MB")
proteins.close()
u2matches.close()
u2proteome.close()
logger.info("populating taxonomy tables")
con = MySQLdb.connect(**url2dict(stg_url), charset="utf8mb4")
cur = con.cursor()
cur.execute("DROP TABLE IF EXISTS webfront_taxonomy")
cur.execute("""
CREATE TABLE webfront_taxonomy
(
accession VARCHAR(20) PRIMARY KEY NOT NULL,
scientific_name VARCHAR(255) NOT NULL,
full_name VARCHAR(512) NOT NULL,
lineage LONGTEXT NOT NULL,
parent_id VARCHAR(20),
rank VARCHAR(20) NOT NULL,
children LONGTEXT,
counts LONGTEXT NOT NULL
) CHARSET=utf8mb4 DEFAULT COLLATE=utf8mb4_unicode_ci
""")
cur.execute("DROP TABLE IF EXISTS webfront_taxonomyperentry")
cur.execute("""
CREATE TABLE webfront_taxonomyperentry
(
id INT NOT NULL AUTO_INCREMENT PRIMARY KEY,
tax_id VARCHAR(20) NOT NULL,
entry_acc VARCHAR(25) NOT NULL,
counts LONGTEXT NULL NULL
) CHARSET=utf8mb4 DEFAULT COLLATE=utf8mb4_unicode_ci
""")
cur.execute("DROP TABLE IF EXISTS webfront_taxonomyperentrydb")
cur.execute("""
CREATE TABLE webfront_taxonomyperentrydb
(
id INT NOT NULL AUTO_INCREMENT PRIMARY KEY,
tax_id VARCHAR(20) NOT NULL,
source_database VARCHAR(10) NOT NULL,
counts LONGTEXT NOT NULL
) CHARSET=utf8mb4 DEFAULT COLLATE=utf8mb4_unicode_ci
""")
cur.close()
table = Table(con,
query="""
INSERT INTO webfront_taxonomy VALUES (%s, %s, %s, %s, %s, %s, %s, %s)
""")
per_entry = Table(con,
query="""
INSERT INTO webfront_taxonomyperentry (tax_id,entry_acc,counts)
VALUES (%s, %s, %s)
""")
per_database = Table(con,
query="""
INSERT INTO webfront_taxonomyperentrydb (tax_id,source_database,counts)
VALUES (%s, %s, %s)
""")
with DumpFile(p_interpro2taxonomy, compress=True) as interpro2taxonomy:
interpro_entries = {
entry.accession
for entry in entries.values()
if entry.database == "interpro" and not entry.is_deleted
}
i = 0
for taxon_id, taxon_xrefs in merge_dumps(files):
taxon = taxonomy[taxon_id]
protein_counts = taxon_xrefs.pop("proteins")
structure_counts = taxon_xrefs.pop("structures")
counts = reduce(taxon_xrefs)
# Add total protein count (not grouped by database/entry)
counts["proteins"] = protein_counts["all"]
# Add total structure count
counts["structures"] = len(structure_counts["all"])
# Add total entry count (not grouped by database)
counts["entries"]["total"] = sum(counts["entries"].values())
table.insert(
(taxon_id, taxon["sci_name"], taxon["full_name"],
f" {' '.join(taxon['lineage'])} ", taxon["parent"],
taxon["rank"], jsonify(taxon["children"]), jsonify(counts)))
# Remove the 'entry' property
# (no needed for webfront_taxonomyperentry)
entry_counts = counts.pop("entries")
database_structures = {}
for entry_acc, count in protein_counts["entries"].items():
if entry_acc in interpro_entries:
interpro2taxonomy.dump((entry_acc, taxon_id, count))
counts["proteins"] = count
try:
entry_structures = structure_counts["entries"][entry_acc]
except KeyError:
counts["structures"] = 0
else:
counts["structures"] = len(entry_structures)
database = entries[entry_acc].database
try:
database_structures[database] |= entry_structures
except KeyError:
database_structures[database] = entry_structures.copy()
finally:
per_entry.insert((taxon_id, entry_acc, jsonify(counts)))
for database, count in protein_counts["databases"].items():
counts.update({
"entries":
entry_counts[database],
"proteins":
count,
"structures":
len(database_structures.get(database, []))
})
per_database.insert((taxon_id, database, jsonify(counts)))
i += 1
if not i % 100000:
logger.info(f"{i:>12,}")
logger.info(f"{i:>12,}")
table.close()
per_entry.close()
per_database.close()
con.commit()
dt.remove()
logger.info("indexing")
cur = con.cursor()
cur.execute("""
CREATE INDEX i_webfront_taxonomyperentry_tax
ON webfront_taxonomyperentry (tax_id)
""")
cur.execute("""
CREATE INDEX i_webfront_taxonomyperentry_entry
ON webfront_taxonomyperentry (entry_acc)
""")
cur.execute("""
CREATE INDEX i_webfront_taxonomyperentrydb_tax
ON webfront_taxonomyperentrydb (tax_id)
""")
cur.execute("""
CREATE INDEX i_webfront_taxonomyperentrydb_database
ON webfront_taxonomyperentrydb (source_database)
""")
cur.close()
con.close()
logger.info("complete")
def export_documents(src_proteins: str, src_entries: str, src_proteomes: str,
src_structures: str, src_taxonomy: str,
src_uniprot2ida: str, src_uniprot2matches: str,
src_uniprot2proteomes: str, outdirs: Sequence[str],
version: str, cache_size: int = 100000):
logger.info("preparing data")
os.umask(0o002)
organizers = []
for path in outdirs:
try:
shutil.rmtree(path)
except FileNotFoundError:
pass
os.makedirs(path, mode=0o775)
organizers.append(DirectoryTree(path))
open(os.path.join(path, f"{version}{LOAD_SUFFIX}"), "w").close()
logger.info("loading domain architectures")
domains = {}
with Store(src_uniprot2ida) as u2ida:
for dom_members, dom_arch, dom_arch_id in u2ida.values():
try:
dom = domains[dom_arch_id]
except KeyError:
domains[dom_arch_id] = {
"ida_id": dom_arch_id,
"ida": dom_arch,
"counts": 1
}
else:
dom["counts"] += 1
logger.info("writing IDA documents")
num_documents = 0
domains = list(domains.values())
for i in range(0, len(domains), cache_size):
documents = []
for dom in domains[i:i + cache_size]:
documents.append((
IDA_INDEX + version,
dom["ida_id"],
dom
))
num_documents += len(documents)
for org in organizers:
filepath = org.mktemp()
dumpobj(filepath, documents)
os.rename(filepath, f"{filepath}{EXTENSION}")
domains = None
proteins = Store(src_proteins)
uniprot2ida = Store(src_uniprot2ida)
uniprot2matches = Store(src_uniprot2matches)
uniprot2proteomes = Store(src_uniprot2proteomes)
entries = loadobj(src_entries) # mem: ~1.5 GB
proteomes = loadobj(src_proteomes) # mem: <1 GB
structures = loadobj(src_structures) # mem: ~ 4GB
taxonomy = loadobj(src_taxonomy) # mem: ~ 2.5GB
uniprot2pdbe = {} # mem: <1 GB
for pdb_id, entry in structures.items():
for uniprot_acc in entry["proteins"]:
try:
uniprot2pdbe[uniprot_acc].append(pdb_id)
except KeyError:
uniprot2pdbe[uniprot_acc] = [pdb_id]
logger.info("writing relationship documents")
i = 0
documents = []
used_entries = set()
used_taxa = set()
for uniprot_acc, info in proteins.items():
taxid = info["taxid"]
taxon = taxonomy[taxid]
used_taxa.add(taxid) # remember that this taxon has been used
try:
dom_members, dom_arch, dom_arch_id = uniprot2ida[uniprot_acc]
except KeyError:
dom_members = []
dom_arch = dom_arch_id = None
# Create an empty document (all properties set to None)
doc = init_rel_doc()
doc.update({
"protein_acc": uniprot_acc.lower(),
"protein_length": info["length"],
"protein_is_fragment": info["fragment"],
"protein_db": "reviewed" if info["reviewed"] else "unreviewed",
"text_protein": join(uniprot_acc, info["identifier"]),
# Taxonomy
"tax_id": taxid,
"tax_name": taxon["sci_name"],
"tax_lineage": taxon["lineage"],
"tax_rank": taxon["rank"],
"text_taxonomy": join(taxid, taxon["full_name"], taxon["rank"])
})
proteome_id = uniprot2proteomes.get(uniprot_acc)
if proteome_id:
proteome = proteomes[proteome_id]
doc.update({
"proteome_acc": proteome_id.lower(),
"proteome_name": proteome["name"],
"proteome_is_reference": proteome["is_reference"],
"text_proteome": join(proteome_id,
proteome["name"],
proteome["assembly"],
proteome["taxon_id"],
proteome["strain"]),
})
# Adding PDBe structures/chains
pdb_chains = {} # mapping PDB-chain ID -> chain segments
pdb_documents = {} # mapping PDB-chain ID -> ES document
for pdb_id in uniprot2pdbe.get(uniprot_acc, []):
pdb_entry = structures[pdb_id]
chains = pdb_entry["proteins"][uniprot_acc]
pdb_doc = doc.copy()
pdb_doc.update({
"structure_acc": pdb_id.lower(),
"structure_resolution": pdb_entry["resolution"],
"structure_date": pdb_entry["date"],
"structure_evidence": pdb_entry["evidence"],
"protein_structure": chains,
"text_structure": join(pdb_id,
pdb_entry["evidence"],
pdb_entry["name"])
})
for chain_id, segments in chains.items():
pdb_chain_id = f"{pdb_id}-{chain_id}"
locations = []
for segment in segments:
locations.append({
"fragments": [{
"start": segment["protein_start"],
"end": segment["protein_end"],
}]
})
chain_doc = pdb_doc.copy()
chain_doc.update({
"structure_chain_acc": chain_id,
"structure_protein_locations": locations,
"structure_chain": pdb_chain_id
})
pdb_documents[pdb_chain_id] = chain_doc
pdb_chains[pdb_chain_id] = segments
# Adding entries
overlapping_chains = set() # chains associated to at least one entry
matches = uniprot2matches.get(uniprot_acc, {})
num_protein_docs = 0
for entry_acc, locations in matches.items():
used_entries.add(entry_acc) # this entry has been used
entry = entries[entry_acc]
if entry.integrated_in:
interpro_acc = entry.integrated_in.lower()
else:
interpro_acc = None
entry_obj = {
"entry_acc": entry_acc.lower(),
"entry_db": entry.database,
"entry_type": entry.type.lower(),
"entry_date": entry.creation_date.strftime("%Y-%m-%d"),
"entry_protein_locations": locations,
"entry_go_terms": [t["identifier"] for t in entry.go_terms],
"entry_integrated": interpro_acc,
"text_entry": join(entry_acc, entry.short_name, entry.name,
entry.type.lower(), interpro_acc),
}
if entry.clan:
entry_obj.update({
"set_acc": entry.clan["accession"].lower(),
"set_db": entry.database,
"text_set": join(entry.clan["accession"],
entry.clan["name"]),
})
if entry_acc in dom_members:
entry_obj.update({
"ida_id": dom_arch_id,
"ida": dom_arch,
})
# Test if the entry overlaps PDB chains
entry_chains = set()
for pdb_chain_id, segments in pdb_chains.items():
if overlaps_pdb_chain(locations, segments):
# Entry overlaps chain: associate entry to struct/chain
chain_doc = pdb_documents[pdb_chain_id]
entry_doc = chain_doc.copy()
entry_doc.update(entry_obj)
documents.append((
entry.database + version,
get_rel_doc_id(entry_doc),
entry_doc
))
entry_chains.add(pdb_chain_id)
num_protein_docs += 1
if entry_chains:
# Entry overlaps at least one chain
overlapping_chains |= entry_chains
else:
# Associate entry to protein directly
entry_doc = doc.copy()
entry_doc.update(entry_obj)
documents.append((
entry.database + version,
get_rel_doc_id(entry_doc),
entry_doc
))
num_protein_docs += 1
# Add chains not overlapping any entry
for chain_id, chain_doc in pdb_documents.items():
if chain_id in overlapping_chains:
continue
chain_doc.update({
"ida_id": dom_arch_id,
"ida": dom_arch,
})
documents.append((
# Not overlapping any entry -> not associated to a member DB
REL_INDEX + version,
get_rel_doc_id(chain_doc),
chain_doc
))
num_protein_docs += 1
if not num_protein_docs:
# No relationships for this protein: fallback to protein doc
documents.append((
REL_INDEX + version,
get_rel_doc_id(doc),
doc
))
while len(documents) >= cache_size:
for org in organizers:
filepath = org.mktemp()
dumpobj(filepath, documents[:cache_size])
os.rename(filepath, f"{filepath}{EXTENSION}")
del documents[:cache_size]
num_documents += cache_size
i += 1
if not i % 10000000:
logger.info(f"{i:>12,}")
logger.info(f"{i:>12,}")
logger.info("writing remaining documents")
# Add unused entries
for entry in entries.values():
if entry.accession in used_entries or entry.is_deleted:
continue
if entry.integrated_in:
interpro_acc = entry.integrated_in.lower()
else:
interpro_acc = None
doc = init_rel_doc()
doc.update({
"entry_acc": entry.accession.lower(),
"entry_db": entry.database,
"entry_type": entry.type.lower(),
"entry_date": entry.creation_date.strftime("%Y-%m-%d"),
"entry_protein_locations": [],
"entry_go_terms": [t["identifier"] for t in entry.go_terms],
"entry_integrated": interpro_acc,
"text_entry": join(entry.accession, entry.short_name, entry.name,
entry.type.lower(), interpro_acc),
})
if entry.clan:
doc.update({
"set_acc": entry.clan["accession"].lower(),
"set_db": entry.database,
"text_set": join(entry.clan["accession"],
entry.clan["name"]),
})
documents.append((
entry.database + version,
get_rel_doc_id(doc),
doc
))
# Add unused taxa
for taxon in taxonomy.values():
if taxon["id"] in used_taxa:
continue
doc = init_rel_doc()
doc.update({
"tax_id": taxon["id"],
"tax_name": taxon["full_name"],
"tax_lineage": taxon["lineage"],
"tax_rank": taxon["rank"],
"text_taxonomy": join(taxon["id"], taxon["full_name"],
taxon["rank"])
})
documents.append((
REL_INDEX + version,
get_rel_doc_id(doc),
doc
))
num_documents += len(documents)
while documents:
for org in organizers:
filepath = org.mktemp()
dumpobj(filepath, documents[:cache_size])
os.rename(filepath, f"{filepath}{EXTENSION}")
del documents[:cache_size]
proteins.close()
uniprot2ida.close()
uniprot2matches.close()
uniprot2proteomes.close()
for path in outdirs:
open(os.path.join(path, f"{version}{DONE_SUFFIX}"), "w").close()
logger.info(f"complete ({num_documents:,} documents)")
def export_entries(url: str, p_metacyc: str, p_clans: str,
p_proteins: str, p_structures: str,
p_uniprot2matches: str, p_uniprot2proteome: str,
p_uniprot2ida: str, p_entry2xrefs: str, p_entries: str,
**kwargs):
min_overlap = kwargs.get("overlap", 0.2)
processes = kwargs.get("processes", 1)
min_similarity = kwargs.get("similarity", 0.75)
tmpdir = kwargs.get("tmpdir")
con = cx_Oracle.connect(url)
cur = con.cursor()
entries = {}
logger.info("loading active InterPro entries")
for entry in _get_interpro_entries(cur):
entries[entry.accession] = entry
logger.info("enriching entries with IntAct data")
for accession, interactions in intact.get_interactions(cur).items():
try:
entry = entries[accession]
except KeyError:
continue
else:
entry.ppi = interactions
logger.info("loading deleted InterPro entries")
for entry in _get_retired_interpro_entries(cur):
if entry.accession in entries:
cur.close()
con.close()
raise RuntimeError(f"entry cannot be active "
f"and deleted {entry.accession}")
entries[entry.accession] = entry
logger.info("loading member database signatures")
for entry in _get_signatures(cur):
if entry.integrated_in and entry.integrated_in not in entries:
cur.close()
con.close()
raise RuntimeError(f"{entry.accession} integrated "
f"in missing entry ({entry.integrated_in})")
entries[entry.accession] = entry
logger.info("loading past entry names")
past_names = _get_name_history(cur)
logger.info("loading past signature integrations")
past_integrations = _get_integration_history(cur)
logger.info("loading ENZYME")
u2enzyme = uniprot.get_swissprot2enzyme(cur)
logger.info("loading Reactome pathways")
u2reactome = uniprot.get_swissprot2reactome(cur)
cur.close()
con.close()
logger.info("loading MetaCyc pathways")
ec2metacyc = metacyc.get_ec2pathways(p_metacyc)
# Updating entry history
for entry in entries.values():
try:
names = past_names[entry.accession]
except KeyError:
pass
else:
entry.history["names"] = names
try:
signatures = past_integrations[entry.accession]
except KeyError:
pass
else:
entry.history["signatures"] = signatures
# Updating entry clan info
for clan in loadobj(p_clans).values():
for entry_acc, score, seq_length in clan["members"]:
try:
entry = entries[entry_acc]
except:
continue
else:
entry.clan = {
"accession": clan["accession"],
"name": clan["name"]
}
inqueue = Queue(maxsize=processes)
outqueue = Queue()
workers = []
for _ in range(max(1, processes - 1)):
dt = DirectoryTree(tmpdir)
p = Process(target=_process_proteins,
args=(inqueue, entries, min_overlap, dt, outqueue))
p.start()
workers.append((p, dt))
logger.info("processing")
uniprot2pdbe = {}
for pdb_id, entry in loadobj(p_structures).items():
for uniprot_acc, chains in entry["proteins"].items():
try:
uniprot2pdbe[uniprot_acc][pdb_id] = chains
except KeyError:
uniprot2pdbe[uniprot_acc] = {pdb_id: chains}
proteins = Store(p_proteins)
u2matches = Store(p_uniprot2matches)
u2proteome = Store(p_uniprot2proteome)
i = 0
for uniprot_acc, matches in u2matches.items():
inqueue.put((
uniprot_acc,
proteins[uniprot_acc],
matches,
u2proteome.get(uniprot_acc),
uniprot2pdbe.get(uniprot_acc, {}),
set(u2enzyme.get(uniprot_acc, [])),
set(u2reactome.get(uniprot_acc, []))
))
i += 1
if not i % 10000000:
logger.info(f"{i:>15,}")
proteins.close()
u2matches.close()
u2proteome.close()
logger.info(f"{i:>15,}")
# Send sentinel
for _ in workers:
inqueue.put(None)
# Merge results from workers
logger.info("exporting domain architectures")
entries_with_xrefs = set()
xref_files = []
entry_counts = {}
entry_intersections = {}
interpro2enzyme = {}
interpro2reactome = {}
with Store(p_uniprot2ida, u2matches.get_keys(), tmpdir) as u2ida:
for _ in workers:
obj = outqueue.get()
xref_files.append(obj[0]) # str
entries_with_xrefs |= obj[1] # set
ida_file = obj[2] # str
deepupdate(obj[3], entry_counts, replace=False) # dict
deepupdate(obj[4], entry_intersections, replace=False) # dict
deepupdate(obj[5], interpro2enzyme) # dict
deepupdate(obj[6], interpro2reactome) # dict
with DumpFile(ida_file) as df:
i = 0
for uniprot_acc, dom_members, dom_str, dom_id in df:
u2ida[uniprot_acc] = (
dom_members,
dom_str,
dom_id
)
i += 1
if not i % 1000:
u2ida.sync()
u2ida.sync()
size = u2ida.merge(processes=processes)
# Adding empty EntryXrefs objects for entries without xrefs
xref_files.append(workers[0][1].mktemp())
with DumpFile(xref_files[-1], compress=True) as df:
for entry_acc in sorted(set(entries.keys()) - entries_with_xrefs):
df.dump((entry_acc, EntryXrefs().asdict()))
logger.info("exporting cross-references")
with DumpFile(p_entry2xrefs, compress=True) as df:
for entry_acc, xrefs in merge_dumps(xref_files):
df.dump((entry_acc, xrefs))
entry = entries[entry_acc]
# Reactome pathways
if entry_acc in interpro2reactome:
pathways = interpro2reactome[entry_acc]
entry.pathways["reactome"] = [
dict(zip(("id", "name"), pthw))
for pthw in sorted(pathways)
]
# EC numbers
if entry_acc in interpro2enzyme:
ecnos = sorted(interpro2enzyme[entry_acc])
entry.cross_references["ec"] = ecnos
# MetaCyc pathways
pathways = set()
for ecno in ecnos:
pathways |= set(ec2metacyc.get(ecno, []))
if pathways:
entry.pathways["metacyc"] = [
dict(zip(("id", "name"), pthw))
for pthw in sorted(pathways)
]
for p, dt in workers:
size += dt.size
dt.remove()
logger.info(f"temporary files: {size / 1024 / 1024:.0f} MB")
logger.info("calculating overlapping relationships")
supfam = "homologous_superfamily"
types = (supfam, "domain", "family", "repeat")
for entry_acc, overlaps in entry_intersections.items():
entry1 = entries[entry_acc]
entry_cnt = entry_counts[entry_acc]
type1 = entry1.type.lower()
for other_acc, overlap_counts in overlaps.items():
o1 = overlap_counts["1"]
o2 = overlap_counts["2"]
other_cnt = entry_counts[other_acc]
# Independent coefficients
coef1 = o1 / (entry_cnt + other_cnt - o1)
coef2 = o2 / (entry_cnt + other_cnt - o2)
# Final coefficient: average of independent coefficients
coef = (coef1 + coef2) * 0.5
# Containment indices
c1 = o1 / entry_cnt
c2 = o2 / other_cnt
if all([item < min_similarity for item in (coef, c1, c2)]):
continue
# Entries are similar enough
entry2 = entries[other_acc]
type2 = entry2.type.lower()
if ((type1 == supfam and type2 in types)
or (type1 in types and type2 == supfam)):
# e1 -> e2 relationship
entry1.overlaps_with.append({
"accession": other_acc,
"name": entry2.name,
"type": type2
})
# e2 -> e1 relationship
entry2.overlaps_with.append({
"accession": entry_acc,
"name": entry1.name,
"type": type1
})
dumpobj(p_entries, entries)
logger.info("populating ENTRY2PATHWAY")
con = cx_Oracle.connect(url)
cur = con.cursor()
cur.execute("TRUNCATE TABLE INTERPRO.ENTRY2PATHWAY")
cur.close()
sql = "INSERT INTO INTERPRO.ENTRY2PATHWAY VALUES (:1, :2, :3, :4)"
with Table(con, sql) as table:
for e in entries.values():
for database, pathways in e.pathways.items():
code = PATHWAY_DATABASE[database]
for pthw in pathways:
table.insert((
e.accession,
code,
pthw["id"],
pthw["name"]
))
con.commit()
con.close()
logger.info("complete")