def store_proteins_descriptions(pgdb, fastafn, tsvfn, mapfn, header, decoy,
fastadelim, genefield):
if not fastafn:
proteins = {}
for psm in tsvreader.generate_tsv_psms(tsvfn, header):
proteins.update({x: 1 for x in
tsvreader.get_proteins_from_psm(psm)})
proteins = [(protein,) for protein in proteins.keys()]
pgdb.store_proteins(proteins)
else:
proteins, sequences, evidences = fastareader.get_proteins_for_db(
fastafn)
proteins = [x for x in proteins]
pgdb.store_proteins(proteins, evidences, sequences)
if not mapfn:
associations = fastareader.get_proteins_genes(fastafn, fastadelim,
genefield)
genes, descriptions = [], []
for assoc in associations:
genes.append((assoc[1], assoc[0]))
descriptions.append((assoc[0], assoc[3]))
pgdb.store_descriptions(descriptions)
pgdb.store_genes(genes)
if mapfn:
proteins_with_versions = {}
for protein in proteins:
proteins_with_versions[protein[0].split('.')[0]] = protein
if decoy:
mod = fastareader.get_decoy_mod_string(proteins[0][0])
proteins_with_versions = {k.replace(mod, ''): v for k, v
in proteins_with_versions.items()}
gpmap = get_protein_gene_map(mapfn, proteins_with_versions, decoy)
pgdb.store_gene_and_associated_id(gpmap)
return set([x[0] for x in proteins])
def add_genes_to_psm_table(psms, pgdb):
gpmap = pgdb.get_protein_gene_map()
for psm in psms:
outpsm = {x: y for x, y in psm.items()}
proteins = tsvreader.get_proteins_from_psm(psm)
outpsm[mzidtsvdata.HEADER_GENE] = ';'.join(get_genes(proteins, gpmap))
symbols = get_symbols(proteins, gpmap)
desc = get_descriptions(proteins, gpmap)
outpsm[mzidtsvdata.HEADER_SYMBOL] = ';'.join(symbols)
outpsm[mzidtsvdata.HEADER_DESCRIPTION] = ';'.join(desc)
yield outpsm
def add_genes_to_psm_table(psmfn, oldheader, pgdb):
gpmap = pgdb.get_protein_gene_map()
for psm in tsvreader.generate_tsv_psms(psmfn, oldheader):
outpsm = {x: y for x, y in psm.items()}
proteins = tsvreader.get_proteins_from_psm(psm)
outpsm[mzidtsvdata.HEADER_GENE] = ';'.join(get_genes(proteins, gpmap))
symbols = get_symbols(proteins, gpmap)
desc = get_descriptions(proteins, gpmap)
outpsm[mzidtsvdata.HEADER_SYMBOL] = ';'.join(symbols)
outpsm[mzidtsvdata.HEADER_DESCRIPTION] = ';'.join(desc)
yield outpsm
def store_proteins_descriptions(pgdb, fastafn, fastamd5, tsvfn, header,
fastadelim, genefield):
if not fastafn:
prots = {}
for psm in tsvreader.generate_split_tsv_lines(tsvfn, header):
prots.update({x: 1 for x in tsvreader.get_proteins_from_psm(psm)})
prots = [(protein, ) for protein in prots.keys()]
pgdb.store_proteins(prots)
else:
prots, seqs, desc, evids, ensgs, symbols = fastareader.get_proteins_for_db(
fastafn, fastadelim, genefield)
pgdb.store_fasta(fastafn, fastamd5, prots, evids, seqs, desc, ensgs,
symbols)
return set([x[0] for x in prots])
def generate_psms_with_proteingroups(psms, pgdb, specfncol, unroll):
rownr = 0
use_evi = pgdb.check_evidence_tables()
all_protein_group_content = pgdb.get_all_psms_proteingroups(use_evi)
protein = next(all_protein_group_content)
for psm in psms:
if unroll:
psm_id = tsvreader.get_psm_id(psm, specfncol)
lineproteins = get_all_proteins_from_unrolled_psm(psm_id, pgdb)
else:
lineproteins = tsvreader.get_proteins_from_psm(psm)
proteins_in_groups = {}
while protein[0] == rownr:
try:
proteins_in_groups[protein[lookups.MASTER_INDEX]].append(
protein)
except KeyError:
proteins_in_groups[protein[lookups.MASTER_INDEX]] = [protein]
try:
protein = next(all_protein_group_content)
except StopIteration:
protein = [-1]
sorted_pgs = sort_protein_groups(proteins_in_groups, use_evi)
psm_masters = []
psm_pg_proteins = []
for master, group in sorted(sorted_pgs.items()):
psm_masters.append(master)
psm_pg_proteins.append(
[protein[lookups.PROTEIN_ACC_INDEX] for protein in group])
outpsm = {
mzidtsvdata.HEADER_MASTER_PROT:
';'.join(psm_masters),
mzidtsvdata.HEADER_PG_CONTENT:
';'.join([','.join([y for y in x]) for x in psm_pg_proteins]),
mzidtsvdata.HEADER_PG_AMOUNT_PROTEIN_HITS:
';'.join(count_protein_group_hits(lineproteins, psm_pg_proteins))
}
outpsm.update(psm)
rownr += 1
yield outpsm
def generate_psms_with_proteingroups(fn, oldheader, newheader, pgdb,
unroll=False):
rownr = 0
use_evi = pgdb.check_evidence_tables()
all_protein_group_content = pgdb.get_all_psms_proteingroups(use_evi)
protein = next(all_protein_group_content)
for psm in tsvreader.generate_tsv_psms(fn, oldheader):
if unroll:
psm_id = tsvreader.get_psm_id(psm)
lineproteins = get_all_proteins_from_unrolled_psm(psm_id, pgdb)
else:
lineproteins = tsvreader.get_proteins_from_psm(psm)
proteins_in_groups = {}
while protein[0] == rownr:
try:
proteins_in_groups[protein[
lookups.MASTER_INDEX]].append(protein)
except KeyError:
proteins_in_groups[protein[lookups.MASTER_INDEX]] = [protein]
try:
protein = next(all_protein_group_content)
except StopIteration:
protein = [-1]
sorted_pgs = sorters.sort_protein_groups(proteins_in_groups, use_evi)
psm_masters = []
psm_pg_proteins = []
for master, group in sorted_pgs.items():
psm_masters.append(master)
psm_pg_proteins.append([protein[lookups.PROTEIN_ACC_INDEX]
for protein in group])
outpsm = {mzidtsvdata.HEADER_MASTER_PROT: ';'.join(psm_masters),
mzidtsvdata.HEADER_PG_CONTENT: ';'.join(
[','.join([y for y in x]) for x in psm_pg_proteins]),
mzidtsvdata.HEADER_PG_AMOUNT_PROTEIN_HITS: ';'.join(
count_protein_group_hits(lineproteins, psm_pg_proteins))
}
outpsm.update(psm)
rownr += 1
yield outpsm
def store_proteins_descriptions(pgdb, fastafn, tsvfn, mapfn, header, decoy,
fastadelim, genefield):
if not fastafn:
proteins = {}
for psm in tsvreader.generate_tsv_psms(tsvfn, header):
proteins.update(
{x: 1
for x in tsvreader.get_proteins_from_psm(psm)})
proteins = [(protein, ) for protein in proteins.keys()]
pgdb.store_proteins(proteins)
else:
proteins, sequences, evidences = fastareader.get_proteins_for_db(
fastafn)
proteins = [x for x in proteins]
pgdb.store_proteins(proteins, evidences, sequences)
if not mapfn:
associations = fastareader.get_proteins_genes(
fastafn, fastadelim, genefield)
genes, descriptions = [], []
for assoc in associations:
genes.append((assoc[1], assoc[0]))
descriptions.append((assoc[0], assoc[3]))
pgdb.store_descriptions(descriptions)
pgdb.store_genes(genes)
if mapfn:
proteins_with_versions = {}
for protein in proteins:
proteins_with_versions[protein[0].split('.')[0]] = protein
if decoy:
mod = fastareader.get_decoy_mod_string(proteins[0][0])
proteins_with_versions = {
k.replace(mod, ''): v
for k, v in proteins_with_versions.items()
}
gpmap = get_protein_gene_map(mapfn, proteins_with_versions, decoy)
pgdb.store_gene_and_associated_id(gpmap)
return set([x[0] for x in proteins])