def sample_5():
"""EPost - ELink - ESummary/EFetch
Downloads gene records linked to a set of proteins corresponding
to a list of protein GI numbers.
"""
# Input: List of Entrez UIDs in database protein (protein GIs).
id_list = '194680922,50978626,28558982,9507199,6678417'
elems_prot = ez.eselect(tool='post', db='protein', id=id_list)
elems_gene = ez.eselect(tool='link',
dbfrom='protein',
db='gene',
elems=elems_prot,
linkname='protein_gene',
cmd='neighbor_history')
for line in ez.eapply(tool='summary', db='gene', elems=elems_gene):
print(line)
for line in ez.eapply(tool='fetch',
db='gene',
elems=elems_gene,
rettype='xml',
retmode='xml'):
print(line)
def sample_4():
"""ESearch - ELink - ESummary/EFetch
Download protein FASTA records linked to abstracts published
in 2009 that are indexed in MeSH for both asthma and leukotrienes.
"""
# Input: Entrez text query in database pubmed.
query = 'asthma[mesh] AND leukotrienes[mesh] AND 2009[pdat]'
elems_pubmed = ez.eselect(tool='search', db='pubmed', term=query)
elems_prot = ez.eselect(tool='link',
dbfrom='pubmed',
db='protein',
elems=elems_pubmed,
linkname='pubmed_protein',
cmd='neighbor_history')
# Linked XML Document Summaries from database protein.
for line in ez.eapply(tool='summary', db='protein', elems=elems_prot):
print(line)
# Formatted data records of selected proteins (FASTA in this case).
for line in ez.eapply(tool='fetch',
db='protein',
elems=elems_prot,
rettype='fasta'):
print(line)
def sample_3():
"""ELink - ESummary/Efetch
Download gene records linked to a set of proteins corresponding to
a list of GI numbers.
"""
# Input UIDs (protein GIs).
id_list = '194680922,50978626,28558982,9507199,6678417'
# Select elements, linking dbs protein and gene with the name protein_gene.
elems = ez.eselect(tool='link',
dbfrom='protein',
db='gene',
id=id_list,
linkname='protein_gene',
cmd='neighbor_history')
# XML document summaries of selected genes.
for line in ez.eapply(tool='summary', db='gene', elems=elems):
print(line)
# Formatted data records of selected genes (FASTA in this case).
for line in ez.eapply(tool='fetch',
db='gene',
elems=elems,
rettype='fasta'):
print(line)
def sample_4():
"""ESearch - ELink - ESummary/EFetch
Download protein FASTA records linked to abstracts published
in 2009 that are indexed in MeSH for both asthma and leukotrienes.
"""
# Input: Entrez text query in database pubmed.
query = 'asthma[mesh] AND leukotrienes[mesh] AND 2009[pdat]'
elems_pubmed = entrez.eselect(tool='search', db='pubmed', term=query)
elems_prot = entrez.eselect(tool='link', dbfrom='pubmed', db='protein',
elems=elems_pubmed, linkname='pubmed_protein',
cmd='neighbor_history')
# Linked XML Document Summaries from database protein.
for line in entrez.eapply(tool='summary', db='protein', elems=elems_prot):
print(line)
# Formatted data records of selected proteins (FASTA in this case).
for line in entrez.eapply(tool='fetch', db='protein', elems=elems_prot,
rettype='fasta'):
print(line)
def sample_6():
"""EPost - ESearch
Given an input set of protein GI numbers, create a history set containing
the members of the input set that correspond to human proteins.
(Which of these proteins are from human?)
"""
id_list = '194680922,50978626,28558982,9507199,6678417'
elems = ez.eselect(tool='post', db='protein', id=id_list)
for line in ez.eapply(tool='search',
db='protein',
term='human[orgn]',
elems=elems):
print(line)
def sample_2():
"""EPost - ESummary/EFetch
Download protein records corresponding to a list of GI numbers.
"""
# Input: List of Entrez UIDs (integer identifiers, e.g. PMID, GI, Gene ID).
id_list = '194680922,50978626,28558982,9507199,6678417'
elems = entrez.eselect(tool='post', db='protein', id=id_list)
# XML document summaries.
for line in entrez.eapply(tool='summary', db='protein', elems=elems):
print(line)
# Formatted data records (FASTA in this case).
for line in entrez.eapply(tool='fetch', db='protein', elems=elems,
rettype='fasta'):
print(line)
def sample_1():
"""ESearch - ESummary/EFetch
Download PubMed records that are indexed in MeSH for both asthma
and leukotrienes and were also published in 2009.
"""
# Input query.
query = 'asthma[mesh] AND leukotrienes[mesh] AND 2009[pdat]'
# Select the elements: query pubmed and keep the reference.
elems = entrez.eselect(tool='search', db='pubmed', term=query)
# XML document summaries.
for line in entrez.eapply(tool='summary', db='pubmed', elems=elems):
print(line)
# Formatted data records (abstracts in this case).
for line in entrez.eapply(tool='fetch', db='pubmed', elems=elems,
rettype='abstract'):
print(line)
def sample_2():
"""EPost - ESummary/EFetch
Download protein records corresponding to a list of GI numbers.
"""
# Input: List of Entrez UIDs (integer identifiers, e.g. PMID, GI, Gene ID).
id_list = '194680922,50978626,28558982,9507199,6678417'
elems = ez.eselect(tool='post', db='protein', id=id_list)
# XML document summaries.
for line in ez.eapply(tool='summary', db='protein', elems=elems):
print(line)
# Formatted data records (FASTA in this case).
for line in ez.eapply(tool='fetch',
db='protein',
elems=elems,
rettype='fasta'):
print(line)
def sample_3():
"""ELink - ESummary/Efetch
Download gene records linked to a set of proteins corresponding to
a list of GI numbers.
"""
# Input UIDs (protein GIs)
id_list = '194680922,50978626,28558982,9507199,6678417'
# Select elements, linking dbs protein and gene with the name protein_gene
elems = entrez.eselect(tool='link', dbfrom='protein', db='gene', id=id_list,
linkname='protein_gene', cmd='neighbor_history')
# XML document summaries of selected genes.
for line in entrez.eapply(tool='summary', db='gene', elems=elems):
print(line)
# Formatted data records of selected genes (FASTA in this case).
for line in entrez.eapply(tool='fetch', db='gene', elems=elems,
rettype='fasta'):
print(line)
def sample_7():
"""ELink - ESearch
Given an input set of protein GI numbers, create a history set containing
the gene IDs linked to members of the input set that also are on human
chromosome X.
(Which of the input proteins are encoded by a gene on human chromosome X?)
"""
# Input: UIDs in database protein (protein GIs).
id_list = '148596974,42544182,187937179,4557377,6678417'
elems = ez.eselect(tool='link',
dbfrom='protein',
db='gene',
id=id_list,
linkname='protein_gene',
cmd='neighbor_history')
query = 'human[orgn] AND x[chr]'
for line in ez.eapply(tool='search', db='gene', term=query, elems=elems):
print(line)
def sample_1():
"""ESearch - ESummary/EFetch
Download PubMed records that are indexed in MeSH for both asthma
and leukotrienes and were also published in 2009.
"""
# Input query.
query = 'asthma[mesh] AND leukotrienes[mesh] AND 2009[pdat]'
# Select the elements: query pubmed and keep the reference.
elems = ez.eselect(tool='search', db='pubmed', term=query)
# XML document summaries.
for line in ez.eapply(tool='summary', db='pubmed', elems=elems):
print(line)
# Formatted data records (abstracts in this case).
for line in ez.eapply(tool='fetch',
db='pubmed',
elems=elems,
rettype='abstract'):
print(line)