def AnnotateWithMGI(infile, outfile):
'''
Uses the list of mouse gene symbols generated using homologene above
to annotate mouse phenotypes provided through MGI at mousemine.org
Tables:
ensemblg2mgi$annot - original host ensemblg to mouse phenotype ID
mgi$details - mouse phenotype ID to mouse phenotype details
'''
genelist = PipelineGeneInfo.getSymbols(infile)
MGI = PipelineGeneInfo.MGIAnnotation(PARAMS['homologues_mousemine'],
PARAMS['db_name'])
PipelineGeneInfo.runall(MGI, genelist, submit=True)
def AnnotateWithMousePathway(infile, outfile):
'''
Uses the list of mouse gene symbols generated using homologene above
to annotate mouse pathways provided at mousemine.org
Tables:
ensemblg2mousepathway$annot - original host ensemblg to
mouse pathway ID
mousepathway$details - mouse pathway ID to mouse pathway details
'''
genelist = PipelineGeneInfo.getSymbols(infile)
MP = PipelineGeneInfo.MousePathwayAnnotation(
PARAMS['homologues_mousemine'], PARAMS['db_name'])
PipelineGeneInfo.runall(MP, genelist, submit=True)
def AnnotateWithMGI(infile, outfile):
'''
Uses the list of mouse gene symbols generated using homologene above
to annotate mouse phenotypes provided through MGI at mousemine.org
Tables:
ensemblg2mgi$annot - original host ensemblg to mouse phenotype ID
mgi$details - mouse phenotype ID to mouse phenotype details
'''
genelist = list(set(PipelineGeneInfo.getSymbols(infile)))
MGI = PipelineGeneInfo.MGIAnnotation(
PARAMS['homologues_mousemine'],
PARAMS['db_name'], ohost=PARAMS['entrez_host'])
PipelineGeneInfo.runall(MGI, genelist, submit=True)
def GetAndTranslateAllGenes(outfile):
'''
This step is required.
1. All Entrez gene IDs are downloaded from entrez gene.
2. Corresponding ensembl gene, ensembl transcript and ensembl protein
IDs are downloaded from mygene.info
3. Corresponding gene symbols are downloaded from mygene.info
4. These are loaded into the database
5. A list of all gene Entrez IDs is stored as 'allgenes.tsv
Tables:
ensemblg2entrez$geneid - ensemblg to entrez ID
ensemblg2ensemblt$other - ensemblg to ensembl transcript
ensemblg2ensemblp$other - ensemblg to ensembl protein
ensemblg2symbol_xxx$geneid - ensemblg to symbol in species xxx
'''
GeneAnnot = PipelineGeneInfo.EntrezGeneAnnotation(
PARAMS['db_name'], PARAMS['entrez_email'])
if PARAMS['test'] == 1:
entrezgenelist = GeneAnnot.download_all(PARAMS['entrez_host'],
count=100)
else:
entrezgenelist = GeneAnnot.download_all(PARAMS['entrez_host'])
# Generate a SymbolAnnotation object
Sym = PipelineGeneInfo.SymbolAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['entrez_host'],
PARAMS['entrez_sciname'])
# Get Symbol Annotations
PipelineGeneInfo.runall(Sym, entrezgenelist, ['symbol'],
scope='entrezgene', species=PARAMS['entrez_host'],
submit=True)
genesymbols = list(pd.read_csv("entrez2symbol_%s.tsv" % PARAMS[
'entrez_host'], sep="\t")['symbol_%s' % PARAMS['entrez_host']])
# Generate an EnsemblAnnotation object
Ens = PipelineGeneInfo.EnsemblAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['entrez_host'])
# Get Ensembl annotations
PipelineGeneInfo.runall(Ens, genesymbols, ['ensembl'], scope="symbol",
species=PARAMS['entrez_host'], submit=True)
# Make output gene list
outf = IOTools.openFile(outfile, "w")
for gene in genesymbols:
outf.write("%s\n" % gene)
outf.close()
def AnnotateWithHomologene(infile, outfile):
'''
Annotates all genes in allgenes.tsv with homologous gene symbols from
either a list of species provided in the pipeline.ini or all species
available in homologene via mygene.info
Tables:
ensemblg2symbol_xxx$geneid - ensemblg in original species to symbol in xxx
'''
genelist = PipelineGeneInfo.readGeneList(infile)
HG = PipelineGeneInfo.HomologeneAnnotation(
PARAMS['my_gene_info_source'], PARAMS['db_name'],
PARAMS['my_gene_info_homologene'], PARAMS['entrez_host'],
PARAMS['entrez_email'])
PipelineGeneInfo.runall(HG, genelist, ['homologene'], submit=True)
def AnnotateWithPathway(infile, outfile):
'''
Annotates all genes in allgenes.tsv with pathway details, either
for all pathway databases available via mygene.info or those
specified in the pipeline.ini
Tables:
ensemblg2xxx$annot - ensemblg to ID in pathway database
xxx$details - pathway database ID to pathway details
'''
genelist = PipelineGeneInfo.readGeneList(infile)
PW = PipelineGeneInfo.PathwayAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['my_gene_info_pathway'])
PipelineGeneInfo.runall(PW, genelist, ['pathway'], submit=True)
def AnnotateWithMousePathway(infile, outfile):
'''
Uses the list of mouse gene symbols generated using homologene above
to annotate mouse pathways provided at mousemine.org
Tables:
ensemblg2mousepathway$annot - original host ensemblg to
mouse pathway ID
mousepathway$details - mouse pathway ID to mouse pathway details
'''
genelist = list(set(PipelineGeneInfo.getSymbols(infile)))
MP = PipelineGeneInfo.MousePathwayAnnotation(
PARAMS['homologues_mousemine'],
PARAMS['db_name'], ohost=PARAMS['entrez_host'])
PipelineGeneInfo.runall(MP, genelist, submit=True)
def AnnotateWithHPO(infile, outfile):
'''
Uses the list of human gene symbols generated using homologene above
to annotate human phenotypes provided through HPO at humanmine.org
Tables:
ensemblg2hpo$annot - original host ensemblg to human phenotype ID
hpo$details - human phenotype ID to human phenotype details
'''
genelist = PipelineGeneInfo.getSymbols(infile)
HPO = PipelineGeneInfo.HPOAnnotation(PARAMS['homologues_humanmine'],
PARAMS['db_name'])
PipelineGeneInfo.runall(HPO, genelist, submit=True)
ont = PipelineGeneInfo.OntologyAnnotation('hpo',
PARAMS['homologues_hpoont'],
PARAMS['db_name'])
ont.runall(genelist)
def AnnotateWithHomologene(infile, outfile):
'''
Annotates all genes in allgenes.tsv with homologous gene symbols from
either a list of species provided in the pipeline.ini or all species
available in homologene via mygene.info
Tables:
ensemblg2symbol_xxx$geneid - ensemblg in original species to symbol in xxx
'''
genelist = PipelineGeneInfo.readGeneList(infile)
HG = PipelineGeneInfo.HomologeneAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS[
'my_gene_info_homologene'],
PARAMS['entrez_host'],
PARAMS['entrez_email'])
PipelineGeneInfo.runall(HG, genelist, ['homologene'],
species=PARAMS['entrez_host'], submit=True)
def AnnotateWithPathway(infile, outfile):
'''
Annotates all genes in allgenes.tsv with pathway details, either
for all pathway databases available via mygene.info or those
specified in the pipeline.ini
Tables:
ensemblg2xxx$annot - ensemblg to ID in pathway database
xxx$details - pathway database ID to pathway details
'''
genelist = PipelineGeneInfo.readGeneList(infile)
PW = PipelineGeneInfo.PathwayAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['my_gene_info_pathway'],
PARAMS['entrez_host'])
PipelineGeneInfo.runall(PW, genelist,
['pathway'], species=PARAMS['entrez_host'],
submit=True)
def AnnotateWithGO(infile, outfile):
'''
Annotates all genes in allgenes.tsv with GO ontology terms using
information from mygene.info
Tables:
ensemblg2go$annot- ensemblg to go ID
go$details - go ID to details of go term
go$ont - go ID to parent go IDs
'''
genelist = PipelineGeneInfo.readGeneList(infile)
# Generate a GoAnnotation object with details from mygene.info
GO = PipelineGeneInfo.GoAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['my_gene_info_go'],
PARAMS['entrez_host'])
PipelineGeneInfo.runall(GO,
genelist, ['go'],
species=PARAMS['entrez_host'],
submit=True)
# Get the GO hierarcical ontology from OBO foundry
ont = PipelineGeneInfo.OntologyAnnotation('go',
PARAMS['my_gene_info_goont'],
PARAMS['db_name'])
PipelineGeneInfo.runall(ont,
genelist,
species=PARAMS['entrez_host'],
submit=True)
def AnnotateWithHPO(infile, outfile):
'''
Uses the list of human gene symbols generated using homologene above
to annotate human phenotypes provided through HPO at humanmine.org
Tables:
ensemblg2hpo$annot - original host ensemblg to human phenotype ID
hpo$details - human phenotype ID to human phenotype details
'''
genelist = list(set(PipelineGeneInfo.getSymbols(infile)))
HPO = PipelineGeneInfo.HPOAnnotation(
PARAMS['homologues_humanmine'],
PARAMS['db_name'], PARAMS['entrez_host'])
PipelineGeneInfo.runall(HPO, genelist, submit=True)
ont = PipelineGeneInfo.OntologyAnnotation('hpo',
PARAMS['homologues_hpoont'],
PARAMS['db_name'])
PipelineGeneInfo.runall(ont, genelist, species=PARAMS['entrez_host'],
submit=True)
def GetAndTranslateAllGenes(outfile):
'''
This step is required.
1. All Entrez gene IDs are downloaded from entrez gene.
2. Corresponding ensembl gene, ensembl transcript and ensembl protein
IDs are downloaded from mygene.info
3. Corresponding gene symbols are downloaded from mygene.info
4. These are loaded into the database
5. A list of all gene Entrez IDs is stored as 'allgenes.tsv
Tables:
ensemblg2entrez$geneid - ensemblg to entrez ID
ensemblg2ensemblt$other - ensemblg to ensembl transcript
ensemblg2ensemblp$other - ensemblg to ensembl protein
ensemblg2symbol_xxx$geneid - ensemblg to symbol in species xxx
'''
GeneAnnot = PipelineGeneInfo.EntrezGeneAnnotation(PARAMS['db_name'],
PARAMS['entrez_email'])
if PARAMS['test'] == 1:
entrezgenelist = GeneAnnot.download_all(PARAMS['entrez_host'],
count=100)
else:
entrezgenelist = GeneAnnot.download_all(PARAMS['entrez_host'])
# Generate a SymbolAnnotation object
Sym = PipelineGeneInfo.SymbolAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['entrez_host'],
PARAMS['entrez_sciname'])
# Get Symbol Annotations
PipelineGeneInfo.runall(Sym,
entrezgenelist, ['symbol'],
scope='entrezgene',
species=PARAMS['entrez_host'],
submit=True)
genesymbols = list(
pd.read_csv("entrez2symbol_%s.tsv" % PARAMS['entrez_host'],
sep="\t")['symbol_%s' % PARAMS['entrez_host']])
# Generate an EnsemblAnnotation object
Ens = PipelineGeneInfo.EnsemblAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['entrez_host'])
# Get Ensembl annotations
PipelineGeneInfo.runall(Ens,
genesymbols, ['ensembl'],
scope="symbol",
species=PARAMS['entrez_host'],
submit=True)
# Make output gene list
outf = IOTools.open_file(outfile, "w")
for gene in genesymbols:
outf.write("%s\n" % gene)
outf.close()
def MakeSubDBs(infile, outfile):
'''
Takes any lists of genes provided in genesets.dir and makes a database
in genesetdbs.dir containing only annotations for genes in the list.
These will have the same gene ID type as the input lists
and allow the user to quickly see the annotations for their genes
of interest.
'''
PipelineGeneInfo.MakeSubDBs(infile,
outfile,
PARAMS['db_subsettype'],
PARAMS['db_name'],
submit=True)
def AnnotateWithGO(infile, outfile):
'''
Annotates all genes in allgenes.tsv with GO ontology terms using
information from mygene.info
Tables:
ensemblg2go$annot- ensemblg to go ID
go$details - go ID to details of go term
go$ont - go ID to parent go IDs
'''
genelist = PipelineGeneInfo.readGeneList(infile)
# Generate a GoAnnotation object with details from mygene.info
GO = PipelineGeneInfo.GoAnnotation(PARAMS['my_gene_info_source'],
PARAMS['db_name'],
PARAMS['my_gene_info_go'],
PARAMS['entrez_host'])
PipelineGeneInfo.runall(GO, genelist, ['go'],
species=PARAMS['entrez_host'], submit=True)
# Get the GO hierarcical ontology from OBO foundry
ont = PipelineGeneInfo.OntologyAnnotation('go',
PARAMS['my_gene_info_goont'],
PARAMS['db_name'])
PipelineGeneInfo.runall(ont, genelist, species=PARAMS['entrez_host'],
submit=True)