def available_datasets(type=None,*args):
if((type == 'GWAS') or (type == 'Ontology')):
return jsonify(gwas_sets)
elif((type == 'Expr') or (type == 'Network')):
return jsonify(network_list)
elif(type == 'All'):
return str(co.available_datasets())
else:
return jsonify({"data" : list(co.available_datasets(type)[
['Name','Description']].itertuples(index=False))})
def available_datasets(type=None,*args):
# Find the datasets
if(type == None):
datasets = co.available_datasets()
else:
datasets = co.available_datasets(type)
# Return the results in a table friendly format
return jsonify({"data" : list(datasets[
['Name','Description']].itertuples(index=False))})
def available_datasets(type=None,*args):
# Find the datasets
if(type == None):
datasets = co.available_datasets()
else:
datasets = co.available_datasets(type)
# Return the results in a table friendly format
return jsonify({"data" : list(datasets[
['Name','Description']].itertuples(index=False))})
def AtRoot(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtRoot', force=True)
if not co.available_datasets('Expr', 'AtRoot'):
Root = [
'GSE14578', 'GSE46205', 'GSE7631', 'GSE10576', 'GSE42007',
'GSE34130', 'GSE21611', 'GSE22966', 'GSE7641', 'GSE5620',
'GSE8934', 'GSE5628', 'GSE30095', 'GSE30097', 'GSE5624', 'GSE5626',
'GSE5749', 'GSE5621', 'GSE5622', 'GSE5623', 'GSE5625', 'GSE5688'
]
RootFam = sum([
co.Family.from_file(
os.path.join(cf.options.testdir, 'raw', 'GSE',
'{}_family.soft.gz'.format(x))) for x in Root
])
#RootFam.to_keepfile("RootKeep.tsv", keep_hint='root')
return co.COB.from_DataFrame(
RootFam.series_matrix(keepfile=os.path.join(
cf.options.testdir, 'raw', 'GSE', 'RootKeep.tsv')),
'AtRoot',
'Arab Root',
AtTair10,
rawtype='MICROARRAY',
quantile=True)
else:
return co.COB('AtRoot')
def AtLeafHydroIonome(AtTair10):
if cf.test.force.Ontology:
co.del_dataset('GWAS', 'AtLeafHydroIonome', force=True)
if not co.available_datasets('GWAS', 'AtLeafHydroIonome'):
# glob glob is god
csvs = glob.glob(
os.path.join(cf.options.testdir, 'raw', 'GWAS', 'AtIonome',
'AtLeafHydroIonome', '*.csv.gz'))
# Read in each table individually then concat for GIANT table
df = pd.concat([pd.read_table(x, sep=' ') for x in csvs])
df = df.loc[df.pval <= cf.options.alpha, :]
# Kill groups of SNPs that have identical (beta,pval)s
df = df.groupby(['beta', 'pval']).filter(lambda x: len(x) < 5)
# Add 'Chr' to chromosome column
df.CHR = df.CHR.apply(lambda x: 'Chr' + str(x))
# Import class from dataframe
return co.GWAS.from_DataFrame(df,
'AtLeafHydroIonome',
'Arabidopsis second pass 1.6M',
AtTair10,
term_col='Trait',
chr_col='CHR',
pos_col='POS')
else:
return co.GWAS('AtLeafHydroIonome')
def AtGen(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtGen', force=True)
if not co.available_datasets('Expr', 'AtGen'):
General = [
'GSE18975', 'GSE39384', 'GSE19271', 'GSE5632', 'GSE39385',
'GSE5630', 'GSE15617', 'GSE5617', 'GSE5686', 'GSE2473', 'GSE5633',
'GSE5620', 'GSE5628', 'GSE5624', 'GSE5626', 'GSE5621', 'GSE5622',
'GSE5623', 'GSE5625', 'GSE5688'
]
GenFam = sum([
co.Family.from_file(
os.path.join(cf.options.testdir, 'raw', 'GSE',
'{}_family.soft.gz'.format(x))) for x in General
])
#GenFam.to_keepfile("GenKeep.tsv")
return co.COB.from_DataFrame(
GenFam.series_matrix(keepfile=os.path.join(
cf.options.testdir, 'raw', 'GSE', 'GenKeep.tsv')),
'AtGen',
'Arab General',
AtTair10,
rawtype='MICROARRAY',
quantile=True)
else:
return co.COB('AtGen')
def AtSeed(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtSeed', force=True)
if not co.available_datasets('Expr', 'AtSeed'):
Seed = [
'GSE12404', #'GSE30223',
'GSE1051',
'GSE11852',
'GSE5634'
]
SeedFam = sum([
co.Family.from_file(
os.path.join(cf.options.testdir, 'raw', 'GSE',
'{}_family.soft.gz'.format(x))) for x in Seed
])
#SeedFam.to_keepfile("SeedKeep.tsv", keep_hint='seed')
return co.COB.from_DataFrame(
SeedFam.series_matrix(keepfile=os.path.join(
cf.options.testdir, 'raw', 'GSE', 'SeedKeep.tsv')),
'AtSeed',
'Arabidopsis Seed',
AtTair10,
rawtype='MICROARRAY',
quantile=True)
else:
return co.COB('AtSeed')
def ZmRNASeqTissueAtlas(Zm5bFGS):
if cf.test.force.COB:
print('Rebuilding ZmRNASeqTissueAtlas')
co.del_dataset('COB', 'ZmRNASeqTissueAtlas', force=True)
co.del_dataset('Expr', 'ZmRNASeqTissueAtlas', force=True)
if not co.available_datasets('Expr', 'ZmRNASeqTissueAtlas'):
# Build it
return co.COB.from_table(
os.path.join(
cf.options.testdir,
'raw',
'Expr',
'RNASEQ',
'MaizeRNASeqTissue.tsv.bz2',
),
'ZmRNASeqTissueAtlas',
'Maize RNASeq Tissue Atlas Network, Sekhon 2013, PLoS ONE',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.3,
max_accession_missing_data=0.08,
min_single_sample_expr=1,
min_expr=0.001,
quantile=False,
max_val=300,
dry_run=True)
else:
return co.COB('ZmRNASeqTissueAtlas')
def AtSeed(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtSeed', safe=False)
if not co.available_datasets('Expr', 'AtSeed'):
Seed = ['GSE12404', #'GSE30223',
'GSE1051', 'GSE11852', 'GSE5634']
SeedFam = sum(
[co.Family.from_file(
os.path.join(
cf.options.testdir,
'raw', 'GSE', '{}_family.soft.gz'.format(x)
)
)
for x in Seed ]
)
#SeedFam.to_keepfile("SeedKeep.tsv", keep_hint='seed')
return co.COB.from_DataFrame(
SeedFam.series_matrix(
keepfile=os.path.join(
cf.options.testdir,
'raw', 'GSE', 'SeedKeep.tsv'
)
),
'AtSeed', 'Arabidopsis Seed',
AtTair10,
rawtype='MICROARRAY',
quantile=True
)
else:
return co.COB('AtSeed')
def AtGen(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtGen', safe=False)
if not co.available_datasets('Expr', 'AtGen'):
General = ['GSE18975', 'GSE39384', 'GSE19271', 'GSE5632', 'GSE39385',
'GSE5630', 'GSE15617', 'GSE5617', 'GSE5686', 'GSE2473',
'GSE5633', 'GSE5620', 'GSE5628', 'GSE5624',
'GSE5626', 'GSE5621', 'GSE5622', 'GSE5623', 'GSE5625', 'GSE5688']
GenFam = sum(
[co.Family.from_file(
os.path.join(
cf.options.testdir,
'raw', 'GSE', '{}_family.soft.gz'.format(x)
)
)
for x in General ]
)
#GenFam.to_keepfile("GenKeep.tsv")
return co.COB.from_DataFrame(
GenFam.series_matrix(
keepfile=os.path.join(
cf.options.testdir,
'raw', 'GSE', 'GenKeep.tsv'
)
),
'AtGen', 'Arab General',
AtTair10,
rawtype='MICROARRAY',
quantile=True
)
else:
return co.COB('AtGen')
def AtLeaf(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtLeaf', safe=False)
if not co.available_datasets('Expr', 'AtLeaf'):
Leaf = ['GSE14578', 'GSE5630', 'GSE13739', #'GSE26199',
'GSE5686', 'GSE5615', 'GSE5620', 'GSE5628',
'GSE5624', 'GSE5626', 'GSE5621', 'GSE5622',
'GSE5623', 'GSE5625', 'GSE5688']
LeafFam = sum(
[co.Family.from_file(
os.path.join(
cf.options.testdir,
'raw', 'GSE', '{}_family.soft.gz'.format(x)
)
)
for x in Leaf ]
)
#LeafFam.to_keepfile("LeafKeep.tsv", keep_hint="lea")
return co.COB.from_DataFrame(
LeafFam.series_matrix(
keepfile=os.path.join(
cf.options.testdir,
'raw', 'GSE', 'LeafKeep.tsv'
)
),
'AtLeaf', 'Arabidopsis Leaf',
AtTair10,
rawtype='MICROARRAY',
max_gene_missing_data=0.3,
min_expr=0.01,
quantile=True,
)
else:
return co.COB('AtLeaf')
def AtRoot(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtRoot', safe=False)
if not co.available_datasets('Expr', 'AtRoot'):
Root = ['GSE14578', 'GSE46205', 'GSE7631', 'GSE10576', 'GSE42007',
'GSE34130', 'GSE21611', 'GSE22966', 'GSE7641', 'GSE5620',
'GSE8934', 'GSE5628', 'GSE30095', 'GSE30097', 'GSE5624',
'GSE5626', 'GSE5749', 'GSE5621', 'GSE5622',
'GSE5623', 'GSE5625', 'GSE5688']
RootFam = sum(
[co.Family.from_file(
os.path.join(
cf.options.testdir,
'raw', 'GSE', '{}_family.soft.gz'.format(x)
)
)
for x in Root ]
)
#RootFam.to_keepfile("RootKeep.tsv", keep_hint='root')
return co.COB.from_DataFrame(
RootFam.series_matrix(
keepfile=os.path.join(
cf.options.testdir,
'raw', 'GSE', 'RootKeep.tsv')
),
'AtRoot', 'Arab Root',
AtTair10,
rawtype='MICROARRAY',
quantile=True
)
else:
return co.COB('AtRoot')
def ZmIonome(Zm5bFGS):
# Delete the old dataset
if cf.test.force.Ontology:
co.del_dataset('GWAS','ZmIonome',safe=False)
if not co.available_datasets('GWAS','ZmIonome'):
# Grab path the csv
csv = os.path.join(
cf.options.testdir,
'raw','GWAS','Ionome',
'sigGWASsnpsCombinedIterations.longhorn.allLoc.csv.gz'
)
# Define our reference geneome
df = pd.DataFrame.from_csv(csv,index_col=None)
# Import class from dataframe
IONS = co.GWAS.from_DataFrame(
df,'ZmIonome','Maize Ionome',
Zm5bFGS,
term_col='el',chr_col='chr',pos_col='pos'
)
# Get rid of pesky Cobalt
IONS.del_term('Co59')
# I guess we need a test in here too
return IONS
else:
return co.GWAS('ZmIonome')
def AtRootHydroIonome(AtTair10):
if cf.test.force.Ontology:
co.del_dataset('GWAS','AtRootHydroIonome',safe=False)
if not co.available_datasets('GWAS', 'AtRootHydroIonome'):
# glob glob is god
csvs = glob.glob(os.path.join(
cf.options.testdir,
'raw','GWAS','AtIonome',
'AtRootHydroIonome','*.csv.gz'
))
# Read in each table individually then concat for GIANT table
df = pd.concat([pd.read_table(x,sep=' ') for x in csvs])
# Only keep significant pvals
df = df.loc[df.pval <= cf.options.alpha,:]
# Kill groups of SNPs that have identical (beta,pval)s
df = df.groupby(['beta','pval']).filter(lambda x: len(x) < 5)
# Add 'Chr' to chromosome column
df.CHR = df.CHR.apply(lambda x: 'Chr'+str(x))
# Chase dat refgen
# Import class from dataframe
return co.GWAS.from_DataFrame(
df,'AtRootHydroIonome','Arabidopsis second pass 1.6M',
AtTair10, term_col='Trait', chr_col='CHR', pos_col='POS'
)
else:
return co.GWAS('AtRootHydroIonome')
def ZmIonome(Zm5bFGS):
# Delete the old dataset
if cf.test.force.Ontology:
co.del_dataset('GWAS', 'ZmIonome', force=True)
if not co.available_datasets('GWAS', 'ZmIonome'):
# Grab path the csv
csv = os.path.join(
cf.options.testdir, 'raw', 'GWAS', 'Ionome',
'sigGWASsnpsCombinedIterations.longhorn.allLoc.csv.gz')
# Define our reference geneome
df = pd.DataFrame.from_csv(csv, index_col=None)
# Import class from dataframe
IONS = co.GWAS.from_DataFrame(df,
'ZmIonome',
'Maize Ionome',
Zm5bFGS,
term_col='el',
chr_col='chr',
pos_col='pos')
# Get rid of pesky Cobalt
IONS.del_term('Co59')
# I guess we need a test in here too
return IONS
else:
return co.GWAS('ZmIonome')
def ZmRNASeqTissueAtlas(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('COB', 'ZmRNASeqTissueAtlas', safe=False)
co.del_dataset('Expr', 'ZmRNASeqTissueAtlas', safe=False)
if not co.available_datasets('Expr', 'ZmRNASeqTissueAtlas'):
# Build it
return co.COB.from_table(
os.path.join(cf.options.testdir,
'raw', 'Expr', 'RNASEQ',
'MaizeRNASeqTissue.tsv.bz2',
),
'ZmRNASeqTissueAtlas',
'Maize RNASeq Tissue Atlas Network, Sekhon 2013, PLoS ONE',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.3,
max_accession_missing_data=0.08,
min_single_sample_expr=1,
min_expr=0.001,
quantile=False,
max_val=300,
dry_run=True
)
else:
return co.COB('ZmRNASeqTissueAtlas')
def available_datasets(type=None,*args):
return jsonify({
"data" : list(
co.available_datasets(type)[
['Name','Description']
].itertuples(index=False))
}
)
def list_command(args):
if args.type != None and args.name != None:
if args.terms:
if args.type == 'GWAS':
gwas = co.GWAS(args.name)
print('\n'.join([x.id for x in gwas.iter_terms()]))
elif args.type =='GOnt':
gont = co.GOnt(args.name)
print('\n'.join([x.id for x in gont.iter_terms()]))
else:
print(co.available_datasets(args.type,args.name))
elif args.type != None and args.name == None:
args.name = '%'
print(co.available_datasets(args.type,args.name).to_string())
else:
args.type = '%'
args.name = '%'
print(co.available_datasets(args.type,args.name).to_string())
def ZmGO(Zm5bFGS):
if cf.test.force.Ontology:
co.del_dataset('GOnt', 'ZmGO', force=True)
if not co.available_datasets('GOnt', 'ZmGO'):
obo = os.path.join(cf.options.testdir, 'raw', 'GOnt', 'go.obo.bz2')
gene_map_file = os.path.join(cf.options.testdir, 'raw', 'GOnt',
'zm_go.tsv.bz2')
return co.GOnt.from_obo(obo, gene_map_file, 'ZmGO',
'Maize Gene Ontology', Zm5bFGS)
else:
return co.GOnt('ZmGO')
def TestGO(Zm5bFGS):
if cf.test.force.Ontology:
co.del_dataset('GOnt', 'TestGO', force=True)
if not co.available_datasets('GOnt', 'TestGO'):
obo = os.path.join(cf.options.testdir, 'raw', 'GOnt', 'go.test.obo')
gene_map_file = os.path.join(cf.options.testdir, 'raw', 'GOnt',
'go.test.tsv')
return co.GOnt.from_obo(obo, gene_map_file, 'TestGO', 'Test GO',
Zm5bFGS)
else:
return co.GOnt('TestGO')
def AtTair10():
if cf.test.force.RefGen:
co.del_dataset('RefGen', 'AtTair10', force=True)
if not co.available_datasets('RefGen', 'AtTair10'):
gff = os.path.expanduser(
os.path.join(cf.options.testdir, 'raw', 'RefGen',
'TAIR10_GFF3_genes.gff.gz'))
return co.RefGen.from_gff(gff, 'AtTair10', 'Tair 10', '10',
'Arabidopsis')
else:
return co.RefGen('AtTair10')
def list_command(args):
if args.type and args.name:
if args.type == 'GWAS':
gwas = co.GWAS(args.name)
print('\n'.join([x.id for x in gwas.iter_terms()]))
elif args.type =='GOnt':
gont = co.GOnt(args.name)
print('\n'.join([x.id for x in gont.iter_terms()]))
else:
args.type = '%'
args.name = '%'
print(co.available_datasets(args.type,args.name))
def Zm5bFGS():
if cf.test.force.RefGen:
co.del_dataset('RefGen', 'Zm5bFGS', force=True)
if not co.available_datasets('RefGen', 'Zm5bFGS'):
# We have to build it
gff = os.path.expanduser(
os.path.join(cf.options.testdir, 'raw', 'RefGen',
'ZmB73_5b_FGS.gff.gz'))
# This is stupid and necessary because pytables wont let me open
# more than one table
co.RefGen.from_gff(gff, 'Zm5bFGS', 'Maize 5b Filtered Gene Set', '5b',
'Zea Mays')
return co.RefGen('Zm5bFGS')
def AtTair10():
if cf.test.force.RefGen:
co.del_dataset('RefGen', 'AtTair10', safe=False)
if not co.available_datasets('RefGen', 'AtTair10'):
gff = os.path.expanduser(
os.path.join(
cf.options.testdir,
'raw', 'RefGen', 'TAIR10_GFF3_genes.gff.gz'
)
)
return co.RefGen.from_gff(
gff, 'AtTair10', 'Tair 10', '10', 'Arabidopsis'
)
else:
return co.RefGen('AtTair10')
def build_gont(args):
refgen = co.RefGen(args.refgen)
# Check to see if this dataset is already built
if co.available_datasets('GOnt', args.name):
print('Warning! This dataset has already been built.')
co.del_dataset('GOnt', args.name, force=args.force)
go = co.GOnt.from_obo(args.obo_filename,
args.filename,
args.name,
args.description,
refgen,
go_col=args.go_col,
id_col=args.id_col)
print("Done: {}".format(go.summary()))
print('Build Successful')
def AtGO(AtTair10):
if cf.test.force.Ontology:
co.del_dataset('GOnt', 'AtGO', force=True)
if not co.available_datasets('GOnt', 'AtGO'):
obo = os.path.join(cf.options.testdir, 'raw', 'GOnt', 'go.obo.bz2')
gene_map_file = os.path.join(cf.options.testdir, 'raw', 'GOnt',
'ath_go.tsv.bz2')
return co.GOnt.from_obo(obo,
gene_map_file,
'AtGO',
'Arabidopsis Gene Ontology',
AtTair10,
id_col=0,
go_col=5)
else:
return co.GOnt('AtGO')
def build_cob(args):
# Build the refgen
refgen = co.RefGen(args.refgen)
# Check that the sep is likely right.
if len(pd.read_table(args.filename, sep=args.sep).columns) == 1:
print(
("Detected only 1 column in {}, are you sure "
"colunms are separated by '{}'?").format(args.filename, args.sep))
return None
if args.allow_non_membership:
refgen = refgen.copy('{}_tmp'.format(refgen.name),
'temp refgen'.format(refgen.name))
# Add non membership genes
for gid in pd.read_table(args.filename, sep=args.sep).index:
refgen.add_gene(Gene(None, None, id=gid))
quality_control = False if args.skip_quality_control else True
normalize = False if args.skip_normalization else True
# Check to see if this dataset is already built
if co.available_datasets('Expr', args.name):
print('Warning! This dataset has already been built.')
co.del_dataset('Expr', args.name, safe=args.force)
# Basically just pass all the CLI arguments to the COB class method
cob = co.COB.from_table(
args.filename,
args.name,
args.description,
refgen,
# Optional arguments
sep=args.sep,
rawtype=args.rawtype,
# Data Processing
quality_control=quality_control,
normalization=normalize,
quantile=args.quantile,
# Data processing parameters
max_gene_missing_data=args.max_gene_missing_data,
max_accession_missing_data=args.max_accession_missing_data,
min_single_sample_expr=args.min_single_sample_expr,
min_expr=args.min_expr,
max_val=args.max_val,
dry_run=args.dry_run,
index_col=args.index_col)
print("Build successful!")
print(cob.summary())
def Zm5bFGS():
if cf.test.force.RefGen:
co.del_dataset('RefGen', 'Zm5bFGS', safe=False)
if not co.available_datasets('RefGen', 'Zm5bFGS'):
# We have to build it
gff = os.path.expanduser(
os.path.join(
cf.options.testdir,
'raw', 'RefGen', 'ZmB73_5b_FGS.gff.gz'
)
)
# This is stupid and necessary because pytables wont let me open
# more than one table
return co.RefGen.from_gff(
gff, 'Zm5bFGS', 'Maize 5b Filtered Gene Set', '5b', 'Zea Mays'
)
return co.RefGen('Zm5bFGS')
def ZmSAM(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('Expr', 'ZmSAM', force=True)
if not co.available_datasets('Expr', 'ZmSAM'):
return co.COB.from_table(os.path.join(
cf.options.testdir, 'raw', 'Expr', 'RNASEQ',
'TranscriptomeProfiling_B73_Atlas_SAM_FGS_LiLin_20140316.txt.gz'),
'ZmSAM',
'Maize Root Network',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.4,
min_expr=0.1,
quantile=False,
dry_run=False,
max_val=250)
else:
return co.COB('ZmSAM')
def ZmGO(Zm5bFGS):
if cf.test.force.Ontology:
co.del_dataset('GOnt','ZmGO',safe=False)
if not co.available_datasets('GOnt','ZmGO'):
obo = os.path.join(
cf.options.testdir,
'raw','GOnt','go.obo.bz2'
)
gene_map_file = os.path.join(
cf.options.testdir,
'raw','GOnt','zm_go.tsv.bz2'
)
return co.GOnt.from_obo(
obo, gene_map_file, 'ZmGO',
'Maize Gene Ontology', Zm5bFGS
)
else:
return co.GOnt('ZmGO')
def ZmPAN(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('Expr', 'ZmPAN', force=True)
if not co.available_datasets('Expr', 'ZmPAN'):
return co.COB.from_table(os.path.join(cf.options.testdir, 'raw',
'Expr', 'RNASEQ',
'PANGenomeFPKM.txt.gz'),
'ZmPAN',
'Maize Root Network',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.4,
min_expr=1,
quantile=False,
dry_run=False,
sep=',',
max_val=300)
else:
return co.COB('ZmPAN')
def AtGO(AtTair10):
if cf.test.force.Ontology:
co.del_dataset('GOnt','AtGO',safe=False)
if not co.available_datasets('GOnt','AtGO'):
obo = os.path.join(
cf.options.testdir,
'raw','GOnt','go.obo.bz2'
)
gene_map_file = os.path.join(
cf.options.testdir,
'raw','GOnt','ath_go.tsv.bz2'
)
return co.GOnt.from_obo(
obo, gene_map_file, 'AtGO',
'Arabidopsis Gene Ontology', AtTair10,
id_col=0, go_col=5
)
else:
return co.GOnt('AtGO')
def ZmRoot(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('Expr', 'ZmRoot', force=True)
if not co.available_datasets('Expr', 'ZmRoot'):
return co.COB.from_table(os.path.join(cf.options.testdir, 'raw',
'Expr', 'RNASEQ',
'ROOTFPKM.tsv.gz'),
'ZmRoot',
'Maize Root Network',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.3,
max_accession_missing_data=0.08,
min_single_sample_expr=1,
min_expr=0.001,
quantile=False,
max_val=300)
else:
return co.COB('ZmRoot')
def ZmWallace(Zm5bFGS):
if cf.test.force.Ontology:
co.del_dataset('GWAS', 'ZmWallace', force=True)
if not co.available_datasets('GWAS', 'ZmWallace'):
# Grab path the csv
csv = os.path.join(
cf.options.testdir, 'raw', 'GWAS', 'WallacePLoSGenet',
'Wallace_etal_2014_PLoSGenet_GWAS_hits-150112.txt.bz2')
# Define our reference geneome
df = pd.DataFrame.from_csv(csv, index_col=None, sep='\t')
# Import class from dataframe
gwas = co.GWAS.from_DataFrame(df,
'ZmWallace',
'Wallace PLoS ONE Dataset.',
Zm5bFGS,
term_col='trait',
chr_col='chr',
pos_col='pos')
return gwas
else:
return co.GWAS('ZmWallace')
def ZmWallace(Zm5bFGS):
if cf.test.force.Ontology:
co.del_dataset('GWAS','ZmWallace',safe=False)
if not co.available_datasets('GWAS','ZmWallace'):
# Grab path the csv
csv = os.path.join(
cf.options.testdir,
'raw','GWAS','WallacePLoSGenet',
'Wallace_etal_2014_PLoSGenet_GWAS_hits-150112.txt.bz2'
)
# Define our reference geneome
df = pd.DataFrame.from_csv(csv,index_col=None,sep='\t')
# Import class from dataframe
gwas = co.GWAS.from_DataFrame(
df, 'ZmWallace', 'Wallace PLoS ONE Dataset.',
Zm5bFGS,
term_col='trait', chr_col='chr', pos_col='pos'
)
return gwas
else:
return co.GWAS('ZmWallace')
def AtLeaf(AtTair10):
if cf.test.force.COB:
co.del_dataset('Expr', 'AtLeaf', force=True)
if not co.available_datasets('Expr', 'AtLeaf'):
Leaf = [
'GSE14578',
'GSE5630',
'GSE13739', #'GSE26199',
'GSE5686',
'GSE5615',
'GSE5620',
'GSE5628',
'GSE5624',
'GSE5626',
'GSE5621',
'GSE5622',
'GSE5623',
'GSE5625',
'GSE5688'
]
LeafFam = sum([
co.Family.from_file(
os.path.join(cf.options.testdir, 'raw', 'GSE',
'{}_family.soft.gz'.format(x))) for x in Leaf
])
#LeafFam.to_keepfile("LeafKeep.tsv", keep_hint="lea")
return co.COB.from_DataFrame(
LeafFam.series_matrix(keepfile=os.path.join(
cf.options.testdir, 'raw', 'GSE', 'LeafKeep.tsv')),
'AtLeaf',
'Arabidopsis Leaf',
AtTair10,
rawtype='MICROARRAY',
max_gene_missing_data=0.3,
min_expr=0.01,
quantile=True,
)
else:
return co.COB('AtLeaf')
def ZmSAM(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('Expr','ZmSAM',safe=False)
if not co.available_datasets('Expr','ZmSAM'):
return co.COB.from_table(
os.path.join(
cf.options.testdir,
'raw','Expr','RNASEQ',
'TranscriptomeProfiling_B73_Atlas_SAM_FGS_LiLin_20140316.txt.gz'
),
'ZmSAM',
'Maize Root Network',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.4,
min_expr=0.1,
quantile=False,
dry_run=False,
max_val=250
)
else:
return co.COB('ZmSAM')
def ZmRoot(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('Expr','ZmRoot',safe=False)
if not co.available_datasets('Expr','ZmRoot'):
return co.COB.from_table(
os.path.join(
cf.options.testdir,
'raw','Expr',
'RNASEQ','ROOTFPKM.tsv.gz'
),
'ZmRoot',
'Maize Root Network',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.3,
max_accession_missing_data=0.08,
min_single_sample_expr=1,
min_expr=0.001,
quantile=False,
max_val=300
)
else:
return co.COB('ZmRoot')
def ZmPAN(Zm5bFGS):
if cf.test.force.COB:
co.del_dataset('Expr','ZmPAN',safe=False)
if not co.available_datasets('Expr','ZmPAN'):
return co.COB.from_table(
os.path.join(
cf.options.testdir,
'raw','Expr','RNASEQ',
'PANGenomeFPKM.txt.gz'
),
'ZmPAN',
'Maize Root Network',
Zm5bFGS,
rawtype='RNASEQ',
max_gene_missing_data=0.4,
min_expr=1,
quantile=False,
dry_run=False,
sep=',',
max_val=300
)
else:
return co.COB('ZmPAN')
def snp2gene(args):
'''
Perform SNP (locus) to candidate gene mapping
'''
if args.out != sys.stdout:
# Create any non-existant directories
if os.path.dirname(args.out) != '':
os.makedirs(os.path.dirname(args.out),exist_ok=True)
if os.path.exists(args.out) and not args.force:
print(
"Output for {} exists! Skipping!".format(
args.out
),file=sys.stderr
)
return None
# Set a flag saying this is from a COB refgen
from_cob = False
# Create the refgen (option to create it from a COB)
if co.available_datasets('Expr',args.refgen):
refgen = co.COB(args.refgen).refgen
from_cob = args.refgen
elif co.available_datasets('RefGen',args.refgen):
refgen = co.RefGen(args.refgen)
# Create the GWAS object
ont = co.GWAS(args.gwas)
if 'all' in args.terms:
terms = ont.iter_terms()
else:
terms = [ont[term] for term in args.terms]
data = pd.DataFrame()
results = []
for term in terms:
for window_size in args.candidate_window_size:
for flank_limit in args.candidate_flank_limit:
if 'effective' in args.snp2gene:
# Map to effective
effective_loci = term.effective_loci(
window_size=window_size
)
elif 'strongest' in args.snp2gene:
effective_loci = term.strongest_loci(
window_size=window_size,
attr=args.strongest_attr,
lowest=args.strongest_higher
)
genes = pd.DataFrame([ x.as_dict() for x in
refgen.candidate_genes(
effective_loci,
flank_limit=flank_limit,
include_parent_locus=True,
include_num_siblings=True,
include_num_intervening=True,
include_rank_intervening=True,
include_SNP_distance=True,
include_parent_attrs=args.include_parent_attrs,
attrs={'Term':term.id},
)
])
genes['FlankLimit'] = flank_limit
genes['WindowSize'] = window_size
genes['RefGen'] = refgen.name
if from_cob != False:
genes['COB'] = from_cob
data = pd.concat([data,genes])
# Add data from gene info files
original_number_genes = len(data)
for info_file in args.gene_info:
log('Adding info for {}',info_file)
# Assume the file is a table
info = pd.read_table(info_file,sep='\t')
if len(info.columns) == 1:
info = pd.read_table(info_file,sep=',')
# try to match as many columns as possible
matching_columns = set(data.columns).intersection(info.columns)
log("Joining SNP2Gene mappings with info file on: {}",','.join(matching_columns))
data = pd.merge(data,info,how='left')
if len(data) != original_number_genes:
log.warn(
'There were multiple info rows for some genes. '
'Beware of potential duplicate candidate gene entries! '
)
# Generate the output file
data.to_csv(args.out,index=None,sep='\t')
log("Summary stats")
print('-'*100)
#print('With {}kb windows and up to {} flanking genes'.format(int(args.candidate_window_size/1000),args.candidate_flank_limit))
print("Mapped {} SNPs to {} genes".format(len(data.parent_locus.unique()),len(data.ID.unique())))
print("Number of candidate genes per term:")
print(data.groupby('Term').apply(lambda df: len(df.ID)))
'default':dflt['snpLevels'],'min':1,'max':10,'int':True},
'pCutoff':{'title':'Probability Cutoff',
'default':dflt['pCutoff'],'min':0.0,'max':1.0,'int':False},
'minTerm':{'title':'Min Genes (GO)',
'default':dflt['minTerm'],'min':1,'max':99,'int':True},
'maxTerm':{'title':'Max Genes (GO)',
'default':dflt['maxTerm'],'min':100,'max':1000,'int':True},
}
# ----------------------------------------
# Load things to memeory to prepare
# ----------------------------------------
# Generate network list based on allowed list
print('Preloading networks into memory...')
if len(conf['networks']) < 1:
conf['networks'] = list(co.available_datasets('Expr')['Name'].values)
networks = {x:co.COB(x) for x in conf['networks']}
network_info = [[net.name, net._global('parent_refgen'), net.description] for name,net in networks.items()]
print('Availible Networks: ' + str(networks))
# Generate ontology list based on allowed list and load them into memory
print('Preloading GWASes into Memory...')
if len(conf['gwas']) < 1:
conf['gwas'] = list(co.available_datasets('GWAS')['Name'].values)
onts = {x:co.GWAS(x) for x in conf['gwas']}
onts_info = {}
for m,net in networks.items():
ref = net._global('parent_refgen')
onts_info[net.name] = []
for n,ont in onts.items():
if ont.refgen.name == ref:
def snp2gene(args):
'''
Perform SNP (locus) to candidate gene mapping
'''
if args.out != sys.stdout:
# Create any non-existant directories
if os.path.dirname(args.out) != '':
os.makedirs(os.path.dirname(args.out), exist_ok=True)
if os.path.exists(args.out) and not args.force:
print("Output for {} exists! Skipping!".format(args.out),
file=sys.stderr)
return None
# Set a flag saying this is from a COB refgen
from_cob = False
# Create the refgen (option to create it from a COB)
if co.available_datasets('Expr', args.refgen):
refgen = co.COB(args.refgen).refgen
from_cob = args.refgen
elif co.available_datasets('RefGen', args.refgen):
refgen = co.RefGen(args.refgen)
# Create the GWAS object
ont = co.GWAS(args.gwas)
if 'all' in args.terms:
terms = ont.iter_terms()
else:
terms = [ont[term] for term in args.terms]
data = pd.DataFrame()
results = []
for term in terms:
for window_size in args.candidate_window_size:
for flank_limit in args.candidate_flank_limit:
if 'effective' in args.snp2gene:
# Map to effective
effective_loci = term.effective_loci(
window_size=window_size)
elif 'strongest' in args.snp2gene:
effective_loci = term.strongest_loci(
window_size=window_size,
attr=args.strongest_attr,
lowest=args.strongest_higher)
genes = pd.DataFrame([
x.as_dict() for x in refgen.candidate_genes(
effective_loci,
flank_limit=flank_limit,
include_parent_locus=True,
include_num_siblings=True,
include_num_intervening=True,
include_rank_intervening=True,
include_SNP_distance=True,
include_parent_attrs=args.include_parent_attrs,
attrs={'Term': term.id},
)
])
genes['FlankLimit'] = flank_limit
genes['WindowSize'] = window_size
genes['RefGen'] = refgen.name
if from_cob != False:
genes['COB'] = from_cob
data = pd.concat([data, genes])
# Add data from gene info files
original_number_genes = len(data)
for info_file in args.gene_info:
log('Adding info for {}', info_file)
# Assume the file is a table
info = pd.read_table(info_file, sep='\t')
if len(info.columns) == 1:
info = pd.read_table(info_file, sep=',')
# try to match as many columns as possible
matching_columns = set(data.columns).intersection(info.columns)
log("Joining SNP2Gene mappings with info file on: {}",
','.join(matching_columns))
data = pd.merge(data, info, how='left')
if len(data) != original_number_genes:
log.warn('There were multiple info rows for some genes. '
'Beware of potential duplicate candidate gene entries! ')
# Generate the output file
data.to_csv(args.out, index=None, sep='\t')
log("Summary stats")
print('-' * 100)
#print('With {}kb windows and up to {} flanking genes'.format(int(args.candidate_window_size/1000),args.candidate_flank_limit))
print("Mapped {} SNPs to {} genes".format(len(data.parent_locus.unique()),
len(data.ID.unique())))
print("Number of candidate genes per term:")
print(data.groupby('Term').apply(lambda df: len(df.ID)))
# Prefetch the gene names for all the networks
print('Fetching gene names for networks...')
network_genes = {}
for name, net in networks.items():
ids = list(net._expr.index.values)
als = co.RefGen(net._global('parent_refgen')).aliases(ids)
for k,v in als.items():
ids += v
network_genes[name] = list(set(ids))
print('Found gene names')
# Find all of the GWAS data we have available
print('Finding GWAS Data...')
gwas_data_db = {}
for gwas in co.available_datasets('GWASData')['Name']:
gwas_data_db[gwas] = co.GWASData(gwas)
# Find any functional annotations we have
print('Finding functional annotations...')
func_data_db = {}
for func in co.available_datasets('RefGenFunc')['Name']:
print('Processing annotations for {}...'.format(func))
func_data_db[func] = co.RefGenFunc(func)
func_data_db[func].to_csv(os.path.join(scratch_folder,(func+'.tsv')))
geneWordBuilder(func,[os.path.join(scratch_folder,(func+'.tsv'))],[1],['2 end'],['tab'],[True])
# Find any GO ontologies we have for the networks we have
print('Finding applicable GO Ontologies...')
GOnt_db = {}
for name in co.available_datasets('GOnt')['Name']:
print('Availible Networks: ' + str(networks))
# Prefetch the gene neames for all the networks
print('Fetching gene names for networks...')
network_genes = {}
for name, net in networks.items():
ids = list(net._expr.index.values)
als = co.RefGen(net._global('parent_refgen')).aliases(ids)
for k,v in als.items():
ids += v
network_genes[name] = list(set(ids))
print('Found gene names')
# Generate in Memory Avalible GWAS datasets list
print('Finding available GWAS datasets...')
gwas_sets = {"data" : list(co.available_datasets('GWAS')[
['Name','Description']].itertuples(index=False))}
# Find all of the GWAS data we have available
print('Finding GWAS Data...')
gwas_data_db = {}
for gwas in co.available_datasets('GWASData')['Name']:
gwas_data_db[gwas] = co.GWASData(gwas)
# Find any functional annotations we have
print('Finding functional annotations...')
func_data_db = {}
for func in co.available_datasets('RefGenFunc')['Name']:
print('Processing annotations for {}...'.format(func))
func_data_db[func] = co.RefGenFunc(func)
func_data_db[func].to_csv(os.path.join(scratch_folder,(func+'.tsv')))
geneWordBuilder(func,[os.path.join(scratch_folder,(func+'.tsv'))],[1],['2 end'],['tab'],[True])
def all_available_datasets():
return str(co.available_datasets())
'default':dflt['hpo'],
'state':dflt['hpo'],
'isBool':True},
'visEnrich':{
'default':dflt['visEnrich'],
'state':dflt['visEnrich'],
'isBool':True},
}
# ----------------------------------------
# Load things to memeory to prepare
# ----------------------------------------
# Generate network list based on allowed list
print('Preloading networks into memory...')
if len(conf['networks']) < 1:
conf['networks'] = list(co.available_datasets('Expr')['Name'].values)
networks = {x:co.COB(x) for x in conf['networks']}
network_info = []
refLinks = {}
for name,net in networks.items():
network_info.append({
'name':net.name,
'refgen':net._global('parent_refgen'),
'desc':net.description,
})
if net._global('parent_refgen') in conf['refLinks']:
refLinks[net.name] = conf['refLinks'][net._global('parent_refgen')]
print('Availible Networks: ' + str(networks))
# Generate ontology list based on allowed list and load them into memory