def query_uniprot(gene):
u = up.UniProt()
res = u.search("gene_exact:" + gene +
"+AND+reviewed:yes+AND+organism:9606",
columns="id").split("\n")
if len(res[1:-1]) == 1:
return res[1]
else:
return res[1:-1]
def test_muscle():
m = MUSCLE(verbose=False)
m.parameters
m.getParametersDetails("format")
u = uniprot.UniProt(verbose=False)
f1 = u.get_fasta("P18812")
f2 = u.get_fasta("P18813")
jobid = m.run(frmt="fasta", sequence=f1+f2, email="*****@*****.**")
m.getStatus(jobid)
m.wait(jobid)
m.getResultTypes(jobid)
m.getResult(jobid, 'phylotree')
def test_muscle():
m = MUSCLE(verbose=False)
m.parameters
m.get_parameter_details("format")
try:
m.get_parameter_details("formattt")
assert False
except:
assert True
u = uniprot.UniProt(verbose=False)
f1 = u.get_fasta("P18812")
f2 = u.get_fasta("P18813")
jobid = m.run(frmt="fasta", sequence=f1 + f2, email="*****@*****.**")
m.get_status(jobid)
m.wait(jobid)
m.get_result_types(jobid)
m.get_result(jobid, 'phylotree')
def query_uniprot(gene):
u = up.UniProt()
return u.search(
"gene_exact:" + gene + "+AND+reviewed:yes+AND+organism:9606",
columns="id, protein names, comment(FUNCTION)").split("\n")[1]
def query_uniprot(gene):
u = up.UniProt()
return u.search("gene_exact:"+gene+"+AND+reviewed:yes+AND+organism:9606",
columns = "id").split("\n")[1]
def __init__(self,
folder,
requests_per_sec=10,
padj_threshold=0.05,
log2_fc_threshold=0,
fc_threshold=None,
pattern="*complete*.xls"):
assert log2_fc_threshold >= 0, "log2 fc_threshold must be >=0"
if fc_threshold is not None:
log2_fc_threshold = pylab.log2(fc_threshold)
from bioservices import panther, quickgo, uniprot
self.panther = panther.Panther()
self.valid_taxons = [
x['taxon_id'] for x in self.panther.get_supported_genomes()
]
self.quickgo = quickgo.QuickGO(cache=True)
self.uniprot = uniprot.UniProt(cache=True)
self.quickgo.requests_per_sec = requests_per_sec
self.uniprot.requests_per_sec = requests_per_sec
self.ancestors = {
"MF": "GO:0003674",
"CC": "GO:0005575",
"BP": "GO:0008150"
}
self.aspects = {"MF": "molecular_function"}
self.ontologies = [
'GO:0003674', 'GO:0008150', 'GO:0005575',
'ANNOT_TYPE_ID_PANTHER_GO_SLIM_MF',
'ANNOT_TYPE_ID_PANTHER_GO_SLIM_BP',
'ANNOT_TYPE_ID_PANTHER_GO_SLIM_CC', 'ANNOT_TYPE_ID_PANTHER_PC',
'ANNOT_TYPE_ID_PANTHER_PATHWAY', 'ANNOT_TYPE_ID_REACTOME_PATHWAY'
]
self.ontology_aliases = [
"MF", "BP", "CC", 'SLIM_MF', 'SLIM_BP', 'SLIM_CC', 'PROTEIN',
'PANTHER_PATHWAY', 'REACTOME_PATHWAY'
]
from sequana.rnadiff import RNADiffResults
self.rnadiff = RNADiffResults(folder, pattern=pattern)
logger.info(
"Ignoring pvalue adjusted > {} and fold change in [{}, {}]".format(
padj_threshold, 1 / (2**log2_fc_threshold),
2**log2_fc_threshold))
fc_threshold = log2_fc_threshold
self.mygenes = self.rnadiff.df.query(
"padj<=@padj_threshold and (log2FoldChange<=-@fc_threshold or log2FoldChange>=@fc_threshold)"
)
self.mygenes_down = self.rnadiff.df.query(
"padj<=@padj_threshold and log2FoldChange<=-@fc_threshold")
self.mygenes_up = self.rnadiff.df.query(
"padj<=@padj_threshold and log2FoldChange>=@fc_threshold")
self.mygenes = list(self.mygenes.sort_values('padj').index)
self.mygenes_down = list(self.mygenes_down.sort_values('padj').index)
self.mygenes_up = list(self.mygenes_up.sort_values('padj').index)
# When using ENSEMBL, prefix "gene:" should be removed to be understood
# by PantherDB
self.mygenes = [x.replace("gene:", "") for x in self.mygenes]
self.mygenes_down = [x.replace("gene:", "") for x in self.mygenes_down]
self.mygenes_up = [x.replace("gene:", "") for x in self.mygenes_up]
logger.info("Kept {} genes ({} up; {} down)".format(
len(self.mygenes), len(self.mygenes_down), len(self.mygenes_up)))