from ete3 import PhylomeDBConnector
# This connects to the main phylomeDB server (default parameters)
p = PhylomeDBConnector()
# Obtains the phylomeDB internal ID for my gene of interest
idmatches = p.search_id("ENSG00000146556")
# Take the only match (several would be possible)
geneid = idmatches[0]
# Gets the 'geneid' tree in phylome 1 reconstructed using WAG evolutionary model
t, likelihood = p.get_tree(geneid, "WAG", 1)
print t
#
# /-Xtr0044988
# |
# | /-Gga0000980
# | |
# /---| | /-Bta0018700
# | | | |
# | | | | /-Hsa0000001
# | | | | /---|
# | | | /---| /---| \-Hsa0010733
# | \---| | | | |
# | | | | /---| \-Hsa0010710
# | | | | | |
# | | /---| \---| \-Ptr0000001
# /---| | | | |
# | | | | | \-Cfa0016699
# | | | | |
# | | \---| | /-Rno0030248
# | | | \---|
# | | | \-Mms0024821
# /---| | |
from ete3 import PhylomeDBConnector
# This connects to the main phylomeDB server (default parameters)
p = PhylomeDBConnector()
# Obtains the phylomeDB internal ID for my gene of interest
idmatches = p.search_id("ENSG00000146556")
# Take the only match (several would be possible)
geneid = idmatches[0]
# Gets the 'geneid' tree in phylome 1 reconstructed using WAG evolutionary model
t, likelihood = p.get_tree(geneid, "WAG", 1)
print t
#
# /-Xtr0044988
# |
# | /-Gga0000980
# | |
# /---| | /-Bta0018700
# | | | |
# | | | | /-Hsa0000001
# | | | | /---|
# | | | /---| /---| \-Hsa0010733
# | \---| | | | |
# | | | | /---| \-Hsa0010710
# | | | | | |
# | | /---| \---| \-Ptr0000001
# /---| | | | |
# | | | | | \-Cfa0016699
# | | | | |
# | | \---| | /-Rno0030248
# | | | \---|
# | | | \-Mms0024821
# /---| | |
from ete3 import PhylomeDBConnector
# This connects to the main phylomeDB server (default parameters)
p = PhylomeDBConnector()
PHYLOME_ID = 1
# This is the species code/age dictionary used to correctly root the
# tree in the human phylome. You can define your own, or use the
# midpoint outgroup method
species2age = {'Aga': 8, 'Ago': 9, 'Ame': 8, 'Ath': 10, 'Bta': 3, 'Cal': 9, 'Cbr': 8,\
'Cel': 8, 'Cfa': 3, 'Cgl': 9, 'Cin': 7, 'Cne': 9, 'Cre': 10, 'Ddi': 10, \
'Dha': 9, 'Dme': 8, 'Dre': 6, 'Ecu': 9, 'Fru': 6, 'Gga': 4, 'Gth': 10,\
'Gze': 9, 'Hsa': 1, 'Kla': 9, 'Lma': 10, 'Mdo': 3, 'Mms': 3, 'Mmu': 2,\
'Ncr': 9, 'Pfa': 10, 'Pte': 10, 'Ptr': 2, 'Pyo': 10, 'Rno': 3, 'Sce': 9,\
'Spb': 9, 'Tni': 6, 'Xtr': 5, 'Yli': 9 }
# Iterator over each sequence in the human proteme
for i, seqid in enumerate(p.get_seed_ids(PHYLOME_ID)):
if i>2: break # Just process the first 2 ids
winner_model, lks, t = p.get_best_tree(seqid, PHYLOME_ID)
# If tree was sucsesfully reconstructed, runs the species overalp algorithm
if t and seqid in t:
outgroup = t.get_farthest_oldest_leaf(species2age)
# Returned outgroup is used to root the tree
t.set_outgroup(outgroup)
# Finds the node representing the seed sequence.
# We want the orthology relationships of such sequence.
seed_node = t.search_nodes(name=seqid)[0]
evol_events = seed_node.get_my_evol_events()
for ev in evol_events:
# Speciation event
if ev.etype == "S":
inparalogs = filter(lambda n: n.startswith("Hsa"), ev.in_seqs)
print 'ORTHOLOGY RELATIONSHIP:', ','.join(inparalogs), "<===>", ','.join(ev.out_seqs)
from ete3 import PhyloTree, PhylomeDBConnector, SeqGroup
p = PhylomeDBConnector()
w,x, t = p.get_best_tree("Hsa0000001", 1)
a, l = p.get_clean_alg("Hsa0000001", 1)
A = SeqGroup(a, "iphylip")
for s in A.id2seq:
A.id2seq[s]=A.id2seq[s][:30]
t.link_to_alignment(A)
print t.get_species()
print t
t.set_outgroup(t&"Ddi0002240")
sp = PhyloTree("(((((((((((Hsa, Ptr), Mmu), ((Mms, Rno), (Bta, Cfa))), Mdo), Gga), Xtr), (Dre, Fru))),Cin) (Dme, Aga)), Ddi);")
reconciled, evs = t.reconcile(sp)
print reconciled
reconciled.show()
from ete3 import PhylomeDBConnector
# This connects to the main phylomeDB server (default parameters)
p = PhylomeDBConnector()
# This connects to a local version of phylomeDB, and you can set the
# user and password arguments
p = PhylomeDBConnector(host="localhost",
user="******",
passwd="public",
port=3306)
from ete3 import PhyloTree, PhylomeDBConnector, SeqGroup
p = PhylomeDBConnector()
w, x, t = p.get_best_tree("Hsa0000001", 1)
a, l = p.get_clean_alg("Hsa0000001", 1)
A = SeqGroup(a, "iphylip")
for s in A.id2seq:
A.id2seq[s] = A.id2seq[s][:30]
t.link_to_alignment(A)
print t.get_species()
print t
t.set_outgroup(t & "Ddi0002240")
sp = PhyloTree(
"(((((((((((Hsa, Ptr), Mmu), ((Mms, Rno), (Bta, Cfa))), Mdo), Gga), Xtr), (Dre, Fru))),Cin) (Dme, Aga)), Ddi);"
)
reconciled, evs = t.reconcile(sp)
print reconciled
reconciled.show()
from ete3 import PhylomeDBConnector
# This connects to the main phylomeDB server (default parameters)
p = PhylomeDBConnector()
# Obtains a list of available phylomes
phylomes_list = p.get_phylomes()
# Obtains the list of proteomes used in phylome 1 (the human phylome)
phylomes_list = p.get_proteomes_in_phylome(1)
# all seeds (potentially, trees) in the human phylome
all_seed_sequences = p.get_seed_ids(1)
# Gets species info from associated to the "Hsa" code
print p.get_species_info("Hsa")
# {'code': 'Hsa', 'taxid': 9606L, 'name': 'Homo_sapiens'}
#
# You can also use the same method to find the species code given a ncbi taxid
print p.get_species_info(9606)
# {'code': 'Hsa', 'taxid': 9606L, 'name': 'Homo_sapiens'}
#
# Get phylomeDB IDs matching a given Ensembl protein ID. Always
# returns the code of the longest isoform.
idmatches = p.search_id("ENSG00000146556")
# You can also use the search_id method to find the longest isoform of
# the gene associated to a given phylomeID. Note that phylomeDB trees
# are always reconstructed using the longest isoform associated to a
# gene.
#
print p.search_id("Hsa0000125")
# ['Hsa0000122']
