def addFamilies(self, eventsfile, discard=[]):
if not tableExists(self.cur, "Families"):
self.makeFamiliesTable()
util.tic("add families")
events_tab = tablelib.read_table(eventsfile)
events_lookup = events_tab.lookup("partid")
familyGeneNames = self.makeFamilyGeneNames()
discard = set(discard)
for row in events_tab:
famid = row["partid"]
if famid in discard:
util.logger("discarding '%s'" % famid)
continue
tree = treelib.read_tree(self.getTreeFile(famid))
treelen = sum(x.dist for x in tree)
seqs = fasta.read_fasta(self.getFastaFile(famid))
seqlen = stats.median(map(len, seqs.values()))
self.cur.execute(
"""INSERT INTO Families VALUES
("%s", "%s", %f, %f, %f, %d, %d, %d,
"%s");""" %
(row["partid"], familyGeneNames.get(row["partid"],
("", ""))[0],
row["famrate"], treelen, seqlen * 3, row["dup"], row["loss"],
row["genes"], familyGeneNames.get(row["partid"],
("", ""))[1]))
util.toc()
def addFamilies(self, eventsfile, discard=[]):
if not tableExists(self.cur, "Families"):
self.makeFamiliesTable()
util.tic("add families")
events_tab = tablelib.read_table(eventsfile)
events_lookup = events_tab.lookup("partid")
familyGeneNames = self.makeFamilyGeneNames()
discard = set(discard)
for row in events_tab:
famid = row["partid"]
if famid in discard:
util.logger("discarding '%s'" % famid)
continue
tree = treelib.read_tree(self.getTreeFile(famid))
treelen = sum(x.dist for x in tree)
seqs = fasta.read_fasta(self.getFastaFile(famid))
seqlen = stats.median(map(len, seqs.values()))
self.cur.execute(
"""INSERT INTO Families VALUES
("%s", "%s", %f, %f, %f, %d, %d, %d,
"%s");""" %
(row["partid"],
familyGeneNames.get(row["partid"], ("", ""))[0],
row["famrate"], treelen, seqlen * 3,
row["dup"], row["loss"], row["genes"],
familyGeneNames.get(row["partid"], ("", ""))[1]))
util.toc()
def layout_frags(self, genome_name, chrom_name, start, end, direction=1):
ref_chrom = self.chroms_lookup[(genome_name, chrom_name)]
# setup genome display order
order = {}
for i, genome in enumerate(self.genomes):
order[genome] = i
# swap the genome with order 0 and the reference genome
j = order[self.ref_genome]
order[self.genomes[0]] = j
order[self.ref_genome] = 0
# init reference fragment
ref_frag = Frag(genome=genome_name,
chrom=chrom_name,
start=max(start, 0),
end=min(end, ref_chrom.end),
strand=direction,
x=max(start,0),
y=0)
self.frags.add(ref_frag)
self.layout_frag_contents(ref_frag)
# find all synteny blocks in this region
# sort blocks by appearance in ref_chrom
blocks = list(self.filter_blocks(self.blocks, ref_chrom, start, end))
def blocksort(a):
if a[1] == 0:
starta = a[0].region1.start
else:
starta = a[0].region2.start
blocks.sort(key=blocksort)
# make lookup for genes to block and block to fragment
block_lookup = {}
frag_lookup = {}
for block, flip in blocks:
if flip == 0:
other = block.region2
else:
other = block.region1
frag = Frag()
frag.genome = other.species
frag.chrom = other.seqname
frag_lookup[block] = frag
for gene2 in iter_chrom(self.db.get_regions(frag.genome,
frag.chrom),
other.start, other.end):
block_lookup[gene2] = block
self.block_lookup = block_lookup
# find all genes that will be drawn
# walk along ref_chrom and store drawn genes into fragments
refLookup = {}
for gene in iter_chrom(self.db.get_regions(genome_name, chrom_name),
start, end):
for name2 in self.orth_lookup.get(gene.data["ID"], []):
gene2 = self.db.get_region(name2)
if gene2 in block_lookup:
frag_lookup[block_lookup[gene2]].genes.append(gene2)
refLookup[gene2] = gene
self.refLookup = refLookup
# determine fragment dimensions
for frag in frag_lookup.itervalues():
if len(frag.genes) == 0:
frag.x = None
continue
frag.genes.sort(key=lambda a: a.start)
# set fragment start and end
frag.start = frag.genes[0].start
frag.end = frag.genes[-1].end
# find fragment direction
vote = 0
last = None
for gene2 in frag.genes:
pos = refLookup[gene2].start
if last != None and pos != last:
if last < pos:
vote += 1
else:
vote -= 1
last = pos
if vote > 0:
frag.direction = direction
else:
frag.direction = -direction
# find fragment x-coordinate
diffs = []
for gene2 in frag.genes:
if direction == 1:
offset1 = refLookup[gene2].start - ref_frag.start
else:
offset1 = ref_frag.end - refLookup[gene2].end
if frag.direction == 1:
offset2 = gene2.start - frag.start
else:
offset2 = frag.end - gene2.end
diffs.append(offset2 - offset1)
frag.x = ref_frag.x - stats.median(diffs)
# place blocks
fragY = util.Dict(default=-self.genome_sep)
for block, flip in blocks:
frag = frag_lookup[block]
otherGenome = frag.genome
if frag.x == None:
# fragment could not be placed
continue
frag.y = fragY[otherGenome] - \
((order[otherGenome] - 1) *
self.max_genome_sep)
# re-get all genes between those coordinates
#frag.genes = list(iter_chrom(self.db.get_regions(frag.genome,
# frag.chrom),
# frag.start, frag.end))
# store and lyaout frag
self.frags.add(frag)
self.layout_frag_contents(frag)
# stagger fragments
fragY[otherGenome] -= self.frag_sep
if fragY[otherGenome] < -self.max_genome_sep:
fragY[otherGenome] = -self.genome_sep
def layout_frags(self, genome_name, chrom_name, start, end, direction=1):
ref_chrom = self.chroms_lookup[(genome_name, chrom_name)]
# setup genome display order
order = {}
for i, genome in enumerate(self.genomes):
order[genome] = i
# swap the genome with order 0 and the reference genome
j = order[self.ref_genome]
order[self.genomes[0]] = j
order[self.ref_genome] = 0
# init reference fragment
ref_frag = Frag(genome=genome_name,
chrom=chrom_name,
start=max(start, 0),
end=min(end, ref_chrom.end),
strand=direction,
x=max(start, 0),
y=0)
self.frags.add(ref_frag)
self.layout_frag_contents(ref_frag)
# find all synteny blocks in this region
# sort blocks by appearance in ref_chrom
blocks = list(self.filter_blocks(self.blocks, ref_chrom, start, end))
def blocksort(a):
if a[1] == 0:
starta = a[0].region1.start
else:
starta = a[0].region2.start
blocks.sort(key=blocksort)
# make lookup for genes to block and block to fragment
block_lookup = {}
frag_lookup = {}
for block, flip in blocks:
if flip == 0:
other = block.region2
else:
other = block.region1
frag = Frag()
frag.genome = other.species
frag.chrom = other.seqname
frag_lookup[block] = frag
for gene2 in iter_chrom(
self.db.get_regions(frag.genome, frag.chrom), other.start,
other.end):
block_lookup[gene2] = block
self.block_lookup = block_lookup
# find all genes that will be drawn
# walk along ref_chrom and store drawn genes into fragments
refLookup = {}
for gene in iter_chrom(self.db.get_regions(genome_name, chrom_name),
start, end):
for name2 in self.orth_lookup.get(gene.data["ID"], []):
gene2 = self.db.get_region(name2)
if gene2 in block_lookup:
frag_lookup[block_lookup[gene2]].genes.append(gene2)
refLookup[gene2] = gene
self.refLookup = refLookup
# determine fragment dimensions
for frag in frag_lookup.itervalues():
if len(frag.genes) == 0:
frag.x = None
continue
frag.genes.sort(key=lambda a: a.start)
# set fragment start and end
frag.start = frag.genes[0].start
frag.end = frag.genes[-1].end
# find fragment direction
vote = 0
last = None
for gene2 in frag.genes:
pos = refLookup[gene2].start
if last != None and pos != last:
if last < pos:
vote += 1
else:
vote -= 1
last = pos
if vote > 0:
frag.direction = direction
else:
frag.direction = -direction
# find fragment x-coordinate
diffs = []
for gene2 in frag.genes:
if direction == 1:
offset1 = refLookup[gene2].start - ref_frag.start
else:
offset1 = ref_frag.end - refLookup[gene2].end
if frag.direction == 1:
offset2 = gene2.start - frag.start
else:
offset2 = frag.end - gene2.end
diffs.append(offset2 - offset1)
frag.x = ref_frag.x - stats.median(diffs)
# place blocks
fragY = util.Dict(default=-self.genome_sep)
for block, flip in blocks:
frag = frag_lookup[block]
otherGenome = frag.genome
if frag.x == None:
# fragment could not be placed
continue
frag.y = fragY[otherGenome] - \
((order[otherGenome] - 1) *
self.max_genome_sep)
# re-get all genes between those coordinates
#frag.genes = list(iter_chrom(self.db.get_regions(frag.genome,
# frag.chrom),
# frag.start, frag.end))
# store and lyaout frag
self.frags.add(frag)
self.layout_frag_contents(frag)
# stagger fragments
fragY[otherGenome] -= self.frag_sep
if fragY[otherGenome] < -self.max_genome_sep:
fragY[otherGenome] = -self.genome_sep