cn.sort()
mers = "%d-mers" % options.k
print '#', total, 'total', mers
print '#', distinct, 'distinct', mers
table = SimpleTable(
['CopyNumber', 'Count', 'BasePct', 'BaseTotal', 'KmerPct', 'KmerTotal'],
[], 'Kmer Copy Number (k=' + str(options.k) + ')')
btotal = 0.0
ktotal = 0.0
for n in cn:
c = by_count[n]
bpct = n * c * 100.0 / total
btotal += bpct
kpct = c * 100.0 / distinct
ktotal += kpct
table.add_row([
n, c,
"%.2f%%" % bpct,
"%.2f%%" % btotal,
"%.2f%%" % kpct,
"%.2f%%" % ktotal
])
if options.o:
table.print_output(options.o + ".kmer_copy_number", options.html)
else:
print table.to_table()
def __write_output_data(agp_file=None,
flank_kmer=None,
asm_kmer=None,
contig_seqs=None,
asm_counts=None,
cg_ss_counts=None,
ue_ss_counts=None):
#captured gap stats
cg_seqs = []
cg_sizes = []
cg_dist = []
cg_cn = []
cg_gc = []
#uncaptured end stats
ue_seqs = []
ue_dist = []
ue_cn = []
ue_gc = []
print "Pulling gap end sequence..."
agp = AgpFile(agp_file)
scaffolds = agp.get_agp_scaffolds()
for scaffold in scaffolds:
print "Scaffold:", scaffold
for record in agp.get_agp_file_record(scaffold):
if (not agp.is_gap(scaffold, record)):
ctg_seq = contig_seqs[agp.get_contig_id(scaffold, record)]
if (len(ctg_seq) < options.e):
print "WARNING:", agp.get_contig_id(
scaffold,
record), " is less than ", options.e, ". Ignoring."
continue
if (record == 1):
#print "\tFirst contig..."
#print "SEQ: ", contig_seqs[agp.get_contig_id(scaffold,record)][:options.e]
(gc, dist, copy) = analyze_seq(
contig_seqs[agp.get_contig_id(scaffold,
record)][:options.e],
flank_kmer, asm_kmer, asm_counts)
ue_dist.append(dist)
ue_cn.append(copy)
ue_gc.append(gc)
ue_ss_counts = get_simple_sequences(
ue_ss_counts,
contig_seqs[agp.get_contig_id(scaffold,
record)][:options.e])
#print "UE", ue_ss_counts
if (record == len(agp.get_agp_file_record(scaffold))):
#print "\tLast contig..."
#print "SEQ: ", contig_seqs[agp.get_contig_id(scaffold,record)][-options.e:]
(gc, dist, copy) = analyze_seq(
contig_seqs[agp.get_contig_id(scaffold,
record)][-options.e:],
flank_kmer, asm_kmer, asm_counts)
ue_dist.append(dist)
ue_cn.append(copy)
ue_gc.append(gc)
ue_ss_counts = get_simple_sequences(
ue_ss_counts,
contig_seqs[agp.get_contig_id(scaffold,
record)][-options.e:])
#print "UE", ue_ss_counts
if (agp.is_gap(scaffold, record)):
#print "Gap..."
left_ctg_record = record - 1
right_ctg_record = record + 1
if (len(contig_seqs[agp.get_contig_id(
scaffold, left_ctg_record)]) < options.e) or (len(
contig_seqs[agp.get_contig_id(
scaffold, right_ctg_record)]) < options.e):
print "Warning: This gap is flanked by a contig less than", options.e, "long. Skipping analysis."
continue
left_seq = contig_seqs[agp.get_contig_id(
scaffold, left_ctg_record)][-options.e:]
#left_seq = contig_seqs[agp.get_contig_id(scaffold,left_ctg_record)][:options.e]
#print "LEFT: ", left_seq
(left_gc, left_dist,
left_copy) = analyze_seq(left_seq, flank_kmer, asm_kmer,
asm_counts)
cg_ss_counts = get_simple_sequences(cg_ss_counts, left_seq)
#print "CG", cg_ss_counts
#print left_seq
#print left_gc,left_dist,left_copy
right_seq = contig_seqs[agp.get_contig_id(
scaffold, right_ctg_record)][:options.e]
#right_seq = contig_seqs[agp.get_contig_id(scaffold,right_ctg_record)][-options.e:]
#print "RIGHT SEQ: ", right_seq
(right_gc, right_dist,
right_copy) = analyze_seq(right_seq, flank_kmer, asm_kmer,
asm_counts)
cg_ss_counts = get_simple_sequences(cg_ss_counts, right_seq)
#print "CG", cg_ss_counts
#print right_gc,right_dist,right_copy
cg_sizes.append(agp.get_feature_length(scaffold, record))
cg_dist.append((left_dist + right_dist) / 2)
cg_gc.append((left_gc + right_gc) / 2)
cg_cn.append((left_copy + right_copy) / 2)
headers = ["Metric", "Uncaptured Ends", "Captured Gaps"]
table = SimpleTable(headers, [], "Gap Analysis Metrics")
ss_table = SimpleTable([
"Sequence", "Uncaptured Ends Bases", "Uncaptured Ends Percent",
"Captured Gap Bases", "Captured Gap Percent"
], [], "Gap Simple Sequence Analysis")
if (len(cg_sizes) > 0):
chart_tools.gen_histogram(cg_sizes, "Gap Sizes", "Number of Gaps",
"Histogram of Captured Gap Sizes",
options.header + ".cg_sizes")
chart_tools.gen_histogram(cg_dist, "Gap Flank Complexity",
"Number of Gaps",
"Histogram of Gap Flank Complexity",
options.header + ".cg_distinctness")
chart_tools.gen_histogram(cg_cn, "Gap Flank Copy Number",
"Number of Gaps",
"Histogram of Gap Flank Copy Number",
options.header + ".cg_copy_number")
chart_tools.gen_histogram(cg_gc, "Gap Flank GC", "Number of Gaps",
"Histogram of Gap Flank GC",
options.header + ".cg_gc")
table.add_row(["Number", len(ue_dist), len(cg_dist)])
table.add_row([
"Average Complexity",
"%.0f" % (sum(ue_dist) / len(ue_dist)),
"%.0f" % (sum(cg_dist) / len(cg_dist))
])
table.add_row([
"Less than " + str(options.l) + "% Complex",
len(filter(lambda x: x < options.l, ue_dist)),
len(filter(lambda x: x < options.l, cg_dist))
])
table.add_row([
"Average GC",
"%.0f" % (sum(ue_gc) / len(ue_gc)),
"%.0f" % (sum(cg_gc) / len(cg_gc))
])
table.add_row([
"Less than 30% GC",
len(filter(lambda x: x < 30, ue_gc)),
len(filter(lambda x: x < 30, cg_gc))
])
table.add_row([
"Greater than 70% GC",
len(filter(lambda x: x > 70, ue_gc)),
len(filter(lambda x: x > 70, cg_gc))
])
table.add_row([
"Average Copy Number",
"%.0f" % (sum(ue_cn) / len(ue_cn)),
"%.0f" % (sum(cg_cn) / len(cg_cn))
])
ss_table.add_row([
"End Bases",
len(ue_dist) * options.e, "",
len(cg_dist) * options.e, ""
])
ss_table.add_row([
"Total SS",
sum(ue_ss_counts.itervalues()),
"%.2f%%" % (float(sum(ue_ss_counts.itervalues()) * 100) /
(len(ue_dist) * options.e)),
sum(cg_ss_counts.itervalues()),
"%.2f%%" % (float(sum(cg_ss_counts.itervalues()) * 100) /
(len(cg_dist) * options.e))
])
for n in cg_ss_counts:
ss_table.add_row([
n, ue_ss_counts[n],
"%.2f%%" % (float(ue_ss_counts[n] * 100) /
(len(ue_dist) * options.e)), cg_ss_counts[n],
"%.2f%%" % (float(cg_ss_counts[n] * 100) /
(len(cg_dist) * options.e))
])
else:
print "No captured gaps."
table.add_row(["Number", len(ue_dist), len(cg_dist)])
table.add_row([
"Average Uniqueness",
"%.0f" % (sum(ue_dist) / len(ue_dist)), "N/A"
])
table.add_row([
"Less than " + str(options.l) + "% distinct",
"%.2f" % (len(filter(lambda x: x < options.l, ue_dist))),
"%.2f" % (len(filter(lambda x: x < options.l, cg_dist)))
])
table.add_row(
["Average GC",
"%.0f" % (sum(ue_gc) / len(ue_gc)), "N/A"])
table.add_row([
"Less than 30% GC",
len(filter(lambda x: x < 30, ue_gc)),
len(filter(lambda x: x < 30, cg_gc))
])
table.add_row([
"Greater than 70% GC",
len(filter(lambda x: x > 70, ue_gc)),
len(filter(lambda x: x > 70, cg_gc))
])
table.add_row(
["Average Copy Number",
"%.0f" % (sum(ue_cn) / len(ue_cn)), "N/A"])
ss_table.add_row(["End Bases", len(ue_dist) * options.e, "", "NA", ""])
ss_table.add_row([
"Total SS",
sum(ue_ss_counts.itervalues()),
"%.2f%%" % (float(sum(ue_ss_counts.itervalues()) * 100) /
(len(ue_dist) * options.e)), "NA", "NA"
])
for n in cg_ss_counts:
ss_table.add_row([
n, ue_ss_counts[n],
"%.2f%%" % (float(ue_ss_counts[n] * 100) /
(len(ue_dist) * options.e)), "NA", "NA"
])
chart_tools.gen_histogram(ue_dist, "End Distinctness",
"Number of Uncaptured Ends",
"Histogram of End Complexity",
options.header + ".ue_distinctness")
chart_tools.gen_histogram(ue_cn, "End Copy Number",
"Number of Uncaptured Ends",
"Histogram of End Copy Number",
options.header + ".ue_copy_number")
chart_tools.gen_histogram(ue_gc, "End GC", "Number of Uncaptured Ends",
"Histogram of End GC", options.header + ".ue_gc")
table.print_output(options.t_header + ".gap_analysis", options.html)
ss_table.print_output(options.t_header + ".gap_ss_analysis", options.html)