def sam2graph(sam):
""" Convert a BAM / SAM file into a alignement set dictionary"""
refDict = {}
G = {}
with pysam.AlignmentFile(sam) as samfile:
for read in samfile.fetch():
# Read and Reference data
target = Read(read.query_name)
target.sequence = read.query_sequence
refName = read.reference_name
if(refName not in refDict):
reference = Read(refName)
reference.sequence = fastaDict[refName]
refDict[refName] = reference
G[refName] = set()
else:
reference = refDict[refName]
# Alignment data
s1 = read.query_alignment_start
e1 = read.query_alignment_end
s2 = read.reference_start
e2 = read.reference_end
cigar = read.cigarstring
relPos = "-" if read.is_reverse else "+"
align = Align(target, reference, s1, e1, s2, e2, cigar, relPos)
G[refName].add(align)
return(G)
def sam2graph(sam, fasta):
""" Convert a BAM / SAM file into a alignement set dictionary"""
refDict = {}
targetDict = {}
G = {}
with pysam.AlignmentFile(sam) as samfile:
for read in samfile.fetch():
if(not read.flag & 4 ):
# Fetching read and reference names
targetName = read.query_name
refName = read.reference_name
# Checking existence and creating / fetching objects
if(targetName not in targetDict):
target = Read(read.query_name)
targetDict[targetName] = target
else:
target = targetDict[targetName]
# Since one read can be mapped on multiple transcripts,
# sequences are only stored on "prefered" mapping.
# Need to account for this when filling target objects
if(read.query_sequence):
target.sequence = read.query_sequence
if(refName not in refDict):
reference = Read(refName)
try:
refGene = fasta.genes[fasta.transcriptMap[refName]]
except KeyError:
print(refName)
exit()
reference.sequence = refGene.transcripts[refName]
refDict[refName] = reference
G[refName] = set()
else:
reference = refDict[refName]
# Alignment data
s1 = read.query_alignment_start
e1 = read.query_alignment_end
s2 = read.reference_start
e2 = read.reference_end
cigar = read.cigarstring
relPos = "-" if read.is_reverse else "+"
align = Align(target, reference, s1, e1, s2, e2, cigar, relPos)
G[refName].add(align)
return(G)
def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
command = lines[0]
lines = lines[1:]
counter = Counter(lines)
if command == 'reads':
frags = [Read(r, i) for r, c in counter.items() for i in range(c)]
elif command == 'read-pairs':
frags = [ReadPair(Kdmer(r.split('|')[0], r.split('|')[2], int(r.split('|')[1])), i) for r, c in counter.items() for i in range(c)]
else:
raise
graph = to_overlap_graph(frags)
print(f'Given the fragments {lines}, the overlap graph is...', end="\n\n")
print(f'```{{dot}}\n{to_graphviz(graph)}\n```\n\n')
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
frag_to_count = [l.split() for l in lines]
print(f'Sequenced fragments:', end='\n\n')
for f in frag_to_count:
print(f' * {f[0]} was scanned in {f[1]} times.')
raw_reads = [read for e in frag_to_count for read in [Read(e[0])] * int(e[1])]
occurrence_probabilities = calculate_fragment_occurrence_probabilities(raw_reads)
print(f'', end='\n\n')
print(f'Probability of occurrence in genome:', end='\n\n')
for read, appearances in occurrence_probabilities.items():
print(f' * {read} probably has {appearances} appearances in the genome.')
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
command = lines[0]
lines = lines[1:]
counter = Counter(lines)
if command == 'reads':
frags = [Read(r, i) for r, c in counter.items() for i in range(c)]
elif command == 'read-pairs':
frags = [ReadPair(Kdmer(r.split('|')[0], r.split('|')[2], int(r.split('|')[1])), i) for r, c in counter.items() for i in range(c)]
else:
raise
graph = to_debruijn_graph(frags)
print(f'Given the fragments {lines}, the de Bruijn graph is...', end="\n\n")
print(f'```{{dot}}\n{to_graphviz(graph)}\n```\n\n')
print(f'... and a Eulerian cycle is ...', end="\n\n")
path = walk_eulerian_cycle(graph, frags[0].prefix())
print(f'{" -> ".join([str(p) for p in path])}')
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
def append_overlap(self: ReadPair, other: ReadPair, skip: int = 1) -> ReadPair:
self_head = Read(self.data.head)
other_head = Read(other.data.head)
new_head = self_head.append_overlap(other_head)
new_head = new_head.data
self_tail = Read(self.data.tail)
other_tail = Read(other.data.tail)
new_tail = self_tail.append_overlap(other_tail)
new_tail = new_tail.data
# WARNING: new_d may go negative -- In the event of a negative d, it means that rather than there being a gap
# in between the head and tail, there's an OVERLAP in between the head and tail. To get rid of the overlap, you
# need to remove either the last d chars from head or first d chars from tail.
new_d = self.d - skip
kdmer = Kdmer(new_head, new_tail, new_d)
return ReadPair(kdmer, source=('overlap', [self, other]))
def create_string(self, min_size, max_size, min_distance, max_distance,
error, overlap_chance):
index = 0
while index < self.size:
read_size = random.randint(min_size, max_size)
if random.random() < 0.5:
data = self.H1[index:index + read_size]
else:
data = self.H2[index:index + read_size]
if len(data) > 0:
read = Read(index, data, error) # error will be 0 for now
self.reads.append(read)
if random.random() > overlap_chance:
index += min(random.randint(min_distance, max_distance),
read_size - 1)
def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
command = lines[0]
lines = lines[1:]
counter = Counter(lines)
if command == 'reads':
frags = [Read(r, i) for r, c in counter.items() for i in range(c)]
elif command == 'read-pairs':
frags = [
ReadPair(
Kdmer(
r.split('|')[0],
r.split('|')[2], int(r.split('|')[1])), i)
for r, c in counter.items() for i in range(c)
]
else:
raise
graph = to_overlap_graph(frags)
print(f'Given the fragments {lines}, the overlap graph is...',
end="\n\n")
print(f'```{{dot}}\n{to_graphviz(graph)}\n```', end="\n\n")
print(f'... and the Hamiltonian paths are ...', end="\n\n")
all_paths = set([
tuple(path) for node in graph.get_nodes()
for path in walk_hamiltonian_paths(graph, node)
])
for path in all_paths:
print(f' * {" -> ".join([str(p) for p in path])}')
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
def bamToHap(fasta, bim, bam, quality_threshold=14):
logger_bamToHap = logging.getLogger('bamToHap')
logger_bamToHap.info(
'bamToHap(fasta={}, bim={}, bam={}, quality_threshold={})'.format(
fasta, bim, bam, quality_threshold))
for x in bam:
r = Read(x, fasta)
try:
read_bim_l, read_bim_r, read_error_rate, read_hap_str = process_read(
r, bim, quality_threshold)
except KeyError as e:
logger_bamToHap.WARNING('{} KeyError {}'.format(r.query_name, e))
except Exception as e:
logger_bamToHap.WARNING('{} {} {}'.format(r.query_name, type(e),
e))
else:
# name, chr, start, end, MAPQ, bim_l, bim_r, hapstr
read_output = (r.reference_name, r.l.get_pos(), r.r.get_pos(),
r.query_name, r.mapping_quality, read_error_rate,
read_bim_l, read_bim_r, read_hap_str)
print('\t'.join([str(x) for x in read_output]))
def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
command = lines[0]
lines = lines[1:]
counter = Counter(lines)
if command == 'reads':
frags = [Read(r, i) for r, c in counter.items() for i in range(c)]
elif command == 'read-pairs':
frags = [
ReadPair(
Kdmer(
r.split('|')[0],
r.split('|')[2], int(r.split('|')[1])), i)
for r, c in counter.items() for i in range(c)
]
else:
raise
graph = to_debruijn_graph(frags)
graph, head_nodes, tail_nodes = balance_graph(graph)
print(
f'Given the fragments {lines}, the artificially balanced de Bruijn graph is...',
end="\n\n")
print(f'```{{dot}}\n{to_graphviz(graph)}\n```\n\n')
print(
f'... with original head nodes at {head_nodes} and tail nodes at {tail_nodes}.'
)
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
from Read import Read
from ToDeBruijnGraph import to_debruijn_graph
from Utils import slide_window
with open('/home/user/Downloads/dataset_240257_6(1).txt',
mode='r',
encoding='utf-8') as f:
data = f.read()
lines = data.split('\n')
k = int(lines[0].strip())
dna = lines[1].strip()
reads = [Read(kmer) for kmer, _ in slide_window(dna, k)]
graph = to_debruijn_graph(reads)
for node, other_nodes in graph.get_all_outputs():
other_nodes = list(other_nodes)
if len(other_nodes) == 0:
continue
print(f'{node} -> {",".join([str(x) for x in other_nodes])}')
#!/usr/bin/env python
# -*- coding: utf8 -*-
from Read import Read
from Attendance import Attendance
from Email import Email
import sys
if len(sys.argv) > 1:
PASSED_ARG = sys.argv[1]
MODE = None
if PASSED_ARG == "--register":
MODE = 0
Read(MODE).start()
elif PASSED_ARG == "--read":
MODE = 1
Read(MODE).start()
elif PASSED_ARG == "--offline":
Attendance().markOfflineAttendance()
elif PASSED_ARG == "--email":
Email().send()
elif PASSED_ARG == "--help":
print open("manual.txt", "r").read()
else:
print "app: invalid option -- " + PASSED_ARG
print "Try python app.py --help for more information."
else:
print "Try python app.py --help for more information."
from random import shuffle
from Read import Read
from ToOverlapGraphHash import to_overlap_graph
from Utils import enumerate_patterns
segments = [Read(segment) for segment in enumerate_patterns(4, '01')]
print(f'{segments}')
graph = to_overlap_graph(segments)
graph_items_randomized = list(graph.get_all_outputs())
shuffle(graph_items_randomized)
for segment, other_segments in graph_items_randomized:
other_segments = list(other_segments)
print(f'{segment} -> {",".join([str(x) for x in other_segments])}')
def walk(path):
if len(path) == len(graph):
print(f'{path} -> {path[0].stitch(path)}')
return
n = path[-1]
for child_n in graph.get_outputs(n):
if child_n not in path:
path.append(child_n)
walk(path)
path.pop()
from typing import List
from Graph import Graph
from Read import Read
from WalkRandomEulerianCycle import walk_eulerian_cycle
graph = Graph()
graph.insert_edge(Read('00'), Read('00'))
graph.insert_edge(Read('00'), Read('01'))
graph.insert_edge(Read('01'), Read('10'))
graph.insert_edge(Read('01'), Read('11'))
graph.insert_edge(Read('10'), Read('00'))
graph.insert_edge(Read('10'), Read('01'))
graph.insert_edge(Read('11'), Read('10'))
graph.insert_edge(Read('11'), Read('11'))
def eularian_path_to_kmers(cycle_path: List[Read]) -> List[Read]:
out = []
for i in range(len(cycle_path) - 1):
kmer = cycle_path[i].data + cycle_path[i + 1].data[-1]
out.append(Read(kmer))
return out
def do_kmers_cycle(reads: List[Read]) -> bool:
for i in range(len(reads) - 1):
if reads[i].suffix() != reads[i + 1].prefix():
return False
if reads[-1].suffix() != reads[0].prefix():
return False
from Read import Read
from ToOverlapGraphHash import to_overlap_graph
with open('/home/user/Downloads/dataset_240256_10(1).txt', mode='r', encoding='utf-8') as f:
data = f.read()
lines = data.split('\n')
dnas = lines[:]
dnas = [l.strip() for l in dnas] # get rid of whitespace
dnas = [l for l in dnas if len(l) > 0] # get rid of empty lines
reads = [Read(kmer) for kmer in dnas]
overlaps = to_overlap_graph(reads)
for kmer, other_kmers in overlaps.get_all_outputs():
other_kmers = list(other_kmers)
if len(other_kmers) == 0:
continue
print(f'{kmer} -> {",".join([str(x) for x in other_kmers])}')
from Read import Read
from ToDeBruijnGraph import to_debruijn_graph
from Utils import enumerate_patterns
from WalkRandomEulerianCycle import walk_eulerian_cycle
with open('/home/user/Downloads/dataset_240261_11(1).txt',
mode='r',
encoding='utf-8') as f:
data = f.read()
lines = data.split('\n')
k = int(lines[0])
reads = [Read(s) for s in enumerate_patterns(k, '01')]
graph = to_debruijn_graph(reads)
path = walk_eulerian_cycle(graph, next(graph.get_nodes()))
k_universal_str = path[0].stitch(path)
print(k_universal_str)
from BalanceNearlyBalancedGraph import balance_graph
from Read import Read
from ToDeBruijnGraph import to_debruijn_graph
from WalkRandomEulerianCycle import walk_eulerian_cycle
with open('/home/user/Downloads/dataset_240261_7(1).txt',
mode='r',
encoding='utf-8') as f:
data = f.read()
lines = data.split('\n')
k = int(lines[0].strip())
kmers = lines[1:]
kmers = [l.strip() for l in kmers] # get rid of whitespace
kmers = [l for l in kmers if len(l) > 0] # get rid of empty lines
reads = [Read(kmer) for kmer in kmers]
graph = to_debruijn_graph(reads)
graph, roots, tails = balance_graph(graph)
path = walk_eulerian_cycle(graph, roots.pop())
path.pop(
) # last conn in cycle is artificial -- it was created from balancing so generating this path would be fast
genome = path[0].stitch(path)
print(f'{genome}')
def check_catch_bad_input(test, samline):
print Read(sam_line)
def eularian_path_to_kmers(cycle_path: List[Read]) -> List[Read]:
out = []
for i in range(len(cycle_path) - 1):
kmer = cycle_path[i].data + cycle_path[i + 1].data[-1]
out.append(Read(kmer))
return out
else:
continue_loop = False
exit(0)
while continue_loop:
menu_input = int(input("[1] Add new ToDo file and add your text"
"\n[2] Append to an existing file\n""[3] Read from an existing file\n"))
if menu_input == 1:
to_do = Add_to_dos()
to_do.add_file()
return_to_main()
elif menu_input == 2:
try:
append = Append()
append.append_file()
return_to_main()
except OSError as e:
print("Error!\nThe file was not found")
elif menu_input == 3:
try:
read = Read()
read.read_file()
except OSError as e:
print("Error!\nThe file was not found")
#except:
#print("Error \nAnother error occurred, please try again")
return_to_main()
else:
print("Error \nCould not find the menu choice in your input")
return_to_main()
reads_filepath = 'FinalChallengeReads.txt.xz'
with lzma.open(reads_filepath, mode='rt', encoding='utf-8') as f:
lines = f.read().splitlines()
lines = [l.strip() for l in lines] # get rid of whitespace
lines = [l for l in lines if len(l) > 0] # get rid of empty lines
lines_split = [tuple(l.split('|', maxsplit=2)) for l in lines]
kdmers = [Kdmer(k1, k2, 1000) for k1, k2 in lines_split]
rps = [ReadPair(kdmer) for kdmer in kdmers]
broken_rps = [broken_rp for rp in rps for broken_rp in rp.shatter(40)]
broken_rps = list(set(broken_rps))
graph = to_debruijn_graph(broken_rps)
contig_paths = find_maximal_non_branching_paths(graph)
contig_paths.sort(key=lambda x: len(x))
for path in contig_paths:
if len(path) >= path[0].d:
out = path[0].stitch(path)
print(f'{len(path)} kd-mers = {out}')
else:
heads = [Read(p.data.head) for p in path]
heads_out = heads[0].stitch(heads)
tails = [Read(p.data.tail) for p in path]
tails_out = tails[0].stitch(tails)
print(f'{len(heads)} k-mers = {heads_out}')
print(f'{len(tails)} k-mers = {tails_out}')
def create_read(self, dna_seq):
nucleotides = apply_errors(dna_seq)
qualities = create_qualities(self.read_length, self.avg_quality,
self.quality_min, self.quality_max)
return Read(nucleotides, qualities)
def setup():
"""Create fixtures"""
# Define chromosome sizes
Read.extract_chromosome_sizes([
"@HD\tVN:1.0\tSO:unsorted", "@SQ\tSN:chr1\tLN:300",
"@SQ\tSN:chr2\tLN:200", "@PG\tID:test\tVN:0.1"
])
Feature.process_set_chromosome_conversion(["1\tchr1", "2\tchr2"])
good_input["bed input counting all of the read"] = (
"all",
"[17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42]"
)
good_input["bed input counting start of the read"] = (
"start", "[17, 18, 19, 20, 21, 22, 23]")
good_input["bed input counting end of the read"] = (
"end", "[36, 37, 38, 39, 40, 41, 42]")
good_input["gff input counting all of the read"] = (
"all",
"[43, 42, 41, 40, 39, 38, 37, 36, 35, 34, 33, 32, 31, 30, 29, 28, 27, 26, 25, 24, 23, 22, 21, 20, 19, 18, 17, 16, 15, 14, 13, 12, 11, 10, 9, 8]"
)
good_input["gff input counting start of the read"] = (
"start", "[43, 42, 41, 40, 39, 38, 37]")
good_input["gff input counting end of the read"] = (
"end", "[14, 13, 12, 11, 10, 9, 8]")
for method in ['all', 'start', 'end']:
print "\nTesting feature_count option: ****{}****".format(method)
if method == 'all':
metagene = Metagene(10, 4, 2)
print "\t with Metagene:\t{}".format(metagene)
print "\t with chromosome conversions:\t{}".format(
Feature.chromosome_conversion)
else:
metagene = Metagene(1, 4, 2)
print "\t with Metagene:\t{}".format(metagene)
print "\t with chromosome conversions:\t{}".format(
Feature.chromosome_conversion)
# create feature from BED line
try:
bedline = "{}\t{}\t{}\t{}\t{}\t{}\n".format(
1, 20, 40, "first", 44, "+")
print "\t with BED line:\t{}".format(bedline.strip())
feature1 = Feature.create_from_bed(method, metagene, bedline,
False, False)
if str(feature1.position_array) != correct_features['bed'][method]:
print "**FAILED**\t Create Feature from BED line ?"
print "\t Desired positions:\t{}".format(
correct_features['bed'][method])
print "\t Created positions:\t{}".format(
feature1.position_array)
except MetageneError as err:
print "**FAILED**\t Create Feature from BED line ?"
else:
print "PASSED\t Create Feature from BED line ?\t\t{}".format(
feature1.get_chromosome_region())
# create feature from GFF line
try:
gffline = "{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n".format(
2, "test", "gene", 10, 39, ".", "-", ".", "second")
print "\t with GFF line:\t{}".format(gffline.strip())
feature2 = Feature.create_from_gff(method, metagene, gffline,
False, False)
if str(feature2.position_array) != correct_features['gff'][method]:
print "**FAILED**\t Create Feature from GFF line ?\t**FAIL**"
print "\t Desired positions:\t{}".format(
correct_features['gff'][method])
print "\t Created positions:\t{}".format(
feature2.position_array)
except MetageneError as err:
print "**FAILED**\t Create Feature from GFF line ?"
else:
print "PASSED\t Create Feature from GFF line ?\t\t{}".format(
feature2.get_chromosome_region())
# create feature from GFF line with start and end swapped
try:
gffline = "{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n".format(
2, "test", "gene", 39, 10, ".", "-", ".", "second")
print "\t with GFF line:\t{}".format(gffline.strip())
feature2 = Feature.create_from_gff(method, metagene, gffline,
False, False)
if str(feature2.position_array) != correct_features['gff'][method]:
print "**FAILED**\t Create Feature from GFF line with swapped start and end ?\t**FAIL**"
print "\t Desired positions:\t{}".format(
correct_features['gff'][method])
print "\t Created positions:\t{}".format(
feature2.position_array)
except MetageneError as err:
print "**FAILED**\t Create Feature from GFF line with swapped start and end ?"
else:
print "PASSED\t Create Feature from GFF line with swapped start and end ?\t\t{}".format(
feature2.get_chromosome_region())
try:
gffline = "{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n".format(
2, "test", "gene", 39, 10, ".", "+", ".", "second")
print "\t with GFF line:\t{}".format(gffline.strip())
feature2 = Feature.create_from_gff(method, metagene, gffline,
False, False)
if str(feature2.position_array) != correct_features['gff'][method]:
print "**FAILED**\t Do not create Feature from GFF line with swapped start and end, + strand ?\t**FAIL**"
print "\t Desired positions:\t{}".format(
correct_features['gff'][method])
print "\t Created positions:\t{}".format(
feature2.position_array)
except MetageneError as err:
print "PASSED\t Do not create Feature from GFF line with swapped start and end, + strand ?\t\t{}".format(
err)
else:
print "**FAILED**\t Do not create Feature from GFF line with swapped start and end, + strand ?\t\t{}".format(
feature2.get_chromosome_region())
##TODO finish complete testing of Feature class
print "\n##TODO finish testing of Feature class creation\n"
print "\n**** Testing counting and maniputlation ****\n"
expected = {'all': {}, 'start': {}, 'end': {}}
# Positions in metagene: 17 18 19 20 21-22,23-24,25-26,27-28,29-30,31-32,33-34,35-36,37-38,39-40, 41, 42
expected['all'] = {
'all':
"first,sense:allreads,0.333,0.333,0.000,0.000,0.000,0.000,0.000,0.000,0.286,0.571,0.571,0.000,0.000,0.286,0.286,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.100,0.100,0.100,0.100,0.100,0.000,0.000,0.000,0.000,0.000,0.111",
'start':
"first,sense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,2.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.500,0.000,0.000,0.000,0.000,0.000,0.000",
'end':
"first,sense:allreads,0.000,3.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,2.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.500,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,0.000,1.000"
}
# Positions in metagene: 17 18 19 20 [21] 22 23
expected['start'] = {
'all':
"first,sense:allreads,0.333,0.333,0.000,0.000,0.000,0.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.050",
'start':
"first,sense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.000",
'end':
"first,sense:allreads,0.000,3.000,0.000,0.000,0.000,0.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.500"
}
# Positions in metagene: 36 37 38 39 [40] 41 42
expected['end'] = {
'all':
"first,sense:allreads,0.000,0.000,0.000,0.000,0.286,0.286,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.111",
'start':
"first,sense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,0.000",
'end':
"first,sense:allreads,0.000,0.000,0.000,0.000,0.000,2.000,0.000\nfirst,antisense:allreads,0.000,0.000,0.000,0.000,0.000,0.000,1.000"
}
metagene = {
'all': Metagene(10, 4, 2),
'start': Metagene(1, 4, 2),
'end': Metagene(1, 4, 2)
}
for method in ['all', 'start', 'end']:
if method == 'all':
print "\t with Metagene:\t{}".format(metagene[method])
print "\t with chromosome conversions:\t{}".format(
Feature.chromosome_conversion)
else:
print "\t with Metagene:\t{}".format(metagene[method])
print "\t with chromosome conversions:\t{}".format(
Feature.chromosome_conversion)
print "\nTesting feature_count option: ****{}****".format(method)
feature_line = "{}\t{}\t{}\t{}\t{}\t{}\n".format(
1, 20, 40, "first", 44, "+")
feature1 = Feature.create_from_bed(method, metagene[method],
feature_line, False, False)
print "\tFeature:\t{}".format(feature1.position_array)
reads = []
reads.append(
Read("chr1", "+", 3, 1, [10, 11, 12, 13, 14, 15, 16, 17, 18]))
reads.append(
Read("chr1", "-", 1, 2, [23, 24, 25, 26, 27, 28, 29, 30, 31, 32]))
reads.append(Read("chr1", "+", 4, 2, [30, 31, 32, 33, 34, 40, 41]))
reads.append(
Read("chr1", "-", 1, 1, [42, 43, 44, 45, 46, 47, 48, 49, 50]))
reads.append(Read("chr1", "+", 10, 1, [51, 52, 53, 54, 55]))
reads.append(Read("chr2", "+", 10, 1,
[18, 19, 20, 21, 22, 23, 24, 25]))
# starting count
for count_method in ['all', 'start', 'end']:
print "\nTesting count_method option: ****{}****".format(
count_method)
output = "{}\n".format(feature1)
for r in reads:
output += "{}\n".format(r)
feature1.count_read(r, count_method, count_partial_reads=True)
output += "{}\n".format(feature1)
output += feature1.print_metagene(pretty=True)
if str(feature1.print_metagene()).strip() == str(
expected[method][count_method]).strip():
print "PASSED\tCreated correct metagene with feature method {} and count method {} ?".format(
method, count_method)
else:
print "**FAILED**\tCreated correct metagene with feature method {} and count method {} ?".format(
method, count_method)
print "\tExpected:\n{}".format(expected[method][count_method])
print "\tActual :\n{}".format(feature1.print_metagene())
print "\tSummary of run:\n{}".format(output)
feature1 = Feature.create_from_bed(
method, metagene[method], feature_line, False,
False) # zero out counter for next round
try:
unstranded_read = Read("chr1", ".", 10, 1,
[18, 19, 20, 21, 22, 23, 24, 25])
feature1.count_read(unstranded_read, 'all')
except MetageneError as err:
print "PASSED\tCaught unstranded read on stranded count ?\t\t".format(
err)
else:
print "**FAILED**\tCaught unstranded read on stranded count ?"
try:
feature_line = "{}\t{}\t{}\t{}\t{}\t{}\n".format(
1, 20, 40, "first", 44, ".")
feature1 = Feature.create_from_bed(method, metagene[method],
feature_line, False, False)
unstranded_read = Read("chr1", ".", 10, 1,
[18, 19, 20, 21, 22, 23, 24, 25])
feature1.count_read(unstranded_read, 'all')
except MetageneError as err:
print "**FAILED**\tAllowed unstranded read on unstranded count ?\t\t".format(
err)
else:
print "PASSED\tAllowed unstranded read on unstranded count ?"
print "\n**** Testing adjust_to_metagene ****\n"
chromosome_converter = {"1": "chr1", "2": "chr2"}
# ((metagene_tupple),(feature_tupple),expected_result_string, message_string)
tests = [((8, 2, 2), (16, 8, 24, 4),
'8.000,8.000,4.000,4.000,12.000,12.000,2.000,2.000',
"Expand to metagene ?"),
((4, 2, 2), (6, 8, 6, 2, 4, 4, 2, 4, 24, 8),
'17.000,9.000,8.000,34.000', "Contract to metagene ?"),
((4, 2, 2), (2.5, 4, (10.0 / 3), 10, 11, 7.3, 4),
'5.500,9.333,17.825,9.475', "Contract with messy floats ?"),
((3, 2, 2), (2.5, 4, (10.0 / 3), 10, 11, 7.3, 4),
'7.611,19.556,14.967', "Contract with other messy floats ?")]
for t in tests:
metagene = Metagene(*t[0])
print "\t{}".format(metagene)
feature_line = "{}\t{}\t{}\n".format(1, 0, len(t[1]))
feature = Feature.create_from_bed('all',
metagene,
feature_line,
False,
False,
short=True)
adjusted_feature = ""
for f in feature.adjust_to_metagene(t[1]):
adjusted_feature += "{0:0.3f},".format(f)
if adjusted_feature[:-1] == t[2]:
print "PASSED\t{}".format(t[3])
else:
print "**FAILED**\t{}".format(t[3])
print "\tExpected:\t{}".format(t[2])
print "\tActual :\t{}".format(adjusted_feature[:-1])
print "\tOriginal:\t{}".format(feature.adjust_to_metagene(t[1]))
print "\n**** End of Testing the Feature class ****\n"
# end of Feature.test method
def onResult(data):
print "PLC Time is", data
return data
d.addCallback(onResult)
#plcTime.set(None) # Set PLC to current server time
# Start listening as HTTP server
root = File("www")
#root.putChild("membrane_insert", Membrane(plc))
root.putChild("events", EventSource(plc))
root.putChild("write", Write(plc))
root.putChild("read", Read(plc))
root.putChild("logger", Logger(plc))
root.putChild("membrane", Membrane())
root.putChild("product", Product())
root.putChild("chemical", Chemical())
root.putChild("bag-filter", BagFilter())
factory = Site(root)
reactor.listenTCP(8000, factory)
reactor.run()
exit()
# /////////////////////////
# What follows is test code
# Read log value
