def user_defined_exons(tmp_sg, line):
chr, strand = utils.get_chr(
line[utils.TARGET]), line[utils.TARGET][0] # get chr and strand
upstream_exon = utils.get_pos(
line[utils.UPSTREAM_EXON]) # get user-defined flanking exons
downstream_exon = utils.get_pos(line[utils.DOWNSTREAM_EXON])
first_primer, second_primer = utils.get_primer_coordinates(
line[utils.PRIMER_COORD])
# get possible exons for primer amplification
tmp = sorted(tmp_sg.get_graph().nodes(), key=lambda x: (x[0], x[1]))
first_ex = utils.find_first_exon(first_primer, tmp)
last_ex = utils.find_last_exon(second_primer, tmp)
my_exons = tmp[first_ex:last_ex + 1]
# if tmp_sg.strand == '+':
# my_exons = tmp[tmp.index(upstream_exon):tmp.index(downstream_exon) + 1]
# else:
# my_exons = tmp[tmp.index(downstream_exon):tmp.index(upstream_exon) + 1]
# Use correct tx's and estimate counts/psi
all_paths = algs.AllPaths(
tmp_sg,
my_exons,
utils.get_pos(line[utils.TARGET]), # tuple (start, end)
chr=chr,
strand=strand)
# all_paths.trim_tx_paths()
fexon = upstream_exon if strand == "+" else downstream_exon
lexon = downstream_exon if strand == "+" else upstream_exon
all_paths.trim_tx_paths_using_primers(first_primer, second_primer, fexon,
lexon)
all_paths.set_all_path_coordinates()
paths, counts = all_paths.estimate_counts() # run EM algorithm
return paths, counts
def user_defined_exons(tmp_sg, line):
chr, strand = utils.get_chr(line[utils.TARGET]), line[utils.TARGET][0] # get chr and strand
upstream_exon = utils.get_pos(line[utils.UPSTREAM_EXON]) # get user-defined flanking exons
downstream_exon = utils.get_pos(line[utils.DOWNSTREAM_EXON])
first_primer, second_primer = utils.get_primer_coordinates(line[utils.PRIMER_COORD])
# get possible exons for primer amplification
tmp = sorted(tmp_sg.get_graph().nodes(), key=lambda x: (x[0], x[1]))
first_ex = utils.find_first_exon(first_primer, tmp)
last_ex = utils.find_last_exon(second_primer, tmp)
my_exons = tmp[first_ex:last_ex + 1]
# if tmp_sg.strand == '+':
# my_exons = tmp[tmp.index(upstream_exon):tmp.index(downstream_exon) + 1]
# else:
# my_exons = tmp[tmp.index(downstream_exon):tmp.index(upstream_exon) + 1]
# Use correct tx's and estimate counts/psi
all_paths = algs.AllPaths(tmp_sg,
my_exons,
utils.get_pos(line[utils.TARGET]), # tuple (start, end)
chr=chr,
strand=strand)
# all_paths.trim_tx_paths()
fexon = upstream_exon if strand == "+" else downstream_exon
lexon = downstream_exon if strand == "+" else upstream_exon
all_paths.trim_tx_paths_using_primers(first_primer, second_primer, fexon, lexon)
all_paths.set_all_path_coordinates()
paths, counts = all_paths.estimate_counts() # run EM algorithm
return paths, counts
def save_isforms_and_counts(line, options):
# get information about each row
ID, target_coordinate = line[:2]
strand = target_coordinate[0]
chr = utils.get_chr(target_coordinate[1:])
tmp_start, tmp_end = utils.get_pos(target_coordinate)
logging.debug('Saving isoform and count information for event %s . . .' %
ID)
# get information from GTF annotation
gene_dict, gene_name = retrieve_gene_information(options, strand, chr,
tmp_start, tmp_end)
# get edge weights
edge_weights_list = [
sam_obj.extractSamRegion(chr, gene_dict['start'], gene_dict['end'])
for sam_obj in options['rnaseq']
]
# construct splice graph for each BAM file
bam_splice_graphs = sg.construct_splice_graph(edge_weights_list,
gene_dict,
chr,
strand,
options['read_threshold'],
options['min_jct_count'],
output_type='list',
both=options['both_flag'])
for bam_ix, my_splice_graph in enumerate(bam_splice_graphs):
# this case is meant for user-defined flanking exons
if line[utils.PSI_UP] == '-1' and line[utils.PSI_DOWN] == '-1':
# find path and count information
paths, counts = user_defined_exons(my_splice_graph, line)
# filter out single exon paths
# my_tmp = [(path, count) for path, count in zip(paths, counts) if len(path) > 1]
# paths, counts = zip(*my_tmp)
# this case is meant for automatic choice of flanking exons
else:
paths, counts = primerseq_defined_exons(my_splice_graph, line,
options['psi'])
utils.save_path_info('%s.%d' % (ID, bam_ix),
paths,
counts,
save_dir='tmp/indiv_isoforms/')
logging.debug(
'Finished saving isoform and count information for event %s.' % ID)
def save_isforms_and_counts(line, options):
# get information about each row
ID, target_coordinate = line[:2]
strand = target_coordinate[0]
chr = utils.get_chr(target_coordinate[1:])
tmp_start, tmp_end = utils.get_pos(target_coordinate)
logging.debug('Saving isoform and count information for event %s . . .' % ID)
# get information from GTF annotation
gene_dict, gene_name = retrieve_gene_information(options,
strand, chr, tmp_start, tmp_end)
# get edge weights
edge_weights_list = [sam_obj.extractSamRegion(chr, gene_dict['start'], gene_dict['end'])
for sam_obj in options['rnaseq']]
# construct splice graph for each BAM file
bam_splice_graphs = sg.construct_splice_graph(edge_weights_list,
gene_dict,
chr,
strand,
options['read_threshold'],
options['min_jct_count'],
output_type='list',
both=options['both_flag'])
for bam_ix, my_splice_graph in enumerate(bam_splice_graphs):
# this case is meant for user-defined flanking exons
if line[utils.PSI_UP] == '-1' and line[utils.PSI_DOWN] == '-1':
# find path and count information
paths, counts = user_defined_exons(my_splice_graph, line)
# filter out single exon paths
# my_tmp = [(path, count) for path, count in zip(paths, counts) if len(path) > 1]
# paths, counts = zip(*my_tmp)
# this case is meant for automatic choice of flanking exons
else:
paths, counts = primerseq_defined_exons(my_splice_graph, line, options['psi'])
utils.save_path_info('%s.%d' % (ID, bam_ix),
paths, counts,
save_dir='tmp/indiv_isoforms/')
logging.debug('Finished saving isoform and count information for event %s.' % ID)
def read_depth_plot(my_bigwigs, output, options):
if type(options['position']) == type(list()):
chr = utils.get_chr(options['position'][0])
start, stop = zip(
*map(lambda x: utils.get_pos(x), options['position']))
else:
chr = utils.get_chr(options['position'])
start, stop = utils.get_pos(options['position'])
bigwigs = my_bigwigs.split(',')
num_subplots = len(bigwigs) # num of bam files equals number of subplots
fig, axes = plt.subplots(num_subplots,
1,
sharex=True,
sharey=True,
figsize=(6, options['size'] * num_subplots))
gray = (0.9, 0.9, 0.9)
# iterate over subplots (bigwig files)
max_count_holder = 0
if num_subplots == 1:
# axes.set_title('Read Depth Plot on %s' % chr)
iterable = [axes]
else:
# axes.flat[0].set_title('Read Depth Plot on %s' % chr)
iterable = axes.flat
for i, ax in enumerate(iterable):
#ax.locator_params(nbins=2)
ax.yaxis.set_label_text('')
# set bg
ax.patch.set_facecolor(gray)
ax.patch.set_edgecolor(gray)
ax.grid()
# plot/label
max_count, real_start, real_stop = generate_plot(
ax, bigwigs[i], chr, start, stop, options) # does the actual work
draw_text(
ax, '%s -- ' % options['gene'] +
os.path.splitext(os.path.basename(bigwigs[i]))[0])
# format options
ax.xaxis.grid(color='white', linestyle='--', linewidth=1.5)
ax.yaxis.grid(color='white', linestyle='--', linewidth=1.5)
ax.xaxis.set_major_formatter(DropFormatter())
ax.yaxis.set_major_formatter(DropFormatter())
ax.set_axisbelow(True)
# hide some ugly lines
for line in ax.xaxis.get_ticklines() + ax.yaxis.get_ticklines():
line.set_color(gray)
# set y-axis
if max_count > max_count_holder:
ax.set_ylim(0, 1.5 * max_count)
ax.set_yticks([
0,
int(.375 * max_count),
int(.75 * max_count),
int(1.125 * max_count),
int(1.5 * max_count)
])
max_count_holder = max_count
# set x-axis options
ax.set_xlim(real_start, real_stop) # set x limits
ax.set_xticks([real_start, real_stop]) # explicitly set ticks
ax.xaxis.set_ticklabels(
map(addCommas,
[real_start, real_stop])) # make nice looking text for labels
ax.get_xticklabels()[0].set_horizontalalignment('left')
ax.get_xticklabels()[1].set_horizontalalignment('right')
# make text box to display chromosome information
if i == num_subplots - 1:
offset_text(ax, '%s:' % chr, 3, (-.15, -.17))
# adjust spacing between subplots
fig.subplots_adjust(wspace=0.05, hspace=0.05, bottom=.12)
# save figure
plt.savefig(output)
def main(options, args_output='tmp/debug.json'):
"""
The gtf main function is the function designed to be called from other
scripts. It iterates through each target exons and returns the necessary
information for primer design.
"""
genome, args_gtf, args_target = options['fasta'], options['gtf'], options['target']
# the sam object interfaces with the user specified BAM/SAM file!!!
sam_obj_list = options['rnaseq']
# iterate through each target exon
output = [] # output from program
for line in args_target: # was line in handle
name, line = line # bad style of reassignment
tgt = line[0]
strand = tgt[0]
tmp_start, tmp_end = get_pos(tgt)
chr = get_chr(tgt[1:]) # [1:] since strand is first character
USER_DEFINED_FLANKING_EXONS = True if len(line) == 3 else False
if USER_DEFINED_FLANKING_EXONS:
up_exon = utils.get_pos(line[1]) # user's upstream exon
down_exon = utils.get_pos(line[2]) # user's downstream exon
else:
up_exon = None # user did not provide upstream exon
down_exon = None # user did not provide downstream exon
# This try block is to catch assertions made about the graph. If a
# PrimerSeqError is raised it only impacts a single target for primer
# design so complete exiting of the program is not warranted.
try:
# if the gtf doesn't have a valid gene_id attribute then use
# the first method otherwise use the second method.
if options['no_gene_id']:
gene_dict, gene_name = get_weakly_connected_tx(args_gtf, strand, chr, tmp_start, tmp_end) # hopefully filter out junk
else:
gene_dict, gene_name = get_from_gtf_using_gene_name(args_gtf, strand, chr, tmp_start, tmp_end)
# extract all edge weights only once
edge_weights_list = [sam_obj.extractSamRegion(chr, gene_dict['start'], gene_dict['end'])
for sam_obj in sam_obj_list]
# The following options['both_flag'] determines how the splice graph is constructed.
# The splice graph can be either constructed from annotation junctions
# where options['both_flag']==False or RNA-Seq + annotation junctions when
# options['both_flag']==True.
# single pooled count data splice graph
splice_graph = construct_splice_graph(edge_weights_list,
gene_dict,
chr,
strand,
options['read_threshold'],
options['min_jct_count'],
output_type='single',
both=options['both_flag'])
# Second, get a splice graph for each BAM file
single_bam_splice_graphs = construct_splice_graph(edge_weights_list,
gene_dict,
chr,
strand,
options['read_threshold'],
options['min_jct_count'],
output_type='list',
both=options['both_flag'])
### Logic for choosing methodology of primer design ###
# user-defined flanking exon case
if up_exon and down_exon:
if gene_dict['target'] not in gene_dict['exons']:
raise utils.PrimerSeqError('Error: target exon was not found in gtf annotation')
elif up_exon not in gene_dict['exons']:
raise utils.PrimerSeqError('Error: upstream exon not in gtf annotation')
elif down_exon not in gene_dict['exons']:
raise utils.PrimerSeqError('Error: downstream exon not in gtf annotation')
tmp = predefined_exons_case(name, # ID for exon (need to save as json)
gene_dict['target'], # target exon tuple (start, end)
splice_graph, # SpliceGraph object
genome, # pygr genome variable
up_exon, # upstream flanking exon
down_exon) # downstream flanking exon
# always included case
elif options['psi'] > .9999:
# note this function ignores edge weights
tmp = get_flanking_biconnected_exons(tgt, gene_dict['target'],
splice_graph,
genome)
# user specified a sufficient psi value to call constitutive exons
else:
tmp = get_sufficient_psi_exons(tgt, gene_dict['target'],
splice_graph,
genome,
name,
options['psi'],
up_exon,
down_exon) # note, this function utilizes edge wieghts
### End methodology specific primer design ###
# Error msgs are of length one, so only do psi calculations for
# non-error msgs
if len(tmp) > 1:
# edit target psi value
tmp_all_paths = tmp[-4] # CAREFUL the index for the AllPaths object may change
tmp[2] = calculate_target_psi(gene_dict['target'],
single_bam_splice_graphs,
tmp_all_paths.component,
up_exon=None,
down_exon=None)
# up_exon=up_exon,
# down_exon=down_exon) # CAREFUL index for psi_target may change
tmp.append(gene_name)
# append result to output list
output.append(tmp)
except (utils.PrimerSeqError,):
t, v, trace = sys.exc_info()
output.append([str(v)]) # just append assertion msg
return output
def main(options, args_output='tmp/debug.json'):
"""
The gtf main function is the function designed to be called from other
scripts. It iterates through each target exons and returns the necessary
information for primer design.
"""
genome, args_gtf, args_target = options['fasta'], options['gtf'], options[
'target']
# the sam object interfaces with the user specified BAM/SAM file!!!
sam_obj_list = options['rnaseq']
# iterate through each target exon
output = [] # output from program
for line in args_target: # was line in handle
name, line = line # bad style of reassignment
tgt = line[0]
strand = tgt[0]
tmp_start, tmp_end = get_pos(tgt)
chr = get_chr(tgt[1:]) # [1:] since strand is first character
USER_DEFINED_FLANKING_EXONS = True if len(line) == 3 else False
if USER_DEFINED_FLANKING_EXONS:
up_exon = utils.get_pos(line[1]) # user's upstream exon
down_exon = utils.get_pos(line[2]) # user's downstream exon
else:
up_exon = None # user did not provide upstream exon
down_exon = None # user did not provide downstream exon
# This try block is to catch assertions made about the graph. If a
# PrimerSeqError is raised it only impacts a single target for primer
# design so complete exiting of the program is not warranted.
try:
# if the gtf doesn't have a valid gene_id attribute then use
# the first method otherwise use the second method.
if options['no_gene_id']:
gene_dict, gene_name = get_weakly_connected_tx(
args_gtf, strand, chr, tmp_start,
tmp_end) # hopefully filter out junk
else:
gene_dict, gene_name = get_from_gtf_using_gene_name(
args_gtf, strand, chr, tmp_start, tmp_end)
# extract all edge weights only once
edge_weights_list = [
sam_obj.extractSamRegion(chr, gene_dict['start'],
gene_dict['end'])
for sam_obj in sam_obj_list
]
# The following options['both_flag'] determines how the splice graph is constructed.
# The splice graph can be either constructed from annotation junctions
# where options['both_flag']==False or RNA-Seq + annotation junctions when
# options['both_flag']==True.
# single pooled count data splice graph
splice_graph = construct_splice_graph(edge_weights_list,
gene_dict,
chr,
strand,
options['read_threshold'],
options['min_jct_count'],
output_type='single',
both=options['both_flag'])
# Second, get a splice graph for each BAM file
single_bam_splice_graphs = construct_splice_graph(
edge_weights_list,
gene_dict,
chr,
strand,
options['read_threshold'],
options['min_jct_count'],
output_type='list',
both=options['both_flag'])
### Logic for choosing methodology of primer design ###
# user-defined flanking exon case
if up_exon and down_exon:
if gene_dict['target'] not in gene_dict['exons']:
raise utils.PrimerSeqError(
'Error: target exon was not found in gtf annotation')
elif up_exon not in gene_dict['exons']:
raise utils.PrimerSeqError(
'Error: upstream exon not in gtf annotation')
elif down_exon not in gene_dict['exons']:
raise utils.PrimerSeqError(
'Error: downstream exon not in gtf annotation')
tmp = predefined_exons_case(
name, # ID for exon (need to save as json)
gene_dict['target'], # target exon tuple (start, end)
splice_graph, # SpliceGraph object
genome, # pygr genome variable
up_exon, # upstream flanking exon
down_exon) # downstream flanking exon
# always included case
elif options['psi'] > .9999:
# note this function ignores edge weights
tmp = get_flanking_biconnected_exons(tgt, gene_dict['target'],
splice_graph, genome)
# user specified a sufficient psi value to call constitutive exons
else:
tmp = get_sufficient_psi_exons(
tgt, gene_dict['target'], splice_graph, genome, name,
options['psi'], up_exon,
down_exon) # note, this function utilizes edge wieghts
### End methodology specific primer design ###
# Error msgs are of length one, so only do psi calculations for
# non-error msgs
if len(tmp) > 1:
# edit target psi value
tmp_all_paths = tmp[
-4] # CAREFUL the index for the AllPaths object may change
tmp[2] = calculate_target_psi(gene_dict['target'],
single_bam_splice_graphs,
tmp_all_paths.component,
up_exon=None,
down_exon=None)
# up_exon=up_exon,
# down_exon=down_exon) # CAREFUL index for psi_target may change
tmp.append(gene_name)
# append result to output list
output.append(tmp)
except (utils.PrimerSeqError, ):
t, v, trace = sys.exc_info()
output.append([str(v)]) # just append assertion msg
return output
def read_depth_plot(my_bigwigs, output, options):
if type(options['position']) == type(list()):
chr = utils.get_chr(options['position'][0])
start, stop = zip(*map(lambda x: utils.get_pos(x), options['position']))
else:
chr = utils.get_chr(options['position'])
start, stop = utils.get_pos(options['position'])
bigwigs = my_bigwigs.split(',')
num_subplots = len(bigwigs) # num of bam files equals number of subplots
fig, axes = plt.subplots(num_subplots, 1, sharex=True, sharey=True, figsize=(6, options['size'] * num_subplots))
gray = (0.9, 0.9, 0.9)
# iterate over subplots (bigwig files)
max_count_holder = 0
if num_subplots == 1:
# axes.set_title('Read Depth Plot on %s' % chr)
iterable = [axes]
else:
# axes.flat[0].set_title('Read Depth Plot on %s' % chr)
iterable = axes.flat
for i, ax in enumerate(iterable):
#ax.locator_params(nbins=2)
ax.yaxis.set_label_text('')
# set bg
ax.patch.set_facecolor(gray)
ax.patch.set_edgecolor(gray)
ax.grid()
# plot/label
max_count, real_start, real_stop = generate_plot(ax, bigwigs[i], chr, start, stop, options) # does the actual work
draw_text(ax, '%s -- ' % options['gene'] + os.path.splitext(os.path.basename(bigwigs[i]))[0])
# format options
ax.xaxis.grid(color='white', linestyle='--', linewidth=1.5)
ax.yaxis.grid(color='white', linestyle='--', linewidth=1.5)
ax.xaxis.set_major_formatter(DropFormatter())
ax.yaxis.set_major_formatter(DropFormatter())
ax.set_axisbelow(True)
# hide some ugly lines
for line in ax.xaxis.get_ticklines() + ax.yaxis.get_ticklines():
line.set_color(gray)
# set y-axis
if max_count > max_count_holder:
ax.set_ylim(0, 1.5 * max_count)
ax.set_yticks([0, int( .375 * max_count ), int( .75 * max_count ), int( 1.125 * max_count ), int(1.5 * max_count)])
max_count_holder = max_count
# set x-axis options
ax.set_xlim(real_start, real_stop) # set x limits
ax.set_xticks([real_start, real_stop]) # explicitly set ticks
ax.xaxis.set_ticklabels(map(addCommas, [real_start, real_stop])) # make nice looking text for labels
ax.get_xticklabels()[0].set_horizontalalignment('left')
ax.get_xticklabels()[1].set_horizontalalignment('right')
# make text box to display chromosome information
if i == num_subplots - 1:
offset_text(ax, '%s:' % chr, 3, (-.15, -.17))
# adjust spacing between subplots
fig.subplots_adjust(wspace=0.05, hspace=0.05, bottom=.12)
# save figure
plt.savefig(output)
