def pergola_rules(path, map_file_path, sel_tracks=None, list=None, range=None, track_actions=None,
data_types_actions=None, data_types_list=None, write_format=None, relative_coord=False,
intervals_gen=False, multiply_f=None, no_header=False, fields2read=None, window_size=None,
no_track_line=False, separator=None, bed_lab_sw=False, color_dict=None, window_mean=False,
value_mean=False, min_t=None, max_t=None, interval_step=None):
print >> stderr, "@@@Pergola_rules.py: Input file: %s" % path
print >> stderr, "@@@Pergola_rules.py: Configuration file: %s" % map_file_path
# Tracks selected by user
print >> stderr, "@@@Pergola_rules.py: Selected tracks are: ", sel_tracks
# Configuration file
map_file_dict = mapping.MappingInfo(map_file_path)
# Reading color dictionary to set data_types
if color_dict:
print >> stderr, "@@@Pergola_rules.py: Color for data_types in file............ %s" % color_dict
d_colors_data_types = parsers.read_colors (color_dict)
else:
d_colors_data_types = None
# Handling list or range of tracks to join if set
if list and range:
raise ValueError("@@@Pergola_rules.py: Argument -l/--list and -r/--range are not compatible. " \
"As both arguments set tracks to be joined.")
elif (list):
tracks2merge = list
elif (range):
tracks2merge = range
else:
tracks2merge = ""
if tracks2merge: print >> stderr, "@@@Pergola_rules.py: Tracks to join are............ ", tracks2merge
# Handling argument track actions
if tracks2merge and track_actions:
raise ValueError ("Options --list -l or --range -r are incompatible with " \
"--track_actions -a, please change your options")
track_act = track_actions
print >> stderr, "@@@Pergola_rules.py: Track actions are.............................. ", track_act
data_types_list = data_types_list
print >> stderr, "@@@Pergola_rules.py: data_types list is: ", data_types_list
# Handling argument data_types actions
data_types_act = data_types_actions
print >> stderr, "@@@Pergola_rules.py: data_types actions are......................... ", data_types_act
# Handling argument format
if write_format:
print >> stderr, "@@@Pergola_rules.py format to write files....................... ", write_format
else:
write_format = 'bed'
print >>stderr, "@@@Pergola_rules.py format to write files has been set" \
" to default value:", write_format
# Handling relative coordinates
print >> stderr, "@@@Pergola_rules.py: Relative coordinates set to................. %s" % relative_coord
# Handling intervals_gen
print >> stderr, "@@@Pergola_rules.py: Intervals parameter set to.................. %s" % intervals_gen
# Handling interval_step
if interval_step:
if intervals_gen:
print >> stderr, "@@@Pergola_rules.py: Interval step set to........................ %s" % interval_step
else:
raise ValueError("Interval step needs intervals paramater to be set -n/--intervals_gen")
# Handling multiply_intervals
if multiply_f:
print >>stderr, "@@@Pergola_rules.py: Multiply intervals parameter set to...... %s" % multiply_f
else:
multiply_f = 1
print >> stderr, "@@@Pergola_rules.py: Selected tracks are......................... ", sel_tracks
# Setting whether input file has header or not
header_sw = True
if no_header:
header_sw = False
print >> stderr, "@@@Pergola_rules.py: Data file has header set to............. ", header_sw
# Handling fields to read
if fields2read:
print >>stderr, "@@@Pergola_rules.py: Fields to read from the file are......... %s" % fields2read
else:
fields2read = None
# When binning data setting the window of time used in seconds
# if not size provided set to False
if window_size:
print >>stderr, "@@@Pergola_rules.py: Window size set to....................... %d" % window_size
else:
# window_size = 300
window_size = False
print >>stderr, "@@@Pergola_rules.py: Window size set by default to............ %d" % window_size
if window_mean:
print >>stderr, "@@@Pergola_rules.py: Window mean set to....................... %d" % window_mean
else:
window_mean = False
if value_mean:
print >> stderr, "@@@Pergola_rules.py: Value mean set to....................... %d" % value_mean
else:
value_mean = False
if no_track_line:
track_line=False
else:
track_line=True
print >>stderr, "@@@Pergola_rules.py: track_line set to............................ %s" % track_line
# Handling input file field delimiter
if not separator:
separator = "\t"
print >> stderr, "@@@Pergola_rules.py input file field separator set by default to...... \"\\t\"."
else:
print >>stderr, "@@@Pergola_rules.py input file field separator set to..... \"%s\"" % separator
if bed_lab_sw:
bed_lab = True
print >>stderr, "@@@Pergola_rules.py: bed_label set to......................... %s" % bed_lab
else:
bed_lab = False
intData = intervals.IntData(path, map_dict=map_file_dict.correspondence,
fields_names=fields2read,
header=header_sw, delimiter=separator)
start = intData.min
end = intData.max
if relative_coord:
start = 0
end = intData.max - intData.min
print >> stderr, "@@@Pergola_rules.py: min time in file......................... %d" % start
print >> stderr, "@@@Pergola_rules.py: max time in file......................... %d" % end
if min_t or min_t == 0:
min_time = min_t
print >> stderr, "@@@Pergola_rules.py: min_time set by user to.............. %d" % min_t
else:
min_time = start
if max_t:
max_time = max_t
print >> stderr, "@@@Pergola_rules.py: max_time set by user to............... %d" % max_t
else:
if interval_step:
max_time = end + interval_step
else:
max_time = end + 1
if multiply_f:
min_time = min_time * multiply_f
max_time = max_time * multiply_f
if track_act: tracks2merge = parsers.read_track_actions(tracks=intData.tracks, track_action=track_act)
data_read = intData.read(relative_coord=relative_coord,
intervals=intervals_gen,
multiply_t=multiply_f,
min_time=min_time, max_time=max_time,
int_step=interval_step)
mapping.write_chr(data_read)#mantain
mapping.write_chr_sizes(data_read)
# writes cytoband and light, dark and light_dark bed files
mapping.write_cytoband(end=end, track_line=track_line, lab_bed=False)
# mapping.write_period_seq(start=0, end=intData.max, delta=43200, name_file="phases_dark", track_line=False)
data_read.save_track(name_file="all_intervals")
bed_str = data_read.convert(mode=write_format, tracks=sel_tracks,
tracks_merge=tracks2merge, data_types=data_types_list,
data_types_actions=data_types_act, window=window_size,
mean_win=window_mean, mean_value=value_mean, color_restrictions=d_colors_data_types)
#min_t_trim=min_t, max_t_trim=max_t)
for key in bed_str:
bedSingle = bed_str[key]
bedSingle.save_track(track_line=track_line, bed_label=bed_lab)
norm=True,
data_type=annotated_behavior)
scores_chase_int = intervals.IntData(
tmp_track.name, map_dict=mappings_jaaba.correspondence).read()
data_type_col = {annotated_behavior: 'blue'}
if tag_group == "pBDPGAL4":
# data_type_col = {annotated_behavior: 'orange'}
data_type_col = {annotated_behavior: 'red'}
dict_bed_annotated_int = scores_chase_int.convert(
mode="bed", color_restrictions=data_type_col)
chr_file_n = "chrom"
mapping.write_chr_sizes(scores_chase_int, file_n=chr_file_n)
mapping.write_chr(scores_chase_int)
chr_file = chr_file_n + ".sizes"
for tr, bed_tr in dict_bed_annotated_int.iteritems():
id_worm, var = tr
pybed_tr = bed_tr.create_pybedtools()
pybed_tr.saveas('tr_' + id_worm + '_dt_' + tag_group + '.bed')
df_by_tr = pybed_tr.genome_coverage(
g=chr_file).to_dataframe() # .saveas('tr_' + id_worm + '.bed')
print "%f\t%s" % (df_by_tr.score[(df_by_tr.chrom == 'chr1')
& (df_by_tr.start == 1)].values[0],
annotated_behavior + '_' + tag_group)
# pybedtools.BedTool.to_dataframe()
else:
print >> stderr, "Behavioral data type not available in script, please try again with \"drinking\" or \"feeding\""
mapping_data = mapping.MappingInfo(args.mapping_file)
behavior_mice = dict()
end_time = -10000
data_read_all_batches = None
for f in args.file_mice_behavior:
int_data = intervals.IntData(f, map_dict=mapping_data.correspondence)
data_read = int_data.read(relative_coord=True)
chr_file_n = "chrom"
mapping.write_chr_sizes(data_read, file_n=chr_file_n)
chr_file = chr_file_n + ".sizes"
if end_time < int_data.max - int_data.min:
end_time = int_data.max - int_data.min
if not data_read_all_batches:
data_read_all_batches = data_read
else:
data_read_all_batches = tracks.merge_tracks(data_read_all_batches,
data_read)
stdout.write(str(end_time))
list_ctrl = [1, 3, 5, 7, 9, 11, 13, 15, 17]
list_hf = [2, 4, 8, 10, 12, 14, 16, 18]
###################
# Generate to BedTool objects containing light and dark phases
# Write phases file
mapping.write_cytoband(end=int_data.max - int_data.min,
delta=43200,
start_phase="dark")
light_ph_f = out_dir + "phases_light.bed"
dark_ph_f = out_dir + "phases_dark.bed"
light_bed = pybedtools.BedTool(light_ph_f)
dark_bed = pybedtools.BedTool(dark_ph_f)
# Generate a chr.size file in order to calculate complement of merged meals
chr_file_n = "chrom"
mapping.write_chr_sizes(data_read, path_w=out_dir, file_n=chr_file_n)
chr_file = out_dir + chr_file_n + ".sizes"
# Dictionary to set colors of each type of food
data_type_col = {'food_sc': 'orange', 'food_fat': 'blue'}
data_type_col_m = {'food_sc': 'orange', 'food_fat_food_sc': 'blue'}
bed_str = data_read.convert(mode="bed",
data_types=["food_sc", "food_fat"],
data_types_actions="all",
color_restrictions=data_type_col)
bed_str_out = data_read.convert(mode="bed",
data_types=["food_sc", "food_fat"],
data_types_actions="all",
color_restrictions=data_type_col)
mapping_bed = mapping.MappingInfo(out_dir + "/pybed2perg.txt")