def align_pairwise(genomes, new_align, r_root_dir, g_root_dir,dirs, run, max_size, chop_mode, mauve_exec, mtype, segtype, min_size):
"""Make a pairwise alignment."""
# set up directories
aln_dir = r_root_dir+run+dirs['aln_segs']
map_dir = r_root_dir+run+dirs['maps']
# load inputs and process genomes
seq_dir = g_root_dir
ref = [Noodle(genome, seq_dir) for genome in genomes
if genome['order'] == 1][0]
query = [Noodle(genome, seq_dir) for genome in genomes
if genome['order'] == 2][0]
# align if needed
print "Aligning", ref.name, "and", query.name, "...",
if new_align:
mauve_pw_align(ref, query, r_root_dir, g_root_dir, dirs, run, max_size, chop_mode, mauve_exec, mtype)
# process data segments
print "Processing segments ..",
seg_file = aln_dir+ref.name+"_"+query.name+"_segs.txt"
pair_data = process_segdata(seg_file, ref, query, segtype)
print "OK"
# map of query aligned to reference
print "Mapping ...",
map_file = map_dir+run+"_"+ref.name+"_vs_"+query.name+".pdf"
pairwise_draw(ref, query, pair_data, map_file, 'dual', 'dual', 'm',
'fct', 'fct', idpt, fct_flags, fct_colors, min_size)
print "OK\n"
def map_cst_aln(run_ref, ref_gbk, genome, scaff_gbk, segs_root, maps_root,
segtype, min_size, fct_flags, fct_colors, idpt):
"""Generate map of construct aligned to reference."""
# set inputs and outputs
g_name = genome['name']
ref_ctg_n = run_ref.name
seg_file = segs_root + g_name + "/" + g_name + "_" + ref_ctg_n + "_segs.txt"
map_file = maps_root + g_name + "_vs_" + ref_ctg_n + ".pdf"
# start mapping
try:
open(scaff_gbk)
except IOError:
print "WARNING: No scaffold construct to map"
else:
try:
# load segments TODO: add idp-based clumping
segdata = np.loadtxt(seg_file, skiprows=1, dtype=segtype)
except IOError:
msg = "\nERROR: could not load segments data"
run_ref.log(msg)
print msg
except StopIteration:
msg = "\nERROR: could not make map"
run_ref.log(msg)
print msg
else:
# offset coordinates where desired
try:
g_offset = genome['offset']
if g_offset[0] != 0 or g_offset[1] != 0:
q_len = len(load_genbank(scaff_gbk).seq)
segdata = offset_q2r_coords(segdata, q_len, g_offset,
segtype)
# determine whether to flip the query sequence (negative offset)
if g_offset[1] < 0:
q_invert = True
else:
q_invert = False
except KeyError:
g_offset = (0, 0)
q_invert = False
# generate graphical map
pairwise_draw(ref_ctg_n, g_name, ref_gbk, scaff_gbk, segdata,
map_file, q_invert, g_offset, 'dual', 'dual', 'm',
'fct', 'fct', min_size, fct_flags, fct_colors, idpt)
def map_cst_aln(run_ref, ref_gbk, genome, scaff_gbk, segs_root, maps_root,
segtype, min_size, fct_flags, fct_colors, idpt):
"""Generate map of construct aligned to reference."""
# set inputs and outputs
g_name = genome['name']
ref_ctg_n = run_ref.name
seg_file = segs_root+g_name+"/"+g_name+"_"+ref_ctg_n+"_segs.txt"
map_file = maps_root+g_name+"_vs_"+ref_ctg_n+".pdf"
# start mapping
try: open(scaff_gbk)
except IOError:
print "WARNING: No scaffold construct to map"
else:
try:
# load segments TODO: add idp-based clumping
segdata = np.loadtxt(seg_file, skiprows=1, dtype=segtype)
except IOError:
msg = "\nERROR: could not load segments data"
run_ref.log(msg)
print msg
except StopIteration:
msg = "\nERROR: could not make map"
run_ref.log(msg)
print msg
else:
# offset coordinates where desired
try:
g_offset = genome['offset']
if g_offset[0] != 0 or g_offset[1] != 0:
q_len = len(load_genbank(scaff_gbk).seq)
segdata = offset_q2r_coords(segdata, q_len, g_offset,
segtype)
# determine whether to flip the query sequence (negative offset)
if g_offset[1] < 0:
q_invert = True
else:
q_invert = False
except KeyError:
g_offset = (0,0)
q_invert = False
# generate graphical map
pairwise_draw(ref_ctg_n, g_name, ref_gbk, scaff_gbk, segdata,
map_file, q_invert, g_offset, 'dual', 'dual', 'm',
'fct', 'fct', min_size, fct_flags, fct_colors, idpt)
def align_multi(genomes, new_align, r_root_dir, g_root_dir, dirs, run, max_size, chop_mode, mauve_exec, mtype, segtype, idpt, fct_flags, fct_colors, min_size):
"""Make a multiple alignment."""
# set up directories
aln_dir = r_root_dir+run+dirs['aln_segs']
map_dir = r_root_dir+run+dirs['maps']
# load inputs, process and pair up genomes
seq_dir = g_root_dir
g_pairs = []
counter = 1
while counter < len(genomes):
g_pairs.append(([Noodle(genome, seq_dir) for genome in genomes if
genome['order'] == counter][0],
[Noodle(genome, seq_dir) for genome in genomes if
genome['order'] == counter+1][0]))
counter +=1
# process pairs
for (ref, query) in g_pairs:
# align if needed
print "Aligning", ref.name, "and", query.name, "...",
if new_align:
mauve_pw_align(ref, query, r_root_dir, g_root_dir, dirs, run, max_size, chop_mode,
mauve_exec, mtype)
# traverse genome pairs
segdata_list = []
counter = 0
for (ref, query) in g_pairs:
counter +=1
# process data segments
print "Processing pair", counter, "segments ...",
p_seg_file = aln_dir+ref.name+"_"+query.name+"_segs.txt"
pair_data = process_segdata(p_seg_file, ref, query, segtype)
segdata_list.append(pair_data)
print "OK"
# make a pairwise map while we're at it
print "Mapping pair", counter, "...",
p_map_file = map_dir+run+"_"+ref.name+"_vs_"+query.name+".pdf"
pairwise_draw(ref, query, pair_data, p_map_file, 'dual', 'dual', 'm',
'fct', 'fct', idpt, fct_flags, fct_colors, min_size)
print "OK"
# map of query aligned to reference
print "Mapping multiple alignment...",
map_file = map_dir+run+".pdf"
multi_draw(g_pairs, segdata_list, map_file, idpt, fct_flags, fct_colors, min_size)
print "OK\n"
def align_multi(genomes, new_align, dirs, run):
"""Make a multiple alignment."""
# load inputs, process and pair up genomes
seq_dir = dirs['seqfiles']
g_pairs = []
counter = 1
while counter < len(genomes):
g_pairs.append(([Noodle(genome, seq_dir) for genome in genomes if
genome['order'] == counter][0],
[Noodle(genome, seq_dir) for genome in genomes if
genome['order'] == counter+1][0]))
counter +=1
# process pairs
for (ref, query) in g_pairs:
# align if needed
print "Aligning", ref.name, "and", query.name, "...",
if new_align:
mauve_pw_align(ref, query, dirs)
# traverse genome pairs
segdata_list = []
counter = 0
for (ref, query) in g_pairs:
counter +=1
# process data segments
print "Processing pair", counter, "segments ...",
p_seg_file = dirs['aln_segs']+"/"+ref.name+"_"+query.name+"_segs.txt"
pair_data = process_segdata(p_seg_file, ref, query)
segdata_list.append(pair_data)
print "OK"
# make a pairwise map while we're at it
print "Mapping pair", counter, "...",
p_map_file = dirs['maps']+run+"_"+ref.name+"_vs_"+query.name+".pdf"
pairwise_draw(ref, query, pair_data, p_map_file, 'dual', 'dual', 'm',
'fct', 'fct')
print "OK"
# map of query aligned to reference
print "Mapping multiple alignment...",
map_file = dirs['maps']+run+".pdf"
multi_draw(g_pairs, segdata_list, map_file)
print "OK\n"
def map_ctg_alns(run_ref, ref_gbk, genome, ctg_segs_root, maps_root,
fixed_dirs, segtype, min_size, fct_flags, fct_colors, idpt):
"""Generate maps of contigs aligned to reference."""
# set inputs and outputs
g_name = genome['name']
ref_ctg_n = run_ref.name
segs_root = ctg_segs_root+g_name+"/"
ctgs_dir = fixed_dirs['gbk_contigs_dir']+g_name+"/"
# list genbank files in matches directory
try:
dir_contents = listdir(segs_root)
except OSError:
msg = "\nWARNING: no matching segments"
run_ref.log(msg)
print msg
else:
for ctg_num in dir_contents:
ctg_gbk = ctgs_dir+g_name+"_"+ctg_num+".gbk"
seg_file = segs_root+ctg_num+"/"+ctg_num+"_"+ref_ctg_n+"_segs.txt"
map_file = maps_root+g_name+"_"+ctg_num+"_vs_"+ref_ctg_n+".pdf"
# start mapping
try:
# load segments TODO: add idp-based clumping
segdata = np.loadtxt(seg_file, skiprows=1, dtype=segtype)
# deactivate offsetting
g_offset = (0,0)
q_invert = False
# generate graphical map
pairwise_draw(ref_ctg_n, g_name+"_"+ctg_num, ref_gbk, ctg_gbk,
segdata, map_file, q_invert, g_offset, 'dual',
'dual', 'm', 'fct', 'fct', min_size,
fct_flags, fct_colors, idpt)
except IOError:
msg = "\nERROR: could not load segments data"
run_ref.log(msg)
print msg
except StopIteration:
msg = "\nERROR: could not make map"
run_ref.log(msg)
print msg
def map_ctg_alns(run_ref, ref_gbk, genome, ctg_segs_root, maps_root,
fixed_dirs, segtype, min_size, fct_flags, fct_colors, idpt):
"""Generate maps of contigs aligned to reference."""
# set inputs and outputs
g_name = genome['name']
ref_ctg_n = run_ref.name
segs_root = ctg_segs_root + g_name + "/"
ctgs_dir = fixed_dirs['gbk_contigs_dir'] + g_name + "/"
# list genbank files in matches directory
try:
dir_contents = listdir(segs_root)
except OSError:
msg = "\nWARNING: no matching segments"
run_ref.log(msg)
print msg
else:
for ctg_num in dir_contents:
ctg_gbk = ctgs_dir + g_name + "_" + ctg_num + ".gbk"
seg_file = segs_root + ctg_num + "/" + ctg_num + "_" + ref_ctg_n + "_segs.txt"
map_file = maps_root + g_name + "_" + ctg_num + "_vs_" + ref_ctg_n + ".pdf"
# start mapping
try:
# load segments TODO: add idp-based clumping
segdata = np.loadtxt(seg_file, skiprows=1, dtype=segtype)
# deactivate offsetting
g_offset = (0, 0)
q_invert = False
# generate graphical map
pairwise_draw(ref_ctg_n, g_name + "_" + ctg_num, ref_gbk,
ctg_gbk, segdata, map_file, q_invert, g_offset,
'dual', 'dual', 'm', 'fct', 'fct', min_size,
fct_flags, fct_colors, idpt)
except IOError:
msg = "\nERROR: could not load segments data"
run_ref.log(msg)
print msg
except StopIteration:
msg = "\nERROR: could not make map"
run_ref.log(msg)
print msg
def map_ref_segs(run_ref, run_id, r_root_dir, run_dirs, min_size,
fct_flags, fct_colors, idpt):
"""Generate map of reference contig with segment details.
This provides a comparison of the original reference and the
re-annotated version.
"""
# set inputs and outputs
ref_n = run_ref.name
run_root = r_root_dir+run_id+"/"
ori_file = run_ref.file
ref_maps_root = run_root+run_dirs['ref_map_dir']
ensure_dir([ref_maps_root])
gbk_file = run_root+run_dirs['ref_gbk_dir']+ref_n+"_re-annot.gbk"
map_file = ref_maps_root+ref_n+"_ref.pdf"
# start mapping
try:
# make mock segment, full-length with 100% id
record = load_genbank(gbk_file)
length = len(record.seq)
segdata = [[1, length, 1, length, 100]]
# deactivate offsetting
g_offset = (0,0)
q_invert = False
# generate graphical map
pairwise_draw(ref_n+"_ra", ref_n+"_ori", gbk_file, ori_file,
segdata, map_file, q_invert, g_offset, 'dual', 'dual',
'm', 'fct', 'product', min_size, fct_flags,
fct_colors, idpt)
except IOError:
msg = "\nERROR: could not load segments data"
run_ref.log(msg)
print msg
except StopIteration:
msg = "\nERROR: could not make map"
run_ref.log(msg)
print msg
def map_ref_segs(run_ref, run_id, r_root_dir, run_dirs, min_size, fct_flags,
fct_colors, idpt):
"""Generate map of reference contig with segment details.
This provides a comparison of the original reference and the
re-annotated version.
"""
# set inputs and outputs
ref_n = run_ref.name
run_root = r_root_dir + run_id + "/"
ori_file = run_ref.file
ref_maps_root = run_root + run_dirs['ref_map_dir']
ensure_dir([ref_maps_root])
gbk_file = run_root + run_dirs['ref_gbk_dir'] + ref_n + "_re-annot.gbk"
map_file = ref_maps_root + ref_n + "_ref.pdf"
# start mapping
try:
# make mock segment, full-length with 100% id
record = load_genbank(gbk_file)
length = len(record.seq)
segdata = [[1, length, 1, length, 100]]
# deactivate offsetting
g_offset = (0, 0)
q_invert = False
# generate graphical map
pairwise_draw(ref_n + "_ra", ref_n + "_ori", gbk_file, ori_file,
segdata, map_file, q_invert, g_offset, 'dual', 'dual',
'm', 'fct', 'product', min_size, fct_flags, fct_colors,
idpt)
except IOError:
msg = "\nERROR: could not load segments data"
run_ref.log(msg)
print msg
except StopIteration:
msg = "\nERROR: could not make map"
run_ref.log(msg)
print msg
def align_pairwise(genomes, new_align, dirs, run):
"""Make a pairwise alignment."""
# load inputs and process genomes
seq_dir = dirs['seqfiles']
ref = [Noodle(genome, seq_dir) for genome in genomes
if genome['order'] == 1][0]
query = [Noodle(genome, seq_dir) for genome in genomes
if genome['order'] == 2][0]
# align if needed
print "Aligning", ref.name, "and", query.name, "...",
if new_align:
mauve_pw_align(ref, query, dirs)
# process data segments
print "Processing segments ..",
seg_file = dirs['aln_segs']+"/"+ref.name+"_"+query.name+"_segs.txt"
pair_data = process_segdata(seg_file, ref, query)
print "OK"
# map of query aligned to reference
print "Mapping ...",
map_file = dirs['maps']+run+"_"+ref.name+"_vs_"+query.name+".pdf"
pairwise_draw(ref, query, pair_data, map_file, 'dual', 'dual', 'm',
'fct', 'fct')
print "OK\n"