def main():
args = handle_program_options()
try:
with open(args.otu_id_fp):
pass
except IOError as ioe:
sys.exit("\nError with file containing OTUIDs/BIOM format:{}\n".format(ioe))
with open(args.otu_id_fp, "rU") as otuF:
if args.reverse_lookup:
otu_ids = []
for line in otuF.readlines():
if line:
otu_ids.append(line.strip())
else:
otu_ids = [line.strip().split("\t") for line in otuF.readlines()]
taxa = util.parse_taxonomy_table(args.taxonomy_fp)
with open(args.output_fp, "w") as outF:
for entry in otu_ids:
if isinstance(entry, list):
# check for comments in BIOM files
if not entry[0][0] == "#":
ID = entry[0]
else:
outF.write("{}\n".format("\t".join(entry)))
continue
# instead of a BIOM file, a line-by-line list of OTU IDs
else:
ID = entry
# for looking up OTUIDs
if args.reverse_lookup:
for id, fulltaxa in taxa.iteritems():
otuname = otuc.otu_name(fulltaxa.split("; "))
if otuname == ID:
taxa_id = id
# for looking up OTU name
else:
if ID in taxa:
named_ID = otuc.otu_name(taxa[ID].split("; "))
else:
print "Error: OTU ID {} not found in supplied taxonomy file.".format(ID)
return
# write out to file
out_str = "{}\t{}\n"
if isinstance(entry, list):
outF.write(out_str.format(named_ID, "\t".join(entry[1:])))
else:
if args.reverse_lookup:
outF.write("{}\n".format(taxa_id))
else:
outF.write(out_str.format(ID, named_ID))
def main():
args = handle_program_options()
# Read biom format file
try:
biomf = biom.load_table(args.otu_table)
except IOError as ioe:
sys.exit("\nError with biom format file (-i): {}\n".format(ioe))
# Read in otus file data
try:
with open(args.otu_id_fp, "rU") as inf:
dialect = csv.Sniffer().sniff(inf.read(1024))
inf.seek(0)
csvr = csv.reader(inf, dialect)
otu_ids = [line[0] for line in csvr]
except IOError as ioe:
sys.exit("\nError with file containing OTUs:{}\n".format(ioe))
output = {}
for val, idx, md in biomf.iter(axis="observation"):
name = otuc.otu_name(md["taxonomy"])
if args.reverse_lookup:
if name in otu_ids:
output[name] = idx # Get otuids from otu names
else:
if idx in otu_ids:
output[idx] = name # Get otu name from otu IDs
with open(args.output_fp, "w") as outf:
outf.write("Input\tOutput\n")
for k, v in output.items():
outf.write("{0}\t{1}\n".format(k, v))
def write_relative_abundance(rel_abd, biomf, out_fn, sort_by=None):
"""
Given a BIOM table, calculate per-sample relative abundance for
each OTU and write out to a tab-separated file listing OTUs as
rows and Samples as columns.
:type biom: biom object
:param biom: BIOM-formatted OTU/Sample abundance data
:type out_fn: str
:param out_fn: The full path to the desired output file.
:type sort_by: function
:param sort_by: A function acting as a sorting key that will determine
the order in which the Sample IDs appear as columns in
the output file.
"""
with open(out_fn, 'w') as out_f:
sids = sorted(set(biomf.ids()), key=sort_by)
out_f.write('#OTU ID\t{}\n'.format('\t'.join(sids)))
for otuid in biomf.ids(axis="observation"):
otuName = oc.otu_name(biomf.metadata(otuid, "observation")
["taxonomy"])
sabd = [str(rel_abd[sid][otuid])
if sid in rel_abd and otuid in rel_abd[sid] else '0'
for sid in sids]
out_f.write('{}\t{}\n'.format(otuName, '\t'.join(sabd)))
def test_otu_name(self):
"""
Testing the otu_name() function of otu_calc.py.
:return: Returns OK if the test goals were achieved, otherwise
raises error.
"""
self.tax = {
"Unclassified_Methanosarcinales":
["k__Archaea", "p__Euryarchaeota", "c__Methanomicrobia",
"o__Methanosarcinales", "f__",
"g__", "s__concilii"
],
"Campylobacter_gracilis":
["k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria",
"o__Campylobacterales", "f__Campylobacteraceae", "g__Campylobacter",
"s__gracilis"],
"Escherichia_spp.":
["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria",
"o__Enterobacteriales", "f__Enterobacteriaceae", "g__Escherichia",
"s__"]
}
for expected, test in self.tax.items():
self.result = oc.otu_name(test)
# Testing the validity of the otu_name() function
self.assertEqual(
self.result, expected,
msg='Error! Expected result: {}. otu_name() result: {}'.format(
expected, self.result)
)
def get_relative_abundance(biomfile):
"""
Return arcsine transformed relative abundance from a BIOM format file.
:type biomfile: BIOM format file
:param biomfile: BIOM format file used to obtain relative abundances for each OTU in
a SampleID, which are used as node sizes in network plots.
:type return: Dictionary of dictionaries.
:return: Dictionary keyed on SampleID whose value is a dictionarykeyed on OTU Name
whose value is the arc sine tranfsormed relative abundance value for that
SampleID-OTU Name pair.
"""
biomf = biom.load_table(biomfile)
norm_biomf = biomf.norm(inplace=False)
rel_abd = {}
for sid in norm_biomf.ids():
rel_abd[sid] = {}
for otuid in norm_biomf.ids("observation"):
otuname = oc.otu_name(norm_biomf.metadata(otuid, axis="observation")["taxonomy"])
otuname = " ".join(otuname.split("_"))
abd = norm_biomf.get_value_by_ids(otuid, sid)
rel_abd[sid][otuname] = abd
ast_rel_abd = bc.arcsine_sqrt_transform(rel_abd)
return ast_rel_abd
def get_relative_abundance(biomfile):
"""
Return arcsine transformed relative abundance from a BIOM format file.
:type biomfile: BIOM format file
:param biomfile: BIOM format file used to obtain relative abundances for each OTU in
a SampleID, which are used as node sizes in network plots.
:type return: Dictionary of dictionaries.
:return: Dictionary keyed on SampleID whose value is a dictionarykeyed on OTU Name
whose value is the arc sine tranfsormed relative abundance value for that
SampleID-OTU Name pair.
"""
biomf = biom.load_table(biomfile)
norm_biomf = biomf.norm(inplace=False)
rel_abd = {}
for sid in norm_biomf.ids():
rel_abd[sid] = {}
for otuid in norm_biomf.ids("observation"):
otuname = oc.otu_name(
norm_biomf.metadata(otuid, axis="observation")["taxonomy"])
otuname = " ".join(otuname.split("_"))
abd = norm_biomf.get_value_by_ids(otuid, sid)
rel_abd[sid][otuname] = abd
ast_rel_abd = bc.arcsine_sqrt_transform(rel_abd)
return ast_rel_abd
def write_relative_abundance(rel_abd, biomf, out_fn, sort_by=None):
"""
Given a BIOM table, calculate per-sample relative abundance for
each OTU and write out to a tab-separated file listing OTUs as
rows and Samples as columns.
:type biom: biom object
:param biom: BIOM-formatted OTU/Sample abundance data
:type out_fn: str
:param out_fn: The full path to the desired output file.
:type sort_by: function
:param sort_by: A function acting as a sorting key that will determine
the order in which the Sample IDs appear as columns in
the output file.
"""
with open(out_fn, 'w') as out_f:
sids = sorted(set(biomf.ids()), key=sort_by)
out_f.write('#OTU ID\t{}\n'.format('\t'.join(sids)))
for otuid in biomf.ids(axis="observation"):
otuName = oc.otu_name(
biomf.metadata(otuid, "observation")["taxonomy"])
sabd = [
str(rel_abd[sid][otuid])
if sid in rel_abd and otuid in rel_abd[sid] else '0'
for sid in sids
]
out_f.write('{}\t{}\n'.format(otuName, '\t'.join(sabd)))
def calc_rel_abd(biomf, sampleIDs=None):
"""
Calculate relative abundance from a biom table either based on sampleIDs or
otuIDs.
:type biomf: Biom file format
:param biomf: Biom table loaded object
:type sampleIDs: list
:param sampleIDs: Only calculate relative abundances for these sampleIDs.
Default is None.
:return type: defaultdict(dict)
:return: A dict keyed on sampleID with its value denoting a dict keyed on
otuID and abundance value for that [sampleID, otuID] pair.
"""
norm_biomf = biomf.norm(inplace=False)
if sampleIDs is None:
sampleIDs = norm_biomf.ids()
otuIDs = norm_biomf.ids(axis="observation")
rel_abd = defaultdict(dict)
for sample in sampleIDs:
for otu in otuIDs:
abd = norm_biomf.get_value_by_ids(otu, sample)
otu_tax = norm_biomf.metadata(otu, "observation")["taxonomy"]
otu_name = oc.otu_name(otu_tax)
rel_abd[sample][otu_name] = abd
trans_rel_abd = bc.arcsine_sqrt_transform(rel_abd)
return trans_rel_abd
def calc_rel_abd(biomf, sampleIDs=None):
"""
Calculate relative abundance from a biom table either based on sampleIDs or
otuIDs.
:type biomf: Biom file format
:param biomf: Biom table loaded object
:type sampleIDs: list
:param sampleIDs: Only calculate relative abundances for these sampleIDs.
Default is None.
:return type: defaultdict(dict)
:return: A dict keyed on sampleID with its value denoting a dict keyed on
otuID and abundance value for that [sampleID, otuID] pair.
"""
norm_biomf = biomf.norm(inplace=False)
if sampleIDs is None:
sampleIDs = norm_biomf.ids()
otuIDs = norm_biomf.ids(axis="observation")
rel_abd = defaultdict(dict)
for sample in sampleIDs:
for otu in otuIDs:
abd = norm_biomf.get_value_by_ids(otu, sample)
otu_tax = norm_biomf.metadata(otu, "observation")["taxonomy"]
otu_name = oc.otu_name(otu_tax)
rel_abd[sample][otu_name] = abd
trans_rel_abd = bc.arcsine_sqrt_transform(rel_abd)
return trans_rel_abd
def newick_replace_otuids(tree, biomf):
"""
Replace the OTU ids in the Newick phylogenetic tree format with truncated
OTU names
"""
for val, id_, md in biomf.iter(axis="observation"):
otu_loc = find_otu(id_, tree)
if otu_loc is not None:
tree = tree[:otu_loc] + \
oc.otu_name(md["taxonomy"]) + \
tree[otu_loc + len(id_):]
return tree
def newick_replace_otuids(tree, biomf):
"""
Replace the OTU ids in the Newick phylogenetic tree format with truncated
OTU names
"""
for val, id_, md in biomf.iter(axis="observation"):
otu_loc = find_otu(id_, tree)
if otu_loc is not None:
tree = tree[:otu_loc] + \
oc.otu_name(md["taxonomy"]) + \
tree[otu_loc + len(id_):]
return tree
def get_relative_abundance(biomfile):
"""
Return relative abundance from a OTU table. OTUIDs are converted to their
genus-species identifier.
"""
biomf = biom.load_table(biomfile)
norm_biomf = biomf.norm(inplace=False)
rel_abd = {}
for sid in norm_biomf.ids():
rel_abd[sid] = {}
for otuid in norm_biomf.ids("observation"):
otuname = oc.otu_name(norm_biomf.metadata(otuid, axis="observation")["taxonomy"])
abd = norm_biomf.get_value_by_ids(otuid, sid)
rel_abd[sid][otuname] = abd
ast_rel_abd = bc.arcsine_sqrt_transform(rel_abd)
return ast_rel_abd
def load_core_file(core_fp):
"""
For core OTU data file, returns Genus-species identifier for each data
entry.
:type core_fp: str
:param core_fp: A file containing core OTU data.
:rtype: str
:return: Returns genus-species identifier based on identified taxonomical
level.
"""
core = {}
with open(core_fp) as in_f:
for line in in_f.read().splitlines():
if not line.startswith("#"):
otu_id, tax = line.split("\t")
core[otu_id] = oc.otu_name(ast.literal_eval(tax))
return core
def load_core_file(core_fp):
"""
For core OTU data file, returns Genus-species identifier for each data
entry.
:type core_fp: str
:param core_fp: A file containing core OTU data.
:rtype: str
:return: Returns genus-species identifier based on identified taxonomical
level.
"""
core = {}
with open(core_fp) as in_f:
for line in in_f.read().splitlines():
if not line.startswith("#"):
otu_id, tax = line.split("\t")
core[otu_id] = oc.otu_name(ast.literal_eval(tax))
return core
def test_otu_name(self):
"""
Testing otu_name() function of otu_calc.py.
:return: Returns OK if the test goals were achieved, otherwise
raises error.
"""
self.tax = [
"k__Archaea", "p__Euryarchaeota", "c__Methanomicrobia",
"o__Methanosarcinales", "f__",
"g__", "s__"
]
self.result = oc.otu_name(self.tax)
hand_calc = 'Unclassified_Methanosarcinales'
# Testing the validity of the otu_name() function
self.assertEqual(
self.result, hand_calc,
msg='Error! The output is not as expected.'
)
def test_otu_name(self):
"""
Testing the otu_name() function of otu_calc.py.
:return: Returns OK if the test goals were achieved, otherwise
raises error.
"""
self.taxa = {
"Unclassified_Methanosarcinales": [
"k__Archaea", "p__Euryarchaeota", "c__Methanomicrobia",
"o__Methanosarcinales", "f__", "g__", "s__concilii"
],
"Campylobacter_gracilis": [
"k__Bacteria", "p__Proteobacteria", "c__Epsilonproteobacteria",
"o__Campylobacterales", "f__Campylobacteraceae",
"g__Campylobacter", "s__gracilis"
],
"Escherichia_spp.": [
"k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria",
"o__Enterobacteriales", "f__Enterobacteriaceae",
"g__Escherichia", "s__"
],
"Fusobacterium_nucleatum": [
"k__Bacteria", "p__Fusobacteria", "c__Fusobacteria", "o__",
"f__", "g__Fusobacterium", "s__nucleatum"
],
"Fusobacterium_spp.": [
"k__Bacteria", "p__Fusobacteria", "c__Fusobacteria", "o__",
"f__", "g__Fusobacterium", "s__"
]
}
for expected, test in self.taxa.items():
self.result = oc.otu_name(test)
# Testing the validity of the otu_name() function
self.assertEqual(
self.result,
expected,
msg="Error!\nExpected result: {}.\notu_name() result: {}".
format(expected, self.result))
def main():
args = handle_program_options()
# Read gramox data from master file
try:
with open(args.master_fnh, "rU") as bgof:
bgodata = {
line.strip().split("\t")[1]:
"\t".join(line.strip().split("\t")[2:4])
for line in bgof.readlines()
}
except Exception as err:
sys.exit(
"\nError parsing master gramox file: {}. Please check master gramox data"
" file and re-run this script.".format(err))
# Read relative abundance data
try:
biomf = biom.load_table(args.biom_file)
except Exception as err:
sys.exit("\nError opening BIOM file: {}\n".format(err))
else:
otus = [
otu_name(biomf.metadata(otuid, "observation")["taxonomy"])
for otuid in biomf.ids("observation")
]
# Write classified gramox data to tsv file
print(
"\nWriting out results to file. For OTUs with missing gramox data, please "
"manually input the relevant information or fill in NA for unverified "
"information. This is required before running pct_abd_gramox.py script.\n"
)
with open(args.out_fnh, "w") as gramoxout:
gramoxout.write("#OTU\tGram Status\tOxygen Requirement\n")
for otu in otus:
if otu in bgodata.keys():
gramoxout.write("{}\t{}\n".format(otu, bgodata[otu]))
else:
gramoxout.write("{}\n".format(otu))
def main():
args = handle_program_options()
try:
with open(args.otu_id_fp):
pass
except IOError as ioe:
sys.exit('\nError with file containing OTUIDs/BIOM format:{}\n'.format(ioe))
with open(args.otu_id_fp, 'rU') as otuF:
otu_ids = [line.strip().split('\t') for line in otuF.readlines()]
taxa = util.parse_taxonomy_table(args.taxonomy_fp)
with open(args.output_fp, 'w') as outF:
for entry in otu_ids:
if isinstance(entry, list):
# check for comments in BIOM files
if not entry[0][0] == '#':
ID = entry[0]
else:
outF.write('{}\n'.format('\t'.join(entry)))
continue
# instead of a BIOM file, a line-by-line list of OTU IDs
else:
ID = entry
if ID in taxa:
named_ID = otuc.otu_name(taxa[ID].split('; '))
else:
print 'Error: OTU ID {} not found in supplied taxonomy file; stopping...'.format(ID)
return
# write out to file
out_str = '{}\t{}\n'
if isinstance(entry, list):
outF.write(out_str.format(named_ID, '\t'.join(entry[1:])))
else:
outF.write(out_str.format(ID, named_ID))
def main():
args = handle_program_options()
try:
with open(args.otu_table):
pass
except IOError as ioe:
sys.exit(
"\nError with OTU_Sample abundance data file:{}\n".format(ioe))
try:
with open(args.mapping):
pass
except IOError as ioe:
sys.exit("\nError with mapping file:{}\n".format(ioe))
# input data
biomf = biom.load_table(args.otu_table)
map_header, imap = util.parse_map_file(args.mapping)
# rewrite tree file with otu names, skip if keep_otuids specified
if args.input_tree and not args.keep_otuids:
with open(args.input_tree) as treF, open(args.output_tre, "w") as outF:
tree = treF.readline()
if "'" in tree:
tree = tree.replace("'", '')
outF.write(newick_replace_otuids(tree, biomf))
if not args.keep_otuids:
oid_rows = {
id_: md["taxonomy"]
for val, id_, md in biomf.iter(axis="observation")
}
# calculate analysis results
categories = None
if args.map_categories is not None and args.analysis_metric != "raw":
categories = args.map_categories.split(",")
# set transform if --stabilize_variance is specfied
tform = bc.arcsine_sqrt_transform if args.stabilize_variance else None
groups = util.gather_categories(imap, map_header, categories)
for group in groups.values():
if args.analysis_metric in ["MRA", "NMRA"]:
results = bc.MRA(biomf, group.sids, transform=tform)
elif args.analysis_metric == "raw":
results = bc.transform_raw_abundance(biomf,
sampleIDs=group.sids,
sample_abd=False)
if args.keep_otuids:
group.results.update({oid: results[oid] for oid in results})
else:
group.results.update(
{oc.otu_name(oid_rows[oid]): results[oid]
for oid in results})
# write iTol data set file
with open(args.output_itol_table, "w") as itolF:
if args.analysis_metric == "raw":
itolF.write("DATASET_GRADIENT\nSEPARATOR TAB\n")
itolF.write("DATASET_LABEL\tLog Total Abundance\n")
itolF.write("COLOR\t#000000\n")
itolF.write("LEGEND_TITLE\tLog Total Abundance\n")
itolF.write("LEGEND_SHAPES\t1\n")
itolF.write("LEGEND_COLORS\t#000000\n")
itolF.write("LEGEND_LABELS\tLog Total Abundance\n")
itolF.write("COLOR_MIN\t#FFFFFF\n")
itolF.write("COLOR_MAX\t#000000\n")
else:
itolF.write("DATASET_MULTIBAR\nSEPARATOR TAB\n")
itolF.write("DATASET_LABEL\t{}\n".format(args.analysis_metric))
itolF.write("FIELD_COLORS\t{}\n".format("\t".join(
["#ff0000" for _ in range(len(groups))])))
itolF.write("FIELD_LABELS\t" + "\t".join(groups.keys()) + "\n")
itolF.write("LEGEND_TITLE\t{}\n".format(args.analysis_metric))
itolF.write("LEGEND_SHAPES\t{}\n".format("\t".join(
["1" for _ in range(len(groups))])))
itolF.write("LEGEND_COLORS\t{}\n".format("\t".join(
["#ff0000" for _ in range(len(groups))])))
itolF.write("LEGEND_LABELS\t" + "\t".join(groups.keys()) + "\n")
itolF.write("WIDTH\t300\n")
itolF.write("DATA\n")
if args.keep_otuids:
all_otus = frozenset(
{id_
for id_ in biomf.ids(axis="observation")})
else:
all_otus = frozenset({
oc.otu_name(md["taxonomy"])
for val, id_, md in biomf.iter(axis="observation")
})
for oname in all_otus:
row = ["{name}"] # \t{s:.2f}\t{ns:.2f}\n"
row_data = {"name": oname}
msum = 0
for name, group in groups.iteritems():
row.append("{{{}:.5f}}".format(name))
if oname in group.results:
row_data[name] = group.results[oname]
else:
row_data[name] = 0.0
msum += row_data[name]
# normalize avg relative abundance data
if args.analysis_metric == "NMRA" and msum > 0:
row_data.update({
key: data / msum
for key, data in row_data.items() if key != "name"
})
itolF.write("\t".join(row).format(**row_data) + "\n")
def main():
args = handle_program_options()
# Parse and read mapping file
try:
header, imap = util.parse_map_file(args.map_fp)
category_idx = header.index(args.group_by)
except IOError as ioe:
err_msg = "\nError in metadata mapping filepath (-m): {}\n"
sys.exit(err_msg.format(ioe))
# Obtain group colors
class_colors = util.color_mapping(imap, header, args.group_by, args.color_by)
# Get otus for LDA bubble plots
try:
bubble_otus = set(pd.read_csv(args.otu_ids_fp, sep="\n", header=None)[0])
except IOError as ioe:
err_msg = "\nError in OTU IDs file (--bubble): {}\n"
sys.exit(err_msg.format(ioe))
# Load biom file and calculate relative abundance
try:
biomf = biom.load_table(args.otu_table)
except IOError as ioe:
err_msg = "\nError with biom format file (-d): {}\n"
sys.exit(err_msg.format(ioe))
# Get normalized relative abundances
rel_abd = bc.relative_abundance(biomf)
rel_abd = bc.arcsine_sqrt_transform(rel_abd)
abd_val = {abd for sid, v1 in rel_abd.items() for otuid, abd in v1.items() if abd > 0}
bubble_range = np.linspace(min(abd_val), max(abd_val), num=5) * args.scale_by
# Get abundance to the nearest 50
bubble_range = [int(50 * round(float(abd)/50)) for abd in bubble_range[1:]]
# Set up input for LDA calc and get LDA transformed data
if args.dist_matrix_file:
try:
uf_data = pd.read_csv(args.dist_matrix_file, sep="\t", index_col=0)
except IOError as ioe:
err_msg = "\nError with unifrac distance matrix file (-d): {}\n"
sys.exit(err_msg.format(ioe))
uf_data.insert(0, "Condition", [imap[sid][category_idx] for sid in uf_data.index])
sampleids = uf_data.index
if args.save_lda_input:
uf_data.to_csv(args.save_lda_input, sep="\t")
# Run LDA
X_lda, y_lda, exp_var = run_LDA(uf_data)
else:
df_rel_abd = pd.DataFrame(rel_abd).T
df_rel_abd.insert(0, "Condition", [imap[sid][category_idx]
for sid in df_rel_abd.index])
sampleids = df_rel_abd.index
if args.save_lda_input:
df_rel_abd.to_csv(args.save_lda_input, sep="\t")
# Run LDA
X_lda, y_lda, exp_var = run_LDA(df_rel_abd)
# Calculate position and size of SampleIDs to plot for each OTU
for otuid in bubble_otus:
otuname = oc.otu_name(biomf.metadata(otuid, axis="observation")["taxonomy"])
plot_data = {cat: {"x": [], "y": [], "size": [], "label": []}
for cat in class_colors.keys()}
for sid, data in zip(sampleids, X_lda):
category = plot_data[imap[sid][category_idx]]
try:
size = rel_abd[sid][otuid] * args.scale_by
except KeyError as ke:
print("{} not found in {} sample.".format(ke, sid))
continue
category["x"].append(float(data[0]))
category["y"].append(float(data[1]))
category["size"].append(size)
# Plot LDA bubble for each OTU
fig = plt.figure(figsize=args.figsize)
ax = fig.add_subplot(111)
for i, cat in enumerate(plot_data):
plt.scatter(plot_data[cat]["x"], plot_data[cat]["y"],
s=plot_data[cat]["size"], label=cat, color=class_colors[cat],
alpha=0.85, edgecolors="k")
if X_lda.shape[1] == 1:
plt.ylim((0.5, 2.5))
plt.title(" ".join(otuname.split("_")), style="italic", fontsize=13)
try:
plt.xlabel("LD1 (Percent Explained Variance: {:.3f}%)".format(exp_var[0]*100),
fontsize=13, labelpad=15)
except:
plt.xlabel("LD1", fontsize=13, labelpad=15)
try:
plt.ylabel("LD2 (Percent Explained Variance: {:.3f}%)".format(exp_var[1]*100),
fontsize=13, labelpad=15)
except:
plt.ylabel("LD2", fontsize=13, labelpad=15)
lgnd1 = plt.legend(loc="best", scatterpoints=3, fontsize=13)
for i in range(len(class_colors.keys())):
lgnd1.legendHandles[i]._sizes = [80] # Change the legend marker size manually
# Add the legend manually to the current plot
plt.gca().add_artist(lgnd1)
c = [plt.scatter([], [], c="w", edgecolors="k", s=s1) for s1 in bubble_range]
plt.legend(c, ["{}".format(s2) for s2 in bubble_range],
title="Scaled Bubble\n Sizes", frameon=True, labelspacing=2,
fontsize=13, loc=4, scatterpoints=1, borderpad=1.1)
# Set style for LDA bubble plots
if args.ggplot2_style:
gu.ggplot2_style(ax)
fc = "0.8"
else:
fc = "none"
# Save LDA bubble plots to output directory
if args.verbose:
print("Saving chart for {}".format(" ".join(otuname.split("_"))))
fig.savefig(pj(args.output_dir, "_".join(otuname.split())) + "." + args.save_as,
facecolor=fc, edgecolor="none", dpi=300,
bbox_inches="tight", pad_inches=0.2)
plt.close(fig)
def main():
args = handle_program_options()
try:
with open(args.otu_table):
pass
except IOError as ioe:
sys.exit("\nError with BIOM format file:{}\n".format(ioe))
try:
with open(args.pcoa_fp):
pass
except IOError as ioe:
sys.exit("\nError with principal coordinates file:{}\n".format(ioe))
try:
with open(args.mapping):
pass
except IOError as ioe:
sys.exit("\nError with mapping file:{}\n".format(ioe))
# check that the output dir exists, create it if not
util.ensure_dir(args.output_dir)
# load the BIOM table
biomtbl = biom.load_table(args.otu_table)
# Read unifrac principal coordinates file
unifrac = util.parse_unifrac(args.pcoa_fp)
# Read otu data file
otus = set()
with open(args.otu_ids_fp, "rU") as nciF:
for line in nciF.readlines():
line = line.strip()
otus.add(line)
# Gather categories from mapping file
header, imap = util.parse_map_file(args.mapping)
try:
category_idx = header.index(args.group_by)
except ValueError:
msg = "Error: Specified mapping category '{}' not found."
sys.exit(msg.format(args.group_by))
category_ids = util.gather_categories(imap, header, [args.group_by])
color_map = util.color_mapping(imap, header, args.group_by, args.colors)
rel_abd = bc.relative_abundance(biomtbl)
rel_abd = bc.arcsine_sqrt_transform(rel_abd)
# plot samples based on relative abundance of some OTU ID
for otuid in otus:
otuname = oc.otu_name(
biomtbl.metadata(otuid, axis="observation")["taxonomy"])
cat_data = {
cat: {
"pc1": [],
"pc2": [],
"size": []
}
for cat in category_ids
}
for sid in unifrac["pcd"]:
category = cat_data[imap[sid][category_idx]]
try:
size = rel_abd[sid][otuid] * args.scale_by
except KeyError as ke:
print("{} not found in {} sample.".format(ke, sid))
continue
category["pc1"].append(float(unifrac["pcd"][sid][0]))
category["pc2"].append(float(unifrac["pcd"][sid][1]))
category["size"].append(size)
if args.verbose:
print("Saving chart for {}".format(" ".join(otuname.split("_"))))
xr, yr = calculate_xy_range(cat_data)
plot_PCoA(cat_data, otuname, unifrac, color_map.keys(), color_map, xr,
yr, args.output_dir, args.save_as, args.ggplot2_style)
def main():
args = handle_program_options()
try:
with open(args.otu_table):
pass
except IOError as ioe:
sys.exit(
"\nError with OTU_Sample abundance data file:{}\n"
.format(ioe)
)
try:
with open(args.mapping):
pass
except IOError as ioe:
sys.exit(
"\nError with mapping file:{}\n"
.format(ioe)
)
# input data
biomf = biom.load_table(args.otu_table)
map_header, imap = util.parse_map_file(args.mapping)
# rewrite tree file with otu names
if args.input_tree:
with open(args.input_tree) as treF, open(args.output_tre, "w") as outF:
tree = treF.readline()
if "'" in tree:
tree = tree.replace("'", '')
outF.write(newick_replace_otuids(tree, biomf))
oid_rows = {id_: md["taxonomy"]
for val, id_, md in biomf.iter(axis="observation")}
# calculate analysis results
categories = None
if args.map_categories is not None:
categories = args.map_categories.split(",")
# set transform if --stabilize_variance is specfied
tform = bc.arcsine_sqrt_transform if args.stabilize_variance else None
groups = util.gather_categories(imap, map_header, categories)
for group in groups.values():
if args.analysis_metric in ["MRA", "NMRA"]:
results = bc.MRA(biomf, group.sids, transform=tform)
elif args.analysis_metric == "raw":
results = bc.transform_raw_abundance(biomf, sampleIDs=group.sids,
sample_abd=False)
group.results.update({oc.otu_name(oid_rows[oid]): results[oid]
for oid in results})
# write iTol data set file
with open(args.output_itol_table, "w") as itolF:
if args.analysis_metric == "raw":
itolF.write("DATASET_GRADIENT\nSEPARATOR TAB\n")
itolF.write("DATASET_LABEL\tLog Total Abundance\n")
itolF.write("COLOR\t#000000\n")
itolF.write("LEGEND_TITLE\tLog Total Abundance\n")
itolF.write("LEGEND_SHAPES\t1\n")
itolF.write("LEGEND_COLORS\t#000000\n")
itolF.write("LEGEND_LABELS\tLog Total Abundance\n")
itolF.write("COLOR_MIN\t#FFFFFF\n")
itolF.write("COLOR_MAX\t#000000\n")
else:
itolF.write("DATASET_MULTIBAR\nSEPARATOR TAB\n")
itolF.write("DATASET_LABEL\tNMRA\n")
itolF.write("FIELD_COLORS\t{}\n".format("\t".join(["#ff0000"
for _ in range(len(groups))])))
itolF.write("FIELD_LABELS\t" + "\t".join(groups.keys())+"\n")
itolF.write("LEGEND_TITLE\tNMRA\n")
itolF.write("LEGEND_SHAPES\t{}\n".format("\t".join(["1"
for _ in range(len(groups))])))
itolF.write("LEGEND_COLORS\t{}\n".format("\t".join(["#ff0000"
for _ in range(len(groups))])))
itolF.write("LEGEND_LABELS\t" + "\t".join(groups.keys())+"\n")
itolF.write("WIDTH\t300\n")
itolF.write("DATA\n")
all_otus = frozenset({oc.otu_name(md["taxonomy"])
for val, id_, md in
biomf.iter(axis="observation")})
for oname in all_otus:
row = ["{name}"] # \t{s:.2f}\t{ns:.2f}\n"
row_data = {"name": oname}
msum = 0
for name, group in groups.iteritems():
row.append("{{{}:.5f}}".format(name))
if oname in group.results:
row_data[name] = group.results[oname]
else:
row_data[name] = 0.0
msum += row_data[name]
# normalize avg relative abundance data
if args.analysis_metric == "NMRA" and msum > 0:
row_data.update({key: data/msum
for key, data in row_data.items()
if key != "name"})
itolF.write("\t".join(row).format(**row_data) + "\n")
def main():
args = handle_program_options()
try:
with open(args.otu_table):
pass
except IOError as ioe:
sys.exit("\nError with BIOM format file:{}\n".format(ioe))
try:
with open(args.pcoa_fp):
pass
except IOError as ioe:
sys.exit("\nError with principal coordinates file:{}\n".format(ioe))
try:
with open(args.mapping):
pass
except IOError as ioe:
sys.exit("\nError with mapping file:{}\n".format(ioe))
if not os.path.exists(args.output_dir):
try:
os.mkdir(args.output_dir)
except OSError as oe:
if os.errno == 2:
msg = ("One or more directories in the path provided for " +
"--output-dir ({}) do not exist. If you are specifying " +
"a new directory for output, please ensure all other " +
"directories in the path currently exist.")
sys.exit(msg.format(args.output_dir))
else:
msg = ("An error occurred trying to create the output " +
"directory ({}) with message: {}")
sys.exit(msg.format(args.output_dir, oe.strerror))
# load the BIOM table
biomtbl = biom.load_table(args.otu_table)
# Read unifrac principal coordinates file
unifrac = util.parse_unifrac(args.pcoa_fp)
# Read otu data file
otus = set()
with open(args.otu_ids_fp, "rU") as nciF:
for line in nciF.readlines():
line = line.strip()
otus.add(line)
# Gather categories from mapping file
header, imap = util.parse_map_file(args.mapping)
try:
category_idx = header.index(args.group_by)
except ValueError:
msg = "Error: Specified mapping category '{}' not found."
sys.exit(msg.format(args.group_by))
category_ids = util.gather_categories(imap, header, [args.group_by])
color_map = util.color_mapping(imap, header, args.group_by, args.colors)
rel_abd = get_relative_abundance(biomtbl)
# plot samples based on relative abundance of some OTU ID
for otuid in otus:
otuname = oc.otu_name(biomtbl.metadata(otuid, axis="observation")["taxonomy"])
cat_data = {cat: {"pc1": [], "pc2": [], "size": []}
for cat in category_ids}
for sid in unifrac["pcd"]:
category = cat_data[imap[sid][category_idx]]
try:
size = rel_abd[sid][otuid] * args.scale_by
except KeyError as ke:
print "{} not found in {} sample.".format(ke, sid)
continue
category["pc1"].append(float(unifrac["pcd"][sid][0]))
category["pc2"].append(float(unifrac["pcd"][sid][1]))
category["size"].append(size)
if args.verbose:
print "Saving chart for {}".format(" ".join(otuname.split("_")))
xr, yr = calculate_xy_range(cat_data)
plot_PCoA(cat_data, otuname, unifrac, color_map.keys(),
color_map, xr, yr, args.output_dir,
args.save_as, args.ggplot2_style)
def main():
args = handle_program_options()
try:
with open(args.otu_table):
pass
except IOError as ioe:
sys.exit("\nError with BIOM format file:{}\n".format(ioe))
try:
with open(args.pcoa_fp):
pass
except IOError as ioe:
sys.exit("\nError with principal coordinates file:{}\n".format(ioe))
try:
with open(args.mapping):
pass
except IOError as ioe:
sys.exit("\nError with mapping file:{}\n".format(ioe))
# check that the output dir exists, create it if not
util.ensure_dir(args.output_dir)
# load the BIOM table
biomtbl = biom.load_table(args.otu_table)
# Read unifrac principal coordinates file
unifrac = util.parse_unifrac(args.pcoa_fp)
# Read otu data file
otus = set()
with open(args.otu_ids_fp, "rU") as nciF:
for line in nciF.readlines():
line = line.strip()
otus.add(line)
# Gather categories from mapping file
header, imap = util.parse_map_file(args.mapping)
try:
category_idx = header.index(args.group_by)
except ValueError:
msg = "Error: Specified mapping category '{}' not found."
sys.exit(msg.format(args.group_by))
category_ids = util.gather_categories(imap, header, [args.group_by])
color_map = util.color_mapping(imap, header, args.group_by, args.colors)
rel_abd = bc.relative_abundance(biomtbl)
rel_abd = bc.arcsine_sqrt_transform(rel_abd)
# plot samples based on relative abundance of some OTU ID
for otuid in otus:
otuname = oc.otu_name(biomtbl.metadata(otuid, axis="observation")["taxonomy"])
cat_data = {cat: {"pc1": [], "pc2": [], "size": []}
for cat in category_ids}
for sid in unifrac["pcd"]:
category = cat_data[imap[sid][category_idx]]
try:
size = rel_abd[sid][otuid] * args.scale_by
except KeyError as ke:
print("{} not found in {} sample.".format(ke, sid))
continue
category["pc1"].append(float(unifrac["pcd"][sid][0]))
category["pc2"].append(float(unifrac["pcd"][sid][1]))
category["size"].append(size)
if args.verbose:
print("Saving chart for {}".format(" ".join(otuname.split("_"))))
xr, yr = calculate_xy_range(cat_data)
plot_PCoA(cat_data, otuname, unifrac, color_map.keys(),
color_map, xr, yr, args.output_dir,
args.save_as, args.ggplot2_style)
