def between_correls(args):
"""TABLES MUST SORT SO THAT SAMPLES ARE IN THE SAME ORDER """
logger = general.Logger("SCNIC_log.txt")
logger["SCNIC analysis type"] = "between"
# correlation and p-value adjustment methods
correl_methods = {'spearman': spearmanr, 'pearson': pearsonr}
p_methods = {'bh': general.bh_adjust, 'bon': general.bonferroni_adjust}
correl_method = correl_methods[args.correl_method]
if args.p_adjust is not None:
p_adjust = p_methods[args.p_adjust]
else:
p_adjust = None
# load tables
table1 = load_table(args.table1)
table2 = load_table(args.table2)
logger["input table 1"] = args.table1
logger["input table 1"] = args.table2
table1 = table1.sort()
table2 = table2.sort()
if not np.array_equal(table1.ids(), table2.ids()):
raise ValueError("Tables have different sets of samples present")
# make new output directory and change to it
if args.output is not None:
os.makedirs(args.output)
os.chdir(args.output)
logger["output directory"] = args.output
# filter tables
if args.min_sample is not None:
table1 = general.filter_table(table1, args.min_sample)
metadata = general.get_metadata_from_table(table1)
table2 = general.filter_table(table2, args.min_sample)
metadata.update(general.get_metadata_from_table(table2))
else:
metadata = general.get_metadata_from_table(table1)
metadata.update(general.get_metadata_from_table(table2))
# make correlations
logger["correlation metric"] = args.correl_method
logger["p adjustment method"] = args.p_adjust
correls = between_correls_from_tables(table1, table2, correl_method)
correls.sort_values(correls.columns[-1], inplace=True)
correls.to_csv(open('correls.txt', 'w'), sep='\t', index=False)
# adjust p-values
correls['p_adj'] = p_adjust(correls['p'])
# make network
net = general.correls_to_net(correls, metadata=metadata, min_p=args.min_p, min_r=args.min_r)
logger["number of nodes"] = net.number_of_nodes()
logger["number of edges"] = net.number_of_edges()
nx.write_gml(net, 'crossnet.gml')
logger.output_log()
print '\a'
def make_modules_on_correlations(correlation_table: pd.DataFrame, feature_table: Table, min_r: float=.35) -> \
(Table, nx.Graph, pd.Series):
modules = ma.make_modules_naive(correlation_table, min_r=min_r)
modules_rev = {asv: module for module, asvs in modules.items() for asv in asvs}
for asv in feature_table.ids(axis='observation'):
if asv not in modules_rev:
modules_rev[asv] = None
module_membership = pd.Series(modules_rev)
coll_table = ma.collapse_modules(feature_table, modules)
metadata = get_metadata_from_table(feature_table)
metadata = ma.add_modules_to_metadata(modules, metadata)
correlation_table_filtered = filter_correls(correlation_table, conet=True, min_r=min_r)
net = correls_to_net(correlation_table_filtered, metadata=metadata)
return coll_table, net, module_membership
def test_get_metadata_from_table(biom_table2):
metadata = get_metadata_from_table(biom_table2)
assert isinstance(metadata, dict)
def module_maker(args):
logger = general.Logger("SCNIC_module_log.txt")
logger["SCNIC analysis type"] = "module"
# read in correlations file
correls = pd.read_table(args.input,
index_col=(0, 1),
sep='\t',
dtype={
'feature1': str,
'feature2': str
})
logger["input correls"] = args.input
if args.verbose:
print("correls.txt read")
# sanity check args
if args.min_r is not None and args.min_p is not None:
raise ValueError(
"arguments min_p and min_r may not be used concurrently")
if args.min_r is None and args.min_p is None:
raise ValueError("argument min_p or min_r must be used")
# read in correlations file and make distance matrix
if args.min_r is not None:
min_dist = ma.cor_to_dist(args.min_r)
logger["minimum r value"] = args.min_r
cor, labels = ma.correls_to_cor(correls)
dist = ma.cor_to_dist(cor)
elif args.min_p is not None:
# TODO: This
raise NotImplementedError()
else:
raise ValueError("this is prevented above")
# read in biom table if given
if args.table is not None:
table = load_table(args.table)
logger["input uncollapsed table"] = args.table
if args.verbose:
print("otu table read")
# make new output directory and change to it
if args.output is not None:
if not os.path.isdir(args.output):
os.makedirs(args.output)
os.chdir(args.output)
logger["output directory"] = os.getcwd()
# make modules
modules = ma.make_modules(dist, min_dist, obs_ids=labels)
logger["number of modules created"] = len(modules)
if args.verbose:
print("Modules Formed")
print("number of modules: %s" % len(modules))
print("number of observations in modules: %s" %
np.sum([len(i) for i in modules]))
print("")
ma.write_modules_to_file(modules)
# collapse modules
if args.table is not None:
coll_table = ma.collapse_modules(table, modules)
ma.write_modules_to_dir(table, modules)
logger["number of observations in output table"] = coll_table.shape[0]
if args.verbose:
print("Table Collapsed")
print("collapsed Table Observations: " + str(coll_table.shape[0]))
print("")
with biom_open('collapsed.biom', 'w') as f:
coll_table.to_hdf5(f, 'make_modules.py')
# make network
if args.table is not None:
metadata = general.get_metadata_from_table(table)
else:
metadata = defaultdict(dict)
metadata = ma.add_modules_to_metadata(modules, metadata)
correls_filter = general.filter_correls(correls,
conet=True,
min_p=args.min_p,
min_r=args.min_r)
net = general.correls_to_net(correls_filter, metadata=metadata)
nx.write_gml(net, 'correlation_network.gml')
if args.verbose:
print("Network Generated")
print("number of nodes: %s" % str(net.number_of_nodes()))
print("number of edges: %s" % str(net.number_of_edges()))
logger["number of nodes"] = net.number_of_nodes()
logger["number of edges"] = net.number_of_edges()
logger.output_log()
def between_correls(args):
"""TABLES MUST SORT SO THAT SAMPLES ARE IN THE SAME ORDER """
logger = general.Logger("SCNIC_log.txt")
logger["SCNIC analysis type"] = "between"
# correlation and p-value adjustment methods
correl_methods = {'spearman': spearmanr, 'pearson': pearsonr}
correl_method = correl_methods[args.correl_method]
# load tables
table1 = load_table(args.table1)
table2 = load_table(args.table2)
logger["input table 1"] = args.table1
logger["input table 1"] = args.table2
table1 = table1.sort()
table2 = table2.sort()
# make new output directory and change to it
if args.force and args.output is not None:
shutil.rmtree(args.output, ignore_errors=True)
if args.output is not None:
os.makedirs(args.output)
os.chdir(args.output)
logger["output directory"] = args.output
# filter tables
if args.sparcc_filter is True:
table1 = general.sparcc_paper_filter(table1)
table2 = general.sparcc_paper_filter(table2)
print("Table 1 filtered: %s observations" % str(table1.shape[0]))
print("Table 2 filtered: %s observations" % str(table2.shape[0]))
logger["sparcc paper filter"] = True
logger["number of observations present in table 1 after filter"] = table1.shape[0]
logger["number of observations present in table 2 after filter"] = table2.shape[0]
if args.min_sample is not None:
table1 = general.filter_table(table1, args.min_sample)
table2 = general.filter_table(table2, args.min_sample)
if not np.array_equal(table1.ids(), table2.ids()):
raise ValueError("Tables have different sets of samples present")
metadata = general.get_metadata_from_table(table1)
metadata.update(general.get_metadata_from_table(table2))
# make correlations
logger["correlation metric"] = args.correl_method
logger["p adjustment method"] = args.p_adjust
correls = ca.between_correls_from_tables(table1, table2, correl_method, nprocs=args.procs)
correls.sort_values(correls.columns[-1], inplace=True)
correls['p_adj'] = general.p_adjust(correls['p'])
correls.to_csv(open('correls.txt', 'w'), sep='\t', index=True)
# make network
correls_filt = general.filter_correls(correls, min_p=args.min_p, min_r=args.min_r)
net = general.correls_to_net(correls_filt, metadata=metadata)
logger["number of nodes"] = net.number_of_nodes()
logger["number of edges"] = net.number_of_edges()
nx.write_gml(net, 'crossnet.gml')
logger.output_log()
def within_correls(input_loc, output_loc, correl_method='sparcc', sparcc_filter=False, min_sample=None, procs=1,
sparcc_p=1000, p_adjust='fdr_bh', verbose=False):
logger = general.Logger(path.join(output_loc, "SCNIC_within_log.txt"))
logger["SCNIC analysis type"] = "within"
# correlation and p-value adjustment methods
correl_methods = {'spearman': spearmanr, 'pearson': pearsonr, 'kendall': kendalltau, 'sparcc': 'sparcc'}
correl_method = correl_methods[correl_method.lower()]
# get features to be correlated
table = load_table(input_loc)
logger["input table"] = input_loc
if verbose:
print("Table loaded: " + str(table.shape[0]) + " observations")
print("")
logger["number of samples in input table"] = table.shape[1]
logger["number of observations in input table"] = table.shape[0]
# make new output directory
if output_loc is not None:
if not path.isdir(output_loc):
os.makedirs(output_loc)
logger["output directory"] = path.abspath(output_loc)
# filter
if sparcc_filter is True:
table_filt = general.sparcc_paper_filter(table)
if verbose:
print("Table filtered: %s observations" % str(table_filt.shape[0]))
print("")
logger["sparcc paper filter"] = True
logger["number of observations present after filter"] = table_filt.shape[0]
elif min_sample is not None:
table_filt = general.filter_table(table, min_sample)
if verbose:
print("Table filtered: %s observations" % str(table_filt.shape[0]))
print("")
logger["min samples present"] = min_sample
logger["number of observations present after filter"] = table_filt.shape[0]
else:
table_filt = table
logger["number of processors used"] = procs
# correlate features
if correl_method in [spearmanr, pearsonr, kendalltau]:
# calculate correlations
if verbose:
print("Correlating with %s" % correl_method)
# correlate feature
correls = ca.calculate_correlations(table_filt, correl_method, nprocs=procs, p_adjust_method=p_adjust)
elif correl_method == 'sparcc':
if sparcc_p is None:
correls = ca.fastspar_correlation(table_filt, verbose=verbose, nprocs=procs)
else:
correls = ca.fastspar_correlation(table_filt, calc_pvalues=True, bootstraps=sparcc_p,
verbose=verbose, nprocs=procs, p_adjust_method=p_adjust)
else:
raise ValueError("How did this even happen?")
logger["distance metric used"] = correl_method
if verbose:
print("Features Correlated")
print("")
correls.to_csv(path.join(output_loc, 'correls.txt'), sep='\t', index_label=('feature1', 'feature2'))
if verbose:
print("Correls.txt written")
# make correlation network
metadata = general.get_metadata_from_table(table_filt)
net = general.correls_to_net(correls, metadata=metadata)
nx.write_gml(net, path.join(output_loc, 'correlation_network.gml'))
if verbose:
print("Network made")
print("")
logger.output_log()
def within_correls(args):
logger = general.Logger("SCNIC_within_log.txt")
logger["SCNIC analysis type"] = "within"
# correlation and p-value adjustment methods
correl_methods = {'spearman': spearmanr, 'pearson': pearsonr, 'kendall': kendalltau, 'sparcc': 'sparcc'}
correl_method = correl_methods[args.correl_method.lower()]
# get features to be correlated
table = load_table(args.input)
logger["input table"] = args.input
if args.verbose:
print("Table loaded: " + str(table.shape[0]) + " observations")
print("")
logger["number of samples in input table"] = table.shape[1]
logger["number of observations in input table"] = table.shape[0]
# make new output directory and change to it
if args.output is not None:
if not os.path.isdir(args.output):
os.makedirs(args.output)
os.chdir(args.output)
logger["output directory"] = os.getcwd()
# filter
if args.sparcc_filter is True:
table_filt = general.sparcc_paper_filter(table)
if args.verbose:
print("Table filtered: %s observations" % str(table_filt.shape[0]))
print("")
logger["sparcc paper filter"] = True
logger["number of observations present after filter"] = table_filt.shape[0]
elif args.min_sample is not None:
table_filt = general.filter_table(table, args.min_sample)
if args.verbose:
print("Table filtered: %s observations" % str(table_filt.shape[0]))
print("")
logger["min samples present"] = args.min_sample
logger["number of observations present after filter"] = table_filt.shape[0]
else:
table_filt = table
logger["number of processors used"] = args.procs
# correlate features
if correl_method in [spearmanr, pearsonr, kendalltau]:
# calculate correlations
if args.verbose:
print("Correlating with %s" % args.correl_method)
# correlate feature
correls = ca.calculate_correlations(table_filt, correl_method)
elif correl_method == 'sparcc':
correls = ca.fastspar_correlation(table_filt, verbose=args.verbose)
if args.sparcc_p is not None:
raise NotImplementedError() # TODO: reimplement with fastspar
else:
raise ValueError("How did this even happen?")
logger["distance metric used"] = args.correl_method
if args.verbose:
print("Features Correlated")
print("")
if 'p' in correls.columns:
correls['p_adj'] = general.p_adjust(correls['p'])
correls.to_csv('correls.txt', sep='\t', index_label=('feature1', 'feature2'))
if args.verbose:
print("Correls.txt written")
# make correlation network
metadata = general.get_metadata_from_table(table_filt)
net = general.correls_to_net(correls, metadata=metadata)
nx.write_gml(net, 'correlation_network.gml')
if args.verbose:
print("Network made")
print("")
logger.output_log()
def module_maker(input_loc, output_loc, min_p=None, min_r=None, method='naive', k_size=3, gamma=.4, table_loc=None,
prefix='module', verbose=False):
logger = general.Logger(path.join(output_loc, "SCNIC_module_log.txt"))
logger["SCNIC analysis type"] = "module"
# read in correlations file
correls = pd.read_csv(input_loc, index_col=(0, 1), sep='\t')
correls.index = pd.MultiIndex.from_tuples([(str(id1), str(id2)) for id1, id2 in correls.index])
logger["input correls"] = input_loc
if verbose:
print("correls.txt read")
# sanity check args
if min_r is not None and min_p is not None:
raise ValueError("arguments min_p and min_r may not be used concurrently")
if min_r is None and min_p is None:
raise ValueError("argument min_p or min_r must be used")
# make new output directory and change to it
if output_loc is not None:
if not path.isdir(output_loc):
os.makedirs(output_loc)
logger["output directory"] = path.abspath(output_loc)
# make modules
if method == 'naive':
modules = ma.make_modules_naive(correls, min_r, min_p, prefix=prefix)
elif method == 'k_cliques':
modules = ma.make_modules_k_cliques(correls, min_r, min_p, k_size, prefix=prefix)
elif method == 'louvain':
modules = ma.make_modules_louvain(correls, min_r, min_p, gamma, prefix=prefix)
else:
raise ValueError('%s is not a valid module picking method' % method)
logger["number of modules created"] = len(modules)
if verbose:
print("Modules Formed")
print("number of modules: %s" % len(modules))
print("number of observations in modules: %s" % np.sum([len(i) for i in modules]))
print("")
ma.write_modules_to_file(modules, path_str=path.join(output_loc, 'modules.txt'))
# collapse modules
if table_loc is not None:
table = load_table(table_loc)
logger["input uncollapsed table"] = table_loc
if verbose:
print("otu table read")
coll_table = ma.collapse_modules(table, modules)
# ma.write_modules_to_dir(table, modules)
logger["number of observations in output table"] = coll_table.shape[0]
if verbose:
print("Table Collapsed")
print("collapsed Table Observations: " + str(coll_table.shape[0]))
print("")
with biom_open(path.join(output_loc, 'collapsed.biom'), 'w') as f:
coll_table.to_hdf5(f, 'make_modules.py')
metadata = general.get_metadata_from_table(table)
else:
metadata = defaultdict(dict)
# make network
metadata = ma.add_modules_to_metadata(modules, metadata)
correls_filter = general.filter_correls(correls, conet=True, min_p=min_p, min_r=min_r)
net = general.correls_to_net(correls_filter, metadata=metadata)
nx.write_gml(net, path.join(output_loc, 'correlation_network.gml'))
if verbose:
print("Network Generated")
print("number of nodes: %s" % str(net.number_of_nodes()))
print("number of edges: %s" % str(net.number_of_edges()))
logger["number of nodes"] = net.number_of_nodes()
logger["number of edges"] = net.number_of_edges()
logger.output_log()
def test_get_metadata_from_table(biom_table1):
metadata = get_metadata_from_table(biom_table1)
assert type(metadata) is dict