def run_enrichment(self, args):
self._check_enrichment(args)
enrichment = Enrichment()
enrichment.enrichment_pipeline( # Input options
args.annotate_output,
args.annotation_matrix,
args.gff_files,
args.metadata,
args.abundance,
args.abundance_metadata,
args.transcriptome,
args.transcriptome_metadata,
# Runtime options
args.pval_cutoff,
args.proportions_cutoff,
args.threshold,
args.multi_test_correction,
args.batchfile,
args.processes,
args.allow_negative_values,
args.ko,
args.pfam,
args.tigrfam,
args.cluster,
args.ortholog,
args.cazy,
args.ec,
args.ko_hmm,
args.range,
args.subblock_size,
args.operon_mismatch_cutoff,
args.operon_match_score_cutoff,
# Outputs
args.output)
def test_check_annotation_type(self):
pfam = ['PF10117']
self.assertEqual(Enrichment().check_annotation_type(pfam),
Enrichment.PFAM)
cazy = ['GH42']
self.assertEqual(Enrichment().check_annotation_type(cazy),
Enrichment.CAZY)
tigrfam = ['TIGR00008']
self.assertEqual(Enrichment().check_annotation_type(tigrfam),
Enrichment.TIGRFAM)
ko = ['K00399']
self.assertEqual(Enrichment().check_annotation_type(ko),
Enrichment.KEGG)
ec = ['1.2.3.4']
self.assertEqual(Enrichment().check_annotation_type(ec), Enrichment.EC)
def run_enrichm(self, args, command):
'''
Parameters
----------
Output
------
'''
self._check_general(args)
self._logging_setup(args)
logging.info("Command: %s" % ' '.join(command))
logging.info("Running the %s pipeline" % args.subparser_name)
if args.subparser_name == self.DATA:
d = Data()
d.do(args.uninstall, args.dry)
if args.subparser_name == self.ANNOTATE:
self._check_annotate(args)
annotate = Annotate(# Define inputs and outputs
args.output,
# Define type of annotation to be carried out
args.ko, args.ko_hmm, args.pfam, args.tigrfam,
args.clusters, args.orthologs, args.cazy,
args.ec,
# Cutoffs
args.evalue, args.bit, args.id, args.aln_query,
args.aln_reference, args.c, args.cut_ga,
args.cut_nc, args.cut_tc, args.cut_ko,
args.inflation, args.chunk_number, args.chunk_max,
args.count_domains,
# Parameters
args.threads, args.parallel, args.suffix, args.light)
annotate.annotate_pipeline(args.genome_directory,
args.protein_directory,
args.genome_files,
args.protein_files)
elif args.subparser_name == self.CLASSIFY:
self._check_classify(args)
classify = Classify()
classify.classify_pipeline(args.custom_modules, args.cutoff, args.aggregate,
args.genome_and_annotation_matrix, args.output)
elif args.subparser_name == self.ENRICHMENT:
self._check_enrichment(args)
enrichment = Enrichment()
enrichment.enrichment_pipeline(# Input options
args.annotate_output, args.annotation_matrix,
args.metadata, args.abundance, args.abundance_metadata,
args.transcriptome, args.transcriptome_metadata,
# Runtime options
args.pval_cutoff, args.proportions_cutoff,
args.threshold, args.multi_test_correction,
args.batchfile, args.processes,
args.allow_negative_values, args.ko, args.pfam,
args.tigrfam, args.cluster, args.ortholog, args.cazy,
args.ec, args.ko_hmm,
# Outputs
args.output)
elif(args.subparser_name == NetworkAnalyser.PATHWAY or
args.subparser_name == NetworkAnalyser.EXPLORE):
self._check_network(args)
network_analyser=NetworkAnalyser()
network_analyser.network_pipeline(args.subparser_name, args.matrix,
args.genome_metadata, args.tpm_values,
args.tpm_metadata, args.abundance,
args.abundance_metadata, args.metabolome,
args.enrichment_output, args.depth, args.filter,
args.limit, args.queries, args.output)
if args.subparser_name == self.PREDICT:
self._check_predict(args)
predict = Predict()
predict.predict_pipeline(args.forester_model_directory,
args.input_matrix,
args.output)
elif args.subparser_name == self.GENERATE:
self._check_generate(args)
generate_model = GenerateModel()
generate_model.generate_pipeline(args.input_matrix,
args.groups,
args.model_type,
args.testing_portion,
args.grid_search,
args.threads,
args.output)
elif args.subparser_name == self.USES:
self._check_uses(args)
uses = Uses()
uses.uses_pipeline(args.compounds_list,
args.annotation_matrix,
args.metadata,
args.output,
args.count)
logging.info('Finished running EnrichM')
def main(self, args, command):
'''
Parameters
----------
Output
------
'''
self._check_general(args)
self._logging_setup(args)
logging.info("Running command: %s" % ' '.join(command))
if args.subparser_name == self.DATA:
d = Data()
d.do(args.uninstall)
if args.subparser_name == self.ANNOTATE:
self._check_annotate(args)
a = Annotate(# Define inputs and outputs
args.output,
# Define type of annotation to be carried out
args.ko,
args.pfam,
args.tigrfam,
args.hypothetical,
args.cazy,
# Cutoffs
args.evalue,
args.bit,
args.id,
args.aln_query,
args.aln_reference,
args.c,
args.cut_ga,
args.cut_nc,
args.cut_tc,
args.inflation,
args.chunk_number,
args.chunk_max,
# Parameters
args.threads,
args.parallel,
args.suffix,
args.light)
a.do(args.genome_directory,
args.protein_directory,
args.genome_files,
args.protein_files)
elif args.subparser_name == self.CLASSIFY:
self._check_classify(args)
c = Classify()
c.do(args.custom_modules,
args.cutoff,
args.genome_and_annotation_file,
args.genome_and_annotation_matrix,
args.output)
elif args.subparser_name == self.ENRICHMENT:
self._check_enrichment(args)
e = Enrichment()
e.do(# Input options
args.annotate_output,
args.metadata,
args.modules,
args.abundances,
# Runtime options
args.genomes_to_compare_with_group,
args.pval_cutoff,
args.proportions_cutoff,
args.threshold,
args.multi_test_correction,
args.batchfile,
args.processes,
args.ko,
args.pfam,
args.tigrfam,
args.hypothetical,
args.cazy,
# Outputs
args.output)
elif args.subparser_name == self.CONNECT:
self._check_connect(args)
c = Connect()
c.do(args.annotate_output,
args.metadata,
args.custom_modules,
args.cutoff,
args.output)
elif(args.subparser_name == NetworkAnalyser.PATHWAY or
args.subparser_name == NetworkAnalyser.EXPLORE or
args.subparser_name == NetworkAnalyser.TRAVERSE):
self._check_network(args)
na=NetworkAnalyser(args.metadata)
na.do(args.matrix,
args.transcriptome,
args.metabolome,
args.depth,
args.filter,
args.limit,
args.queries,
args.subparser_name,
args.starting_compounds,
args.steps,
args.number_of_queries,
args.output)
if args.subparser_name == self.PREDICT:
self._check_predict(args)
p = Predict()
p.do(args.forester_model_directory,
args.input_matrix,
args.output)
elif args.subparser_name == self.GENERATE:
self._check_generate(args)
gm = GenerateModel()
gm.do(args.input_matrix,
args.groups,
args.model_type,
args.testing_portion,
args.grid_search,
args.threads,
args.output)
logging.info('Done!')
class Tests(unittest.TestCase):
genome_annotation_simple_example = {
"genome_1": {
"K00001": 1,
"K00002": 2
},
"genome_2": {
"K00003": 1
},
"genome_3": {
"K00001": 5,
"K00002": 4,
"K00003": 5
}
}
genome_groups_simple_example = {
"group_1": ["genome_1"],
"group_2": ["genome_2", "genome_3"]
}
sample_abundance = {
"sample_1": {
"genome_1": 1.0,
"genome_2": 0.5,
"genome_3": 3.0
},
"sample_2": {
"genome_1": 0.5,
"genome_2": 1.2,
"genome_3": 5.0
},
"sample_3": {
"genome_1": 0.1,
"genome_2": 1.1,
"genome_3": 6.0
},
"sample_4": {
"genome_1": 5.0,
"genome_2": 5.2,
"genome_3": 0.2
},
"sample_5": {
"genome_1": 6.0,
"genome_2": 4.9,
"genome_3": 0.1
},
"sample_6": {
"genome_1": 7.0,
"genome_2": 5.0,
"genome_3": 0.0
}
}
sample_groups = {
"sample_group_1": ["sample_1", "sample_2", "sample_3"],
"sample_group_2": ["sample_4", "sample_5", "sample_6"]
}
genomes = ["genome_1", "genome_2", "genome_3"]
annotations = ["K00001", "K00002", "K00003"]
enrichment_test_object = Enrichment()
def test_check_annotation_type(self):
pfam = ['PF10117']
self.assertEqual(Enrichment().check_annotation_type(pfam),
Enrichment.PFAM)
cazy = ['GH42']
self.assertEqual(Enrichment().check_annotation_type(cazy),
Enrichment.CAZY)
tigrfam = ['TIGR00008']
self.assertEqual(Enrichment().check_annotation_type(tigrfam),
Enrichment.TIGRFAM)
ko = ['K00399']
self.assertEqual(Enrichment().check_annotation_type(ko),
Enrichment.KEGG)
ec = ['1.2.3.4']
self.assertEqual(Enrichment().check_annotation_type(ec), Enrichment.EC)
def test_calculate_portions(self):
expected = [['Annotation', 'group_1', 'group_2'],
['K00001', '1.0', '0.5'], ['K00002', '1.0', '0.5'],
['K00003', '0.0', '1.0']]
result = self.enrichment_test_object.calculate_portions(
self.annotations, self.genome_groups_simple_example,
self.genome_annotation_simple_example, self.genomes, 1)
self.assertEqual(result, expected)
def test_enrichment_from_ko_matrix(self):
tmp = tempfile.mkdtemp()
expected_output = os.path.join(path_to_data, 'enrichm_enrichment_ko')
metadata = os.path.join(path_to_data, 'metadata.tsv')
cmd = '%s enrichment --annotate_output %s --metadata %s --output %s --force --ko --verbosity 1' \
% (path_to_script, path_to_annotate, metadata, tmp)
subprocess.call(cmd, shell=True)
self.assertTrue(filecmp.dircmp(tmp, expected_output))
# The pvalues are never exact - cannot compare files directly
#for file in os.listdir(tmp):
# if file == 'enrichment.log': continue
# output_file = os.path.join(tmp, file)
# expected_file = os.path.join(expected_output, file)
# self.assertTrue(filecmp.cmp(output_file, expected_file))
def test_enrichment_from_pfam_matrix(self):
tmp = tempfile.mkdtemp()
expected_output = os.path.join(path_to_data, 'enrichm_enrichment_pfam')
metadata = os.path.join(path_to_data, 'metadata.tsv')
cmd = '%s enrichment --annotate_output %s --metadata %s --output %s --force --pfam --verbosity 1' \
% (path_to_script, path_to_annotate, metadata, tmp)
subprocess.call(cmd, shell=True)
self.assertTrue(filecmp.dircmp(tmp, expected_output))
# The pvalues are never exact - cannot compare files directly
#for file in os.listdir(tmp):
# if file == 'enrichment.log': continue
# output_file = os.path.join(tmp, file)
# expected_file = os.path.join(expected_output, file)
# self.assertTrue(filecmp.cmp(output_file, expected_file))
def test_weight_annotation_matrix(self):
expected = {
'sample_group_1': {
'K00001': [16.0, 25.5, 30.1],
'K00002': [14.0, 21.0, 24.2],
'K00003': [15.5, 26.2, 31.1]
},
'sample_group_2': {
'K00001': [6.0, 6.5, 7.0],
'K00002': [10.8, 12.4, 14.0],
'K00003': [6.2, 5.4, 5.0]
}
}
result = self.enrichment_test_object.weight_annotation_matrix(
self.sample_abundance, self.genome_annotation_simple_example,
self.sample_groups, self.annotations)
self.assertEqual(result, expected)