def dump_inflated_elements(self):
dump_object(
Dumps.GO_Inflated,
(self.inflated_Laplacian,
self.inflated_idx2lbl,
self.inflated_lbl2idx,
self.binding_intensity))
def dump_inflated_elements(self):
dump_object(
Dumps.GO_Inflated,
(self.inflated_Laplacian,
self.inflated_idx2lbl,
self.inflated_lbl2idx,
self.binding_intensity))
def dump_core(self):
dump_object(
Dumps.GO_dump,
(self.UP2GO_Dict, self.GO2UP, self.SeedSet,
self.Reachable_nodes_dict, self.GO_Names, self.GO_Legacy_IDs,
self.rev_GO_IDs, self.All_GOs, self.GO2Num, self.Num2GO,
self.UP_Names, self.UPs_without_GO))
def dump_statics(self):
dump_object(
Dumps.GO_builder_stat,
(self.go_namespace_filter,
self.InitSet,
self.correction_factor,
self.ultraspec_cleaned,
self.ultraspec_lvl))
def dump_statics(self):
dump_object(
Dumps.GO_builder_stat,
(self.go_namespace_filter,
self.InitSet,
self.correction_factor,
self.ultraspec_cleaned,
self.ultraspec_lvl))
def dump_informativities(self):
dump_object(
Dumps.GO_Infos,
(self.UP2GO_Reachable_nodes,
self.GO2UP_Reachable_nodes,
self.UP2GO_step_Reachable_nodes,
self.GO2UP_step_Reachable_nodes,
self.GO2_Pure_Inf,
self.GO2_Weighted_Ent))
def dump_eigen(self):
"""
dumps self.adj_eigenvals and self.laplacian_matrix and writes them to csv
"""
write_to_csv(Dumps.eigen_VaMat, self.adj_eigenvals)
write_to_csv(Dumps.eigen_ConMat, self.cond_eigenvals)
dump_object(Dumps.val_eigen, (self.adj_eigenvals, self.adj_eigenvects))
dump_object(Dumps.cond_eigen,
(self.cond_eigenvals, self.cond_eigenvects))
def dump_informativities(self):
dump_object(
Dumps.GO_Infos,
(self.UP2GO_Reachable_nodes,
self.GO2UP_Reachable_nodes,
self.UP2GO_step_Reachable_nodes,
self.GO2UP_step_Reachable_nodes,
self.GO2_Pure_Inf,
self.GO2_Weighted_Ent))
def dump_memoized(self):
md5 = hashlib.md5(
json.dumps(
sorted(
self.analytic_uniprots),
sort_keys=True)).hexdigest()
payload = {
'UP_hash': md5, 'sys_hash': self.md5_hash(), 'size': len(
self.analytic_uniprots), 'UPs': pickle.dumps(
self.analytic_uniprots), 'currents': pickle.dumps(
(self.current_accumulator, self.node_current)), 'voltages': pickle.dumps(
self.uniprots_2_voltage_and_circulation)}
dump_object(Dumps.GO_Analysis_memoized, payload)
def dump_memoized(self):
md5 = hashlib.md5(
json.dumps(
sorted(
self.analytic_uniprots),
sort_keys=True)).hexdigest()
payload = {
'UP_hash': md5, 'sys_hash': self.md5_hash(), 'size': len(
self.analytic_uniprots), 'UPs': pickle.dumps(
self.analytic_uniprots), 'currents': pickle.dumps(
(self.current_accumulator, self.node_current)), 'voltages': pickle.dumps(
self.uniprots_2_voltage_and_circulation)}
dump_object(Dumps.GO_Analysis_memoized, payload)
def dump_core(self):
dump_object(
Dumps.GO_dump,
(self.UP2GO_Dict,
self.GO2UP,
self.SeedSet,
self.Reachable_nodes_dict,
self.GO_Names,
self.GO_Legacy_IDs,
self.rev_GO_IDs,
self.All_GOs,
self.GO2Num,
self.Num2GO,
self.UP_Names,
self.UPs_without_GO))
def run_analysis_suite(
rna_source,
no_of_experiments,
experimental_groups,
groups_to_compare,
count_filter_level=5,
false_discovery_rate=0.05):
"""
Imports counts table, runs test suite and stores the result of statistical analysis for further
computation. returns stored values to the standard output.
:param rna_source: the file from which the raw counts are to be read
:param no_of_experiments: number of experiments
:param experimental_groups: experiment groupings
:param groups_to_compare: groups to be compared
:param count_filter_level: minimum counts to run statistics
:param false_discovery_rate: desired false discovery rate
"""
names, lengths, counts = load_rna_counts_table(
rna_source, no_of_experiments)
_, _, names[:, 1] = db_io_routines.look_up_annotation_set(names[
:, 0].tolist())
filter_mask = counts_filter(
counts,
experimental_groups,
filter_level=count_filter_level)
names = names[filter_mask, :]
lengths = lengths[filter_mask, :]
counts = counts[filter_mask, :]
rpkms = convert_to_rpkm(lengths, counts)
testres = significantly_different_genes(
rpkms,
experimental_groups,
groups_to_compare,
false_discovery_rate)
filter_masks = [test_[1] for test_ in testres]
dump_object(Dumps.RNA_seq_counts_compare, filter_masks)
return filter_masks
def dump_maps(self):
"""
dumps all the elements required for the mapping between the types and ids
of database entries and matrix columns
"""
log.debug("pre-dump e_p_u_b_i length: %s",
len(self.entry_point_uniprots_bulbs_ids))
log.debug("dumping into: %s", Dumps.interactome_maps)
dump_object(
Dumps.interactome_maps,
(self.bulbs_id_2_matrix_index, self.matrix_index_2_bulbs_id,
self.bulbs_id_2_display_name, self.bulbs_id_2_legacy_id,
self.bulbs_id2_node_type, self.bulbs_id_2_localization,
self.reached_uniprots_bulbs_id_list,
self.all_uniprots_bulbs_id_list, self.Uniprot_attachments,
self.UP2Chrom, self.chromosomes_2_uniprot,
self.uniprot_matrix_index_list,
self.entry_point_uniprots_bulbs_ids
)) # TODO: delete here and below entry point u_b_i
def run_analysis_suite(rna_source,
no_of_experiments,
experimental_groups,
groups_to_compare,
count_filter_level=5,
false_discovery_rate=0.05):
"""
Imports counts table, runs test suite and stores the result of statistical analysis for further
computation. returns stored values to the standard output.
:param rna_source: the file from which the raw counts are to be read
:param no_of_experiments: number of experiments
:param experimental_groups: experiment groupings
:param groups_to_compare: groups to be compared
:param count_filter_level: minimum counts to run statistics
:param false_discovery_rate: desired false discovery rate
"""
names, lengths, counts = load_rna_counts_table(rna_source,
no_of_experiments)
_, _, names[:,
1] = db_io_routines.look_up_annotation_set(names[:,
0].tolist())
filter_mask = counts_filter(counts,
experimental_groups,
filter_level=count_filter_level)
names = names[filter_mask, :]
lengths = lengths[filter_mask, :]
counts = counts[filter_mask, :]
rpkms = convert_to_rpkm(lengths, counts)
testres = significantly_different_genes(rpkms, experimental_groups,
groups_to_compare,
false_discovery_rate)
filter_masks = [test_[1] for test_ in testres]
dump_object(Dumps.RNA_seq_counts_compare, filter_masks)
return filter_masks
def dump_independent_linear_sets(self):
dump_object(Dumps.GO_Indep_Linset, self.Indep_Lapl)
def dump_matrices(self):
"""
dumps self.adjacency_Matrix and self.laplacian_matrix
"""
dump_object(Dumps.interactome_adjacency_matrix, self.adjacency_Matrix)
dump_object(Dumps.interactome_laplacian_matrix, self.laplacian_matrix)
def dump_matrices(self):
dump_object(
Dumps.GO_Mats,
(self.adjacency_matrix,
self.dir_adj_matrix,
self.laplacian_matrix))
def dump_independent_linear_sets(self):
dump_object(Dumps.GO_Indep_Linset, self.Indep_Lapl)
def dump_matrices(self):
dump_object(
Dumps.GO_Mats,
(self.adjacency_matrix,
self.dir_adj_matrix,
self.laplacian_matrix))
