def enrichment_no_t_task( exp, block, T, gs, patterns, base_filename, ): if settings.CELERY_DEBUG: import sys sys.path.append( '/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg' ) import pydevd pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True) gene_set = gs.get_gs() patterns = patterns.get_gs() e = EnrichmentInGeneSets(patterns.genes) enrich = e.getModuleEnrichmentInGeneSets(patterns.genes, gene_set.genes, pval_threshold=T) enrich = dict( (mod, (genes, map(lambda x: (gene_set.description[x[0]], x[0], x[1]), terms))) for (mod, (genes, terms)) in enrich.items()) ds = DictionarySet(exp.get_data_folder(), base_filename) ds.store_dict(enrich) return [ds], {}
def threshold_task(exp, block, es, T, base_filename, ): # def removeTemporaryNegativeFeatures(S, indicator_string = 'negative_feature___'): # """Remove elements starting with the indicator_string and remove possible duplicates.""" # return S.apply(lambda list_element: set([s.replace(indicator_string, '') for s in list_element])) """Computes co-comodules from matrix H by given threshold T.""" if settings.CELERY_DEBUG: import sys sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg') import pydevd pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True) H = es.get_assay_data_frame() print(H) # mu = np.mean(H, axis = 1) # sigma = np.std(H, axis = 1) # Z = H.apply(lambda z: (z-mu)/sigma, axis = 0) # S = [] # S.append(removeTemporaryNegativeFeatures(Z.apply(lambda x: Z.columns[x >= T].tolist(), axis = 1))) # S = pd.DataFrame(S) # S = S.apply(lambda x: set.union(*x)) # result = pd.DataFrame(S) from wrappers.snmnmf.evaluation import EnrichmentInGeneSets z = 1 x = EnrichmentInGeneSets(z) result = x.getGeneSet(H, T) cs = ComoduleSet(exp.get_data_folder(), base_filename) cs.store_set(result) return [cs], {}
def threshold_task( exp, block, es, T, base_filename, ): # def removeTemporaryNegativeFeatures(S, indicator_string = 'negative_feature___'): # """Remove elements starting with the indicator_string and remove possible duplicates.""" # return S.apply(lambda list_element: set([s.replace(indicator_string, '') for s in list_element])) """Computes co-comodules from matrix H by given threshold T.""" if settings.CELERY_DEBUG: import sys sys.path.append( '/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg' ) import pydevd pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True) H = es.get_assay_data_frame() print(H) # mu = np.mean(H, axis = 1) # sigma = np.std(H, axis = 1) # Z = H.apply(lambda z: (z-mu)/sigma, axis = 0) # S = [] # S.append(removeTemporaryNegativeFeatures(Z.apply(lambda x: Z.columns[x >= T].tolist(), axis = 1))) # S = pd.DataFrame(S) # S = S.apply(lambda x: set.union(*x)) # result = pd.DataFrame(S) from wrappers.snmnmf.evaluation import EnrichmentInGeneSets z = 1 x = EnrichmentInGeneSets(z) result = x.getGeneSet(H, T) gene_sets = GeneSets(exp.get_data_folder(), base_filename) gs = GS(result, result) gene_sets.store_gs(gs) # cs = GeneSets(exp.get_data_folder(), base_filename) # cs.store_set(result) return [gene_sets], {}
def enrichment_no_t_task(exp, block, T, gs, cs, base_filename, ): if settings.CELERY_DEBUG: import sys sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg') import pydevd pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True) gene_set = gs.get_gs() cs = cs.load_set() e = EnrichmentInGeneSets(cs) enrich = e.getModuleEnrichmentInGeneSets(cs, gene_set.genes, pval_threshold=T) enrich = dict((mod, (genes, map(lambda x: (gene_set.description[x[0]], x[0], x[1]), terms))) for (mod, (genes, terms)) in enrich.items()) ds = DictionarySet(exp.get_data_folder(), base_filename) ds.store_dict(enrich) return [ds], {}
def enrichment_task(exp, block, gs, H2, T, base_filename, ): if settings.CELERY_DEBUG: import sys sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg') import pydevd pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True) gene_set = gs.get_gs() h2 = H2.get_assay_data_frame() e = EnrichmentInGeneSets(h2) ## compute enrichment in GO terms () enrich_bpGO = e.getEnrichmentInGeneSetsWithH(gene_set.genes, h2, T) # sort resultst accodring p-values # sorted_enrich_bpGO = sorted(enrich_bpGO.iteritems(), key=operator.itemgetter(1)) er_ratio = e.getEnrichmentRatioInGeneSetsWithH(gene_set.genes, h2, T, enrichment_threshold=0.05, N=10) enrich_bpGO['er_ratio'] = er_ratio ds = DictionarySet(exp.get_data_folder(), base_filename) ds.store_dict(enrich_bpGO) return [ds], {}