11/23/2019

AltAnalyze.py

@@ -1,5 +1,5 @@
 ###AltAnalyze
-#Copyright 2005-20019
+#Copyright 2005-2008 J. David Gladstone Institutes, San Francisco California
 #Author Nathan Salomonis - [email protected]
 
 #Permission is hereby granted, free of charge, to any person obtaining a copy 
@@ -5266,16 +5266,19 @@ def AltAnalyzeMain(expr_var,alt_var,goelite_var,additional_var,exp_file_location
   if use_direct_domain_alignments_only == 'direct-alignment': use_direct_domain_alignments_only = 'yes'
   if run_from_scratch == 'Process CEL files': expression_data_format = 'log'
   print "Beginning AltAnalyze Analysis... Format:", expression_data_format
-
 
   if array_type == 'RNASeq': id_name = 'exon/junction IDs'
   else: id_name = 'array IDs'
 
   print_items=[]; #print [permute_p_threshold]; sys.exit()
+  if 'array' in array_type:
+    dataType='Gene Expression'
+  else:
+    dataType=array_type
   print_items.append("AltAnalyze version 2.1.3 - Expression Analysis Parameters Being Used...")
   print_items.append('\t'+'database'+': '+unique.getCurrentGeneDatabaseVersion())
   print_items.append('\t'+'species'+': '+species)
-  print_items.append('\t'+'method'+': '+array_type)
+  print_items.append('\t'+'method'+': '+dataType)
   print_items.append('\t'+'manufacturer'+': '+manufacturer)
   print_items.append('\t'+'probability_statistic'+': '+probability_statistic)
   print_items.append('\t'+'constitutive_source'+': '+constitutive_source)
@@ -6985,6 +6988,7 @@ def commandLineRun():
             colorByGene=None
             separateGenePlots = False
             reimportModelScores = True
+            maskGroups = None
             if 't-SNE' in image_export:
                 pca_algorithm = 't-SNE'
             if 'UMAP' in image_export or 'umap' in image_export:
@@ -7001,6 +7005,7 @@ def commandLineRun():
                 if opt == '--algorithm': pca_algorithm=arg
                 if opt == '--geneSetName': geneSetName=arg
                 if opt == '--genes': colorByGene=arg
+                if opt == '--maskGroups': maskGroups=arg
                 if opt == '--reimportModelScores':
                     if arg == 'yes' or arg == 'True' or arg == 'true':
                         reimportModelScores = True
@@ -7023,7 +7028,9 @@ def commandLineRun():
             if input_file_dir==None:
                 print 'Please provide a valid file location for your input data matrix (must have an annotation row and an annotation column)';sys.exit()
             UI.performPCA(input_file_dir, include_labels, pca_algorithm, transpose, None,
-                          plotType=plotType, display=display, geneSetName=geneSetName, species=species, zscore=zscore, colorByGene=colorByGene, reimportModelScores=reimportModelScores, separateGenePlots=separateGenePlots)
+                          plotType=plotType, display=display, geneSetName=geneSetName, species=species, zscore=zscore,
+                          colorByGene=colorByGene, reimportModelScores=reimportModelScores, separateGenePlots=separateGenePlots,
+                          maskGroups=maskGroups)
             sys.exit()
 
         if 'VennDiagram' in image_export:

Config/source_data.txt

@@ -76,4 +76,4 @@ DEDb	De
 OTT	Ot	
 Symbol	Sy	
 KEGG_Enzyme	KEG	
-AltExon	Ae	
+AltExon	Ae	MOD

ExpressionBuilder.py

@@ -365,8 +365,6 @@ def simpleGroupImport(group_dir,splitHeaders=False, ignoreComps=False, reverseOr
         data = cleanUpLine(line)
         try: sample_filename,group_number,group_name = string.split(data,'\t')
         except Exception:
-            print group_dir
-            print data
             print traceback.format_exc()
             print "\nWARNING!!! Impropper groups file format detected. Terminating AltAnalyze. The groups file must have only three columns (sampleName, groupNumber, groupName).\n"
             forceGroupsError
@@ -4112,7 +4110,7 @@ def convertPSIJunctionIDsToPositions(psi_file,regulated_file):
     try: genesToExclude = excludeGenesImport(excludeGenes)
     except Exception: genesToExclude = {}
     print analysis
-    if array_type == 'RNASeq': 
+    if array_type == 'RNASeq':
         gene_exp_threshold = 50
         gene_rpkm_threshold = 3
     if analysis == 'matchAndCorrelate':

GO_Elite.py

@@ -2110,7 +2110,7 @@ def returnDirectoriesNoReplace(dir):
     dir_list = unique.returnDirectoriesNoReplace(dir); dir_list2 = []
     for entry in dir_list:
         if '.' not in entry: dir_list2.append(entry)
-    return dir_list2 
+    return dir_list2
 
 ###### Command Line Functions (AKA Headless Mode) ######
 def commandLineRun():
@@ -2243,7 +2243,7 @@ def commandLineRun():
 
     if len(resources)>1: resources_to_analyze = resources
     elif len(resources)>0: resources_to_analyze = resources[0]
-    
+
     species_full_original = species_full; species_code_original = species_code
     if image_export != None:
         if image_export == 'WikiPathways':
@@ -2753,8 +2753,11 @@ def commandLineRun():
         try:
             import UI
             species_dirs = UI.returnDirectoriesNoReplace('/Databases')
-        except Exception:
-            print '\nPlease install a species database (to install: python GO_Elite.py --update Official --species Hs --version EnsMart62Plus)';sys.exit()
+        except:
+            try:
+                species_dirs = UI.returnDirectoriesNoReplace('/AltDatabase')
+            except Exception:
+                print '\nPlease install a species database (to install: python GO_Elite.py --update Official --species Hs --version EnsMart62Plus)';sys.exit()
 
         print ''
         root = parent; runGOElite(mod)

InteractionBuilder.py

@@ -128,6 +128,7 @@ def importInteractionDatabases(interactionDirs):
                             except Exception: None
                     except Exception:
                         proceed = False
+
                 if proceed: ### If the interaction data conformed to one of the two above types (typically two valid interacting gene IDs)
                     if (len(ens_ls1)>0 and len(ens_ls2)>0):
                         secondary_proceed = True
@@ -218,7 +219,7 @@ def importInteractionDatabases(interactionDirs):
     ### Evaluate the most promiscous interactors (e.g., UBC)
     remove_list=[]
     for ID in interaction_db:
-        if len(interaction_db[ID])>2000:
+        if len(interaction_db[ID])>20000:
             remove_list.append(ID)
             #print len(interaction_db[ID]),ensembl_symbol_db[ID]
     for ID in remove_list:
@@ -364,7 +365,8 @@ def associateQueryGenesWithInteractions(query_db,query_interactions,dir_file):
     connections = 1
     primary=0
     secondary=0
-    terciary=0 
+    terciary=0
+
     for ensemblGene in query_db:
         if ensemblGene in interaction_db:
             for interacting_ensembl in interaction_db[ensemblGene]: