diff --git a/AltAnalyze.py b/AltAnalyze.py
index d5e6ebd..c662560 100755
--- a/AltAnalyze.py
+++ b/AltAnalyze.py
@@ -6351,7 +6351,7 @@ def commandLineRun():
                                                          'fold=','performDiffExp=','centerMethod=', 'k=','bamdir=',
                                                          'downsample=','query=','referenceFull=', 'maskGroups=',
                                                          'elite_dir=','numGenesExp=','numVarGenes=','accessoryAnalyses=',
-                                                         'dataFormat=','geneTPM=','markerPearsonCutoff='])
+                                                         'dataFormat=','geneTPM=','markerPearsonCutoff=', 'additionalAnalyses='])
     except Exception:
         print traceback.format_exc()
         print "There is an error in the supplied command-line arguments (each flag requires an argument)"; sys.exit()
@@ -6452,7 +6452,7 @@ def commandLineRun():
             compendiumType=arg
         elif opt == '--denom':
             denom_file_dir=arg ### Indicates that GO-Elite is run independent from AltAnalyze itself
-        elif opt == '--accessoryAnalysis' or opt == '--accessoryAnalyses':
+        elif opt == '--accessoryAnalysis' or opt == '--accessoryAnalyses' or opt == '--additionalAnalyses':
             accessoryAnalysis = arg
         elif opt == '--channelToExtract': channel_to_extract=arg
         elif opt == '--genesToReport': genesToReport = int(arg)
@@ -6541,6 +6541,7 @@ def commandLineRun():
 
     ######## Perform analyses independent from AltAnalyze database centric analyses that require additional parameters
     if len(image_export) > 0 or len(accessoryAnalysis)>0 or runICGS:
+        ### python AltAnalyze.py --accessoryAnalysis annotateICGS --elite_dir path --groupdir path
         """ Annotate existing ICGS groups with selected GO-Elite results """
         if 'annotateICGS' in accessoryAnalysis:
             for opt, arg in options: ### Accept user input for these hierarchical clustering variables
diff --git a/Config/species.txt b/Config/species.txt
index 67efc9d..e66490d 100755
--- a/Config/species.txt
+++ b/Config/species.txt
@@ -1,20 +1,70 @@
-species_code	species_name	compatible_algorithms
-Hs	Homo sapiens	
-At	Arabidopsis thaliana	
-Ma	Macaca mulatta	
-Ce	Caenorhabditis elegans	
-Cf	Canis familiaris	
-Bt	Bos taurus	
-Mm	Mus musculus	
-Rn	Rattus norvegicus	
-Xl	Xenopus laevis	
-Gg	Gallus gallus	
-Nc	Neurospora crassa	
-Ac	Anolis carolinensis	
-Dm	Drosophila melanogaster	
-Xl	Test	
-Zm	Zea mays	
-Sc	Saccharomyces cerevisiae	
-Pn	Papio anubis
-Ma	Macaca mulatta
-	
+species_code	species_name	compatible_algorithms
+Hs	Homo sapiens	ASPIRE|splicing_index|MiDAS
+Mm	Mus musculus	ASPIRE|linearregres|splicing_index|MiDAS
+Nc	Neurospora crassa	ASPIRE|splicing_index|MiDAS
+Rn	Rattus norvegicus	ASPIRE|splicing_index|MiDAS
+Pn	Papio anubis	ASPIRE|splicing_index|MiDAS
+Ac	Anolis carolinensis	ASPIRE|splicing_index|MiDAS
+Ag	Anopheles gambiae	ASPIRE|splicing_index|MiDAS
+At	Arabidopsis thaliana	ASPIRE|splicing_index|MiDAS
+Am	Ailuropoda melanoleuca	ASPIRE|splicing_index|MiDAS
+Bt	Bos taurus	ASPIRE|splicing_index|MiDAS
+Ce	Caenorhabditis elegans	ASPIRE|splicing_index|MiDAS
+Cf	Canis familiaris	ASPIRE|splicing_index|MiDAS
+Ch	Choloepus hoffmanni	ASPIRE|splicing_index|MiDAS
+Ci	Ciona intestinalis	ASPIRE|splicing_index|MiDAS
+Cj	Callithrix jacchus	ASPIRE|splicing_index|MiDAS
+Cp	Cavia porcellus	ASPIRE|splicing_index|MiDAS
+Cs	Ciona savignyi	ASPIRE|splicing_index|MiDAS
+Dm	Drosophila melanogaster	ASPIRE|splicing_index|MiDAS
+Dn	Dasypus novemcinctus	ASPIRE|splicing_index|MiDAS
+Do	Dipodomys ordii	ASPIRE|splicing_index|MiDAS
+Dr	Danio rerio	ASPIRE|splicing_index|MiDAS
+Ec	Equus caballus	ASPIRE|splicing_index|MiDAS
+Ee	Erinaceus europaeus	ASPIRE|splicing_index|MiDAS
+Et	Echinops telfairi	ASPIRE|splicing_index|MiDAS
+Fc	Felis catus	ASPIRE|splicing_index|MiDAS
+Ga	Gasterosteus aculeatus	ASPIRE|splicing_index|MiDAS
+Gg	Gallus gallus	ASPIRE|splicing_index|MiDAS
+Gm	Glycine max	ASPIRE|splicing_index|MiDAS
+Go	Gorilla gorilla	ASPIRE|splicing_index|MiDAS
+Hv	Hordeum vulgare	ASPIRE|splicing_index|MiDAS
+La	Loxodonta africana	ASPIRE|splicing_index|MiDAS
+Ma	Macaca mulatta	ASPIRE|splicing_index|MiDAS
+Md	Monodelphis domestica	ASPIRE|splicing_index|MiDAS
+Me	Macropus eugenii	ASPIRE|splicing_index|MiDAS
+Mi	Microcebus murinus	ASPIRE|splicing_index|MiDAS
+Ml	Myotis lucifugus	ASPIRE|splicing_index|MiDAS
+Mg	Meleagris gallopavo	ASPIRE|splicing_index|MiDAS
+Oa	Ornithorhynchus anatinus	ASPIRE|splicing_index|MiDAS
+Oc	Oryctolagus cuniculus	ASPIRE|splicing_index|MiDAS
+Og	Otolemur garnettii	ASPIRE|splicing_index|MiDAS
+Ol	Oryzias latipes	ASPIRE|splicing_index|MiDAS
+Op	Ochotona princeps	ASPIRE|splicing_index|MiDAS
+Os	Oryza sativa	ASPIRE|splicing_index|MiDAS
+Pa	Pseudomonas aeruginosa	ASPIRE|splicing_index|MiDAS
+Pc	Procavia capensis	ASPIRE|splicing_index|MiDAS
+Pf	Plasmodium falciparum	ASPIRE|splicing_index|MiDAS
+Pb	Pongo abelii	ASPIRE|splicing_index|MiDAS
+Po	Populus tremula	ASPIRE|splicing_index|MiDAS
+Pp	Pongo pygmaeus	ASPIRE|splicing_index|MiDAS
+Pt	Pan troglodytes	ASPIRE|splicing_index|MiDAS
+Pv	Pteropus vampyrus	ASPIRE|splicing_index|MiDAS
+Sa	Sorex araneus	ASPIRE|splicing_index|MiDAS
+Sc	Saccharomyces cerevisiae	ASPIRE|splicing_index|MiDAS
+Sl	Solanum lycopersicum	ASPIRE|splicing_index|MiDAS
+Ss	Sus scrofa	ASPIRE|splicing_index|MiDAS
+St	Spermophilus tridecemlineatus	ASPIRE|splicing_index|MiDAS
+Su	Staphylococcus aureus	ASPIRE|splicing_index|MiDAS
+Ta	Triticum aestivum	ASPIRE|splicing_index|MiDAS
+Tb	Tupaia belangeri	ASPIRE|splicing_index|MiDAS
+Tg	Taeniopygia guttata	ASPIRE|splicing_index|MiDAS
+Tn	Tetraodon nigroviridis	ASPIRE|splicing_index|MiDAS
+Tr	Takifugu rubripes	ASPIRE|splicing_index|MiDAS
+Ts	Tarsius syrichta	ASPIRE|splicing_index|MiDAS
+Tt	Tursiops truncatus	ASPIRE|splicing_index|MiDAS
+Vp	Vicugna pacos	ASPIRE|splicing_index|MiDAS
+Vv	Vitis vinifera	ASPIRE|splicing_index|MiDAS
+Xl	Xenopus laevis	ASPIRE|splicing_index|MiDAS
+Xt	Xenopus tropicalis	ASPIRE|splicing_index|MiDAS
+Zm	Zea mays	ASPIRE|splicing_index|MiDAS
\ No newline at end of file
diff --git a/Config/species_archive.txt b/Config/species_archive.txt
index a5c25c2..e66490d 100755
--- a/Config/species_archive.txt
+++ b/Config/species_archive.txt
@@ -1,7 +1,70 @@
 species_code	species_name	compatible_algorithms
-Hs	Homo sapiens	splicing_index|MiDAS
-Mm	Mus musculus	ASPIRE|linearregres|splicing_index|MiDAS
-Nc	Neurospora crassa	ASPIRE|linearregres|splicing_index|MiDAS
-Rn	Rattus norvegicus	splicing_index|MiDAS
-Pn	Papio anubis	ASPIRE|linearregres|splicing_index|MiDAS
-
+Hs	Homo sapiens	ASPIRE|splicing_index|MiDAS
+Mm	Mus musculus	ASPIRE|linearregres|splicing_index|MiDAS
+Nc	Neurospora crassa	ASPIRE|splicing_index|MiDAS
+Rn	Rattus norvegicus	ASPIRE|splicing_index|MiDAS
+Pn	Papio anubis	ASPIRE|splicing_index|MiDAS
+Ac	Anolis carolinensis	ASPIRE|splicing_index|MiDAS
+Ag	Anopheles gambiae	ASPIRE|splicing_index|MiDAS
+At	Arabidopsis thaliana	ASPIRE|splicing_index|MiDAS
+Am	Ailuropoda melanoleuca	ASPIRE|splicing_index|MiDAS
+Bt	Bos taurus	ASPIRE|splicing_index|MiDAS
+Ce	Caenorhabditis elegans	ASPIRE|splicing_index|MiDAS
+Cf	Canis familiaris	ASPIRE|splicing_index|MiDAS
+Ch	Choloepus hoffmanni	ASPIRE|splicing_index|MiDAS
+Ci	Ciona intestinalis	ASPIRE|splicing_index|MiDAS
+Cj	Callithrix jacchus	ASPIRE|splicing_index|MiDAS
+Cp	Cavia porcellus	ASPIRE|splicing_index|MiDAS
+Cs	Ciona savignyi	ASPIRE|splicing_index|MiDAS
+Dm	Drosophila melanogaster	ASPIRE|splicing_index|MiDAS
+Dn	Dasypus novemcinctus	ASPIRE|splicing_index|MiDAS
+Do	Dipodomys ordii	ASPIRE|splicing_index|MiDAS
+Dr	Danio rerio	ASPIRE|splicing_index|MiDAS
+Ec	Equus caballus	ASPIRE|splicing_index|MiDAS
+Ee	Erinaceus europaeus	ASPIRE|splicing_index|MiDAS
+Et	Echinops telfairi	ASPIRE|splicing_index|MiDAS
+Fc	Felis catus	ASPIRE|splicing_index|MiDAS
+Ga	Gasterosteus aculeatus	ASPIRE|splicing_index|MiDAS
+Gg	Gallus gallus	ASPIRE|splicing_index|MiDAS
+Gm	Glycine max	ASPIRE|splicing_index|MiDAS
+Go	Gorilla gorilla	ASPIRE|splicing_index|MiDAS
+Hv	Hordeum vulgare	ASPIRE|splicing_index|MiDAS
+La	Loxodonta africana	ASPIRE|splicing_index|MiDAS
+Ma	Macaca mulatta	ASPIRE|splicing_index|MiDAS
+Md	Monodelphis domestica	ASPIRE|splicing_index|MiDAS
+Me	Macropus eugenii	ASPIRE|splicing_index|MiDAS
+Mi	Microcebus murinus	ASPIRE|splicing_index|MiDAS
+Ml	Myotis lucifugus	ASPIRE|splicing_index|MiDAS
+Mg	Meleagris gallopavo	ASPIRE|splicing_index|MiDAS
+Oa	Ornithorhynchus anatinus	ASPIRE|splicing_index|MiDAS
+Oc	Oryctolagus cuniculus	ASPIRE|splicing_index|MiDAS
+Og	Otolemur garnettii	ASPIRE|splicing_index|MiDAS
+Ol	Oryzias latipes	ASPIRE|splicing_index|MiDAS
+Op	Ochotona princeps	ASPIRE|splicing_index|MiDAS
+Os	Oryza sativa	ASPIRE|splicing_index|MiDAS
+Pa	Pseudomonas aeruginosa	ASPIRE|splicing_index|MiDAS
+Pc	Procavia capensis	ASPIRE|splicing_index|MiDAS
+Pf	Plasmodium falciparum	ASPIRE|splicing_index|MiDAS
+Pb	Pongo abelii	ASPIRE|splicing_index|MiDAS
+Po	Populus tremula	ASPIRE|splicing_index|MiDAS
+Pp	Pongo pygmaeus	ASPIRE|splicing_index|MiDAS
+Pt	Pan troglodytes	ASPIRE|splicing_index|MiDAS
+Pv	Pteropus vampyrus	ASPIRE|splicing_index|MiDAS
+Sa	Sorex araneus	ASPIRE|splicing_index|MiDAS
+Sc	Saccharomyces cerevisiae	ASPIRE|splicing_index|MiDAS
+Sl	Solanum lycopersicum	ASPIRE|splicing_index|MiDAS
+Ss	Sus scrofa	ASPIRE|splicing_index|MiDAS
+St	Spermophilus tridecemlineatus	ASPIRE|splicing_index|MiDAS
+Su	Staphylococcus aureus	ASPIRE|splicing_index|MiDAS
+Ta	Triticum aestivum	ASPIRE|splicing_index|MiDAS
+Tb	Tupaia belangeri	ASPIRE|splicing_index|MiDAS
+Tg	Taeniopygia guttata	ASPIRE|splicing_index|MiDAS
+Tn	Tetraodon nigroviridis	ASPIRE|splicing_index|MiDAS
+Tr	Takifugu rubripes	ASPIRE|splicing_index|MiDAS
+Ts	Tarsius syrichta	ASPIRE|splicing_index|MiDAS
+Tt	Tursiops truncatus	ASPIRE|splicing_index|MiDAS
+Vp	Vicugna pacos	ASPIRE|splicing_index|MiDAS
+Vv	Vitis vinifera	ASPIRE|splicing_index|MiDAS
+Xl	Xenopus laevis	ASPIRE|splicing_index|MiDAS
+Xt	Xenopus tropicalis	ASPIRE|splicing_index|MiDAS
+Zm	Zea mays	ASPIRE|splicing_index|MiDAS
\ No newline at end of file
diff --git a/ExpressionBuilder.py b/ExpressionBuilder.py
index 182cd16..da4e694 100644
--- a/ExpressionBuilder.py
+++ b/ExpressionBuilder.py
@@ -212,16 +212,20 @@ def calculate_expression_measures(expr_input_dir,expr_group_dir,experiment_name,
                         log_fold = math.log((float(fold)+increment),2) ### changed from - log_fold = math.log((float(fold)+1),2) - version 2.05
                         fold_data3.append(log_fold)
                     except ValueError:  ###Not an ideal situation: Value is negative - Convert to zero
-                        if float(fold)<=0:
-                            log_fold = math.log(1.01,2); fold_data3.append(log_fold)
-                        else:
+                        try:
+                            if float(fold)<=0:
+                                log_fold = math.log(1.01,2); fold_data3.append(log_fold)
+                            else:
+                                fold_data3.append('')
+                                blanksPresent = True
+                                """
+                                print_out = 'WARNING!!! The ID'+arrayid+ 'has an invalid expression value:'+fold+'\n. Correct and re-run'
+                                try: UI.WarningWindow(print_out,'Critical Error - Exiting Program!!!'); sys.exit()
+                                except NameError: print print_out; sys.exit()
+                                """
+                        except:
                             fold_data3.append('')
                             blanksPresent = True
-                            """
-                            print_out = 'WARNING!!! The ID'+arrayid+ 'has an invalid expression value:'+fold+'\n. Correct and re-run'
-                            try: UI.WarningWindow(print_out,'Critical Error - Exiting Program!!!'); sys.exit()
-                            except NameError: print print_out; sys.exit()
-                            """
                 fold_data2 = fold_data3
             if (array_type == "AltMouse"):
                 if arrayid in probeset_db: array_folds[arrayid] = fold_data2; y = y+1
diff --git a/LineageProfilerIterate.py b/LineageProfilerIterate.py
index 5ced401..d62f3e6 100755
--- a/LineageProfilerIterate.py
+++ b/LineageProfilerIterate.py
@@ -2841,7 +2841,8 @@ def importAndCombineExpressionFiles(species,reference_exp_file,query_exp_file,cl
             if ':' in sample:
                 sample_alt = string.split(sample,':')[1]
             try: cluster = classified_samples[sample]
-            except: cluster = classified_samples[sample_alt]
+            except:
+                cluster = classified_samples[sample_alt]
             column_clusters.append(cluster)
          
     """ Combine the two datasets, before re-ordering """
diff --git a/UI.py b/UI.py
index a3492fb..da28b73 100755
--- a/UI.py
+++ b/UI.py
@@ -2628,6 +2628,10 @@ def runPredictGroups(self,reportOnly=False):
         gsp.setNormalize('median')
         try: gsp.setCountsNormalization(fl.CountsNormalization())
         except: pass
+        try:
+            downsample = int(self.Results()['downsample'])
+            gsp.setDownsample(downsample)
+        except: pass
         gsp.setSampleDiscoveryParameters(ExpressionCutoff,CountsCutoff,FoldDiff,SamplesDiffering,dynamicCorrelation,
             removeOutliers,featurestoEvaluate,restrictBy,excludeCellCycle,column_metric,column_method,rho_cutoff)
         self._user_variables['gsp'] = gsp
@@ -3106,7 +3110,7 @@ def __init__(self, user_variables):
     def Results(self): return self._user_variables
         
 def getSpeciesList(vendor):
-    try: current_species_dirs = unique.read_directory('/AltDatabase') 
+    try: current_species_dirs = unique.read_directory('/AltDatabase')
     except Exception: ### Occurs when the version file gets over-written with a bad directory name
         try:
             ### Remove the version file and wipe the species file
diff --git a/build_scripts/EnsemblSQL.py b/build_scripts/EnsemblSQL.py
index b615869..1d95471 100755
--- a/build_scripts/EnsemblSQL.py
+++ b/build_scripts/EnsemblSQL.py
@@ -1359,7 +1359,7 @@ def getEnsemblVersions(ftp_server,subdir):
     ftp.dir(data.append); ftp.quit()
     for line in data:
         line = string.split(line,' '); file_dir = line[-1]
-        if 'release' in file_dir and '/' not in file_dir:
+        if 'release' in file_dir and '/' not in file_dir and 'release' not in file_dir:
             version_number = int(string.replace(file_dir,'release-',''))
             if version_number>46: ###Before this version, the SQL FTP folder structure differed substantially
                 ensembl_versions.append(file_dir)
diff --git a/build_scripts/GeneSetDownloader.py b/build_scripts/GeneSetDownloader.py
index a4d2179..8c05e31 100644
--- a/build_scripts/GeneSetDownloader.py
+++ b/build_scripts/GeneSetDownloader.py
@@ -1269,11 +1269,14 @@ def buildAccessoryPathwayDatabases(selected_species,additional_resources,force):
         except Exception:
             #print traceback.format_exc()
             print 'BioGRID import failed (cause unknown)'
+    """
+    ### Now requires a license to use - only use the prior version
     if 'DrugBank' in additional_resources:
         try: importDrugBank(selected_species,force)
         except Exception: print 'Drug Bank import failed (cause unknown)'
     try: exportBioTypes(selected_species)
     except Exception: pass
+    """
 
 def importExistingGeneTermRelationships(fn,new_term_to_gene):
     """ Import the existing relationships and augment with the new """
diff --git a/download.py b/download.py
index b566f1c..1771095 100755
--- a/download.py
+++ b/download.py
@@ -27,6 +27,7 @@
 import unique
 import string
 import export
+import traceback
 
 def filepath(filename):
     fn = unique.filepath(filename)
@@ -84,7 +85,7 @@ def unzipFiles(filename,dir):
 def download(url,dir,file_type):
     try: dp = download_protocol(url,dir,file_type); gz_filepath, status  = dp.getStatus()
     except Exception:
-        gz_filepath='failed'; status = "Internet connection was not established. Re-establsih and try again."
+        gz_filepath='failed'; status = "Internet connection was not established. Re-establish and try again."
 
     if status == 'remove':
         #print "\nRemoving zip file:",gz_filepath
@@ -103,16 +104,28 @@ def __init__(self,url,dir,file_type):
         print "Downloading the following file:",filename,' ',
         self.original_increment = 10
         self.increment = 0
-        import urllib
+        import urllib,urllib2
         from urllib import urlretrieve
         try:
             try: webfile, msg = urlretrieve(url,output_filepath,reporthook=self.reporthookFunction)
-            except IOError:
+            except:
                 if 'Binary' in traceback.format_exc(): #IOError: [Errno ftp error] 200 Switching to Binary mode.
                     ### https://bugs.python.org/issue1067702 - some machines the socket doesn't close and causes an error - reload to close the socket
                     reload(urllib)
                     webfile, msg = urlretrieve(url,output_filepath,reporthook=self.reporthookFunction)
                     reload(urllib)
+                if 'SSL' in traceback.format_exc():
+                    ### SSL error encountered for the target website
+                    #https://github.com/NagiosEnterprises/ncpa/issues/195
+                    import urllib2, ssl
+                    try:
+                        _create_unverified_https_context = ssl._create_unverified_context
+                    except AttributeError:
+                        # Legacy Python that doesn't verify HTTPS certificates by default
+                        pass
+                    ssl._create_default_https_context = _create_unverified_https_context
+                    print '...downloading (be patient)'
+                    webfile, msg = urlretrieve(url,output_filepath)
         except:
             print 'Unknown URL error encountered...'; forceURLError
         print ''
@@ -228,5 +241,8 @@ def decompressZipStackOverflow(zip_file,dir):
     src.close()
 
 if __name__ == '__main__':
-    dp = download_protocol('http://may2009.archive.ensembl.org/biomart/martresults/136?file=martquery_1117221814_599.txt.gz','downloaded','')
+    path = 'http://thebiogrid.org/downloads/archives/Latest%20Release/BIOGRID-ALL-LATEST.tab2.zip'
+    #import urllib
+    #path = urllib.quote(path)
+    dp = download_protocol(path,'downloaded/','')
     
\ No newline at end of file
diff --git a/import_scripts/sampleIndexSelection.py b/import_scripts/sampleIndexSelection.py
index 88468d7..14df7dc 100755
--- a/import_scripts/sampleIndexSelection.py
+++ b/import_scripts/sampleIndexSelection.py
@@ -162,7 +162,10 @@ def filterFile(input_file,output_file,filter_names,force=False,calculateCentroid
             if len(comparisons)>0:
                 fold_matrix=[]
                 for (group2, group1) in comparisons:
-                    fold = means[group2]-means[group1]
+                    try: fold = means[group2]-means[group1]
+                    except:
+                        ### Indicates a missing value - exclude
+                        fold = 0
                     fold_matrix.append(str(fold))
                 filtered_values = fold_matrix
         ########################  End Centroid Calculation  ########################
@@ -443,7 +446,10 @@ def transposeMatrix(input_file):
     eo = export.ExportFile(input_file[:-4]+'-transposed.txt')
     for line in open(input_file,'rU').xreadlines():
         data = cleanUpLine(line)
-        values = string.split(data,'\t')
+        if '.csv' in input_file:
+            values = string.split(data,',')
+        else:
+            values = string.split(data,'\t')
         arrays.append(values)
     t_arrays = zip(*arrays)
     for t in t_arrays:
diff --git a/markerFinder.py b/markerFinder.py
index 3268093..e519f34 100755
--- a/markerFinder.py
+++ b/markerFinder.py
@@ -421,7 +421,7 @@ def generateMarkerHeatMaps(fl,platform,convertNonLogToLog=False,graphics=[],Spec
             reload(clustering)
             try:
                 graphics = clustering.runHCexplicit(custom_path, graphics, row_method, row_metric,
-                                    column_method, column_metric, color_gradient, gsp, contrast=4, display=False)
+                                    column_method, column_metric, color_gradient, gsp, contrast=5, display=False)
             except Exception:
                 print traceback.format_exc()
                 print 'Error occured in generated MarkerGene clusters... see ExpressionOutput/MarkerFinder files.'
diff --git a/stats_scripts/ICGS_NMF.py b/stats_scripts/ICGS_NMF.py
index deb2c08..ba15794 100644
--- a/stats_scripts/ICGS_NMF.py
+++ b/stats_scripts/ICGS_NMF.py
@@ -412,7 +412,7 @@ def PageRankSampling(inputfile,downsample_cutoff):
             diclst[i]=ind
            # diclst[i]=ind.tolist()[0]
         
-        print "creating graphs"
+        print "creating graphs...",
         G=nx.from_dict_of_lists(diclst)
         #nx.write_adjlist(G,"test.adjlist")
         #G=nx.read_adjlist("test.adjlist")
@@ -1045,7 +1045,7 @@ def CompleteICGSWorkflow(root_dir,processedInputExpFile,EventAnnot,iteration,rho
         Guidefile=graphic_links3[-1][-1]
         Guidefile=Guidefile[:-4]+'.txt'
     else:
-        Guidefile="/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/CITE-Seq_mLSK-60ADT/mLSKTA-soupX-0.1/AltAnalyze/ExpressionInput/amplify/DataPlots/Clustering-exp.10X_filtered_matrix_counts-filtered_CPTT-log2-VarGenes-PageRank-downsampled-Guide3-hierarchical_cosine_correlation.txt"
+        Guidefile="/Users/saljh8/Desktop/dataAnalysis/Collaborative/Harinder/D21-D35-PC-5p/forICGS/Euclidean/ICGS/Clustering-exp.D21-D35-PageRank-downsampled-Guide3-hierarchical_euclidean_correlation.txt"
 
     rho_cutoff=0.2
     try:
@@ -1446,10 +1446,26 @@ def runICGS_NMF(inputExpFile,scaling,platform,species,gsp,enrichmentInput='',dyn
                 ### Use dispersion (variance by mean) to define post-Louvain selected cell variable genes
                 inputExpFileVariableGenesDir,n=hgvfinder(inputExpFileScaled,numVarGenes=numVarGenes) ### returns filtered expression file with 500 variable genes
                 ### Run PageRank on the Louvain/dispersion downsampled dataset
-                sampmark=PageRankSampling(inputExpFileVariableGenesDir,downsample_cutoff)
+                """ PageRank can fail at neighbours=list(G.adj[key1]) when the downsample threshold is too low """
+                while PageRankCompleted == False:
+                    try:
+                        sampmark=PageRankSampling(inputExpFileVariableGenesDir,downsample_cutoff)
+                        PageRankCompleted = True
+                    except:
+                        downsample_cutoff+=1000
+                        print 'PageRank encountered an error... increasing cells to downsample to', downsample_cutoff
             else:
                 ### Directly run PageRank on the initial dispersion based dataset
-                sampmark=PageRankSampling(inputExpFileVariableGenesDir,downsample_cutoff)
+                PageRankCompleted = False
+                """ PageRank can fail at neighbours=list(G.adj[key1]) when the downsample threshold is too low """
+                while PageRankCompleted == False:
+                    try:
+                        sampmark=PageRankSampling(inputExpFileVariableGenesDir,downsample_cutoff)
+                        PageRankCompleted = True
+                    except:
+                        #print traceback.format_exc()
+                        downsample_cutoff+=1000
+                        print 'PageRank encountered an error... increasing cells to downsample to', downsample_cutoff
            
             ### Write out final downsampled results to a new file
             output_dir = root_dir+'/ExpressionInput'
@@ -1472,7 +1488,7 @@ def runICGS_NMF(inputExpFile,scaling,platform,species,gsp,enrichmentInput='',dyn
             else: processedInputExpFile = inputExpFile
     else:
         ### Re-run using a prior produced ICGS2 result
-        processedInputExpFile = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/CITE-Seq_mLSK-60ADT/mLSKTA-soupX-0.1/AltAnalyze/ExpressionInput/exp.10X_filtered_matrix_counts-filtered_CPTT-log2-VarGenes-PageRank-downsampled.txt'
+        processedInputExpFile = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Harinder/D21-D35-PC-5p/forICGS/Euclidean/ExpressionInput/exp.D21-D35-PageRank-downsampled.txt'
 
     flag=True
     iteration=1 ### Always equal to 1 for scRNA-Seq but can increment for splice-ICGS
diff --git a/stats_scripts/LineageSeqAnalysis.py b/stats_scripts/LineageSeqAnalysis.py
new file mode 100644
index 0000000..68d6e56
--- /dev/null
+++ b/stats_scripts/LineageSeqAnalysis.py
@@ -0,0 +1,100 @@
+import sys,string,os
+sys.path.insert(1, os.path.join(sys.path[0], '..')) ### import parent dir dependencies
+import export
+import unique
+import traceback
+
+""" Intersecting Coordinate Files """
+
+def cleanUpLine(line):
+    line = string.replace(line,'\n','')
+    line = string.replace(line,'\c','')
+    data = string.replace(line,'\r','')
+    data = string.replace(data,'"','')
+    return data
+
+def importLookupTable(fn):
+    """ Import a gRNA to valid tag lookup table """
+    lookup_table = []
+    for line in open(fn,'rU').xreadlines():
+        data = cleanUpLine(line)
+        t = string.split(data,'\t')
+        gRNA,tag = t
+        lookup_table.append((gRNA,tag))
+    return lookup_table
+  
+def importCountMatrix(fn,mask=False): 
+    """ Import a count matrix """
+    classification = {}
+    firstRow = True
+    for line in open(fn,'rU').xreadlines():
+        data = cleanUpLine(line)
+        t = string.split(data,'\t')
+        if firstRow:
+            headers = t[1:]
+            firstRow = False
+        else:
+            barcode = t[0]
+            values = map(int,t[1:])
+            if mask:
+                sum_counts = sum(values[2:])
+            else:
+                sum_counts = sum(values)
+            def threshold(val):
+                if val>0.3: return 1
+                else: return 0
+
+            if sum_counts>0:
+                ratios = map(lambda x: (1.000*x)/sum_counts, values)
+                if mask:
+                    original_ratios = ratios
+                    ratios = ratios[2:] ### mask the first two controls which are saturating
+                else:
+                    original_ratios = ratios
+                hits = map(lambda x: threshold(x), ratios)
+                hits = sum(hits)
+                if sum_counts>20 and hits == 1:
+                    index=0
+                    for ratio in ratios:
+                        if ratio>0.3:
+                            header = headers[index]
+                        index+=1
+                    classification[barcode] = header
+    print len(classification),fn
+    return classification
+
+def exportGuideToTags(lookup_table,gRNA_barcode,tag_barcode,output):
+    export_object = open(output,'w')
+    for barcode in gRNA_barcode:
+        gRNA = gRNA_barcode[barcode]
+        if barcode in tag_barcode:
+            tag = tag_barcode[barcode]
+            if (gRNA,tag) in lookup_table:
+                uid = tag+'__'+gRNA
+                export_object.write(barcode+'\t'+uid+'\t'+uid+'\n')
+    export_object.close()
+                        
+if __name__ == '__main__':
+    ################  Comand-line arguments ################
+    import getopt
+
+    if len(sys.argv[1:])<=1:  ### Indicates that there are insufficient number of command-line arguments
+        print 'WARNING!!!! Too commands supplied.'
+        
+    else:
+        options, remainder = getopt.getopt(sys.argv[1:],'', ['species=','gRNA=', 'tag=', 'lookup=','output='])
+        #print sys.argv[1:]
+        for opt, arg in options:
+            if opt == '--gRNA':
+                gRNA = arg
+            elif opt == '--tag':
+                tag = arg
+            elif opt == '--lookup':
+                lookup = arg
+            elif opt == '--output':
+                output = arg
+                
+    lookup_table = importLookupTable(lookup)
+    gRNA_barcode = importCountMatrix(gRNA)
+    tag_barcode = importCountMatrix(tag)
+    exportGuideToTags(lookup_table,gRNA_barcode,tag_barcode,output)
diff --git a/stats_scripts/metaDataAnalysis.py b/stats_scripts/metaDataAnalysis.py
index 090fd48..0fe56bc 100755
--- a/stats_scripts/metaDataAnalysis.py
+++ b/stats_scripts/metaDataAnalysis.py
@@ -1731,7 +1731,7 @@ def compareDomainComposition(folder):
     expression_file = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/BreastCancerDemo/FASTQs/all/AltResults/AlternativeOutput/Hs_RNASeq_top_alt_junctions-PSI_EventAnnotation.txt'
     groups_file = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/BreastCancerDemo/FASTQs/all/ExpressionInput/groups.test.txt'
     computed_results_dir = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/BreastCancerDemo/FASTQs/all/ExpressionInput/comps.test.txt'
-    #exportUpDownGenes('/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/cellHarmony-evaluation/HCA-alignment/DEGs');sys.exit()
+    #exportUpDownGenes('/Users/saljh8/Dropbox/Salomonis-Lab/Students/Erica/Van-Galen_Healthy-Filtered/cellHarmony-results/Gran/cellHarmony/DifferentialExpression_Fold_1.2_rawp_0.05');sys.exit()
     #remoteAnalysis(species,expression_file,groups_file,platform='PSI',log_fold_cutoff=0.1,use_adjusted_pval=True,pvalThreshold=0.05,exportHeatmap=True);sys.exit()
     #compareDomainComposition(computed_results_dir)
     ################  Comand-line arguments ################
diff --git a/stats_scripts/multiLineagePredict.py b/stats_scripts/multiLineagePrediction.py
old mode 100755
new mode 100644
similarity index 92%
rename from stats_scripts/multiLineagePredict.py
rename to stats_scripts/multiLineagePrediction.py
index d4630c3..d4605e7
--- a/stats_scripts/multiLineagePredict.py
+++ b/stats_scripts/multiLineagePrediction.py
@@ -57,7 +57,6 @@ def importGeneLists(fn):
     
     def importMarkerFinderHits(fn):
         genes={}
-        genes_to_symbol={}
         ICGS_State_ranked={}
         skip=True
         for line in open(fn,'rU').xreadlines():
@@ -68,9 +67,8 @@ def importMarkerFinderHits(fn):
                     gene,symbol,rho,ICGS_State = string.split(data,'\t')
                 except Exception:
                     gene,symbol,rho,rho_p,ICGS_State = string.split(data,'\t')
-                genes_to_symbol[gene]=symbol
                 #if ICGS_State!=state and float(rho)>0.0:
-                if float(rho)>0.3:
+                if float(rho)>0.15:
                     try: ICGS_State_ranked[ICGS_State].append([float(rho),gene,symbol])
                     except Exception: ICGS_State_ranked[ICGS_State] = [[float(rho),gene,symbol]]
 
@@ -81,15 +79,14 @@ def importMarkerFinderHits(fn):
             for (rho,gene,symbol) in ICGS_State_ranked[ICGS_State][:50]:
                 genes[gene]=rho,ICGS_State ### Retain all population specific genes (lax)
                 genes[symbol]=rho,ICGS_State
-                
-        return genes, genes_to_symbol
+        return genes
     
     def importQueryDataset(fn):
         matrix, column_header, row_header, dataset_name, group_db = clustering.importData(fn)
         return matrix, column_header, row_header, dataset_name, group_db
     
     signatureGenes = importGeneLists(SignatureGenes)
-    markerFinderGenes, genes_to_symbol = importMarkerFinderHits(MarkerFinder)
+    markerFinderGenes = importMarkerFinderHits(MarkerFinder)
     #print len(signatureGenes),len(markerFinderGenes)
 
     ### Determine for each gene, its population frequency per cell state
@@ -134,8 +131,6 @@ def freqCheck(x):
                                 rho, ICGS_State = markerFinderGenes[gene]
                             else:
                                 rho, ICGS_Cell_State = markerFinderGenes[gene] #ICGS_Cell_State
-                            #try: gene = genes_to_symbol[gene]
-                            #except: gene = gene
                             score = int(rho*100*state_frq)*(float(rank)/len(all_states_frq))
                             try: expressedGenesPerState[ICGS_State].append((score,gene))
                             except Exception: expressedGenesPerState[ICGS_State]=[(score,gene)] #(rank*multilin_frq)
@@ -184,7 +179,6 @@ def getBinary(x):
                         else:
                             binaryValues = map(lambda x: getBinary(x), matrix[row_index])
                             values = binaryValues
-                            #values = matrix[row_index]
                         #if gene[1]=='S100a8': print binaryValues;sys.exit()
                         try: representativeMarkers[ICGS_State].append(values)
                         except Exception: representativeMarkers[ICGS_State] = [values]    
@@ -193,21 +187,21 @@ def getBinary(x):
         #int(len(markers)*.25)>5:
         #print ICGS_State, markers
     #sys.exit()
-
+    
     for ICGS_State in representativeMarkers:
         if createPseudoCell:
             signature_values = representativeMarkers[ICGS_State]
             if useProbablityOfExpression:
-                signature_values = [numpy.sum(value) for value in zip(*signature_values)]
+                signature_values = [numpy.median(value) for value in zip(*signature_values)]
             else:
-                signature_values = [float(numpy.mean(value)) for value in zip(*signature_values)]
+                signature_values = [int(numpy.median(value)) for value in zip(*signature_values)]
             representativeMarkers[ICGS_State] = signature_values
         else:
             gene = representativeMarkers[ICGS_State]
             row_index = row_header.index(gene)
             gene_values = matrix[row_index]
             representativeMarkers[ICGS_State] = gene_values
-
+        
     ### Determine for each gene, its population frequency per cell state
     expressedStatesPerCell={}
     multilin_probability={}
@@ -215,8 +209,6 @@ def getBinary(x):
     print 'Writing results matrix to:',MarkerFinder[:-4]+'-cellStateScores.txt'
     eo = export.ExportFile(MarkerFinder[:-4]+'-cellStateScores.txt')
     eo.write(string.join(['UID']+column_header,'\t')+'\n')
-    print 'a'
-    print len(representativeMarkers)
     for ICGS_State in representativeMarkers:
         gene_values = representativeMarkers[ICGS_State]
         index=0
@@ -224,7 +216,6 @@ def getBinary(x):
         HitsCount=0
         for cell in column_header:
             value = gene_values[index]
-            """
             expressedLiklihood = '0'
             if (value<0.05 and useProbablityOfExpression==True) or (value==1 and useProbablityOfExpression==False):
                 try: expressedStatesPerCell[cell].append(ICGS_State)
@@ -234,16 +225,13 @@ def getBinary(x):
             if useProbablityOfExpression:
                 try: multilin_probability[cell].append(value)
                 except Exception: multilin_probability[cell] = [value]
-            """
             index+=1
-            
-            HitsCount+=1
-            scoreMatrix.append(str(value))
+            scoreMatrix.append(expressedLiklihood)
         if HitsCount>1:
             #print ICGS_State,HitsCount
             eo.write(string.join([ICGS_State]+scoreMatrix,'\t')+'\n')
     eo.close()
-    sys.exit()
+            
     def multiply(values):
         p = 1
         for i in values:
@@ -293,6 +281,10 @@ def multiply(values):
     for cell_state in state_scores:
         state_scores2.append((numpy.mean(state_scores[cell_state]),cell_state))
     i=0
+    
+    print 'Writing results matrix to:',MarkerFinder[:-4]+'-cell-combined-scores.txt'
+    eo = export.ExportFile(MarkerFinder[:-4]+'-cell-combined-score.txt')
+    
     for cell in cell_mutlilin_ranking:
         score,cellName = cell
         CellState,CellName = string.split(cellName,':')
@@ -304,11 +296,14 @@ def multiply(values):
                 try: twoStandDeviationsAway[CellState]+=1
                 except Exception: twoStandDeviationsAway[CellState]=1
                 twoStandDeviationsAwayTotal+=1
-            print cell, string.join(expressedStatesPerCell[cell[-1]],'|')
+            #print cell, string.join(expressedStatesPerCell[cell[-1]],'|')
+            a = expressedStatesPerCell[cell[-1]]
+            eo.write(str(cell[1])+'\t'+str(cell[0])+'\t'+'\n')
         i+=1
     state_scores2
     state_scores2.sort()
     state_scores2.reverse()
+    eo.close()
     
     twoStandDeviationsAway = oneStandDeviationAway
     twoStandDeviationsAwayTotal = oneStandDeviationAwayTotal
@@ -355,14 +350,14 @@ def calculateGeneExpressProbilities(values, useZ=False):
     
 if __name__ == '__main__':
     #query_dataset = '/Users/saljh8/Desktop/Old Mac/Desktop/demo/Mm_Gottgens_3k-scRNASeq/ExpressionInput/exp.GSE81682_HTSeq-cellHarmony-filtered.txt'
-    all_tpm = '/Users/saljh8/Downloads/test1/exp.cellHarmony.txt'
-    markerfinder = '/Users/saljh8/Downloads/test1/AllGenes_correlations-ReplicateBased.txt'
-    signature_genes = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/CITE-Seq_mLSK-60ADT/Merged/ExpressionInput/MF.txt'
+    all_tpm = '/Users/saljh8/Desktop/Old Mac/Desktop/demo/BoneMarrow/ExpressionInput/exp.BoneMarrow-scRNASeq.txt'
+    markerfinder = '/Users/saljh8/Desktop/Old Mac/Desktop/demo/BoneMarrow/ExpressionOutput/MarkerFinder/AllGenes_correlations-ReplicateBased.txt'
+    signature_genes = '/Users/saljh8/Desktop/Old Mac/Desktop/Grimes/KashishNormalization/test/Panorama.txt'
     state = 'DC'
 
-    #all_tpm = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/ExpressionInput/exp.Guide3-cellHarmony-revised.txt'
+    all_tpm = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/ExpressionInput/exp.Guide3-cellHarmony-revised.txt'
     #markerfinder = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/ExpressionOutput/MarkerFinder/AllGenes_correlations-ReplicateBased.txt'
-    #signature_genes = '/Users/saljh8/Desktop/Old Mac/Desktop/Grimes/KashishNormalization/test/Panorama.txt'
+    signature_genes = '/Users/saljh8/Desktop/Old Mac/Desktop/Grimes/KashishNormalization/test/Panorama.txt'
     
     query_dataset = None
     query_dataset = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/exp.NaturePan-PreGM-CD150-.txt'
diff --git a/stats_scripts/quantifyBarcodes.py b/stats_scripts/quantifyBarcodes.py
index 8e6ce1a..5807aa1 100755
--- a/stats_scripts/quantifyBarcodes.py
+++ b/stats_scripts/quantifyBarcodes.py
@@ -107,11 +107,13 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
     #print cells_with_virus['CAGAATCCAAACTGCT']
     #sys.exit()
     
-    valid_barcodes = 0
-    for viral in viral_barcodes:
-        if viral in reference_48mers:
-            valid_barcodes+=1
-    print valid_barcodes, 'unique valid viral barcodes present'
+    if reference_48mers !=None:
+        valid_barcodes = 0
+        for viral in viral_barcodes:
+            if viral in reference_48mers:
+                valid_barcodes+=1
+        print valid_barcodes, 'unique valid viral barcodes present'
+        
     #"""
     ### If the viral barcodes have frequent errors - associate the error with the reference in a cell-specific manner
     ### Only one virus for cell should be present unless it is a doublet
@@ -131,7 +133,9 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
                 except Exception: cell_5prime[i[:10]]=[i]
                 try: cell_3prime[i[-10:]].append(i)
                 except Exception: cell_3prime[i[-10:]]=[i]
-                if i in reference_48mers:
+                if reference_48mers == None:
+                    ref_sequences.append(i)
+                elif i in reference_48mers:
                     ref_sequences.append(i)
             if len(ref_sequences)>0:
                 cells_with_valid_barcodes+=1 ### Determine how many cells have valid viral barcodes
@@ -156,7 +160,9 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
                 
         else:
             for i in cells_with_virus[cellular]:
-                if i in reference_48mers:
+                if reference_48mers == None:
+                    cells_with_valid_barcodes+=1
+                elif i in reference_48mers:
                     cells_with_valid_barcodes+=1 ### Determine how many cells have valid viral barcodes
                 try: viral_barcodes_overide[i].append(cellular)
                 except: viral_barcodes_overide[i]=[cellular]
@@ -172,6 +178,8 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
         if v in mismatch_to_match:
             v = mismatch_to_match[v]
             proceed = True
+        elif reference_48mers == None:
+            proceed = True
         elif v in reference_48mers:
             proceed = True
         if proceed:
@@ -182,8 +190,6 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
             else:
                 viral_barcodes2[v] = cell_barcodes
 
-
-    
     print cells_with_valid_barcodes, 'cells with valid viral barcodes.'
     viral_barcodes = viral_barcodes2
     ### Update the cells_with_virus dictionary
@@ -230,7 +236,9 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
         k=len(unique.unique(viral_barcodes[viral]))
         if k>k_value:
             proceed=True
-            if len(reference_48mers)>0:
+            if reference_48mers == None:
+                proceed = True
+            elif len(reference_48mers)>0:
                 if viral in reference_48mers:
                     proceed = True
                 else: proceed = False
@@ -336,23 +344,25 @@ def processBarcodes(viral_barcode_file,cell_cluster_file,reference_48mers):
     #cellClusters = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/Viral-tracking/3-prime/groups.cellHarmony-Celexa5prime-Baso.txt'
     barcode1 = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/Viral-tracking/3-prime/14mer.txt'
     barcode2 = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/Viral-tracking/3-prime/30mer.txt'
-    references = importViralBarcodeReferences(barcode1,barcode2)
     #references={}
-    processBarcodes(cellBarcodes,cellClusters,references);sys.exit()
     import getopt
-    filter_rows=False
-    filter_file=None
-    genome = 'hg19'
-    dataset_name = '10X_filtered'
+    barcode1 = None
+    barcode2 = None
+
     if len(sys.argv[1:])<=1:  ### Indicates that there are insufficient number of command-line arguments
         print "Insufficient options provided";sys.exit()
-        #Filtering samples in a datasets
-        #python 10XProcessing.py --i /Users/test/10X/outs/filtered_gene_bc_matrices/ --g hg19 --n My10XExperiment
     else:
-        options, remainder = getopt.getopt(sys.argv[1:],'', ['i=','g=','n='])
+        options, remainder = getopt.getopt(sys.argv[1:],'', ['c=','v=','b1=','b2='])
         #print sys.argv[1:]
         for opt, arg in options:
-            if opt == '--i': matrices_dir=arg
-            elif opt == '--g': genome=arg
-            elif opt == '--n': dataset_name=arg
+            if opt == '--c': cellClusters=arg
+            elif opt == '--v': cellBarcodes=arg
+            elif opt == '--b1': barcode1=arg
+            elif opt == '--b2': barcode2=arg
+            
+    if barcode1!=None:
+        references = importViralBarcodeReferences(barcode1,barcode2)
+    else:
+        references = None
+    processBarcodes(cellBarcodes,cellClusters,references);sys.exit()
      
\ No newline at end of file
diff --git a/visualization_scripts/clustering.py b/visualization_scripts/clustering.py
index eb4e67a..74bbbca 100644
--- a/visualization_scripts/clustering.py
+++ b/visualization_scripts/clustering.py
@@ -8938,7 +8938,7 @@ def summarizeCovariates(fn):
         eo.write(string.join([ClusterName]+values,'\t')+'\n')
     eo.close()
      
-def computeIsoformRatio(gene_exp_file, isoform_exp_file):
+def computeIsoformRatio(gene_exp_file, isoform_exp_file, pairs=False):
     path = isoform_exp_file[:-4]+'_ratios.txt'
     eo = export.ExportFile(path)
     firstRow=True
@@ -9018,33 +9018,55 @@ def computeIsoformRatio(gene_exp_file, isoform_exp_file):
                     gene_exp = gene_exp_db[gene]
             try: gene_to_isoform[gene].append(original_uid)
             except: gene_to_isoform[gene] = [original_uid]
-
-    for gene in gene_to_isoform:
-        if len(gene_to_isoform[gene])>1:
-            for isoform in gene_to_isoform[gene]:
-                values = isoform_exp_db[isoform]
-                gene_exp = gene_exp_db[gene]
-                index=0
-                ratios=[]
-                for i in values:
-                    #v = math.log(i+1,2)-math.log(gene_exp[index]+1,2)
-                    k = gene_exp[index]
-                    if k>1:
-                        try: v = i/k
-                        except: v = 1
-                    else:
-                        v=''
-                    index+=1
-                    try: ratios.append(str(round(v,2)))
-                    except: ratios.append('')
-                """
-                if 'MYRFL' in isoform:
-                    print isoform
-                    print gene_exp[:10]
-                    print values[:10]
-                    print ratios[:10]"""
-                eo.write(string.join([isoform]+ratios,'\t')+'\n')
-                #max_ratios = max(map(float,ratios))
+            
+    if pairs == False: ### Export isoform to gene ratios
+        for gene in gene_to_isoform:
+            if len(gene_to_isoform[gene])>1:
+                for isoform in gene_to_isoform[gene]:
+                    values = isoform_exp_db[isoform]
+                    gene_exp = gene_exp_db[gene]
+                    index=0
+                    ratios=[]
+                    for i in values:
+                        #v = math.log(i+1,2)-math.log(gene_exp[index]+1,2)
+                        k = gene_exp[index]
+                        if k>1:
+                            try: v = i/k
+                            except: v = 1
+                        else:
+                            v=''
+                        index+=1
+                        try: ratios.append(str(round(v,2)))
+                        except: ratios.append('')
+                    """
+                    if 'MYRFL' in isoform:
+                        print isoform
+                        print gene_exp[:10]
+                        print values[:10]
+                        print ratios[:10]"""
+                    eo.write(string.join([isoform]+ratios,'\t')+'\n')
+                    #max_ratios = max(map(float,ratios))
+    else:
+        for gene in gene_to_isoform:
+            if len(gene_to_isoform[gene])>1:
+                for isoform1 in gene_to_isoform[gene]:
+                    values1 = isoform_exp_db[isoform1]
+                    for isoform2 in gene_to_isoform[gene]:
+                        values2 = isoform_exp_db[isoform2]
+                        if isoform1 != isoform2:
+                            index=0
+                            ratios=[]
+                            for i in values1:
+                                k = values2[index]
+                                if k>1:
+                                    try: v = i/k
+                                    except: v = 1
+                                else:
+                                    v=''
+                                index+=1
+                                try: ratios.append(str(round(v,2)))
+                                except: ratios.append('')
+                            eo.write(string.join([isoform1+'@'+isoform2]+ratios,'\t')+'\n')
 
     eo.close()
        
@@ -9120,14 +9142,14 @@ def TFisoToGene(filename,marker_genes):
     isoform_data = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Isoform-U01/Alt-Analyze/ExpressionInput/exp.GC30-basic-MainTissues_ratios-sparse-filtered.txt'
     psi_annotations = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/GTEx/Hs_RNASeq_top_alt_junctions-PSI_EventAnnotation.txt'
     #correlateIsoformPSIvalues(isoform_data,psi_data,psi_annotations);sys.exit()
-    
-    isoform_exp = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Isoform-U01/6k-Genecode30/protein.Gtex-GC30_6k-selected-tissues-TFs.txt'
-    gene_exp = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Isoform-U01/6k-Genecode30/gene.Gtex-GC30_6k-selected-tissues-TFs.txt'
-    
+
     isoform_exp = '/Volumes/salomonis2/NCI-R01/Harvard/BRC_RNA_seq/kallisto-GC30-6k/ExpressionInput/protein.BRC-GC30-6k.txt'
     gene_exp = '/Volumes/salomonis2/NCI-R01/Harvard/BRC_RNA_seq/kallisto-GC30-6k/ExpressionInput/gene.BRC-GC30-6k.txt'
     
-    #computeIsoformRatio(gene_exp,isoform_exp);sys.exit()
+    isoform_exp = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Isoform-U01/6k-Genecode30/GTEx-revised/protein.GC30-6k-GTEx-filtered.txt'
+    gene_exp = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Isoform-U01/6k-Genecode30/GTEx-revised/gene.GC30-6k-GTEx-filtered.txt'
+    
+    #computeIsoformRatio(gene_exp,isoform_exp,pairs=True);sys.exit()
     #aggregateMarkerFinderResults('/Volumes/salomonis2/LabFiles/TabulaMuris/Smart-Seq2_Nextera/CPTT-Files/all-comprehensive/');sys.exit()
     groups_file = '/data/salomonis2/LabFiles/TabulaMuris/Smart-Seq2_Nextera/CPTT-Files/all-comprehensive/FACS_annotation-edit.txt'
     exp_dir = '/data/salomonis2/LabFiles/TabulaMuris/Smart-Seq2_Nextera/CPTT-Files/all-comprehensive/MergedFiles.txt'
@@ -9148,7 +9170,7 @@ def TFisoToGene(filename,marker_genes):
     #summarizePSIresults(PSI_dir,PSI_dir);sys.exit()
     #tempFunction('/Users/saljh8/Downloads/LungCarcinoma/HCC.S5063.TPM.txt');sys.exit()
     a = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/Leucegene/July-2017/PSI/SpliceICGS.R1.Depleted.12.27.17/all-depleted-and-KD/temp/'
-    compareEventLists(PSI_dir);sys.exit()
+    #compareEventLists(PSI_dir);sys.exit()
     filename = '/Users/saljh8/Downloads/Kerscher_lists_mouse_versus_mouse_and_human_gene_lists/Top50MouseandHuman1-clusters.txt'
     #exportSeuratMarkersToClusters(filename); sys.exit()
     organized_diff_ref = '/Volumes/salomonis2/Grimes/RNA/scRNA-Seq/10x-Genomics/WuXi-David-Nature-Revision/PROJ-00584/fastqs/DM-4-Gfi1-R412X-ModGMP-1694-ADT/outs/filtered_gene_bc_matrices/Merged-Cells/centroid-revised/custom/cellHarmony/OrganizedDifferentials.txt'
@@ -9221,9 +9243,9 @@ def TFisoToGene(filename,marker_genes):
     ##transposeMatrix(a);sys.exit()
     #returnIntronJunctionRatio('/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/Fluidigm_scRNA-Seq/12.09.2107/counts.WT-R412X.txt');sys.exit()
     #geneExpressionSummary('/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/Ly6g/combined-ICGS-Final/ExpressionInput/DEGs-LogFold_1.0_rawp');sys.exit()
-    b = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Claire/Epi/ICGS-NMF/groups.MergedFiles-Rhesus-filtered-epi.txt'
+    b = '/Users/saljh8/Dropbox/Collaborations/Isoform-U01/GTEX-30-sample/TCGA-BRCA/ForAnu/forICGS/ICGS-NMF-cosine/FinalGroups.txt'
     a = '/Users/saljh8/Dropbox/scRNA-Seq Markers/Human/Expression/Lung/Adult/Perl-CCHMC/FinalMarkerHeatmap_all.txt'
-    convertGroupsToBinaryMatrix(b,b,cellHarmony=False);sys.exit()
+    #convertGroupsToBinaryMatrix(b,b,cellHarmony=False);sys.exit()
     a = '/Users/saljh8/Desktop/temp/groups.TNBC.txt'
     b = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/Leucegene/July-2017/tests/clusters.txt'
     #simpleCombineFiles('/Users/saljh8/Desktop/dataAnalysis/Collaborative/Jose/NewTranscriptome/CombinedDataset/ExpressionInput/Events-LogFold_0.58_rawp')
@@ -9318,8 +9340,8 @@ def TFisoToGene(filename,marker_genes):
     gene_list_file = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/Ly6g/combined-ICGS-Final/ExpressionInput/genes.txt'
     gene_list_file = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/Ly6g/combined-ICGS-Final/R412X/genes.txt'
     gene_list_file = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/HCA/BM1-8_CD34+/ExpressionInput/MixedLinPrimingGenes.txt'
-    gene_list_file = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Churko/ExpressionInput/genes.txt'
-    genesets = importGeneList(gene_list_file,n=22)
+    gene_list_file = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/Erica/VanGalen/Health-ICGS/CellHarmonyReference/genes.txt'
+    genesets = importGeneList(gene_list_file,n=30)
     filename = '/Users/saljh8/Desktop/Grimes/KashishNormalization/3-25-2015/comb-plots/exp.IG2_GG1-extended-output.txt'
     filename = '/Users/saljh8/Desktop/Grimes/KashishNormalization/3-25-2015/comb-plots/genes.tpm_tracking-ordered.txt'
     filename = '/Users/saljh8/Desktop/demo/Amit/ExpressedCells/GO-Elite_results/3k_selected_LineageGenes-CombPlotInput2.txt'
@@ -9335,7 +9357,7 @@ def TFisoToGene(filename,marker_genes):
     filename = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/10X-DropSeq-comparison/DropSeq/MultiLinDetect/ExpressionInput/DataPlots/exp.DropSeq-2k-log2.txt'
     filename = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/Ly6g/combined-ICGS-Final/R412X/exp.allcells-v2.txt'
     filename = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/HCA/BM1-8_CD34+/ExpressionInput/exp.CD34+.v5-log2.txt'
-    filename = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Churko/ExpressionInput/exp.10x-Multi-CCA-iPS-CM-CPTT-non-log.txt'
+    filename = '/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/Erica/VanGalen/Health-ICGS/CellHarmonyReference/exp.MarkerFinder-cellHarmony-reference-filtered.txt'
     #filename = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-10x/CITE-Seq-MF-indexed/ExpressionInput/exp.cellHarmony.v3.txt'
     #filename = '/Volumes/salomonis2/Theodosia-Kalfa/Combined-10X-CPTT/ExpressionInput/exp.MergedFiles-ICGS.txt'
     #filename = '/Users/saljh8/Desktop/dataAnalysis/Collaborative/Grimes/All-Fluidigm/updated.8.29.17/Ly6g/combined-ICGS-Final/R412X/exp.cellHarmony-WT-R412X-relative.txt'
@@ -9345,7 +9367,7 @@ def TFisoToGene(filename,marker_genes):
 
     print genesets
     for gene_list in genesets:
-        multipleSubPlots(filename,gene_list,SubPlotType='column',n=22)
+        multipleSubPlots(filename,gene_list,SubPlotType='column',n=30)
     sys.exit()
 
     plotHistogram(filename);sys.exit()