2.1.3 4/14/19

Updates to the core cellHarmony algorithm, support for hdf5 files (10x
Genomics version 2.0), compressed mtx files (10x Genomics 3.0) and
various data visualization improvements.

AltAnalyze.py

@@ -6274,9 +6274,11 @@ def commandLineRun():
     customFASTA = None
     filterFile = None
     PearsonThreshold = 0.1
-    returnCentroids = False
+    returnCentroids = 'community'
     runCompleteWorkflow=True
     k=None
+    labels=None
+
     original_arguments = sys.argv
     arguments=[]
     for arg in original_arguments:
@@ -6457,8 +6459,16 @@ def commandLineRun():
             else:
                 DE = False
         elif opt == '--referenceType':
-            if string.lower(arg) == 'centroid': returnCentroids = True; CenterMethod='centroid'
-            else: CenterMethod='median'; returnCentroids = True
+            if string.lower(arg) == 'centroid' or string.lower(arg) == 'mean':
+                returnCentroids = True; CenterMethod='centroid'
+            elif string.lower(arg) == 'medoid' or string.lower(arg) == 'median':
+                returnCentroids = True; CenterMethod='median'     
+            elif string.lower(arg) == 'community' or string.lower(arg) == 'louvain':
+                returnCentroids = 'community'; CenterMethod='community'
+            elif string.lower(arg) == 'cells' or string.lower(arg) == 'cell':
+                returnCentroids = False; CenterMethod='centroid'
+            else:
+                returnCentroids = 'community'; CenterMethod='community'     
         elif opt == '--multiThreading' or opt == '--multiProcessing':
             multiThreading=arg
             if multiThreading == 'yes': multiThreading = True
@@ -7000,6 +7010,7 @@ def commandLineRun():
                         separateGenePlots = True
                     else:
                         separateGenePlots = False
+
                 if opt == '--zscore':
                     if arg=='yes' or arg=='True' or arg == 'true':
                         zscore=True
@@ -8036,6 +8047,7 @@ def commandLineRun():
                     elif opt == '--adjp': adjp = arg
                     elif opt == '--performDiffExp': performDiffExp = arg
                     elif opt == '--centerMethod': CenterMethod = arg
+                    elif opt == '--labels': labels = arg
                 fl = UI.ExpressionFileLocationData('','','','')
                 fl.setSpecies(species)
                 fl.setVendor(manufacturer)
@@ -8049,6 +8061,7 @@ def commandLineRun():
                     fl.setUseAdjPvalue(adjp)
                     fl.setPvalThreshold(pval)
                     fl.setFoldCutoff(FoldDiff)
+                    fl.setLabels(labels)
                 else:
                     fl.setClassificationAnalysis('LineageProfiler')
                 #fl.setCompendiumType('AltExon')
@@ -8063,9 +8076,8 @@ def commandLineRun():
                             ICGS_files.append(input_file)
                     import LineageProfilerIterate
                     print 'center method =',CenterMethod
-                    try: LineageProfilerIterate.createMetaICGSResults(ICGS_files,output_dir,CenterMethod =CenterMethod,species=species,PearsonThreshold=PearsonThreshold)
-                    except:
-                        LineageProfilerIterate.createMetaICGSResults(ICGS_files,output_dir,CenterMethod=CenterMethod)
+                    LineageProfilerIterate.createMetaICGSResults(ICGS_files,output_dir,CenterMethod =CenterMethod,species=species,PearsonThreshold=PearsonThreshold)
+                    #except: LineageProfilerIterate.createMetaICGSResults(ICGS_files,output_dir,CenterMethod=CenterMethod)
                     sys.exit()
                 try: CenterMethod=CenterMethod
                 except: CenterMethod='centroid'

Config/default-files.csv

@@ -3,11 +3,11 @@
 "exon_seq","","HuEx-1_0-st-v2.hg16.probeset.fa","Hs"
 "exon_seq","","MoEx-1_0-st-v1.mm5.probeset.fa","Mm"
 "exon_seq","","RaEx-1_0-st-v1.rn3.probeset.fa","Rn"
-"PathDir","local","/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/cellHarmony-evaluation/Grimes","all"
+"PathDir","local","/Users/saljh8/Downloads","all"
 "temp","temp","ftp://ftp.geneontology.org/pub/go/ontology-archive/function.ontology.2008-08-01.gz","all"
 "Program/Download","Status","Location","Species"
 "url","url","http://altanalyze.org/archiveDBs/","all"
-"PathFile","local","/Users/saljh8/Desktop/dataAnalysis/SalomonisLab/cellHarmony-evaluation/Grimes","all"
+"PathFile","local","/Volumes/salomonis2/HCA-Immune-10x-data/Bone-Marrow/MantonBM5/cellHarmony/heatmaps","all"
 "TrEMBL","ftp","ftp://ftp.expasy.org/databases/uniprot/current_release/knowledgebase/taxonomic_divisions/uniprot_trembl_human.dat.gz","Hs"
 "TrEMBL","ftp","ftp://ftp.expasy.org/databases/uniprot/current_release/knowledgebase/taxonomic_divisions/uniprot_trembl_rodents.dat.gz","Mm|Rn"
 "APT","local","AltDatabase/affymetrix/APT","all"

ExpressionBuilder.py

@@ -323,15 +323,20 @@ def simplerGroupImport(group_dir):
     fn = filepath(group_dir)
     for line in open(fn,'rU').xreadlines():
         data = cleanUpLine(line)
-        try: sample_filename,group_number,group_name = string.split(data,'\t')
+        try:
+            group_data = string.split(data,'\t')
+            sample_filename = group_data[0]
+            group_name = group_data[-1]
+            if len(group_data)>3:
+                forceError
         except Exception:
             #print 'Non-Standard Groups file or missing relationships'
             print string.split(data,'\t')[:10], 'more than 3 columns present in groups file'
             kill
         sample_group_db[sample_filename] = group_name
     return sample_group_db
 
-def simpleGroupImport(group_dir,splitHeaders=False, ignoreComps=False):
+def simpleGroupImport(group_dir,splitHeaders=False, ignoreComps=False, reverseOrder=False):
 
     """ Used for calculating fold changes prior to clustering for individual samples (genomtric folds) """
     import collections
@@ -366,31 +371,38 @@ def simpleGroupImport(group_dir,splitHeaders=False, ignoreComps=False):
         if splitHeaders:
             if '~' in sample_filename: sample_filename = string.split(sample_filename,'~')[-1]
         group_sample_db[sample_filename] = group_name+':'+sample_filename
-        try: group_name_sample_db[group_name].append(group_name+':'+sample_filename)
-        except Exception: group_name_sample_db[group_name] = [group_name+':'+sample_filename]
+        if reverseOrder==False:
+            try: group_name_sample_db[group_name].append(group_name+':'+sample_filename)
+            except Exception: group_name_sample_db[group_name] = [group_name+':'+sample_filename]
+        else:
+            try: group_name_sample_db[group_name].append(sample_filename)
+            except Exception: group_name_sample_db[group_name] = [sample_filename]
         sample_list.append(sample_filename)
         group_db[sample_filename] = group_name
 
         group_name_db[group_number]=group_name ### used by simpleCompsImport
 
     ### Get the comparisons indicated by the user
     if ignoreComps==False: ### Not required for some analyses
-        comps_name_db,comp_groups = simpleCompsImport(group_dir,group_name_db)
+        comps_name_db,comp_groups = simpleCompsImport(group_dir,group_name_db,reverseOrder=reverseOrder)
     else:
         comps_name_db={}; comp_groups=[]
     return sample_list,group_sample_db,group_db,group_name_sample_db,comp_groups,comps_name_db
 
-def simpleCompsImport(group_dir,group_name_db):
+def simpleCompsImport(group_dir,group_name_db,reverseOrder=False):
     """ Used for calculating fold changes prior to clustering for individual samples (genomtric folds) """
     comps_dir = string.replace(group_dir,'groups.','comps.')
-    comps_name_db={}
+    import collections
+    comps_name_db=collections.OrderedDict()
     comp_groups=[]
     comps_dir = verifyExpressionFile(comps_dir)
     fn = filepath(comps_dir)
     for line in open(fn,'rU').xreadlines():
         data = cleanUpLine(line)
         try:
             exp_group_num,con_group_num = string.split(data,'\t')
+            if reverseOrder:
+                con_group_num, exp_group_num = exp_group_num,con_group_num
             exp_group_name = group_name_db[exp_group_num]
             con_group_name = group_name_db[con_group_num]
             try: comps_name_db[con_group_name].append(exp_group_name)
@@ -2678,7 +2690,10 @@ def compareJunctionExpression(gene):
                                         print incl_exp
                                         print excl_exp;sys.exit()"""
                                 #if 'ENSMUSG00000009350:E14.2_87617106-E15.1' in incl: print feature_exp_db[incl]
-                                altexons = unique.unique(critical_junction_pair_db[incl,excl])
+                                try:
+                                    altexons = unique.unique(critical_junction_pair_db[incl,excl])
+                                except:
+                                    altexons=[]
                                 altexons = string.join(altexons,'|')
                                 if num_excl_events > num_incl_events:
                                     #print max_ratio, '\t',gene

GO_Elite.py

@@ -1849,10 +1849,12 @@ def __init__(self,null):
         self.log = open(log_file, "w")
 
     def write(self, message):
-        self.log = open(log_file, "a")
-        self.terminal.write(message)
-        self.log.write(message)
-        self.log.close()
+        try:
+            self.log = open(log_file, "a")
+            self.terminal.write(message)
+            self.log.write(message)
+            self.log.close()
+        except: pass
 
     def flush(self): pass
 

InteractionBuilder.py

@@ -262,9 +262,11 @@ def importqueryResults(species,dir_file,id_db):
 
     if len(id_db)==0: ### Otherwise, already provided gene IDs to query
         translated=0
+        count=0
         try:
             x=0
             for line in fileRead:
+                count+=1
                 try:
                     data = cleanUpLine(line)
                     t = string.split(data,'\t')
@@ -809,7 +811,35 @@ def getGeneIDs(Genes):
                     except Exception: input_IDs[i] = i ### Currently not dealt with
     return input_IDs
 
+def remoteBuildNetworks(species, outputDir, interactions=['WikiPathways','KEGG','TFTargets']):
+    """ Attempts to output regulatory/interaction networks from a directory of input files """
+
+    directory = 'gene-mapp'
+    interactionDirs=[]
+    obligatorySet=[] ### Always include interactions from these if associated with any input ID period
+    secondarySet=[]
+    inputType = 'IDs'
+    degrees = 'direct'
+
+    for i in interactions:
+        fn = filepath('AltDatabase/goelite/'+species+'/gene-interactions/Ensembl-'+i+'.txt')
+        interactionDirs.append(fn)
+
+    pdfs=[]
+    dir_list = read_directory(outputDir)
+    for file in dir_list:
+        if 'GE.' in file:
+            input_file_dir = outputDir+'/'+file
+
+            output_filename = buildInteractions(species,degrees,inputType,input_file_dir,outputDir,interactionDirs,
+                              directory=outputDir,expressionFile=input_file_dir, IncludeExpIDs=True)
+            try: pdfs.append(output_filename[:-4]+'.pdf')
+            except: pass
+    return pdfs
+
 if __name__ == '__main__':
+    remoteBuildNetworks('Mm', '/Users/saljh8/Desktop/DemoData/cellHarmony/Mouse_BoneMarrow/inputFile/cellHarmony/DifferentialExpression_Fold_2.0_adjp_0.05')
+    sys.exit()
     Species = 'Hs'
     Degrees = 2
     inputType = 'IDs'