def grabExonIntronPromoterSequences(species,array_type,data_type,output_types):
### output_types could be adjacent intron sequences, adjacent exon sequences, targets exon sequence or promoter
sequence_input_dir_list=[]
if data_type == 'probeset': sequence_input_dir = '/AltResults/AlternativeOutput/'+array_type+'/sequence_input'
if data_type == 'gene': sequence_input_dir = '/ExpressionOutput/'+array_type+'/sequence_input'
dir_list = read_directory(sequence_input_dir)
for input_file in dir_list:
filedir = sequence_input_dir[1:]+'/'+input_file
filter_db = inputResultFiles(filedir,data_type)
export_exon_filename = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_Ensembl_probesets.txt'
ensembl_probeset_db = ExonArrayEnsemblRules.reimportEnsemblProbesetsForSeqExtraction(export_exon_filename,data_type,filter_db)
"""for gene in ensembl_probeset_db:
if gene == 'ENSG00000139737':
for x in ensembl_probeset_db[gene]:
exon_id,((probe_start,probe_stop,probeset_id,exon_class,transcript_clust),ed) = x
print gene, ed.ExonID()
kill"""
analysis_type = 'get_sequence'
dir = 'AltDatabase/ensembl/'+species+'/'; gene_seq_filename = dir+species+'_gene-seq-2000_flank'
ensembl_probeset_db = EnsemblImport.import_sequence_data(gene_seq_filename,ensembl_probeset_db,species,analysis_type)
"""
critical_exon_file = 'AltDatabase/'+species+'/'+ array_type + '/' + array_type+'_critical-exon-seq.txt'
if output_types == 'all' and data_type == 'probeset':
output_types = ['alt-promoter','promoter','exon','adjacent-exons','adjacent-introns']
else: output_types = [output_types]
for output_type in output_types:
sequence_input_dir = string.replace(sequence_input_dir,'_input','_output')
filename = sequence_input_dir[1:]+'/ExportedSequence-'+data_type+'-'+output_type+'.txt'
exportExonIntronPromoterSequences(filename, ensembl_probeset_db,data_type,output_type)
"""
if output_types == 'all' and data_type == 'probeset':
output_types = ['alt-promoter','promoter','exon','adjacent-exons','adjacent-introns']
else: output_types = [output_types]
for output_type in output_types:
sequence_input_dir2 = string.replace(sequence_input_dir,'_input','_output')
filename = sequence_input_dir2[1:]+'/'+input_file[:-4]+'-'+data_type+'-'+output_type+'.txt'
exportExonIntronPromoterSequences(filename, ensembl_probeset_db,data_type,output_type)
def displayExpressionGraph(species,
Platform,
exp_file,
gene,
transpose,
display=True,
showIntrons=False,
analysisType='plot'):
### Get gene annotations (users can provide an Ensembl or symbol)
print 'Importing exon-level expression data for visualization (be patient)...'
import ExonAnalyze_module
global platform
platform = Platform
if platform != 'AltMouse':
gene_annotation_file = "AltDatabase/ensembl/" + species + "/" + species + "_Ensembl-annotations.txt"
else:
gene_annotation_file = "AltDatabase/" + species + "/" + platform + "/" + platform + "_gene_annotations.txt"
genes = []
gene = string.replace(gene, '|', ',')
gene = string.replace(gene, ' ', ',')
if ',' in gene:
genes += string.split(gene, ',')
else:
genes.append(gene)
gene_db = {}
for gene in genes:
try:
if 'ENS' in gene:
try:
annotate_db ### If variable is defined
except Exception:
annotate_db = ExonAnalyze_module.import_annotations(
gene_annotation_file, platform,
keyBySymbol=False) ### Make an SQLite call
gene_symbol = annotate_db[gene].Symbol()
else:
try:
annotate_db ### If variable is defined
except Exception:
annotate_db = ExonAnalyze_module.import_annotations(
gene_annotation_file, platform, keyBySymbol=True)
gene_symbol = gene
gene = annotate_db[gene].GeneID()
gene_db[gene] = gene_symbol
except Exception:
print gene, 'not in database'
if len(gene_db) == 0:
force_no_gene_found_error
if 'AltResults' in exp_file:
root_dir = string.split(exp_file, 'AltResults')[0] + 'ExonPlots/'
else:
root_dir = string.split(exp_file, 'ExpressionInput')[0] + 'ExonPlots/'
import ExonAnalyze_module
if platform == 'RNASeq': datatype = 'exons'
else: datatype = 'probesets'
export_exon_filename = 'AltDatabase/' + species + '/' + platform + '/' + species + '_Ensembl_' + datatype + '.txt'
if verifyFileLength(export_exon_filename) == 0:
rootdir = string.replace(root_dir, 'ExonPlots/', '')
export_exon_filename = rootdir + '/' + export_exon_filename
import ExonArrayEnsemblRules
ensembl_exon_db = ExonArrayEnsemblRules.reimportEnsemblProbesetsForSeqExtraction(
export_exon_filename, 'gene-probesets',
gene_db) ### Make an SQLite call
filter_db = {}
for gene in ensembl_exon_db:
ensembl_exon_db[gene].sort()
for (index, ed, id) in ensembl_exon_db[gene]:
filter_db[id] = []
try:
os.mkdir(root_dir)
except Exception:
None ### dir exists
print 'Image results being saved to the folder "ExonPlots" in the AltAnalyze results directory.'
importTableEntries(exp_file,
filter_db,
ensembl_exon_db,
gene_db,
root_dir,
transpose,
display,
showIntrons,
analysisType=analysisType) ### Make an SQLite call
def displayExpressionGraph(species,Platform,exp_file,gene,transpose,display=True,showIntrons=False,analysisType='plot'):
### Get gene annotations (users can provide an Ensembl or symbol)
print 'Importing exon-level expression data for visualization (be patient)...'
import ExonAnalyze_module
global platform
platform = Platform
if platform != 'AltMouse': gene_annotation_file = "AltDatabase/ensembl/"+species+"/"+species+"_Ensembl-annotations.txt"
else: gene_annotation_file = "AltDatabase/"+species+"/"+platform+"/"+platform+"_gene_annotations.txt"
genes=[]
gene=string.replace(gene,'|',',')
gene=string.replace(gene,' ',',')
if ',' in gene:
genes += string.split(gene,',')
else: genes.append(gene)
gene_db={}
for gene in genes:
try:
if 'ENS' in gene:
try: annotate_db ### If variable is defined
except Exception:
annotate_db = ExonAnalyze_module.import_annotations(gene_annotation_file,platform,keyBySymbol=False) ### Make an SQLite call
gene_symbol = annotate_db[gene].Symbol()
else:
try: annotate_db ### If variable is defined
except Exception:
annotate_db = ExonAnalyze_module.import_annotations(gene_annotation_file,platform,keyBySymbol=True)
gene_symbol = gene
gene = annotate_db[gene].GeneID()
gene_db[gene]=gene_symbol
except Exception:
#if len(gene)>0: print gene, 'not in database'
pass
if len(gene_db)==0:
force_no_gene_found_error
if 'AltResults' in exp_file:
root_dir = string.split(exp_file,'AltResults')[0]+'ExonPlots/'
else:
root_dir = string.split(exp_file,'ExpressionInput')[0]+'ExonPlots/'
import ExonAnalyze_module
if platform == 'RNASeq': datatype = 'exons'
else: datatype = 'probesets'
export_exon_filename = 'AltDatabase/'+species+'/'+platform+'/'+species+'_Ensembl_'+datatype+'.txt'
if verifyFileLength(export_exon_filename) == 0:
rootdir = string.replace(root_dir,'ExonPlots/','')
export_exon_filename = rootdir+'/'+export_exon_filename
import ExonArrayEnsemblRules
ensembl_exon_db = ExonArrayEnsemblRules.reimportEnsemblProbesetsForSeqExtraction(export_exon_filename,'gene-probesets',gene_db) ### Make an SQLite call
filter_db = {}
for gene in ensembl_exon_db:
ensembl_exon_db[gene].sort()
for (index,ed,id) in ensembl_exon_db[gene]:
filter_db[id] = []
try: os.mkdir(root_dir)
except Exception: None ### dir exists
print 'Image results being saved to the folder "ExonPlots" in the AltAnalyze results directory.'
importTableEntries(exp_file,filter_db,ensembl_exon_db,gene_db,root_dir,transpose,display,showIntrons,analysisType=analysisType) ### Make an SQLite call
def getJunctionComparisonsFromExport(species,array_type):
type = 'standard'
gene_junction_db = importEnsemblUCSCAltJunctions(species,type)
### Retrieve probesets with exon-junctions associated - these are critical exons
filename = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_Ensembl_'+array_type+'_probesets.txt'
gene_probeset_db = ExonArrayEnsemblRules.reimportEnsemblProbesetsForSeqExtraction(filename,'junctions',{})
left={}; right={}; gene_db={}; gene_exon_db={}; nonjunction_aligning={}
for gene in gene_probeset_db:
for (probe_data,ed) in gene_probeset_db[gene]:
probeset, strand, probeset_start, probeset_stop = probe_data
region_id = string.replace(ed.RegionNumber(),'-','.')
original_region_id = region_id
region_ids = string.split(region_id,'|')
gene_db[probeset[:-2]]=gene
#ed.AssociatedSplicingJunctions()
r_starts=string.split(ed.ExonStart(),'|'); r_stops=string.split(ed.ExonStop(),'|')
for region_id in region_ids:
if '|5' in probeset:
try: left[probeset[:-2]].append(region_id)
except Exception: left[probeset[:-2]]=[region_id]
if strand == '+': ### If the junction probesets DO NOT align to the region coordinates, then the probeset maps to a junction outside the database
if probeset_stop not in r_stops: nonjunction_aligning[probeset[:-2]] = original_region_id+'_'+probeset_stop,'left'
elif probeset_start not in r_starts: nonjunction_aligning[probeset[:-2]] = original_region_id+'_'+probeset_start,'left'
elif '|3' in probeset:
try: right[probeset[:-2]].append(region_id)
except Exception: right[probeset[:-2]]=[region_id]
if strand == '+':
if probeset_start not in r_starts: nonjunction_aligning[probeset[:-2]] = original_region_id+'_'+probeset_start,'right'
elif probeset_stop not in r_stops: nonjunction_aligning[probeset[:-2]] = original_region_id+'_'+probeset_stop,'right'
else:
if '_' in region_id: print killer
try: gene_exon_db[gene,region_id].append(probeset)
except Exception: gene_exon_db[gene,region_id] = [probeset]
print 'len(nonjunction_aligning)',len(nonjunction_aligning)
gene_exon_db = eliminateRedundant(gene_exon_db)
junction_db={} ### Get the exon-region IDs for an exon-junction
for probeset in left:
gene = gene_db[probeset]
if probeset in right:
for region1 in left[probeset]:
for region2 in right[probeset]:
junction = region1+'-'+region2
try: junction_db[gene,junction].append(probeset)
except Exception: junction_db[gene,junction] = [probeset]
probeset_junction_export = 'AltDatabase/' + species + '/'+array_type+'/'+ species + '_junction_comps.txt'
fn=filepath(probeset_junction_export); data = open(fn,'w')
print "Exporting",probeset_junction_export
title = 'gene'+'\t'+'critical_exon'+'\t'+'exclusion_junction_region'+'\t'+'inclusion_junction_region'+'\t'+'exclusion_probeset'+'\t'+'inclusion_probeset'+'\t'+'data_source'+'\n'
data.write(title); temp_list=[]
for (gene,critical_exon,incl_junction,excl_junction) in gene_junction_db:
if (gene,incl_junction) in junction_db:
incl_junction_probesets = junction_db[gene,incl_junction]
if (gene,excl_junction) in junction_db:
excl_junction_probesets = junction_db[gene,excl_junction]
for incl_junction_probeset in incl_junction_probesets:
for excl_junction_probeset in excl_junction_probesets:
try:
for incl_exon_probeset in gene_exon_db[gene,critical_exon]:
if incl_junction_probeset in nonjunction_aligning or excl_junction_probeset in nonjunction_aligning: null=[]
else: ### Ensure the probeset DOES map to the annotated junctions
temp_list.append(string.join([gene,critical_exon,excl_junction,critical_exon,excl_junction_probeset,incl_exon_probeset,'AltAnalyze'],'\t')+'\n')
except Exception: null=[]
if incl_junction_probeset in nonjunction_aligning:
new_region_id, side = nonjunction_aligning[incl_junction_probeset]
incl_junction = renameJunction(incl_junction,side,new_region_id)
if excl_junction_probeset in nonjunction_aligning:
new_region_id, side = nonjunction_aligning[excl_junction_probeset]
excl_junction = renameJunction(excl_junction,side,new_region_id)
if excl_junction_probeset!=incl_junction_probeset:
temp_list.append(string.join([gene,critical_exon,excl_junction,incl_junction,excl_junction_probeset,incl_junction_probeset,'AltAnalyze'],'\t')+'\n')
temp_list = unique.unique(temp_list)
for i in temp_list: data.write(i)
data.close()
print 'Number of compared junctions exported', len(temp_list)
