def geneCoordinates(species,symbols):
genes=[]
import EnsemblImport
ensembl_annotation_db = EnsemblImport.reimportEnsemblAnnotations(species,symbolKey=True)
for symbol in symbols:
ens_geneid = ensembl_annotation_db[symbol]
genes.append((ens_geneid,symbol))
### Get gene genomic locations
gene_location_db = EnsemblImport.getEnsemblGeneLocations(species,'RNASeq','key_by_array')
search_locations=[]
for (gene,symbol) in genes:
chr,strand,start,end = gene_location_db[gene]
if symbol == 'SRSF10': chr = 'chr1'; strand = '-'; start = '24295573'; end = '24306953'
if len(chr)>6: print symbol, 'bad chromosomal reference:',chr
else:
search_locations.append([chr,strand,start,end,symbol])
def exportChromosomeStrandCoordinates(species):
import EnsemblImport
gene_location_db = EnsemblImport.getEnsemblGeneLocations(
species, 'RNASeq', 'key_by_array')
import ExpressionBuilder
gene_biotype_db = ExpressionBuilder.importTranscriptBiotypeAnnotations(
species)
export_path = 'GenMAPPDBs/' + species + '/chr_gene_locations.txt'
export_data = export.ExportFile(export_path)
import ExonAnalyze_module
gene_annotation_file = "AltDatabase/ensembl/" + species + "/" + species + "_Ensembl-annotations.txt"
annotate_db = ExonAnalyze_module.import_annotations(
gene_annotation_file, 'RNASeq')
print 'Annotations for', len(gene_location_db), 'genes imported'
sorted_list = []
protein_coding = 0
for gene in gene_location_db:
chr, strand, start, end = gene_location_db[gene]
if gene in gene_biotype_db:
biotype = gene_biotype_db[gene][-1]
if biotype == 'protein_coding': protein_coding += 1
else: biotype = 'NA'
if len(chr) < 7:
sorted_list.append(
[chr, strand, int(start),
int(end), gene, biotype])
#else: print chr;sys.exit()
print len(sorted_list), 'genes for typical chromosomes present'
print protein_coding, 'protein coding genes present'
sorted_list.sort()
for values in sorted_list:
chr, strand, start, end, gene, biotype = values
try:
symbol = annotate_db[gene].Symbol()
except Exception:
symbol = ''
values = [gene, symbol, chr, strand, str(start), str(end), biotype]
export_data.write(string.join(values, '\t') + '\n')
export_data.close()
print species, 'chromosome locations exported to:\n', export_path
def geneCoordinates(species,symbols):
genes=[]
import EnsemblImport
ensembl_annotation_db = EnsemblImport.reimportEnsemblAnnotations(species,symbolKey=True)
for symbol in symbols:
if symbol in ensembl_annotation_db:
ens_geneid = ensembl_annotation_db[symbol]
genes.append((ens_geneid,symbol))
else:
print symbol, 'not found'
### Get gene genomic locations
gene_location_db = EnsemblImport.getEnsemblGeneLocations(species,'RNASeq','key_by_array')
search_locations=[]
for (gene,symbol) in genes:
chr,strand,start,end = gene_location_db[gene]
#if symbol == 'SRSF10': chr = 'chr1'; strand = '-'; start = '24295573'; end = '24306953'
if len(chr)>6: print symbol, 'bad chromosomal reference:',chr
else:
search_locations.append([chr,strand,start,end,symbol])
def exportChromosomeStrandCoordinates(species):
import EnsemblImport
gene_location_db = EnsemblImport.getEnsemblGeneLocations(species,'RNASeq','key_by_array')
import ExpressionBuilder
gene_biotype_db = ExpressionBuilder.importTranscriptBiotypeAnnotations(species)
export_path = 'GenMAPPDBs/'+species+'/chr_gene_locations.txt'
export_data = export.ExportFile(export_path)
import ExonAnalyze_module
gene_annotation_file = "AltDatabase/ensembl/"+species+"/"+species+"_Ensembl-annotations.txt"
annotate_db = ExonAnalyze_module.import_annotations(gene_annotation_file,'RNASeq')
print 'Annotations for',len(gene_location_db),'genes imported'
sorted_list=[]; protein_coding=0
for gene in gene_location_db:
chr,strand,start,end = gene_location_db[gene]
if gene in gene_biotype_db:
biotype = gene_biotype_db[gene][-1]
if biotype == 'protein_coding': protein_coding+=1
else: biotype = 'NA'
if len(chr)<7:
sorted_list.append([chr,strand,int(start),int(end),gene,biotype])
#else: print chr;sys.exit()
print len(sorted_list),'genes for typical chromosomes present'
print protein_coding, 'protein coding genes present'
sorted_list.sort()
for values in sorted_list:
chr,strand,start,end,gene,biotype=values
try: symbol = annotate_db[gene].Symbol()
except Exception: symbol = ''
values = [gene,symbol,chr,strand,str(start),str(end),biotype]
export_data.write(string.join(values,'\t')+'\n')
export_data.close()
print species, 'chromosome locations exported to:\n',export_path
def reformatPolyAdenylationCoordinates(species,force):
""" PolyA annotations are currently only available from UCSC for human, but flat file
annotations from 2003-2006 are available for multiple species. Convert these to BED format"""
version={}
version['Rn'] = '2003(rn3)'
version['Dr'] = '2003(zv4)'
version['Gg'] = '2004(galGal2)'
version['Hs'] = '2006(hg8)'
version['Mm'] = '2004(mm5)'
print 'Exporting polyADB_2 coordinates as BED for',species
### Obtain the necessary database files
url = 'http://altanalyze.org/archiveDBs/all/polyAsite.txt'
output_dir = 'AltDatabase/ucsc/'+species + '/'
if force == 'yes':
filename, status = update.download(url,output_dir,'')
else: filename = output_dir+'polyAsite.txt'
### Import the refseq to Ensembl information
import gene_associations; import OBO_import; import EnsemblImport; import export
try:
ens_unigene = gene_associations.getGeneToUid(species,'Ensembl-UniGene')
print len(ens_unigene),'Ensembl-UniGene entries imported'
external_ensembl = OBO_import.swapKeyValues(ens_unigene); use_entrez='no'
except Exception:
ens_entrez = gene_associations.getGeneToUid(species,'Ensembl-EntrezGene')
print len(ens_entrez),'Ensembl-EntrezGene entries imported'
external_ensembl = OBO_import.swapKeyValues(ens_entrez); use_entrez='yes'
gene_location_db = EnsemblImport.getEnsemblGeneLocations(species,'RNASeq','key_by_array')
export_bedfile = output_dir+species+'_polyADB_2_predictions.bed'
print 'exporting',export_bedfile
export_data = export.ExportFile(export_bedfile)
header = '#'+species+'\t'+'polyADB_2'+'\t'+version[species]+'\n'
export_data.write(header)
fn=filepath(filename); x=0; not_found={}
for line in open(fn,'rU').xreadlines():
data = cleanUpLine(line)
if x==0: x=1
else:
siteid,llid,chr,sitenum,position,supporting_EST,cleavage = string.split(data,'\t')
if chr == 'chrM': chr = 'chrMT' ### MT is the Ensembl convention whereas M is the Affymetrix and UCSC convention
if chr == 'M': chr = 'MT' ### MT is the Ensembl convention whereas M is the Affymetrix and UCSC convention
if species in siteid:
if 'NA' not in chr: chr = 'chr'+chr
strand = '+'; geneid = siteid
pos_start = str(int(position)-1); pos_end = position
if use_entrez=='no':
external_geneid = string.join(string.split(siteid,'.')[:2],'.')
else: external_geneid=llid
if external_geneid in external_ensembl:
ens_geneid = external_ensembl[external_geneid][0]
geneid += '-'+ens_geneid
chr,strand,start,end = gene_location_db[ens_geneid]
else:
not_found[external_geneid]=[]
bed_format = string.join([chr,pos_start,pos_end,geneid,'0','-'],'\t')+'\n' ### We don't know the strand, so write out both strands
export_data.write(bed_format)
bed_format = string.join([chr,pos_start,pos_end,geneid,'0',strand],'\t')+'\n'
export_data.write(bed_format)
export_data.close()
def reformatPolyAdenylationCoordinates(species, force):
""" PolyA annotations are currently only available from UCSC for human, but flat file
annotations from 2003-2006 are available for multiple species. Convert these to BED format"""
version = {}
version['Rn'] = '2003(rn3)'
version['Dr'] = '2003(zv4)'
version['Gg'] = '2004(galGal2)'
version['Hs'] = '2006(hg8)'
version['Mm'] = '2004(mm5)'
print 'Exporting polyADB_2 coordinates as BED for', species
### Obtain the necessary database files
url = 'http://altanalyze.org/archiveDBs/all/polyAsite.txt'
output_dir = 'AltDatabase/ucsc/' + species + '/'
if force == 'yes':
filename, status = update.download(url, output_dir, '')
else:
filename = output_dir + 'polyAsite.txt'
### Import the refseq to Ensembl information
import gene_associations
import OBO_import
import EnsemblImport
import export
try:
ens_unigene = gene_associations.getGeneToUid(species,
'Ensembl-UniGene')
print len(ens_unigene), 'Ensembl-UniGene entries imported'
external_ensembl = OBO_import.swapKeyValues(ens_unigene)
use_entrez = 'no'
except Exception:
ens_entrez = gene_associations.getGeneToUid(species,
'Ensembl-EntrezGene')
print len(ens_entrez), 'Ensembl-EntrezGene entries imported'
external_ensembl = OBO_import.swapKeyValues(ens_entrez)
use_entrez = 'yes'
gene_location_db = EnsemblImport.getEnsemblGeneLocations(
species, 'RNASeq', 'key_by_array')
export_bedfile = output_dir + species + '_polyADB_2_predictions.bed'
print 'exporting', export_bedfile
export_data = export.ExportFile(export_bedfile)
header = '#' + species + '\t' + 'polyADB_2' + '\t' + version[species] + '\n'
export_data.write(header)
fn = filepath(filename)
x = 0
not_found = {}
for line in open(fn, 'rU').xreadlines():
data = cleanUpLine(line)
if x == 0: x = 1
else:
siteid, llid, chr, sitenum, position, supporting_EST, cleavage = string.split(
data, '\t')
if chr == 'chrM':
chr = 'chrMT' ### MT is the Ensembl convention whereas M is the Affymetrix and UCSC convention
if chr == 'M':
chr = 'MT' ### MT is the Ensembl convention whereas M is the Affymetrix and UCSC convention
if species in siteid:
if 'NA' not in chr: chr = 'chr' + chr
strand = '+'
geneid = siteid
pos_start = str(int(position) - 1)
pos_end = position
if use_entrez == 'no':
external_geneid = string.join(
string.split(siteid, '.')[:2], '.')
else:
external_geneid = llid
if external_geneid in external_ensembl:
ens_geneid = external_ensembl[external_geneid][0]
geneid += '-' + ens_geneid
chr, strand, start, end = gene_location_db[ens_geneid]
else:
not_found[external_geneid] = []
bed_format = string.join(
[chr, pos_start, pos_end, geneid, '0', '-'], '\t'
) + '\n' ### We don't know the strand, so write out both strands
export_data.write(bed_format)
bed_format = string.join(
[chr, pos_start, pos_end, geneid, '0', strand],
'\t') + '\n'
export_data.write(bed_format)
export_data.close()
