def buildAltMouseExonAnnotations(species,array_type,force,genomic_build):
"""Code required to:
1) Extract out Affymetrix provided exon sequence (probeset sequence extracted from "probeset_sequence_reversed.txt", derived
directly from the Affymetrix AltMouse probe annotation file), from the "SEQUENCE-transcript-dbase.txt" (built using
dump-chip1 .gff sequence and AltMerge-Peptide Informatics script "sequence_analysis_AltMouse_refseq.py").
2) Once exported, grab full length exon sequences using exon/intron coordinates matches to full-length gene sequences with 2kb
flanking sequence to efficiently predict microRNA binding site exclusion (reAnnotateCriticalExonSequences) and later for
coordinate mapping to get exons aligning with UCSC annotated splicing annotations and exons. This sequence data replaced
the previous file (don't need to re-run this - see rederive_exonseq == 'yes' below for reference).
3) Match the updated exon sequences to the most recent genomic coordinates and build the exact equivalent of the exon array
Mm_Ensembl_probeset.txt database (same structure and ExonArrayEnsemblRules.py code). This involves running EnsemblImport.
This code should be run before the exon array location build code since the "Mm_Ensembl_probeset.txt" is created and then re-
written as "Mm_AltMouse_Ensembl_probeset.txt".
"""
import JunctionArray
import JunctionArrayEnsemblRules
rederive_exonseq = 'no'
### Only needs to be run once, to export exon sequence for AltMouse array the original (1 and 2 above)
if rederive_exonseq == 'yes':
import AltAnalyze
import ExonAnnotate_module
import ExonAnalyze_module
agglomerate_inclusion_probesets = 'no'; onlyAnalyzeJunctions='no'
probeset_annotations_file = "AltDatabase/"+species+"/"+array_type+"/"+"MASTER-probeset-transcript.txt"
verifyFile(probeset_annotations_file,array_type) ### Will force download if missing
exon_db={}; filtered_arrayids={};filter_status='no'
constituitive_probeset_db,exon_db,genes_being_analyzed = AltAnalyze.importSplicingAnnotationDatabase(probeset_annotations_file,array_type,filtered_arrayids,filter_status)
alt_junction_db,critical_exon_db,exon_dbase,exon_inclusion_db,exon_db = ExonAnnotate_module.identifyPutativeSpliceEvents(exon_db,constituitive_probeset_db,{},agglomerate_inclusion_probesets,onlyAnalyzeJunctions)
ExonAnnotate_module.exportJunctionComparisons(alt_junction_db,critical_exon_db,exon_dbase)
print "Finished exporting junctions used in AltMouse array comparisons."
ExonAnalyze_module.exportAltMouseExonSequence()
JunctionArray.reAnnotateCriticalExonSequences(species,array_type)
### Get UCSC associations (download databases if necessary)
mRNA_Type = 'mrna'; run_from_scratch = 'yes'
export_all_associations = 'no' ### YES only for protein prediction analysis
buildUCSCAnnoationFiles(species,mRNA_Type,export_all_associations,run_from_scratch,force)
reannotate_exon_seq = 'yes'
print 'genomic_build', genomic_build
if genomic_build == 'new':
### Need to run with every new genomic build (match up new coordinates
print "Begining to derive exon sequence from new genomic build"
JunctionArray.identifyCriticalExonLocations(species,array_type)
reannotate_exon_seq = 'yes'
JunctionArrayEnsemblRules.getAnnotations(species,array_type,reannotate_exon_seq,force)
### Download files required during AltAnalyze analysis but not during the database build process
filename = "AltDatabase/"+species+"/"+array_type+"/"+"MASTER-probeset-transcript.txt"
verifyFile(filename,array_type) ### Will force download if missing
filename = "AltDatabase/"+species+'/'+ array_type+'/'+array_type+"_annotations.txt"
verifyFile(filename,array_type) ### Will force download if missing
def getAnnotations(Species,array_type,reannotate_exon_seq,force):
"""Annotate Affymetrix exon array data using files Ensembl data (sync'ed to genome release)."""
global species; species = Species; global test; global test_cluster
test = 'no'; test_cluster = ['TC0701360']; data_type = 'mRNA'
global ensembl_exon_db; global ensembl_exon_db; global exon_clusters; global exon_region_db
ensembl_exon_db,ensembl_annot_db,exon_clusters,intron_clusters,exon_region_db,intron_retention_db,ucsc_splicing_annot_db,ens_transcript_db = EnsemblImport.getEnsemblAssociations(species,data_type,test)
ensembl_probeset_db = importCriticalExonLocations(species,array_type,ensembl_exon_db,force) ###Get Pre-computed genomic locations for critical exons
ensembl_probeset_db = ExonArrayEnsemblRules.annotateExons(ensembl_probeset_db,exon_clusters,ensembl_exon_db,exon_region_db,intron_retention_db,intron_clusters,ucsc_splicing_annot_db); constitutive_gene_db={}
ExonArrayEnsemblRules.exportEnsemblLinkedProbesets(array_type,ensembl_probeset_db,species)
print "\nCritical exon data exported coordinates, exon associations and splicing annotations exported..."
### Change filenames to reflect junction array type
export_filename = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_Ensembl_probesets.txt'; ef=filepath(export_filename)
export_replacement = string.replace(export_filename,'_probe','_'+array_type+'_probe')
er=filepath(export_replacement); shutil.copyfile(ef,er); os.remove(ef) ### Copy file to a new name
### Export full exon seqeunce for probesets/critical exons to replace the original incomplete sequence (used for miRNA analyses)
if reannotate_exon_seq == 'yes':
JunctionArray.reAnnotateCriticalExonSequences(species,array_type)
def buildAltMouseExonAnnotations(species, array_type, force, genomic_build):
"""Code required to:
1) Extract out Affymetrix provided exon sequence (probeset sequence extracted from "probeset_sequence_reversed.txt", derived
directly from the Affymetrix AltMouse probe annotation file), from the "SEQUENCE-transcript-dbase.txt" (built using
dump-chip1 .gff sequence and AltMerge-Peptide Informatics script "sequence_analysis_AltMouse_refseq.py").
2) Once exported, grab full length exon sequences using exon/intron coordinates matches to full-length gene sequences with 2kb
flanking sequence to efficiently predict microRNA binding site exclusion (reAnnotateCriticalExonSequences) and later for
coordinate mapping to get exons aligning with UCSC annotated splicing annotations and exons. This sequence data replaced
the previous file (don't need to re-run this - see rederive_exonseq == 'yes' below for reference).
3) Match the updated exon sequences to the most recent genomic coordinates and build the exact equivalent of the exon array
Mm_Ensembl_probeset.txt database (same structure and ExonArrayEnsemblRules.py code). This involves running EnsemblImport.
This code should be run before the exon array location build code since the "Mm_Ensembl_probeset.txt" is created and then re-
written as "Mm_AltMouse_Ensembl_probeset.txt".
"""
import JunctionArray
import JunctionArrayEnsemblRules
rederive_exonseq = 'no'
### Only needs to be run once, to export exon sequence for AltMouse array the original (1 and 2 above)
if rederive_exonseq == 'yes':
import AltAnalyze
import ExonAnnotate_module
import ExonAnalyze_module
agglomerate_inclusion_probesets = 'no'
onlyAnalyzeJunctions = 'no'
probeset_annotations_file = "AltDatabase/" + species + "/" + array_type + "/" + "MASTER-probeset-transcript.txt"
verifyFile(probeset_annotations_file,
array_type) ### Will force download if missing
exon_db = {}
filtered_arrayids = {}
filter_status = 'no'
constituitive_probeset_db, exon_db, genes_being_analyzed = AltAnalyze.importSplicingAnnotationDatabase(
probeset_annotations_file, array_type, filtered_arrayids,
filter_status)
alt_junction_db, critical_exon_db, exon_dbase, exon_inclusion_db, exon_db = ExonAnnotate_module.identifyPutativeSpliceEvents(
exon_db, constituitive_probeset_db, {},
agglomerate_inclusion_probesets, onlyAnalyzeJunctions)
ExonAnnotate_module.exportJunctionComparisons(alt_junction_db,
critical_exon_db,
exon_dbase)
print "Finished exporting junctions used in AltMouse array comparisons."
ExonAnalyze_module.exportAltMouseExonSequence()
JunctionArray.reAnnotateCriticalExonSequences(species, array_type)
### Get UCSC associations (download databases if necessary)
mRNA_Type = 'mrna'
run_from_scratch = 'yes'
export_all_associations = 'no' ### YES only for protein prediction analysis
buildUCSCAnnoationFiles(species, mRNA_Type, export_all_associations,
run_from_scratch, force)
reannotate_exon_seq = 'yes'
print 'genomic_build', genomic_build
if genomic_build == 'new':
### Need to run with every new genomic build (match up new coordinates
print "Begining to derive exon sequence from new genomic build"
JunctionArray.identifyCriticalExonLocations(species, array_type)
reannotate_exon_seq = 'yes'
JunctionArrayEnsemblRules.getAnnotations(species, array_type,
reannotate_exon_seq, force)
### Download files required during AltAnalyze analysis but not during the database build process
filename = "AltDatabase/" + species + "/" + array_type + "/" + "MASTER-probeset-transcript.txt"
verifyFile(filename, array_type) ### Will force download if missing
filename = "AltDatabase/" + species + '/' + array_type + '/' + array_type + "_annotations.txt"
verifyFile(filename, array_type) ### Will force download if missing
