def buildNonCodingExonTranscript(infile, outfile):
'''
Output of the non-coding exon features from an ENSEMBL gene set
Remove all of the features from a :term:`gtf` file
that are features of ``exon`` and are protein-coding
Arguments
---------
infile : from ruffus
ENSEMBL geneset, filename named in pipeline.yml
outfile : from ruffus
Output filename named in pipeline.yml
filteroption : string
Filter option set in the piepline.yml as feature column in GTF
nomenclature
'''
m = PipelineGtfsubset.SubsetGTF(infile)
filteroptions = [
PARAMS['ensembl_cgat_feature'], PARAMS['ensembl_cgat_gene_biotype']
]
filteritem = ["exon", "protein_coding"]
m.filterGTF(outfile, filteroptions, filteritem, operators="and not")
def buildCdsTranscript(infile, outfile):
'''
Output the CDS features from an ENSEMBL gene set
takes all of the features from a :term:`gtf` file
that are feature types of ``CDS``.
Note - we have not filtered on gene_biotype because some of the CDS
are classified as polymorphic_pseudogene.
Arguments
---------
infile : from ruffus
ENSEMBL geneset, filename named in pipeline.yml
outfile : from ruffus
Output filename named in pipeline.yml
filteroption : string
Filter option set in the piepline.yml as feature column in GTF
nomenclature
'''
m = PipelineGtfsubset.SubsetGTF(infile)
filteroption = PARAMS['ensembl_cgat_feature']
filteritem = ["CDS"]
m.filterGTF(outfile, filteroption, filteritem, operators=None)
def buildLincRNAExonTranscript(infile, outfile):
'''
Output of the lincRNA features from an ENSEMBL gene set
Takes all of the features from a :term:`gtf` file
that are features of ``lincRNA``
Arguments
---------
infile : from ruffus
ENSEMBL geneset, filename named in pipeline.yml
outfile : from ruffus
Output filename named in pipeline.yml
filteroption : string
Filter option set in the piepline.yml as feature column in GTF
nomenclature
'''
m = PipelineGtfsubset.SubsetGTF(infile)
filteroptions = [
PARAMS['ensembl_cgat_feature'], PARAMS['ensembl_cgat_gene_biotype']
]
filteritem = ["exon", "lincRNA"]
m.filterGTF(outfile, filteroptions, filteritem, operators="and")
def buildExonTranscript(infile, outfile):
'''
Output of the exon features from an ENSEMBL gene set
Takes all of the features from a :term:`gtf` file
that are features of ``exon``
Arguments
---------
infile : from ruffus
ENSEMBL geneset, filename named in pipeline.ini
outfile : from ruffus
Output filename named in pipeline.ini
filteroption : string
Filter option set in the piepline.ini as feature column in GTF
nomenclature
'''
m = PipelineGtfsubset.SubsetGTF(infile)
filteroption = PARAMS['ensembl_cgat_feature']
filteritem = ["exon"]
m.filterGTF(outfile, filteroption, filteritem, operators=None)