mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
Merged in BjoernGruening/galaxy-central-1/snpeff_datatype (pull request #640)
Add SnpEff datatypes
This commit is contained in:
John Chilton
@@ -113,7 +113,7 @@
|
||||
<converter file="interval_to_bed12_converter.xml" target_datatype="bed12"/>
|
||||
<converter file="interval_to_bgzip_converter.xml" target_datatype="bgzip"/>
|
||||
<converter file="interval_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/>
|
||||
<converter file="interval_to_bigwig_converter.xml" target_datatype="bigwig"/>
|
||||
<converter file="interval_to_bigwig_converter.xml" target_datatype="bigwig"/>
|
||||
<!-- <display file="ucsc/interval_as_bed.xml" inherit="True" /> -->
|
||||
<display file="ensembl/ensembl_interval_as_bed.xml" inherit="True"/>
|
||||
<display file="gbrowse/gbrowse_interval_as_bed.xml" inherit="True"/>
|
||||
@@ -152,11 +152,11 @@
|
||||
<datatype extension="mafcustomtrack" type="galaxy.datatypes.sequence:MafCustomTrack">
|
||||
<display file="ucsc/maf_customtrack.xml" />
|
||||
</datatype>
|
||||
<datatype extension="encodepeak" type="galaxy.datatypes.interval:ENCODEPeak" display_in_upload="True">
|
||||
<converter file="encodepeak_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/>
|
||||
<converter file="encodepeak_to_bgzip_converter.xml" target_datatype="bgzip"/>
|
||||
<converter file="bed_gff_or_vcf_to_bigwig_converter.xml" target_datatype="bigwig"/>
|
||||
</datatype>
|
||||
<datatype extension="encodepeak" type="galaxy.datatypes.interval:ENCODEPeak" display_in_upload="True">
|
||||
<converter file="encodepeak_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/>
|
||||
<converter file="encodepeak_to_bgzip_converter.xml" target_datatype="bgzip"/>
|
||||
<converter file="bed_gff_or_vcf_to_bigwig_converter.xml" target_datatype="bigwig"/>
|
||||
</datatype>
|
||||
<datatype extension="pdf" type="galaxy.datatypes.images:Pdf" mimetype="application/pdf"/>
|
||||
<datatype extension="pileup" type="galaxy.datatypes.tabular:Pileup" display_in_upload="true">
|
||||
<converter file="interval_to_bgzip_converter.xml" target_datatype="bgzip"/>
|
||||
@@ -172,11 +172,16 @@
|
||||
<datatype extension="qual454" type="galaxy.datatypes.qualityscore:QualityScore454" display_in_upload="true"/>
|
||||
<datatype extension="Roadmaps" type="galaxy.datatypes.assembly:Roadmaps" display_in_upload="false"/>
|
||||
<datatype extension="sam" type="galaxy.datatypes.tabular:Sam" display_in_upload="true">
|
||||
<converter file="sam_to_bam.xml" target_datatype="bam"/>
|
||||
<converter file="sam_to_bigwig_converter.xml" target_datatype="bigwig"/>
|
||||
</datatype>
|
||||
<converter file="sam_to_bam.xml" target_datatype="bam"/>
|
||||
<converter file="sam_to_bigwig_converter.xml" target_datatype="bigwig"/>
|
||||
</datatype>
|
||||
<datatype extension="scf" type="galaxy.datatypes.binary:Scf" mimetype="application/octet-stream" display_in_upload="true" description="A binary sequence file in 'scf' format with a '.scf' file extension. You must manually select this 'File Format' when uploading the file." description_url="https://wiki.galaxyproject.org/Learn/Datatypes#Scf"/>
|
||||
<datatype extension="Sequences" type="galaxy.datatypes.assembly:Sequences" display_in_upload="false"/>
|
||||
<datatype extension="snpeffdb" type="galaxy.datatypes.text:SnpEffDb" display_in_upload="True"/>
|
||||
<datatype extension="snpsiftdbnsfp" type="galaxy.datatypes.txt:SnpSiftDbNSFP" display_in_upload="True"/>
|
||||
<datatype extension="dbnsfp.tabular" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="True">
|
||||
<converter file="tabular_to_dbnsfp.xml" target_datatype="snpsiftdbnsfp"/>
|
||||
</datatype>
|
||||
<datatype extension="sff" type="galaxy.datatypes.binary:Sff" mimetype="application/octet-stream" display_in_upload="true" description="A binary file in 'Standard Flowgram Format' with a '.sff' file extension." description_url="https://wiki.galaxyproject.org/Learn/Datatypes#Sff"/>
|
||||
<datatype extension="svg" type="galaxy.datatypes.images:Image" mimetype="image/svg+xml"/>
|
||||
<datatype extension="taxonomy" type="galaxy.datatypes.tabular:Taxonomy" display_in_upload="true"/>
|
||||
|
||||
@@ -0,0 +1,12 @@
|
||||
<tool id="tabular_to_dbnsfp" name="Convert tabular to dbnsfp" version="1.0.0">
|
||||
<description></description>
|
||||
<command interpreter="python">tabular_to_dbnsfp.py $input $dbnsfp.extra_files_path/dbNSFP.gz</command>
|
||||
<inputs>
|
||||
<param format="tabular" name="input" type="data" label="Choose a dbnsfp tabular file"/>
|
||||
</inputs>
|
||||
<outputs>
|
||||
<data format="snpsiftdbnsfp" name="dbnsfp"/>
|
||||
</outputs>
|
||||
<help>
|
||||
</help>
|
||||
</tool>
|
||||
@@ -2,7 +2,6 @@
|
||||
""" Clearing house for generic text datatypes that are not XML or tabular.
|
||||
"""
|
||||
|
||||
|
||||
from galaxy.datatypes.data import Text
|
||||
from galaxy.datatypes.data import get_file_peek
|
||||
from galaxy.datatypes.data import nice_size
|
||||
@@ -12,13 +11,13 @@ from galaxy import util
|
||||
import tempfile
|
||||
import subprocess
|
||||
import json
|
||||
import gzip
|
||||
import os
|
||||
import re
|
||||
|
||||
import logging
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class Json( Text ):
|
||||
file_ext = "json"
|
||||
|
||||
@@ -259,3 +258,121 @@ class Arff( Text ):
|
||||
dataset.metadata.comment_lines = comment_lines
|
||||
dataset.metadata.columns = column_count
|
||||
|
||||
|
||||
class SnpEffDb( Text ):
|
||||
"""Class describing a SnpEff genome build"""
|
||||
file_ext = "snpeffdb"
|
||||
MetadataElement( name="genome_version", default=None, desc="Genome Version", readonly=True, visible=True, no_value=None )
|
||||
MetadataElement( name="regulation", default=[], desc="Regulation Names", readonly=True, visible=True, no_value=[], optional=True)
|
||||
MetadataElement( name="annotation", default=[], desc="Annotation Names", readonly=True, visible=True, no_value=[], optional=True)
|
||||
|
||||
def __init__( self, **kwd ):
|
||||
Text.__init__( self, **kwd )
|
||||
|
||||
def set_meta( self, dataset, **kwd ):
|
||||
Text.set_meta(self, dataset, **kwd )
|
||||
data_dir = dataset.extra_files_path
|
||||
## search data_dir/genome_version for files
|
||||
regulation_pattern = 'regulation_(.+).bin'
|
||||
# annotation files that are included in snpEff by a flag
|
||||
annotations_dict = {'nextProt.bin' : '-nextprot','motif.bin': '-motif'}
|
||||
regulations = []
|
||||
annotations = []
|
||||
if data_dir and os.path.isdir(data_dir):
|
||||
for root, dirs, files in os.walk(data_dir):
|
||||
for fname in files:
|
||||
if fname.startswith('snpEffectPredictor'):
|
||||
# if snpEffectPredictor.bin download succeeded
|
||||
genome_version = os.path.basename(root)
|
||||
dataset.metadata.genome_version = genome_version
|
||||
else:
|
||||
m = re.match(regulation_pattern,fname)
|
||||
if m:
|
||||
name = m.groups()[0]
|
||||
regulations.append(name)
|
||||
elif fname in annotations_dict:
|
||||
value = annotations_dict[fname]
|
||||
name = value.lstrip('-')
|
||||
annotations.append(name)
|
||||
dataset.metadata.regulation = regulations
|
||||
dataset.metadata.annotation = annotations
|
||||
try:
|
||||
fh = file(dataset.file_name,'w')
|
||||
fh.write("%s\n" % genome_version)
|
||||
if annotations:
|
||||
fh.write("annotations: %s\n" % ','.join(annotations))
|
||||
if regulations:
|
||||
fh.write("regulations: %s\n" % ','.join(regulations))
|
||||
fh.close()
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
class SnpSiftDbNSFP( Text ):
|
||||
"""Class describing a dbNSFP database prepared fpr use by SnpSift dbnsfp """
|
||||
MetadataElement( name='reference_name', default='dbSNFP' , desc='Reference Name', readonly=True, visible=True, set_in_upload=True, no_value='dbSNFP' )
|
||||
MetadataElement( name="bgzip", default=None, desc="dbNSFP bgzip", readonly=True, visible=True, no_value=None )
|
||||
MetadataElement( name="index", default=None, desc="Tabix Index File", readonly=True, visible=True, no_value=None)
|
||||
MetadataElement( name="annotation", default=[], desc="Annotation Names", readonly=True, visible=True, no_value=[] )
|
||||
file_ext = "snpsiftdbnsfp"
|
||||
composite_type = 'auto_primary_file'
|
||||
allow_datatype_change = False
|
||||
"""
|
||||
## The dbNSFP file is a tabular file with 1 header line
|
||||
## The first 4 columns are required to be: chrom pos ref alt
|
||||
## These match columns 1,2,4,5 of the VCF file
|
||||
## SnpSift requires the file to be block-gzipped and the indexed with samtools tabix
|
||||
## Example:
|
||||
## Compress using block-gzip algorithm
|
||||
bgzip dbNSFP2.3.txt
|
||||
## Create tabix index
|
||||
tabix -s 1 -b 2 -e 2 dbNSFP2.3.txt.gz
|
||||
"""
|
||||
def __init__( self, **kwd ):
|
||||
Text.__init__( self, **kwd )
|
||||
self.add_composite_file( '%s.grp', description = 'Group File', substitute_name_with_metadata = 'reference_name', is_binary = False )
|
||||
self.add_composite_file( '%s.ti', description = '', substitute_name_with_metadata = 'reference_name', is_binary = False )
|
||||
def init_meta( self, dataset, copy_from=None ):
|
||||
Text.init_meta( self, dataset, copy_from=copy_from )
|
||||
def generate_primary_file( self, dataset = None ):
|
||||
"""
|
||||
This is called only at upload to write the html file
|
||||
cannot rename the datasets here - they come with the default unfortunately
|
||||
"""
|
||||
regenerate_primary_file( self, dataset)
|
||||
def regenerate_primary_file(self,dataset):
|
||||
"""
|
||||
cannot do this until we are setting metadata
|
||||
"""
|
||||
annotations = "dbNSFP Annotations: %s\n" % ','.join(dataset.metadata.annotation)
|
||||
f = open(dataset.file_name,'a')
|
||||
if dataset.metadata.bgzip:
|
||||
bn = dataset.metadata.bgzip
|
||||
f.write(bn)
|
||||
f.write('\n')
|
||||
f.write(annotations)
|
||||
f.close()
|
||||
def set_meta( self, dataset, overwrite=True, **kwd ):
|
||||
try:
|
||||
efp = dataset.extra_files_path
|
||||
if os.path.exists(efp):
|
||||
flist = os.listdir(efp)
|
||||
for i,fname in enumerate(flist):
|
||||
if fname.endswith('.gz'):
|
||||
dataset.metadata.bgzip = fname
|
||||
try:
|
||||
fh = gzip.open(os.path.join(efp,fname),'r')
|
||||
buf = fh.read(5000)
|
||||
lines = buf.splitlines()
|
||||
headers = lines[0].split('\t')
|
||||
dataset.metadata.annotation = headers[4:]
|
||||
except Exception,e:
|
||||
log.warn("set_meta fname: %s %s" % (fname,str(e)))
|
||||
finally:
|
||||
fh.close()
|
||||
if fname.endswith('.tbi'):
|
||||
dataset.metadata.index = fname
|
||||
self.regenerate_primary_file(dataset)
|
||||
except Exception,e:
|
||||
log.warn("set_meta fname: %s %s" % (dataset.file_name if dataset and dataset.file_name else 'Unkwown',str(e)))
|
||||
|
||||
|
||||
Reference in New Issue
Block a user