].
- Intervals are GenomicInterval objects.
- """
- primary = readers[0]
- features = readers[1]
- either = False
- if region == 'Upstream':
- up, down = True, False
- elif region == 'Downstream':
- up, down = False, True
- else:
- up, down = True, True
- if region == 'Either':
- either = True
-
- # Read features into memory:
- rightTree = quicksect.IntervalTree()
- for item in features:
- if type( item ) is GenomicInterval:
- rightTree.insert( item, features.linenum, item )
-
- for interval in primary:
- if type( interval ) is Header:
- yield interval
- if type( interval ) is Comment and comments:
- yield interval
- elif type( interval ) == GenomicInterval:
- chrom = interval.chrom
- start = int(interval.start)
- end = int(interval.end)
- strand = interval.strand
- if chrom not in rightTree.chroms:
- continue
- else:
- root = rightTree.chroms[chrom] #root node for the chrom tree
- result_up = []
- result_down = []
- if (strand == '+' and up) or (strand == '-' and down):
- #upstream +ve strand and downstream -ve strand cases
- get_closest_feature (root, 1, start, None, lambda node: result_up.append( node ), None)
-
- if (strand == '+' and down) or (strand == '-' and up):
- #downstream +ve strand and upstream -ve strand case
- get_closest_feature (root, 0, None, end-1, None, lambda node: result_down.append( node ))
-
- if result_up:
- if len(result_up) > 1: #The results_up list has a list of intervals upstream to the given interval.
- ends = []
- for n in result_up:
- ends.append(n.end)
- res_ind = ends.index(max(ends)) #fetch the index of the closest interval i.e. the interval with the max end from the results_up list
- else:
- res_ind = 0
- if not(either):
- yield [ interval, result_up[res_ind].other ]
-
- if result_down:
- if not(either):
- #The last element of result_down will be the closest element to the given interval
- yield [ interval, result_down[-1].other ]
-
- if either and (result_up or result_down):
- iter_val = []
- if result_up and result_down:
- if abs(start - int(result_up[res_ind].end)) <= abs(end - int(result_down[-1].start)):
- iter_val = [ interval, result_up[res_ind].other ]
- else:
- #The last element of result_down will be the closest element to the given interval
- iter_val = [ interval, result_down[-1].other ]
- elif result_up:
- iter_val = [ interval, result_up[res_ind].other ]
- elif result_down:
- #The last element of result_down will be the closest element to the given interval
- iter_val = [ interval, result_down[-1].other ]
- yield iter_val
-
-def main():
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
- in1_gff_format = bool( options.gff1 )
- in2_gff_format = bool( options.gff2 )
- in_fname, in2_fname, out_fname, direction = args
- except:
- doc_optparse.exception()
-
- # Set readers to handle either GFF or default format.
- if in1_gff_format:
- in1_reader_wrapper = GFFIntervalToBEDReaderWrapper
- else:
- in1_reader_wrapper = NiceReaderWrapper
- if in2_gff_format:
- in2_reader_wrapper = GFFIntervalToBEDReaderWrapper
- else:
- in2_reader_wrapper = NiceReaderWrapper
-
- g1 = in1_reader_wrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
- g2 = in2_reader_wrapper( fileinput.FileInput( in2_fname ),
- chrom_col=chr_col_2,
- start_col=start_col_2,
- end_col=end_col_2,
- strand_col=strand_col_2,
- fix_strand=True )
-
- # Find flanking features.
- out_file = open( out_fname, "w" )
- try:
- for result in proximal_region_finder([g1,g2], direction):
- if type( result ) is list:
- line, closest_feature = result
- # Need to join outputs differently depending on file types.
- if in1_gff_format:
- # Output is GFF with added attribute 'closest feature.'
-
- # Invervals are in BED coordinates; need to convert to GFF.
- line = convert_bed_coords_to_gff( line )
- closest_feature = convert_bed_coords_to_gff( closest_feature )
-
- # Replace double quotes with single quotes in closest feature's attributes.
- out_file.write( "%s closest_feature \"%s\" \n" %
- ( "\t".join( line.fields ), \
- "\t".join( closest_feature.fields ).replace( "\"", "\\\"" )
- ) )
- else:
- # Output is BED + closest feature fields.
- output_line_fields = []
- output_line_fields.extend( line.fields )
- output_line_fields.extend( closest_feature.fields )
- out_file.write( "%s\n" % ( "\t".join( output_line_fields ) ) )
- else:
- out_file.write( "%s\n" % result )
- except ParseError, exc:
- fail( "Invalid file format: %s" % str( exc ) )
-
- print "Direction: %s" %(direction)
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 1st dataset" )
- if g2.skipped > 0:
- print skipped( g2, filedesc=" of 2nd dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/flanking_features.xml b/tools/new_operations/flanking_features.xml
deleted file mode 100644
index e8018b83677..00000000000
--- a/tools/new_operations/flanking_features.xml
+++ /dev/null
@@ -1,127 +0,0 @@
-
- for every interval
-
- flanking_features.py $input1 $input2 $out_file1 $direction
-
- #if isinstance( $input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
- -1 1,4,5,7 --gff1
- #else:
- -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}
- #end if
-
- #if isinstance( $input2.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
- -2 1,4,5,7 --gff2
- #else:
- -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol}
- #end if
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-.. class:: infomark
-
-**What it does**
-
-For every interval in the **interval** dataset, this tool fetches the **closest non-overlapping** upstream and / or downstream features from the **features** dataset.
-
------
-
-.. class:: warningmark
-
-**Note:**
-
-Every line should contain at least 3 columns: chromosome number, start and stop coordinates. If any of these columns is missing or if start and stop coordinates are not numerical, the lines will be treated as invalid and skipped. The number of skipped lines is documented in the resulting history item as a "data issue".
-
-If the strand column is missing from your input interval dataset, the intervals will be considered to be on positive strand. You can add a strand column to your input dataset by using the *Text Manipulation->Add column* tool.
-
-For GFF files, features are added as a GTF-style attribute at the end of the line.
-
------
-
-**Example**
-
-If the **intervals** are::
-
- chr1 10 100 Query1.1
- chr1 500 1000 Query1.2
- chr1 1100 1250 Query1.3
-
-and the **features** are::
-
- chr1 120 180 Query2.1
- chr1 140 200 Query2.2
- chr1 580 1050 Query2.3
- chr1 2000 2204 Query2.4
- chr1 2500 3000 Query2.5
-
-Running this tool for **Both Upstream and Downstream** will return::
-
- chr1 10 100 Query1.1 chr1 120 180 Query2.1
- chr1 500 1000 Query1.2 chr1 140 200 Query2.2
- chr1 500 1000 Query1.2 chr1 2000 2204 Query2.4
- chr1 1100 1250 Query1.3 chr1 580 1050 Query2.3
- chr1 1100 1250 Query1.3 chr1 2000 2204 Query2.4
-
-
-
-
-
\ No newline at end of file
diff --git a/tools/new_operations/get_flanks.py b/tools/new_operations/get_flanks.py
deleted file mode 100644
index 05d6ef42605..00000000000
--- a/tools/new_operations/get_flanks.py
+++ /dev/null
@@ -1,191 +0,0 @@
-#!/usr/bin/env python
-#Done by: Guru
-
-"""
-Get Flanking regions.
-
-usage: %prog input out_file size direction region
- -l, --cols=N,N,N,N: Columns for chrom, start, end, strand in file
- -o, --off=N: Offset
-"""
-
-import sys, re, os
-from galaxy import eggs
-import pkg_resources; pkg_resources.require( "bx-python" )
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-def stop_err( msg ):
- sys.stderr.write( msg )
- sys.exit()
-
-def main():
- try:
- if int( sys.argv[3] ) < 0:
- raise Exception
- except:
- stop_err( "Length of flanking region(s) must be a non-negative integer." )
-
- # Parsing Command Line here
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols )
- inp_file, out_file, size, direction, region = args
- if strand_col_1 <= 0:
- strand = "+" #if strand is not defined, default it to +
- except:
- stop_err( "Metadata issue, correct the metadata attributes by clicking on the pencil icon in the history item." )
- try:
- offset = int(options.off)
- size = int(size)
- except:
- stop_err( "Invalid offset or length entered. Try again by entering valid integer values." )
-
- fo = open(out_file,'w')
-
- skipped_lines = 0
- first_invalid_line = 0
- invalid_line = None
- elems = []
- j=0
- for i, line in enumerate( file( inp_file ) ):
- line = line.strip()
- if line and (not line.startswith( '#' )) and line != '':
- j+=1
- try:
- elems = line.split('\t')
- #if the start and/or end columns are not numbers, skip that line.
- assert int(elems[start_col_1])
- assert int(elems[end_col_1])
- if strand_col_1 != -1:
- strand = elems[strand_col_1]
- #if the stand value is not + or -, skip that line.
- assert strand in ['+', '-']
- if direction == 'Upstream':
- if strand == '+':
- if region == 'end':
- elems[end_col_1] = str(int(elems[end_col_1]) + offset)
- elems[start_col_1] = str( int(elems[end_col_1]) - size )
- else:
- elems[end_col_1] = str(int(elems[start_col_1]) + offset)
- elems[start_col_1] = str( int(elems[end_col_1]) - size )
- elif strand == '-':
- if region == 'end':
- elems[start_col_1] = str(int(elems[start_col_1]) - offset)
- elems[end_col_1] = str(int(elems[start_col_1]) + size)
- else:
- elems[start_col_1] = str(int(elems[end_col_1]) - offset)
- elems[end_col_1] = str(int(elems[start_col_1]) + size)
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
-
- elif direction == 'Downstream':
- if strand == '-':
- if region == 'start':
- elems[end_col_1] = str(int(elems[end_col_1]) - offset)
- elems[start_col_1] = str( int(elems[end_col_1]) - size )
- else:
- elems[end_col_1] = str(int(elems[start_col_1]) - offset)
- elems[start_col_1] = str( int(elems[end_col_1]) - size )
- elif strand == '+':
- if region == 'start':
- elems[start_col_1] = str(int(elems[start_col_1]) + offset)
- elems[end_col_1] = str(int(elems[start_col_1]) + size)
- else:
- elems[start_col_1] = str(int(elems[end_col_1]) + offset)
- elems[end_col_1] = str(int(elems[start_col_1]) + size)
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
-
- elif direction == 'Both':
- if strand == '-':
- if region == 'start':
- start = str(int(elems[end_col_1]) - offset)
- end1 = str(int(start) + size)
- end2 = str(int(start) - size)
- elems[start_col_1]=start
- elems[end_col_1]=end1
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elems[start_col_1]=end2
- elems[end_col_1]=start
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elif region == 'end':
- start = str(int(elems[start_col_1]) - offset)
- end1 = str(int(start) + size)
- end2 = str(int(start) - size)
- elems[start_col_1]=start
- elems[end_col_1]=end1
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elems[start_col_1]=end2
- elems[end_col_1]=start
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- else:
- start1 = str(int(elems[end_col_1]) - offset)
- end1 = str(int(start1) + size)
- start2 = str(int(elems[start_col_1]) - offset)
- end2 = str(int(start2) - size)
- elems[start_col_1]=start1
- elems[end_col_1]=end1
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elems[start_col_1]=end2
- elems[end_col_1]=start2
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elif strand == '+':
- if region == 'start':
- start = str(int(elems[start_col_1]) + offset)
- end1 = str(int(start) - size)
- end2 = str(int(start) + size)
- elems[start_col_1]=end1
- elems[end_col_1]=start
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elems[start_col_1]=start
- elems[end_col_1]=end2
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elif region == 'end':
- start = str(int(elems[end_col_1]) + offset)
- end1 = str(int(start) - size)
- end2 = str(int(start) + size)
- elems[start_col_1]=end1
- elems[end_col_1]=start
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elems[start_col_1]=start
- elems[end_col_1]=end2
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- else:
- start1 = str(int(elems[start_col_1]) + offset)
- end1 = str(int(start1) - size)
- start2 = str(int(elems[end_col_1]) + offset)
- end2 = str(int(start2) + size)
- elems[start_col_1]=end1
- elems[end_col_1]=start1
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- elems[start_col_1]=start2
- elems[end_col_1]=end2
- assert int(elems[start_col_1]) > 0 and int(elems[end_col_1]) > 0
- fo.write( "%s\n" % '\t'.join( elems ) )
- except:
- skipped_lines += 1
- if not invalid_line:
- first_invalid_line = i + 1
- invalid_line = line
- fo.close()
-
- if skipped_lines == j:
- stop_err( "Data issue: click the pencil icon in the history item to correct the metadata attributes." )
- if skipped_lines > 0:
- print 'Skipped %d invalid lines starting with #%dL "%s"' % ( skipped_lines, first_invalid_line, invalid_line )
- print 'Location: %s, Region: %s, Flank-length: %d, Offset: %d ' %( direction, region, size, offset )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/get_flanks.xml b/tools/new_operations/get_flanks.xml
deleted file mode 100644
index 2c4a0e5b852..00000000000
--- a/tools/new_operations/get_flanks.xml
+++ /dev/null
@@ -1,78 +0,0 @@
-
- returns flanking region/s for every gene
- get_flanks.py $input $out_file1 $size $direction $region -o $offset -l ${input.metadata.chromCol},${input.metadata.startCol},${input.metadata.endCol},${input.metadata.strandCol}
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-This tool finds the upstream and/or downstream flanking region(s) of all the selected regions in the input file.
-
-**Note:** Every line should contain at least 3 columns: Chromosome number, Start and Stop co-ordinates. If any of these columns is missing or if start and stop co-ordinates are not numerical, the tool may encounter exceptions and such lines are skipped as invalid. The number of invalid skipped lines is documented in the resulting history item as a "Data issue".
-
------
-
-
-**Example 1**
-
-- For the following dataset::
-
- chr22 1000 7000 NM_174568 0 +
-
-- running get flanks with Region: Around start, Offset: -200, Flank-length: 300 and Location: Upstream will return **(Red: Dataset positive strand; Blue: Flanks output)**::
-
- chr22 500 800 NM_174568 0 +
-
-.. image:: ${static_path}/operation_icons/flanks_ex1.gif
-
-**Example 2**
-
-- For the following dataset::
-
- chr22 1000 7000 NM_028946 0 -
-
-- running get flanks with Region: Whole, Offset: 200, Flank-length: 300 and Location: Downstream will return **(Orange: Dataset negative strand; Magenta: Flanks output)**::
-
- chr22 500 800 NM_028946 0 -
-
-.. image:: ${static_path}/operation_icons/flanks_ex2.gif
-
-
-
-
-
diff --git a/tools/new_operations/gops_basecoverage.py b/tools/new_operations/gops_basecoverage.py
deleted file mode 100644
index da78701afa9..00000000000
--- a/tools/new_operations/gops_basecoverage.py
+++ /dev/null
@@ -1,50 +0,0 @@
-#!/usr/bin/env python
-"""
-Count total base coverage.
-
-usage: %prog in_file out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.base_coverage import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- in_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col = strand_col_1,
- fix_strand=True )
-
- try:
- bases = base_coverage(g1)
- except ParseError, exc:
- fail( "Invalid file format: %s" % str( exc ) )
- out_file = open( out_fname, "w" )
- out_file.write( "%s\n" % str( bases ) )
- out_file.close()
- if g1.skipped > 0:
- print skipped( g1, filedesc="" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_cluster.py b/tools/new_operations/gops_cluster.py
deleted file mode 100644
index ac2f4f75d0a..00000000000
--- a/tools/new_operations/gops_cluster.py
+++ /dev/null
@@ -1,132 +0,0 @@
-#!/usr/bin/env python
-"""
-Cluster regions of intervals.
-
-usage: %prog in_file out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in file
- -d, --distance=N: Maximum distance between clustered intervals
- -v, --overlap=N: Minimum overlap require (negative distance)
- -m, --minregions=N: Minimum regions per cluster
- -o, --output=N: 1)merged 2)filtered 3)clustered 4) minimum 5) maximum
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.find_clusters import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- distance = 0
- minregions = 2
- output = 1
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- if options.distance: distance = int( options.distance )
- if options.overlap: distance = -1 * int( options.overlap )
- if options.output: output = int( options.output )
- if options.minregions: minregions = int( options.minregions )
- in_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
-
- # Get the cluster tree
- try:
- clusters, extra = find_clusters( g1, mincols=distance, minregions=minregions)
- except ParseError, exc:
- fail( "Invalid file format: %s" % str( exc ) )
-
- f1 = open( in_fname, "r" )
- out_file = open( out_fname, "w" )
-
- # If "merge"
- if output == 1:
- fields = ["." for x in range(max(g1.chrom_col, g1.start_col, g1.end_col)+1)]
- for chrom, tree in clusters.items():
- for start, end, lines in tree.getregions():
- fields[g1.chrom_col] = chrom
- fields[g1.start_col] = str(start)
- fields[g1.end_col] = str(end)
- out_file.write( "%s\n" % "\t".join( fields ) )
-
- # If "filtered" we preserve order of file and comments, etc.
- if output == 2:
- linenums = dict()
- for chrom, tree in clusters.items():
- for linenum in tree.getlines():
- linenums[linenum] = 0
- linenum = -1
- f1.seek(0)
- for line in f1.readlines():
- linenum += 1
- if linenum in linenums or linenum in extra:
- out_file.write( "%s\n" % line.rstrip( "\n\r" ) )
-
- # If "clustered" we output original intervals, but near each other (i.e. clustered)
- if output == 3:
- linenums = list()
- f1.seek(0)
- fileLines = f1.readlines()
- for chrom, tree in clusters.items():
- for linenum in tree.getlines():
- out_file.write( "%s\n" % fileLines[linenum].rstrip( "\n\r" ) )
-
- # If "minimum" we output the smallest interval in each cluster
- if output == 4 or output == 5:
- linenums = list()
- f1.seek(0)
- fileLines = f1.readlines()
- for chrom, tree in clusters.items():
- regions = tree.getregions()
- for start, end, lines in tree.getregions():
- outsize = -1
- outinterval = None
- for line in lines:
- # three nested for loops?
- # should only execute this code once per line
- fileline = fileLines[line].rstrip("\n\r")
- try:
- cluster_interval = GenomicInterval( g1, fileline.split("\t"),
- g1.chrom_col,
- g1.start_col,
- g1.end_col,
- g1.strand_col,
- g1.default_strand,
- g1.fix_strand )
- except Exception, exc:
- print >> sys.stderr, str( exc )
- f1.close()
- sys.exit()
- interval_size = cluster_interval.end - cluster_interval.start
- if outsize == -1 or \
- ( outsize > interval_size and output == 4 ) or \
- ( outsize < interval_size and output == 5 ) :
- outinterval = cluster_interval
- outsize = interval_size
- out_file.write( "%s\n" % outinterval )
-
- f1.close()
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc="" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_complement.py b/tools/new_operations/gops_complement.py
deleted file mode 100644
index 7615f83f4e2..00000000000
--- a/tools/new_operations/gops_complement.py
+++ /dev/null
@@ -1,98 +0,0 @@
-#!/usr/bin/env python
-"""
-Complement regions.
-
-usage: %prog in_file out_file
- -1, --cols1=N,N,N,N: Columns for chrom, start, end, strand in file
- -l, --lengths=N: Filename of .len file for species (chromosome lengths)
- -a, --all: Complement all chromosomes (Genome-wide complement)
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.complement import complement
-from bx.intervals.operations.subtract import subtract
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- allchroms = False
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- lengths = options.lengths
- if options.all: allchroms = True
- in_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
-
- lens = dict()
- chroms = list()
- # dbfile is used to determine the length of each chromosome. The lengths
- # are added to the lens dict and passed copmlement operation code in bx.
- dbfile = fileinput.FileInput( lengths )
-
- if dbfile:
- if not allchroms:
- try:
- for line in dbfile:
- fields = line.split("\t")
- lens[fields[0]] = int(fields[1])
- except:
- # assume LEN doesn't exist or is corrupt somehow
- pass
- elif allchroms:
- try:
- for line in dbfile:
- fields = line.split("\t")
- end = int(fields[1])
- chroms.append("\t".join([fields[0],"0",str(end)]))
- except:
- pass
-
- # Safety...if the dbfile didn't exist and we're on allchroms, then
- # default to generic complement
- if allchroms and len(chroms) == 0:
- allchroms = False
-
- if allchroms:
- chromReader = GenomicIntervalReader(chroms)
- generator = subtract([chromReader, g1])
- else:
- generator = complement(g1, lens)
-
- out_file = open( out_fname, "w" )
-
- try:
- for interval in generator:
- if type( interval ) is GenomicInterval:
- out_file.write( "%s\n" % "\t".join( interval ) )
- else:
- out_file.write( "%s\n" % interval )
- except ParseError, exc:
- out_file.close()
- fail( "Invalid file format: %s" % str( exc ) )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc="" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_concat.py b/tools/new_operations/gops_concat.py
deleted file mode 100644
index 9490c41401d..00000000000
--- a/tools/new_operations/gops_concat.py
+++ /dev/null
@@ -1,76 +0,0 @@
-#!/usr/bin/env python
-"""
-Concatenate two bed files. The concatenated files are returned in the
-same format as the first. If --sameformat is specified, then all
-columns will be treated as the same, and all fields will be saved,
-although the output will be trimmed to match the primary input. In
-addition, if --sameformat is specified, missing fields will be padded
-with a period(.).
-
-usage: %prog in_file_1 in_file_2 out_file
- -1, --cols1=N,N,N,N: Columns for chrom, start, end, strand in first file
- -2, --cols2=N,N,N,N: Columns for chrom, start, end, strand in second file
- -s, --sameformat: All files are precisely the same format.
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.concat import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- sameformat=False
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
- if options.sameformat: sameformat = True
- in_file_1, in_file_2, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_file_1 ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
-
- g2 = NiceReaderWrapper( fileinput.FileInput( in_file_2 ),
- chrom_col=chr_col_2,
- start_col=start_col_2,
- end_col=end_col_2,
- strand_col=strand_col_2,
- fix_strand=True )
-
- out_file = open( out_fname, "w" )
-
- try:
- for line in concat( [g1, g2], sameformat=sameformat ):
- if type( line ) is GenomicInterval:
- out_file.write( "%s\n" % "\t".join( line.fields ) )
- else:
- out_file.write( "%s\n" % line )
- except ParseError, exc:
- out_file.close()
- fail( "Invalid file format: %s" % str( exc ) )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 1st dataset" )
- if g2.skipped > 0:
- print skipped( g2, filedesc=" of 2nd dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_coverage.py b/tools/new_operations/gops_coverage.py
deleted file mode 100644
index 91b3ad19803..00000000000
--- a/tools/new_operations/gops_coverage.py
+++ /dev/null
@@ -1,68 +0,0 @@
-#!/usr/bin/env python
-"""
-Calculate coverage of one query on another, and append the coverage to
-the last two columns as bases covered and percent coverage.
-
-usage: %prog bed_file_1 bed_file_2 out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
- -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.coverage import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
- in_fname, in2_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
- g2 = NiceReaderWrapper( fileinput.FileInput( in2_fname ),
- chrom_col=chr_col_2,
- start_col=start_col_2,
- end_col=end_col_2,
- strand_col=strand_col_2,
- fix_strand=True )
-
- out_file = open( out_fname, "w" )
-
- try:
- for line in coverage( [g1,g2] ):
- if type( line ) is GenomicInterval:
- out_file.write( "%s\n" % "\t".join( line.fields ) )
- else:
- out_file.write( "%s\n" % line )
- except ParseError, exc:
- out_file.close()
- fail( "Invalid file format: %s" % str( exc ) )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 1st dataset" )
- if g2.skipped > 0:
- print skipped( g2, filedesc=" of 2nd dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_intersect.py b/tools/new_operations/gops_intersect.py
deleted file mode 100755
index 11a0c80f902..00000000000
--- a/tools/new_operations/gops_intersect.py
+++ /dev/null
@@ -1,98 +0,0 @@
-#!/usr/bin/env python
-"""
-Find regions of first interval file that overlap regions in a second interval file.
-Interval files can either be BED or GFF format.
-
-usage: %prog interval_file_1 interval_file_2 out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
- -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
- -m, --mincols=N: Require this much overlap (default 1bp)
- -p, --pieces: just print pieces of second set (after padding)
- -G, --gff1: input 1 is GFF format, meaning start and end coordinates are 1-based, closed interval
- -H, --gff2: input 2 is GFF format, meaning start and end coordinates are 1-based, closed interval
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.intersect import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-from galaxy.datatypes.util.gff_util import GFFFeature, GFFReaderWrapper, convert_bed_coords_to_gff
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- mincols = 1
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
- if options.mincols: mincols = int( options.mincols )
- pieces = bool( options.pieces )
- in1_gff_format = bool( options.gff1 )
- in2_gff_format = bool( options.gff2 )
- in_fname, in2_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- # Set readers to handle either GFF or default format.
- if in1_gff_format:
- in1_reader_wrapper = GFFReaderWrapper
- else:
- in1_reader_wrapper = NiceReaderWrapper
- if in2_gff_format:
- in2_reader_wrapper = GFFReaderWrapper
- else:
- in2_reader_wrapper = NiceReaderWrapper
-
- g1 = in1_reader_wrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
- if in1_gff_format:
- # Intersect requires coordinates in BED format.
- g1.convert_to_bed_coord=True
- g2 = in2_reader_wrapper( fileinput.FileInput( in2_fname ),
- chrom_col=chr_col_2,
- start_col=start_col_2,
- end_col=end_col_2,
- strand_col=strand_col_2,
- fix_strand=True )
- if in2_gff_format:
- # Intersect requires coordinates in BED format.
- g2.convert_to_bed_coord=True
-
- out_file = open( out_fname, "w" )
- try:
- for feature in intersect( [g1,g2], pieces=pieces, mincols=mincols ):
- if isinstance( feature, GFFFeature ):
- # Convert back to GFF coordinates since reader converted automatically.
- convert_bed_coords_to_gff( feature )
- for interval in feature.intervals:
- out_file.write( "%s\n" % "\t".join( interval.fields ) )
- elif isinstance( feature, GenomicInterval ):
- out_file.write( "%s\n" % "\t".join( feature.fields ) )
- else:
- out_file.write( "%s\n" % feature )
- except ParseError, e:
- out_file.close()
- fail( "Invalid file format: %s" % str( e ) )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 1st dataset" )
- if g2.skipped > 0:
- print skipped( g2, filedesc=" of 2nd dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_join.py b/tools/new_operations/gops_join.py
deleted file mode 100644
index daab6cb18e0..00000000000
--- a/tools/new_operations/gops_join.py
+++ /dev/null
@@ -1,82 +0,0 @@
-#!/usr/bin/env python
-"""
-Join two sets of intervals using their overlap as the key.
-
-usage: %prog bed_file_1 bed_file_2 out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
- -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
- -m, --mincols=N: Require this much overlap (default 1bp)
- -f, --fill=N: none, right, left, both
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.join import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- mincols = 1
- upstream_pad = 0
- downstream_pad = 0
- leftfill = False
- rightfill = False
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
- if options.mincols: mincols = int( options.mincols )
- if options.fill:
- if options.fill == "both":
- rightfill = leftfill = True
- else:
- rightfill = options.fill == "right"
- leftfill = options.fill == "left"
- in_fname, in2_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
- g2 = NiceReaderWrapper( fileinput.FileInput( in2_fname ),
- chrom_col=chr_col_2,
- start_col=start_col_2,
- end_col=end_col_2,
- strand_col=strand_col_2,
- fix_strand=True )
-
- out_file = open( out_fname, "w" )
-
- try:
- for outfields in join(g1, g2, mincols=mincols, rightfill=rightfill, leftfill=leftfill):
- if type( outfields ) is list:
- out_file.write( "%s\n" % "\t".join( outfields ) )
- else:
- out_file.write( "%s\n" % outfields )
- except ParseError, exc:
- out_file.close()
- fail( "Invalid file format: %s" % str( exc ) )
- except MemoryError:
- out_file.close()
- fail( "Input datasets were too large to complete the join operation." )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 1st dataset" )
- if g2.skipped > 0:
- print skipped( g2, filedesc=" of 2nd dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_merge.py b/tools/new_operations/gops_merge.py
deleted file mode 100644
index 85d215f83f4..00000000000
--- a/tools/new_operations/gops_merge.py
+++ /dev/null
@@ -1,71 +0,0 @@
-#!/usr/bin/env python
-"""
-Merge overlaping regions.
-
-usage: %prog in_file out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
- -m, --mincols=N: Require this much overlap (default 1bp)
- -3, --threecol: Output 3 column bed
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.merge import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- mincols = 1
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- if options.mincols: mincols = int( options.mincols )
- in_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col = strand_col_1,
- fix_strand=True )
-
- out_file = open( out_fname, "w" )
-
- try:
- for line in merge(g1,mincols=mincols):
- if options.threecol:
- if type( line ) is GenomicInterval:
- out_file.write( "%s\t%s\t%s\n" % ( line.chrom, str( line.startCol ), str( line.endCol ) ) )
- elif type( line ) is list:
- out_file.write( "%s\t%s\t%s\n" % ( line[chr_col_1], str( line[start_col_1] ), str( line[end_col_1] ) ) )
- else:
- out_file.write( "%s\n" % line )
- else:
- if type( line ) is GenomicInterval:
- out_file.write( "%s\n" % "\t".join( line.fields ) )
- elif type( line ) is list:
- out_file.write( "%s\n" % "\t".join( line ) )
- else:
- out_file.write( "%s\n" % line )
- except ParseError, exc:
- out_file.close()
- fail( "Invalid file format: %s" % str( exc ) )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 1st dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/gops_subtract.py b/tools/new_operations/gops_subtract.py
deleted file mode 100644
index 9a8aa0d66ad..00000000000
--- a/tools/new_operations/gops_subtract.py
+++ /dev/null
@@ -1,99 +0,0 @@
-#!/usr/bin/env python
-"""
-Find regions of first interval file that do not overlap regions in a second
-interval file. Interval files can either be BED or GFF format.
-
-usage: %prog interval_file_1 interval_file_2 out_file
- -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
- -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
- -m, --mincols=N: Require this much overlap (default 1bp)
- -p, --pieces: just print pieces of second set (after padding)
- -G, --gff1: input 1 is GFF format, meaning start and end coordinates are 1-based, closed interval
- -H, --gff2: input 2 is GFF format, meaning start and end coordinates are 1-based, closed interval
-"""
-from galaxy import eggs
-import pkg_resources
-pkg_resources.require( "bx-python" )
-import sys, traceback, fileinput
-from warnings import warn
-from bx.intervals import *
-from bx.intervals.io import *
-from bx.intervals.operations.subtract import *
-from bx.cookbook import doc_optparse
-from galaxy.tools.util.galaxyops import *
-from galaxy.datatypes.util.gff_util import GFFFeature, GFFReaderWrapper, convert_bed_coords_to_gff
-
-assert sys.version_info[:2] >= ( 2, 4 )
-
-def main():
- mincols = 1
- upstream_pad = 0
- downstream_pad = 0
-
- options, args = doc_optparse.parse( __doc__ )
- try:
- chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
- chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
- if options.mincols: mincols = int( options.mincols )
- pieces = bool( options.pieces )
- in1_gff_format = bool( options.gff1 )
- in2_gff_format = bool( options.gff2 )
- in_fname, in2_fname, out_fname = args
- except:
- doc_optparse.exception()
-
- # Set readers to handle either GFF or default format.
- if in1_gff_format:
- in1_reader_wrapper = GFFReaderWrapper
- else:
- in1_reader_wrapper = NiceReaderWrapper
- if in2_gff_format:
- in2_reader_wrapper = GFFReaderWrapper
- else:
- in2_reader_wrapper = NiceReaderWrapper
-
- g1 = in1_reader_wrapper( fileinput.FileInput( in_fname ),
- chrom_col=chr_col_1,
- start_col=start_col_1,
- end_col=end_col_1,
- strand_col=strand_col_1,
- fix_strand=True )
- if in1_gff_format:
- # Subtract requires coordinates in BED format.
- g1.convert_to_bed_coord=True
-
- g2 = in2_reader_wrapper( fileinput.FileInput( in2_fname ),
- chrom_col=chr_col_2,
- start_col=start_col_2,
- end_col=end_col_2,
- strand_col=strand_col_2,
- fix_strand=True )
- if in2_gff_format:
- # Subtract requires coordinates in BED format.
- g2.convert_to_bed_coord=True
-
- out_file = open( out_fname, "w" )
- try:
- for feature in subtract( [g1,g2], pieces=pieces, mincols=mincols ):
- if isinstance( feature, GFFFeature ):
- # Convert back to GFF coordinates since reader converted automatically.
- convert_bed_coords_to_gff( feature )
- for interval in feature.intervals:
- out_file.write( "%s\n" % "\t".join( interval.fields ) )
- elif isinstance( feature, GenomicInterval ):
- out_file.write( "%s\n" % "\t".join( feature.fields ) )
- else:
- out_file.write( "%s\n" % feature )
- except ParseError, exc:
- out_file.close()
- fail( "Invalid file format: %s" % str( exc ) )
-
- out_file.close()
-
- if g1.skipped > 0:
- print skipped( g1, filedesc=" of 2nd dataset" )
- if g2.skipped > 0:
- print skipped( g2, filedesc=" of 1st dataset" )
-
-if __name__ == "__main__":
- main()
diff --git a/tools/new_operations/intersect.xml b/tools/new_operations/intersect.xml
deleted file mode 100644
index 642a94d34cd..00000000000
--- a/tools/new_operations/intersect.xml
+++ /dev/null
@@ -1,143 +0,0 @@
-
- the intervals of two datasets
- gops_intersect.py
- $input1 $input2 $output
-
- #if isinstance( $input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
- -1 1,4,5,7 --gff1
- #else:
- -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}
- #end if
-
- #if isinstance( $input2.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
- -2 1,4,5,7 --gff2
- #else:
- -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol}
- #end if
-
- -m $min $returntype
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-.. class:: infomark
-
-**TIP:** If your dataset does not appear in the pulldown menu, it means that it is not in interval format. Use "edit attributes" to set chromosome, start, end, and strand columns.
-
------
-
-**Screencasts!**
-
-See Galaxy Interval Operation Screencasts_ (right click to open this link in another window).
-
-.. _Screencasts: http://wiki.g2.bx.psu.edu/Learn/Interval%20Operations
-
------
-
-This operation merges all overlapping intervals into single intervals.
-
-**Example**
-
-.. image:: ${static_path}/operation_icons/gops_merge.gif
-
-
-
\ No newline at end of file
diff --git a/tools/new_operations/operation_filter.py b/tools/new_operations/operation_filter.py
deleted file mode 100644
index a44a043cbd6..00000000000
--- a/tools/new_operations/operation_filter.py
+++ /dev/null
@@ -1,99 +0,0 @@
-# runs after the job (and after the default post-filter)
-import os
-from galaxy import eggs
-from galaxy import jobs
-from galaxy.tools.parameters import DataToolParameter
-
-from galaxy.jobs.handler import JOB_ERROR
-
-# Older py compatibility
-try:
- set()
-except:
- from sets import Set as set
-
-#def exec_before_process(app, inp_data, out_data, param_dict, tool=None):
-# """Sets the name of the data"""
-# dbkeys = sets.Set( [data.dbkey for data in inp_data.values() ] )
-# if len(dbkeys) != 1:
-# raise Exception, 'Both Queries must be from the same genome build
'
-
-def validate_input( trans, error_map, param_values, page_param_map ):
- dbkeys = set()
- data_param_names = set()
- data_params = 0
- for name, param in page_param_map.iteritems():
- if isinstance( param, DataToolParameter ):
- # for each dataset parameter
- if param_values.get(name, None) != None:
- dbkeys.add( param_values[name].dbkey )
- data_params += 1
- # check meta data
- try:
- param = param_values[name]
- if isinstance( param.datatype, trans.app.datatypes_registry.get_datatype_by_extension( 'gff' ).__class__ ):
- # TODO: currently cannot validate GFF inputs b/c they are not derived from interval.
- pass
- else: # Validate interval datatype.
- startCol = int( param.metadata.startCol )
- endCol = int( param.metadata.endCol )
- chromCol = int( param.metadata.chromCol )
- if param.metadata.strandCol is not None:
- strandCol = int ( param.metadata.strandCol )
- else:
- strandCol = 0
- except:
- error_msg = "The attributes of this dataset are not properly set. " + \
- "Click the pencil icon in the history item to set the chrom, start, end and strand columns."
- error_map[name] = error_msg
- data_param_names.add( name )
- if len( dbkeys ) > 1:
- for name in data_param_names:
- error_map[name] = "All datasets must belong to same genomic build, " \
- "this dataset is linked to build '%s'" % param_values[name].dbkey
- if data_params != len(data_param_names):
- for name in data_param_names:
- error_map[name] = "A dataset of the appropriate type is required"
-
-# Commented out by INS, 5/30/2007. What is the PURPOSE of this?
-def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
- """Verify the output data after each run"""
- items = out_data.items()
-
- for name, data in items:
- try:
- if stderr and len( stderr ) > 0:
- raise Exception( stderr )
-
- except Exception, exc:
- data.blurb = JOB_ERROR
- data.state = JOB_ERROR
-
-## def exec_after_process(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
-## pass
-
-
-def exec_after_merge(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
- exec_after_process(
- app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr)
-
- # strip strand column if clusters were merged
- items = out_data.items()
- for name, data in items:
- if param_dict['returntype'] == True:
- data.metadata.chromCol = 1
- data.metadata.startCol = 2
- data.metadata.endCol = 3
- # merge always clobbers strand
- data.metadata.strandCol = None
-
-
-def exec_after_cluster(app, inp_data, out_data, param_dict, tool=None, stdout=None, stderr=None):
- exec_after_process(
- app, inp_data, out_data, param_dict, tool=tool, stdout=stdout, stderr=stderr)
-
- # strip strand column if clusters were merged
- if param_dict["returntype"] == '1':
- items = out_data.items()
- for name, data in items:
- data.metadata.strandCol = None
diff --git a/tools/new_operations/subtract.xml b/tools/new_operations/subtract.xml
deleted file mode 100644
index 9ab69748252..00000000000
--- a/tools/new_operations/subtract.xml
+++ /dev/null
@@ -1,124 +0,0 @@
-
- the intervals of two datasets
- gops_subtract.py
- $input1 $input2 $output
-
- #if isinstance( $input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
- -1 1,4,5,7 --gff1
- #else:
- -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}
- #end if
-
- #if isinstance( $input2.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
- -2 1,4,5,7 --gff2
- #else:
- -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol}
- #end if
-
- -m $min $returntype
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-