map_peptides_to_bed: map_peptides_to

annotate map_peptides_to_bed.py @ 3:704ea6303c4c draft default tip

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80"

author	galaxyp
date	Tue, 07 Apr 2020 11:41:15 -0400
parents	db90662d26f9
children

rev	line source
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	1 #!/usr/bin/env python
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	2 """
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	3 #
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	4 #------------------------------------------------------------------------------
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	5 # University of Minnesota
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	6 # Copyright 2014, Regents of the University of Minnesota
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	7 #------------------------------------------------------------------------------
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	8 # Author:
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	9 #
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	10 # James E Johnson
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	11 #
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	12 #------------------------------------------------------------------------------
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	13 Input: list of protein_accessions, peptide_sequence
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	14 GFF3 with fasta
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	15 Output: GFF3 of peptides
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	16
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	17 Filter: Must cross splice boundary
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	18 """
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	19
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	20 import optparse
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	21 import os.path
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	22 import sys
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	23
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	24 from Bio.Seq import (
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	25 reverse_complement,
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	26 translate
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	27 )
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	28
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	29
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	30 class BedEntry(object):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	31 def __init__(self, line):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	32 self.line = line
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	33 try:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	34 fields = line.rstrip('\r\n').split('\t')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	35 (chrom, chromStart, chromEnd, name, score, strand, thickStart, thickEnd, itemRgb, blockCount, blockSizes, blockStarts) = fields[0:12]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	36 seq = fields[12] if len(fields) > 12 else None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	37 self.chrom = chrom
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	38 self.chromStart = int(chromStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	39 self.chromEnd = int(chromEnd)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	40 self.name = name
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	41 self.score = int(score)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	42 self.strand = strand
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	43 self.thickStart = int(thickStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	44 self.thickEnd = int(thickEnd)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	45 self.itemRgb = itemRgb
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	46 self.blockCount = int(blockCount)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	47 self.blockSizes = [int(x) for x in blockSizes.split(',')]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	48 self.blockStarts = [int(x) for x in blockStarts.split(',')]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	49 self.seq = seq
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	50 except Exception as e:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	51 sys.stderr.write("Unable to read Bed entry %s \n" % e)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	52 exit(1)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	53
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	54 def __str__(self):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	55 return '%s\t%d\t%d\t%s\t%d\t%s\t%d\t%d\t%s\t%d\t%s\t%s%s' % (
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	56 self.chrom, self.chromStart, self.chromEnd, self.name, self.score, self.strand, self.thickStart, self.thickEnd, self.itemRgb, self.blockCount,
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	57 ','.join([str(x) for x in self.blockSizes]),
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	58 ','.join([str(x) for x in self.blockStarts]),
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	59 '\t%s' % self.seq if self.seq else '')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	60
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	61 def get_splice_junctions(self):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	62 splice_juncs = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	63 for i in range(self.blockCount - 1):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	64 splice_junc = "%s:%d_%d" % (self.chrom, self.chromStart + self.blockSizes[i], self.chromStart + self.blockStarts[i + 1])
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	65 splice_juncs.append(splice_junc)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	66 return splice_juncs
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	67
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	68 def get_exon_seqs(self):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	69 exons = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	70 for i in range(self.blockCount):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	71 # splice_junc = "%s:%d_%d" % (self.chrom, self.chromStart + self.blockSizes[i], self.chromStart + self.blockStarts[i+1])
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	72 exons.append(self.seq[self.blockStarts[i]:self.blockStarts[i] + self.blockSizes[i]])
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	73 if self.strand == '-': # reverse complement
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	74 exons.reverse()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	75 for i, s in enumerate(exons):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	76 exons[i] = reverse_complement(s)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	77 return exons
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	78
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	79 def get_spliced_seq(self):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	80 seq = ''.join(self.get_exon_seqs())
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	81 return seq
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	82
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	83 def get_translation(self, sequence=None):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	84 translation = None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	85 seq = sequence if sequence else self.get_spliced_seq()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	86 if seq:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	87 seqlen = int(len(seq) / 3) * 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	88 if seqlen >= 3:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	89 translation = translate(seq[:seqlen])
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	90 return translation
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	91
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	92 def get_translations(self):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	93 translations = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	94 seq = self.get_spliced_seq()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	95 if seq:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	96 for i in range(3):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	97 translation = self.get_translation(sequence=seq[i:])
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	98 if translation:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	99 translations.append(translation)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	100 return translations
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	101
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	102 def get_subrange(self, tstart, tstop):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	103 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	104 (start, end)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	105 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	106 chromStart = self.chromStart
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	107 chromEnd = self.chromEnd
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	108 r = range(self.blockCount)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	109 if self.strand == '-':
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	110 r = list(r)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	111 r.reverse()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	112 bStart = 0
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	113 for x in r:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	114 bEnd = bStart + self.blockSizes[x]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	115 # print >> sys.stderr, "%d chromStart: %d chromEnd: %s bStart: %s bEnd: %d\n" % (x, chromStart, chromEnd, bStart, bEnd)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	116 if bStart <= tstart < bEnd:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	117 if self.strand == '+':
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	118 chromStart = self.chromStart + self.blockStarts[x] + (tstart - bStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	119 else:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	120 chromEnd = self.chromStart + self.blockStarts[x] + self.blockSizes[x] - (tstart - bStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	121 if bStart <= tstop < bEnd:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	122 if self.strand == '+':
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	123 chromEnd = self.chromStart + self.blockStarts[x] + (tstop - bStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	124 else:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	125 chromStart = self.chromStart + self.blockStarts[x] + self.blockSizes[x] - (tstop - bStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	126 bStart += self.blockSizes[x]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	127 return(chromStart, chromEnd)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	128
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	129 def get_blocks(self, chromStart, chromEnd):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	130 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	131 get the blocks for sub range
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	132 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	133 tblockCount = 0
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	134 tblockSizes = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	135 tblockStarts = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	136 for x in range(self.blockCount):
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	137 bStart = self.chromStart + self.blockStarts[x]
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	138 bEnd = bStart + self.blockSizes[x]
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	139 if bStart > chromEnd:
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	140 break
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	141 if bEnd < chromStart:
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	142 continue
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	143 cStart = max(chromStart, bStart)
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	144 tblockStarts.append(cStart - chromStart)
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	145 tblockSizes.append(min(chromEnd, bEnd) - cStart)
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	146 tblockCount += 1
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	147 sys.stderr.write("tblockCount: %d tblockStarts: %s tblockSizes: %s\n" % (tblockCount, tblockStarts, tblockSizes))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	148 return (tblockCount, tblockSizes, tblockStarts)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	149
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	150 def get_filterd_translations(self, untrimmed=False, filtering=True, ignore_left_bp=0, ignore_right_bp=0):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	151 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	152 [[start, end, seq, blockCount, blockSizes, blockStarts], [start, end, seq, blockCount, blockSizes, blockStarts], [start, end, seq, blockCount, blockSizes, blockStarts]]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	153 filter: ignore translation if stop codon in first exon after ignore_left_bp
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	154 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	155 translations = [None, None, None, None, None, None]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	156 seq = self.get_spliced_seq()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	157 ignore = int((ignore_left_bp if self.strand == '+' else ignore_right_bp) / 3)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	158 block_sum = sum(self.blockSizes)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	159 exon_sizes = self.blockSizes
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	160 if self.strand == '-':
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	161 exon_sizes.reverse()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	162 splice_sites = [int(sum(exon_sizes[:x]) / 3) for x in range(1, len(exon_sizes))]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	163 sys.stderr.write("splice_sites: %s\n" % splice_sites)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	164 junc = splice_sites[0] if len(splice_sites) > 0 else exon_sizes[0]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	165 if seq:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	166 for i in range(3):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	167 translation = self.get_translation(sequence=seq[i:])
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	168 if translation:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	169 tstart = 0
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	170 tstop = len(translation)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	171 if not untrimmed:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	172 tstart = translation.rfind('*', 0, junc) + 1
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	173 stop = translation.find('*', junc)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	174 tstop = stop if stop >= 0 else len(translation)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	175 if filtering and tstart > ignore:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	176 continue
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	177 trimmed = translation[tstart:tstop]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	178 # get genomic locations for start and end
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	179 offset = (block_sum - i) % 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	180 sys.stderr.write("tstart: %d tstop: %d offset: %d\n" % (tstart, tstop, offset))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	181 if self.strand == '+':
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	182 chromStart = self.chromStart + i + (tstart * 3)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	183 chromEnd = self.chromEnd - offset - (len(translation) - tstop) * 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	184 else:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	185 chromStart = self.chromStart + offset + (len(translation) - tstop) * 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	186 chromEnd = self.chromEnd - i - (tstart * 3)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	187 # get the blocks for this translation
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	188 tblockCount = 0
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	189 tblockSizes = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	190 tblockStarts = []
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	191 for x in range(self.blockCount):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	192 bStart = self.chromStart + self.blockStarts[x]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	193 bEnd = bStart + self.blockSizes[x]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	194 if bStart > chromEnd:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	195 break
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	196 if bEnd < chromStart:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	197 continue
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	198 cStart = max(chromStart, bStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	199 tblockStarts.append(cStart - chromStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	200 tblockSizes.append(min(chromEnd, bEnd) - cStart)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	201 tblockCount += 1
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	202 sys.stderr.write("tblockCount: %d tblockStarts: %s tblockSizes: %s\n" % (tblockCount, tblockStarts, tblockSizes))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	203 translations[i] = [chromStart, chromEnd, trimmed, tblockCount, tblockSizes, tblockStarts]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	204 return translations
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	205
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	206 def get_seq_id(self, seqtype='unk:unk', reference='', frame=None):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	207 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	208 # Ensembl fasta ID format
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	209 >ID SEQTYPE:STATUS LOCATION GENE TRANSCRIPT
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	210 >ENSP00000328693 pep:splice chromosome:NCBI35:1:904515:910768:1 gene:ENSG00000158815:transcript:ENST00000328693 gene_biotype:protein_coding transcript_biotype:protein_coding
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	211 """
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	212 frame_name = ''
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	213 chromStart = self.chromStart
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	214 chromEnd = self.chromEnd
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	215 strand = 1 if self.strand == '+' else -1
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	216 if frame is not None:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	217 block_sum = sum(self.blockSizes)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	218 offset = (block_sum - frame) % 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	219 frame_name = '_' + str(frame + 1)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	220 if self.strand == '+':
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	221 chromStart += frame
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	222 chromEnd -= offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	223 else:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	224 chromStart += offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	225 chromEnd -= frame
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	226 location = "chromosome:%s:%s:%s:%s:%s" % (reference, self.chrom, chromStart, chromEnd, strand)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	227 seq_id = "%s%s %s %s" % (self.name, frame_name, seqtype, location)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	228 return seq_id
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	229
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	230 def get_line(self, start_offset=0, end_offset=0):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	231 if start_offset or end_offset:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	232 s_offset = start_offset if start_offset else 0
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	233 e_offset = end_offset if end_offset else 0
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	234 if s_offset > self.chromStart:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	235 s_offset = self.chromStart
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	236 chrStart = self.chromStart - s_offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	237 chrEnd = self.chromEnd + e_offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	238 blkSizes = self.blockSizes
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	239 blkSizes[0] += s_offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	240 blkSizes[-1] += e_offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	241 blkStarts = self.blockStarts
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	242 for i in range(1, self.blockCount):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	243 blkStarts[i] += s_offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	244 items = [str(x) for x in [self.chrom, chrStart, chrEnd, self.name, self.score, self.strand, self.thickStart, self.thickEnd, self.itemRgb, self.blockCount, ','.join([str(x) for x in blkSizes]), ','.join([str(x) for x in blkStarts])]]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	245 return '\t'.join(items) + '\n'
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	246 return self.line
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	247
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	248
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	249 def __main__():
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	250 # Parse Command Line
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	251 parser = optparse.OptionParser()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	252 parser.add_option('-t', '--translated_bed', dest='translated_bed', default=None, help='A bed file with added 13th column having a translation')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	253 parser.add_option('-i', '--input', dest='input', default=None, help='Tabular file with peptide_sequence column')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	254 parser.add_option('-p', '--peptide_column', type='int', dest='peptide_column', default=1, help='column ordinal with peptide sequence')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	255 parser.add_option('-n', '--name_column', type='int', dest='name_column', default=2, help='column ordinal with protein name')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	256 parser.add_option('-s', '--start_column', type='int', dest='start_column', default=None, help='column with peptide start position in protein')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	257 parser.add_option('-B', '--bed', dest='bed', default=None, help='Output a bed file with added 13th column having translation')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	258 # parser.add_option('-G', '--gff3', dest='gff', default=None, help='Output translations to a GFF3 file')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	259 # parser.add_option('-f', '--fasta', dest='fasta', default=None, help='Protein fasta')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	260 parser.add_option('-T', '--gffTags', dest='gffTags', action='store_true', default=False, help='Add #gffTags to bed output for IGV')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	261 parser.add_option('-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stderr')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	262 (options, args) = parser.parse_args()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	263 # Input files
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	264 if options.input is not None:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	265 try:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	266 inputPath = os.path.abspath(options.input)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	267 inputFile = open(inputPath, 'r')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	268 except Exception as e:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	269 sys.stderr("failed: %s\n" % e)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	270 exit(2)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	271 else:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	272 inputFile = sys.stdin
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	273 inputBed = None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	274 if options.translated_bed is not None:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	275 inputBed = open(os.path.abspath(options.translated_bed), 'r')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	276 peptide_column = options.peptide_column - 1
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	277 name_column = options.name_column - 1 if options.name_column else None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	278 start_column = options.start_column - 1 if options.start_column else None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	279 # Read in peptides
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	280 # peps[prot_name] = [seq]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	281 prot_peps = dict()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	282 unassigned_peps = set()
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	283 try:
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	284 for i, line in enumerate(inputFile):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	285 # print >> sys.stderr, "%3d\t%s\n" % (i, line)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	286 if line.startswith('#'):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	287 continue
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	288 fields = line.rstrip('\r\n').split('\t')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	289 # print >> sys.stderr, "%3d\t%s\n" % (i, fields)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	290 if peptide_column < len(fields):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	291 peptide = fields[peptide_column]
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	292 prot_name = fields[name_column] if name_column is not None and name_column < len(fields) else None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	293 if prot_name:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	294 offset = fields[start_column] if start_column is not None and start_column < len(fields) else -1
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	295 if prot_name not in prot_peps:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	296 prot_peps[prot_name] = dict()
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	297 prot_peps[prot_name][peptide] = offset
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	298 else:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	299 unassigned_peps.add(peptide)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	300 if options.debug:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	301 sys.stderr.write("prot_peps: %s\n" % prot_peps)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	302 sys.stderr.write("unassigned_peps: %s\n" % unassigned_peps)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	303 except Exception as e:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	304 sys.stderr.write("failed: Error reading %s - %s\n" % (options.input if options.input else 'stdin', e))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	305 exit(1)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	306 # Output files
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	307 bed_fh = None
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	308 if options.bed:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	309 bed_fh = open(options.bed, 'w')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	310 bed_fh.write('track name="%s" type=bedDetail description="%s" \n' % ('novel_junction_peptides', 'test'))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	311 if options.gffTags:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	312 bed_fh.write('#gffTags\n')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	313 # if options.gff:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	314 # gff_fh = open(options.gff, 'w')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	315 # gff_fh.write("##gff-version 3.2.1\n")
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	316 # if options.reference:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	317 # gff_fh.write("##genome-build %s %s\n" % (options.refsource if options.refsource else 'unknown', options.reference))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	318 try:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	319 for i, line in enumerate(inputBed):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	320 # print >> sys.stderr, "%3d:\t%s\n" % (i, line)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	321 if line.startswith('track'):
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	322 continue
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	323 entry = BedEntry(line)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	324 if entry.name in prot_peps:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	325 for (peptide, offset) in prot_peps[entry.name].items():
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	326 if offset < 0:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	327 offset = entry.seq.find(peptide)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	328 if options.debug:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	329 sys.stderr.write("%s\t%s\t%d\t%s\n" % (entry.name, peptide, offset, entry.seq))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	330 if offset >= 0:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	331 tstart = offset * 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	332 tstop = tstart + len(peptide) * 3
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	333 if options.debug:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	334 sys.stderr.write("%d\t%d\t%d\n" % (offset, tstart, tstop))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	335 (pepStart, pepEnd) = entry.get_subrange(tstart, tstop)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	336 if options.debug:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	337 sys.stderr.write("%d\t%d\t%d\n" % (offset, pepStart, pepEnd))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	338 if bed_fh:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	339 entry.thickStart = pepStart
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	340 entry.thickEnd = pepEnd
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	341 bedfields = str(entry).split('\t')
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	342 if options.gffTags:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	343 bedfields[3] = "ID=%s;Name=%s" % (entry.name, peptide)
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	344 bed_fh.write("%s\t%s\t%s\n" % ('\t'.join(bedfields[:12]), peptide, entry.seq))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	345 except Exception as e:
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	346 sys.stderr.write("failed: Error reading %s - %s\n" % (options.input if options.input else 'stdin', e))
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	347 raise
0 51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	348
51f8f9041724 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit e04ed4b4960d6109a85c1cc68a2bf4931c8751ef-dirty galaxyp parents: diff changeset	349
3 704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	350 if __name__ == "__main__":
704ea6303c4c "planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/map_peptides_to_bed commit 2a470e2c775a7427aa530e058510e4dc7b6d8e80" galaxyp parents: 1 diff changeset	351 __main__()

Mercurial > repos > galaxyp > map_peptides_to_bed

annotate map_peptides_to_bed.py @ 3:704ea6303c4c draft default tip