Mercurial > repos > drosofff > msp_sr_readmap_and_size_histograms

comparison readmap.py @ 23:d6b93af0da55 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_sr_readmap_and_size_histograms commit 89caea4594db1ae6d6bb9c651bc6019bb6dd3ce6-dirty
author mvdbeek
date Sun, 24 Apr 2016 09:23:44 -0400
parents f75315939afe
children bf7388df53cf
comparison
equal deleted inserted replaced
22:dbac07fc9186 23:d6b93af0da55
21 the_parser.add_argument('--label',nargs='+', help="labels of multiple input files") 21 the_parser.add_argument('--label',nargs='+', help="labels of multiple input files")
22 the_parser.add_argument('--normalization_factor',nargs='+', type=float, help="Normalization factor for input file") 22 the_parser.add_argument('--normalization_factor',nargs='+', type=float, help="Normalization factor for input file")
23 the_parser.add_argument('--gff', type=str, help="GFF containing regions of interest") 23 the_parser.add_argument('--gff', type=str, help="GFF containing regions of interest")
24 the_parser.add_argument('--minquery', type=int, help="Minimum readsize") 24 the_parser.add_argument('--minquery', type=int, help="Minimum readsize")
25 the_parser.add_argument('--maxquery', type=int, help="Maximum readsize") 25 the_parser.add_argument('--maxquery', type=int, help="Maximum readsize")
26 the_parser.add_argument('--rcode', type=str, help="R script")
27 args = the_parser.parse_args() 26 args = the_parser.parse_args()
28 return args 27 return args
29 28
30 args=Parser() 29 args=Parser()
31 if args.reference_fasta: 30 if args.reference_fasta:
36 genomeRefFile = args.reference_bowtie_index 35 genomeRefFile = args.reference_bowtie_index
37 readmap_file=args.output_readmap 36 readmap_file=args.output_readmap
38 size_distribution_file=args.output_size_distribution 37 size_distribution_file=args.output_size_distribution
39 minquery=args.minquery 38 minquery=args.minquery
40 maxquery=args.maxquery 39 maxquery=args.maxquery
41 Rcode = args.rcode
42 filePath=args.input 40 filePath=args.input
43 fileExt=args.ext 41 fileExt=args.ext
44 fileLabel=args.label 42 fileLabel=args.label
45 normalization_factor=args.normalization_factor 43 normalization_factor=args.normalization_factor
46 44
152 gff_name = gff_fields[-1].split("Name=")[-1].split(";")[0] # to isolate the GFF Name 150 gff_name = gff_fields[-1].split("Name=")[-1].split(";")[0] # to isolate the GFF Name
153 item_upstream_coordinate = int(gff_fields[3]) 151 item_upstream_coordinate = int(gff_fields[3])
154 item_downstream_coordinate = int(gff_fields[4]) 152 item_downstream_coordinate = int(gff_fields[4])
155 item_polarity = gff_fields[6] 153 item_polarity = gff_fields[6]
156 for sample in readDict.keys(): 154 for sample in readDict.keys():
157 ## this is not required anymore but test
158 # if not GFFinstanceDict.has_key(sample):
159 # GFFinstanceDict[sample]={}
160 ####
161 subinstance=extractsubinstance(item_upstream_coordinate, item_downstream_coordinate, readDict[sample].instanceDict[chrom]) 155 subinstance=extractsubinstance(item_upstream_coordinate, item_downstream_coordinate, readDict[sample].instanceDict[chrom])
162 if item_polarity == '-': 156 if item_polarity == '-':
163 subinstance.readDict={key*-1:value for key, value in subinstance.readDict.iteritems()} 157 subinstance.readDict={key*-1:value for key, value in subinstance.readDict.iteritems()}
164 subinstance.gene=gff_name 158 subinstance.gene=gff_name
165 GFFinstanceDict[sample][gff_name]=subinstance 159 GFFinstanceDict[sample][gff_name]=subinstance
170 if args.gff: 164 if args.gff:
171 MasterListOfGenomes=gff_item_subinstances(MasterListOfGenomes, args.gff) 165 MasterListOfGenomes=gff_item_subinstances(MasterListOfGenomes, args.gff)
172 166
173 write_readplot_dataframe(MasterListOfGenomes, readmap_file) 167 write_readplot_dataframe(MasterListOfGenomes, readmap_file)
174 write_size_distribution_dataframe(MasterListOfGenomes, size_distribution_file) 168 write_size_distribution_dataframe(MasterListOfGenomes, size_distribution_file)
175
176 R_command="Rscript "+ Rcode
177 process = subprocess.Popen(R_command.split())
178 process.wait()
179 169