Mercurial > repos > ieguinoa > data_manager_fetch_gff

comparison data_manager/data_manager_fetch_gff.py @ 3:cb0fa3584aeb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author ieguinoa
date Tue, 09 Oct 2018 14:32:48 -0400
parents c57bd7f3fb46
children 0bdfe2e85fb0
comparison
equal deleted inserted replaced
2:c57bd7f3fb46 3:cb0fa3584aeb
91 91
92 def _get_stream_readers_for_bz2( fh, tmp_dir ): 92 def _get_stream_readers_for_bz2( fh, tmp_dir ):
93 return [ bz2.BZ2File( fh.name, 'rb') ] 93 return [ bz2.BZ2File( fh.name, 'rb') ]
94 94
95 95
96 def sort_fasta( fasta_filename, sort_method, params ):
97 if sort_method is None:
98 return
99 assert sort_method in SORTING_METHODS, ValueError( "%s is not a valid sorting option." % sort_method )
100 return SORTING_METHODS[ sort_method ]( fasta_filename, params )
101
102
103 def _move_and_index_fasta_for_sorting( fasta_filename ):
104 unsorted_filename = tempfile.NamedTemporaryFile().name
105 shutil.move( fasta_filename, unsorted_filename )
106 fasta_offsets = {}
107 unsorted_fh = open( unsorted_filename )
108 while True:
109 offset = unsorted_fh.tell()
110 line = unsorted_fh.readline()
111 if not line:
112 break
113 if line.startswith( ">" ):
114 line = line.split( None, 1 )[0][1:]
115 fasta_offsets[ line ] = offset
116 unsorted_fh.close()
117 current_order = map( lambda x: x[1], sorted( map( lambda x: ( x[1], x[0] ), fasta_offsets.items() ) ) )
118 return ( unsorted_filename, fasta_offsets, current_order )
119
120
121 def _write_sorted_fasta( sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename ):
122 unsorted_fh = open( unsorted_fasta_filename )
123 sorted_fh = open( sorted_fasta_filename, 'wb+' )
124
125 for name in sorted_names:
126 offset = fasta_offsets[ name ]
127 unsorted_fh.seek( offset )
128 sorted_fh.write( unsorted_fh.readline() )
129 while True:
130 line = unsorted_fh.readline()
131 if not line or line.startswith( ">" ):
132 break
133 sorted_fh.write( line )
134 unsorted_fh.close()
135 sorted_fh.close()
136
137
138 def _sort_fasta_as_is( fasta_filename, params ):
139 return
140
141 def _sort_fasta_lexicographical( fasta_filename, params ):
142 ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename )
143 sorted_names = sorted( fasta_offsets.keys() )
144 if sorted_names == current_order:
145 shutil.move( unsorted_filename, fasta_filename )
146 else:
147 _write_sorted_fasta( sorted_names, fasta_offsets, fasta_filename, unsorted_filename )
148
149
150 def _sort_fasta_gatk( fasta_filename, params ):
151 #This method was added by reviewer request.
152 ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename )
153 sorted_names = map( str, range( 1, 23 ) ) + [ 'X', 'Y' ]
154 #detect if we have chrN, or just N
155 has_chr = False
156 for chrom in sorted_names:
157 if "chr%s" % chrom in current_order:
158 has_chr = True
159 break
160
161 if has_chr:
162 sorted_names = map( lambda x: "chr%s" % x, sorted_names)
163 sorted_names.insert( 0, "chrM" )
164 else:
165 sorted_names.insert( 0, "MT" )
166 sorted_names.extend( map( lambda x: "%s_random" % x, sorted_names ) )
167
168 existing_sorted_names = []
169 for name in sorted_names:
170 if name in current_order:
171 existing_sorted_names.append( name )
172 for name in current_order:
173 #TODO: confirm that non-canonical names do not need to be sorted specially
174 if name not in existing_sorted_names:
175 existing_sorted_names.append( name )
176
177 if existing_sorted_names == current_order:
178 shutil.move( unsorted_filename, fasta_filename )
179 else:
180 _write_sorted_fasta( existing_sorted_names, fasta_offsets, fasta_filename, unsorted_filename )
181
182
183 def _sort_fasta_custom( fasta_filename, params ):
184 ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename )
185 sorted_names = []
186 for id_repeat in params['param_dict']['sorting']['sequence_identifiers']:
187 sorted_names.append( id_repeat[ 'identifier' ] )
188 handle_not_listed = params['param_dict']['sorting']['handle_not_listed_selector']
189 if handle_not_listed.startswith( 'keep' ):
190 add_list = []
191 for name in current_order:
192 if name not in sorted_names:
193 add_list.append( name )
194 if add_list:
195 if handle_not_listed == 'keep_append':
196 sorted_names.extend( add_list )
197 else:
198 add_list.extend( sorted_names )
199 sorted_names = add_list
200 if sorted_names == current_order:
201 shutil.move( unsorted_filename, fasta_filename )
202 else:
203 _write_sorted_fasta( sorted_names, fasta_offsets, fasta_filename, unsorted_filename )
204
205
206 def _download_file(start, fh): 96 def _download_file(start, fh):
207 tmp = tempfile.NamedTemporaryFile() 97 tmp = tempfile.NamedTemporaryFile()
208 tmp.write(start) 98 tmp.write(start)
209 tmp.write(fh.read()) 99 tmp.write(fh.read())
210 tmp.flush() 100 tmp.flush()
236 except tarfile.ReadError: 126 except tarfile.ReadError:
237 pass 127 pass
238 return fh 128 return fh
239 129
240 130
241 def _get_ucsc_download_address(params, dbkey):
242 """
243 Check if we can find the correct file for the supplied dbkey on UCSC's FTP server
244 """
245 UCSC_FTP_SERVER = 'hgdownload.cse.ucsc.edu'
246 UCSC_DOWNLOAD_PATH = '/goldenPath/%s/bigZips/'
247 COMPRESSED_EXTENSIONS = ['.tar.gz', '.tgz', '.tar.bz2', '.zip', '.fa.gz', '.fa.bz2']
248
249 email = params['param_dict']['__user_email__']
250 if not email:
251 email = 'anonymous@example.com'
252
253 ucsc_dbkey = params['param_dict']['reference_source']['requested_dbkey'] or dbkey
254 UCSC_CHROM_FA_FILENAMES = ['%s.chromFa' % ucsc_dbkey, 'chromFa', ucsc_dbkey]
255
256 ftp = FTP(UCSC_FTP_SERVER)
257 ftp.login('anonymous', email)
258
259 ucsc_path = UCSC_DOWNLOAD_PATH % ucsc_dbkey
260 path_contents = _get_files_in_ftp_path(ftp, ucsc_path)
261 ftp.quit()
262
263 for ucsc_chrom_fa_filename in UCSC_CHROM_FA_FILENAMES:
264 for ext in COMPRESSED_EXTENSIONS:
265 if "%s%s" % (ucsc_chrom_fa_filename, ext) in path_contents:
266 ucsc_file_name = "%s%s%s" % (ucsc_path, ucsc_chrom_fa_filename, ext)
267 return "ftp://%s%s" % (UCSC_FTP_SERVER, ucsc_file_name)
268
269 raise Exception('Unable to determine filename for UCSC Genome for %s: %s' % (ucsc_dbkey, path_contents))
270 131
271 def add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params): 132 def add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params):
272 for data_table_name, data_table_entry in _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ): 133 for data_table_name, data_table_entry in _stream_fasta_to_file( fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params ):
273 if data_table_entry: 134 if data_table_entry:
274 _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name ) 135 _add_data_table_entry( data_manager_dict, data_table_entry, data_table_name )
275 136
276 137
277 def download_from_ucsc( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
278 url = _get_ucsc_download_address(params, dbkey)
279 fasta_readers = get_stream_reader(urlopen(url), tmp_dir)
280 add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params)
281
282
283 def download_from_ncbi( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
284 NCBI_DOWNLOAD_URL = 'http://togows.dbcls.jp/entry/ncbi-nucleotide/%s.fasta' #FIXME: taken from dave's genome manager...why some japan site?
285 requested_identifier = params['param_dict']['reference_source']['requested_identifier']
286 url = NCBI_DOWNLOAD_URL % requested_identifier
287 fasta_readers = get_stream_reader(urlopen(url), tmp_dir)
288 add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, params)
289
290
291 def download_from_url( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): 138 def download_from_url( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
292 urls = filter( bool, map( lambda x: x.strip(), params['param_dict']['reference_source']['user_url'].split( '\n' ) ) ) 139 urls = filter( bool, map( lambda x: x.strip(), params['param_dict']['reference_source']['user_url'].split( '\n' ) ) )
293 fasta_readers = [ get_stream_reader(urlopen( url ), tmp_dir) for url in urls ] 140 fasta_readers = [ get_stream_reader(urlopen( url ), tmp_dir) for url in urls ]
294 add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params) 141 add_fasta_to_table(data_manager_dict, fasta_readers, target_directory, dbkey, dbkey_name, sequence_id,sequence_name, params)
295 142
296 143
297 def download_from_history( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ): 144 def download_from_history( data_manager_dict, params, target_directory, dbkey, dbkey_name, sequence_id, sequence_name, tmp_dir ):
298 #TODO: allow multiple FASTA input files
299 input_filename = params['param_dict']['reference_source']['input_fasta'] 145 input_filename = params['param_dict']['reference_source']['input_fasta']
300 if isinstance( input_filename, list ): 146 if isinstance( input_filename, list ):
301 fasta_readers = [ get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename ] 147 fasta_readers = [ get_stream_reader(open(filename, 'rb'), tmp_dir) for filename in input_filename ]
302 else: 148 else:
303 fasta_readers = get_stream_reader(open(input_filename), tmp_dir) 149 fasta_readers = get_stream_reader(open(input_filename), tmp_dir)
403 fasta_filename = os.path.join( target_directory, fasta_base_filename ) 249 fasta_filename = os.path.join( target_directory, fasta_base_filename )
404 os.symlink( input_filename, fasta_filename ) 250 os.symlink( input_filename, fasta_filename )
405 return [ ( DATA_TABLE_NAME, dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ] 251 return [ ( DATA_TABLE_NAME, dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_filename ) ) ]
406 252
407 253
408 REFERENCE_SOURCE_TO_DOWNLOAD = dict( ucsc=download_from_ucsc, ncbi=download_from_ncbi, url=download_from_url, history=download_from_history, directory=copy_from_directory ) 254 #REFERENCE_SOURCE_TO_DOWNLOAD = dict( ucsc=download_from_ucsc, ncbi=download_from_ncbi, url=download_from_url, history=download_from_history, directory=copy_from_directory )
409 255 REFERENCE_SOURCE_TO_DOWNLOAD = dict( url=download_from_url, history=download_from_history, directory=copy_from_directory )
410 SORTING_METHODS = dict( as_is=_sort_fasta_as_is, lexicographical=_sort_fasta_lexicographical, gatk=_sort_fasta_gatk, custom=_sort_fasta_custom ) 256 #SORTING_METHODS = dict( as_is=_sort_fasta_as_is, lexicographical=_sort_fasta_lexicographical, gatk=_sort_fasta_gatk, custom=_sort_fasta_custom )
411 257
412 258
413 def main(): 259 def main():
414 #Parse Command Line 260 #Parse Command Line
415 parser = optparse.OptionParser() 261 parser = optparse.OptionParser()
416 parser.add_option( '-d', '--dbkey_description', dest='dbkey_description', action='store', type="string", default=None, help='dbkey_description' ) 262 parser.add_option( '-d', '--dbkey_description', dest='dbkey_description', action='store', type="string", default=None, help='dbkey_description' )
417 parser.add_option( '-t', '--type', dest='file_type', action='store', type='string', default=None, help='file_type')
418 (options, args) = parser.parse_args() 263 (options, args) = parser.parse_args()
419 264
420 filename = args[0] 265 filename = args[0]
421 global DATA_TABLE_NAME 266 #global DATA_TABLE_NAME
422 if options.file_type == 'representative':
423 DATA_TABLE_NAME= 'representative_gff'
424 params = loads( open( filename ).read() ) 267 params = loads( open( filename ).read() )
425 target_directory = params[ 'output_data' ][0]['extra_files_path'] 268 target_directory = params[ 'output_data' ][0]['extra_files_path']
426 os.mkdir( target_directory ) 269 os.mkdir( target_directory )
427 data_manager_dict = {} 270 data_manager_dict = {}
428 271