Mercurial > repos > devteam > data_manager_gatk_picard_index_builder

comparison data_manager/data_manager_gatk_picard_index_builder.py @ 3:b31f1fcb203c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_gatk_picard_index_builder commit 8652f36a3a3838dca989426961561e81432acf4f
author iuc
date Tue, 04 Apr 2017 18:08:38 -0400
parents 619dd9e9c09c
children 6287d0ee459e
comparison
equal deleted inserted replaced
2:700f2df51eb0 3:b31f1fcb203c
9 import subprocess 9 import subprocess
10 import sys 10 import sys
11 import tempfile 11 import tempfile
12 12
13 CHUNK_SIZE = 2**20 13 CHUNK_SIZE = 2**20
14
15 DEFAULT_DATA_TABLE_NAME = "fasta_indexes" 14 DEFAULT_DATA_TABLE_NAME = "fasta_indexes"
16 15
16
17 def get_id_name( params, dbkey, fasta_description=None): 17 def get_id_name( params, dbkey, fasta_description=None):
18 #TODO: ensure sequence_id is unique and does not already appear in location file 18 # TODO: ensure sequence_id is unique and does not already appear in location file
19 sequence_id = params['param_dict']['sequence_id'] 19 sequence_id = params['param_dict']['sequence_id']
20 if not sequence_id: 20 if not sequence_id:
21 sequence_id = dbkey 21 sequence_id = dbkey
22 22
23 sequence_name = params['param_dict']['sequence_name'] 23 sequence_name = params['param_dict']['sequence_name']
24 if not sequence_name: 24 if not sequence_name:
25 sequence_name = fasta_description 25 sequence_name = fasta_description
26 if not sequence_name: 26 if not sequence_name:
27 sequence_name = dbkey 27 sequence_name = dbkey
28 return sequence_id, sequence_name 28 return sequence_id, sequence_name
29
29 30
30 def build_picard_index( data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, jar, data_table_name=DEFAULT_DATA_TABLE_NAME ): 31 def build_picard_index( data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, jar, data_table_name=DEFAULT_DATA_TABLE_NAME ):
31 fasta_base_name = os.path.split( fasta_filename )[-1] 32 fasta_base_name = os.path.split( fasta_filename )[-1]
32 gatk_sorted_fasta_filename = os.path.join( target_directory, fasta_base_name ) 33 gatk_sorted_fasta_filename = os.path.join( target_directory, fasta_base_name )
33 shutil.copy( fasta_filename, gatk_sorted_fasta_filename ) 34 shutil.copy( fasta_filename, gatk_sorted_fasta_filename )
39 args = [ 'java', '-jar', jar, 'R=%s' % gatk_sorted_fasta_filename, 'O=%s.dict' % sequence_id ] 40 args = [ 'java', '-jar', jar, 'R=%s' % gatk_sorted_fasta_filename, 'O=%s.dict' % sequence_id ]
40 _run_command( args, target_directory ) 41 _run_command( args, target_directory )
41 data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_name ) 42 data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_name )
42 _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ) 43 _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry )
43 44
45
44 def _run_command( command, target_directory ): 46 def _run_command( command, target_directory ):
45 tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-gatk_picard_index_builder-stderr" ) 47 tmp_stderr = tempfile.NamedTemporaryFile( prefix="tmp-data-manager-gatk_picard_index_builder-stderr" )
46 proc = subprocess.Popen( args=command, shell=False, cwd=target_directory, stderr=tmp_stderr.fileno() ) 48 proc = subprocess.Popen( args=command, shell=False, cwd=target_directory, stderr=tmp_stderr.fileno() )
47 return_code = proc.wait() 49 return_code = proc.wait()
48 if return_code: 50 if return_code:
49 tmp_stderr.flush() 51 tmp_stderr.flush()
50 tmp_stderr.seek( 0 ) 52 tmp_stderr.seek( 0 )
55 break 57 break
56 sys.stderr.write( chunk ) 58 sys.stderr.write( chunk )
57 sys.exit( return_code ) 59 sys.exit( return_code )
58 tmp_stderr.close() 60 tmp_stderr.close()
59 61
62
60 def _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ): 63 def _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ):
61 data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} ) 64 data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
62 data_manager_dict['data_tables'][ data_table_name ] = data_manager_dict['data_tables'].get( data_table_name, [] ) 65 data_manager_dict['data_tables'][ data_table_name ] = data_manager_dict['data_tables'].get( data_table_name, [] )
63 data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry ) 66 data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry )
64 return data_manager_dict 67 return data_manager_dict
68
65 69
66 def _move_and_index_fasta_for_sorting( fasta_filename ): 70 def _move_and_index_fasta_for_sorting( fasta_filename ):
67 unsorted_filename = tempfile.NamedTemporaryFile().name 71 unsorted_filename = tempfile.NamedTemporaryFile().name
68 shutil.move( fasta_filename, unsorted_filename ) 72 shutil.move( fasta_filename, unsorted_filename )
69 fasta_offsets = {} 73 fasta_offsets = {}
75 break 79 break
76 if line.startswith( ">" ): 80 if line.startswith( ">" ):
77 line = line.split( None, 1 )[0][1:] 81 line = line.split( None, 1 )[0][1:]
78 fasta_offsets[ line ] = offset 82 fasta_offsets[ line ] = offset
79 unsorted_fh.close() 83 unsorted_fh.close()
80 current_order = map( lambda x: x[1], sorted( map( lambda x: ( x[1], x[0] ), fasta_offsets.items() ) ) ) 84 current_order = [x[1] for x in sorted( ( x[1], x[0] ) for x in fasta_offsets.items() )]
81 return ( unsorted_filename, fasta_offsets, current_order ) 85 return ( unsorted_filename, fasta_offsets, current_order )
86
82 87
83 def _write_sorted_fasta( sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename ): 88 def _write_sorted_fasta( sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename ):
84 unsorted_fh = open( unsorted_fasta_filename ) 89 unsorted_fh = open( unsorted_fasta_filename )
85 sorted_fh = open( sorted_fasta_filename, 'wb+' ) 90 sorted_fh = open( sorted_fasta_filename, 'wb+' )
86 91
87 for name in sorted_names: 92 for name in sorted_names:
88 offset = fasta_offsets[ name ] 93 offset = fasta_offsets[ name ]
89 unsorted_fh.seek( offset ) 94 unsorted_fh.seek( offset )
90 sorted_fh.write( unsorted_fh.readline() ) 95 sorted_fh.write( unsorted_fh.readline() )
91 while True: 96 while True:
94 break 99 break
95 sorted_fh.write( line ) 100 sorted_fh.write( line )
96 unsorted_fh.close() 101 unsorted_fh.close()
97 sorted_fh.close() 102 sorted_fh.close()
98 103
104
99 def _int_to_roman( integer ): 105 def _int_to_roman( integer ):
100 if not isinstance( integer, int ): 106 if not isinstance( integer, int ):
101 raise TypeError, "expected integer, got %s" % type( integer ) 107 raise TypeError("expected integer, got %s" % type( integer ))
102 if not 0 < integer < 4000: 108 if not 0 < integer < 4000:
103 raise ValueError, "Argument must be between 1 and 3999, got %s" % str( integer ) 109 raise ValueError("Argument must be between 1 and 3999, got %s" % str( integer ))
104 ints = ( 1000, 900, 500, 400, 100, 90, 50, 40, 10, 9, 5, 4, 1 ) 110 ints = ( 1000, 900, 500, 400, 100, 90, 50, 40, 10, 9, 5, 4, 1 )
105 nums = ( 'M', 'CM', 'D', 'CD', 'C', 'XC', 'L', 'XL', 'X', 'IX', 'V', 'IV', 'I' ) 111 nums = ( 'M', 'CM', 'D', 'CD', 'C', 'XC', 'L', 'XL', 'X', 'IX', 'V', 'IV', 'I' )
106 result = "" 112 result = ""
107 for i in range( len( ints ) ): 113 for i in range( len( ints ) ):
108 count = int( integer / ints[ i ] ) 114 count = int( integer / ints[ i ] )
109 result += nums[ i ] * count 115 result += nums[ i ] * count
110 integer -= ints[ i ] * count 116 integer -= ints[ i ] * count
111 return result 117 return result
112 118
119
113 def _sort_fasta_gatk( fasta_filename ): 120 def _sort_fasta_gatk( fasta_filename ):
114 ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename ) 121 ( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename )
115 sorted_names = map( str, range( 1, 100 ) ) + map( _int_to_roman, range( 1, 100 ) ) + [ 'X', 'Y', 'M' ] 122 sorted_names = list(map( str, range( 1, 100 ) )) + list(map( _int_to_roman, range( 1, 100 ) )) + [ 'X', 'Y', 'M' ]
116 #detect if we have chrN, or just N 123 # detect if we have chrN, or just N
117 has_chr = False 124 has_chr = False
118 for chrom in sorted_names: 125 for chrom in sorted_names:
119 if "chr%s" % chrom in current_order: 126 if "chr%s" % chrom in current_order:
120 has_chr = True 127 has_chr = True
121 break 128 break
122 129
123 if has_chr: 130 if has_chr:
124 sorted_names = map( lambda x: "chr%s" % x, sorted_names) 131 sorted_names = ["chr%s" % x for x in sorted_names]
125 else: 132 else:
126 sorted_names.insert( 0, "MT" ) 133 sorted_names.insert( 0, "MT" )
127 sorted_names.extend( map( lambda x: "%s_random" % x, sorted_names ) ) 134 sorted_names.extend( "%s_random" % x for x in sorted_names )
128 135
129 existing_sorted_names = [] 136 existing_sorted_names = []
130 for name in sorted_names: 137 for name in sorted_names:
131 # Append each chromosome only once. 138 # Append each chromosome only once.
132 if name in current_order and name not in existing_sorted_names: 139 if name in current_order and name not in existing_sorted_names:
133 existing_sorted_names.append( name ) 140 existing_sorted_names.append( name )
134 for name in current_order: 141 for name in current_order:
135 #TODO: confirm that non-canonical names do not need to be sorted specially 142 # TODO: confirm that non-canonical names do not need to be sorted specially
136 if name not in existing_sorted_names: 143 if name not in existing_sorted_names:
137 existing_sorted_names.append( name ) 144 existing_sorted_names.append( name )
138 145
139 if existing_sorted_names == current_order: 146 if existing_sorted_names == current_order:
140 shutil.move( unsorted_filename, fasta_filename ) 147 shutil.move( unsorted_filename, fasta_filename )
141 else: 148 else:
142 _write_sorted_fasta( existing_sorted_names, fasta_offsets, fasta_filename, unsorted_filename ) 149 _write_sorted_fasta( existing_sorted_names, fasta_offsets, fasta_filename, unsorted_filename )
143 150
151
144 def main(): 152 def main():
145 #Parse Command Line
146 parser = optparse.OptionParser() 153 parser = optparse.OptionParser()
147 parser.add_option( '-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", default=None, help='fasta_filename' ) 154 parser.add_option( '-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", default=None, help='fasta_filename' )
148 parser.add_option( '-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", default=None, help='fasta_dbkey' ) 155 parser.add_option( '-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", default=None, help='fasta_dbkey' )
149 parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' ) 156 parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' )
150 parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' ) 157 parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' )
151 parser.add_option( '-j', '--jar', dest='jar', action='store', type="string", default=None, help='GATK .jar file' ) 158 parser.add_option( '-j', '--jar', dest='jar', action='store', type="string", default=None, help='GATK .jar file' )
152 (options, args) = parser.parse_args() 159 (options, args) = parser.parse_args()
153 160
154 filename = args[0] 161 filename = args[0]
155 162
156 params = json.loads( open( filename ).read() ) 163 params = json.loads( open( filename ).read() )
157 target_directory = params[ 'output_data' ][0]['extra_files_path'] 164 target_directory = params[ 'output_data' ][0]['extra_files_path']
158 os.mkdir( target_directory ) 165 os.mkdir( target_directory )
159 data_manager_dict = {} 166 data_manager_dict = {}
160 167
161 if options.fasta_dbkey in [ None, '', '?' ]: 168 if options.fasta_dbkey in [ None, '', '?' ]:
162 raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( options.fasta_dbkey ) ) 169 raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( options.fasta_dbkey ) )
163 170
164 sequence_id, sequence_name = get_id_name( params, dbkey=options.fasta_dbkey, fasta_description=options.fasta_description ) 171 sequence_id, sequence_name = get_id_name( params, dbkey=options.fasta_dbkey, fasta_description=options.fasta_description )
165 172
166 #build the index 173 # build the index
167 build_picard_index( data_manager_dict, 174 build_picard_index( data_manager_dict,
168 options.fasta_filename, 175 options.fasta_filename,
169 target_directory, 176 target_directory,
170 options.fasta_dbkey, 177 options.fasta_dbkey,
171 sequence_id, 178 sequence_id,
172 sequence_name, 179 sequence_name,
173 options.jar, 180 options.jar,
174 data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME ) 181 data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME )
175 182
176 #save info to json file 183 # save info to json file
177 open( filename, 'wb' ).write( json.dumps( data_manager_dict ) ) 184 open( filename, 'wb' ).write( json.dumps( data_manager_dict ) )
178 185
179 if __name__ == "__main__": main() 186
187 if __name__ == "__main__":
188 main()