biosak 1.123.7__tar.gz

biosak-1.123.7/BioSAK/BLCA_op_parser.py

@@ -0,0 +1,87 @@
+import argparse
+from BioSAK.global_functions import sep_path_basename_ext
+
+
+BLCA_op_parser_usage = '''
+========== BLCA_op_parser example commands ==========
+
+BioSAK BLCA_op_parser -in OTUs.fasta.blca.out
+
+=====================================================
+'''
+
+
+def BLCA_op_parser(args):
+
+    blca_output = args['in']
+
+    file_in_path, file_in_basename, file_in_ext = sep_path_basename_ext(blca_output)
+    output_file_1 = '%s/%s_reformatted_1.txt' % (file_in_path, file_in_basename)
+    output_file_2 = '%s/%s_reformatted_2.txt' % (file_in_path, file_in_basename)
+
+    # read in input file
+    s16_taxon_blca_dict = {}
+    for each_16s_taxon in open(blca_output):
+        each_16s_taxon_split = each_16s_taxon.strip().split('\t')
+        s16_taxon_blca_dict[each_16s_taxon_split[0]] = each_16s_taxon_split[1]
+
+    taxon_dict_formatted_with_num = {}
+    taxon_dict_formatted_no_num = {}
+    for each_16s in s16_taxon_blca_dict:
+        taxon_blca_raw = s16_taxon_blca_dict[each_16s]
+        formatted_taxon_str_with_num = 'Unclassified'
+        formatted_taxon_str_no_num = 'Unclassified'
+        if taxon_blca_raw != 'Unclassified':
+            taxon_blca_raw_split_1 = taxon_blca_raw.strip().split(':')[1:]
+            formatted_taxon_list_with_num = []
+            formatted_taxon_list_no_num = []
+            for each_str in taxon_blca_raw_split_1:
+                each_str_split = each_str.split(';')
+
+                # determine_current_rank
+                current_rank = ''
+                if each_str_split[-1] == 'phylum':
+                    current_rank = 'd'
+                elif each_str_split[-1] == 'class':
+                    current_rank = 'p'
+                elif each_str_split[-1] == 'order':
+                    current_rank = 'c'
+                elif each_str_split[-1] == 'family':
+                    current_rank = 'o'
+                elif each_str_split[-1] == 'genus':
+                    current_rank = 'f'
+                elif each_str_split[-1] == 'species':
+                    current_rank = 'g'
+                elif each_str_split[-1] == '':
+                    current_rank = 's'
+
+                taxon_with_confidence = '%s(%s)' % (each_str_split[0], each_str_split[1][:5])
+                taxon_without_confidence = '%s__%s' % (current_rank, each_str_split[0])
+
+                formatted_taxon_list_with_num.append(taxon_with_confidence)
+                formatted_taxon_list_no_num.append(taxon_without_confidence)
+
+            formatted_taxon_str_with_num = ';'.join(formatted_taxon_list_with_num)
+            formatted_taxon_str_no_num = ';'.join(formatted_taxon_list_no_num)
+
+        formatted_taxon_str_with_numno_space = '_'.join(formatted_taxon_str_with_num.split(' '))
+        formatted_taxon_str_no_num_no_space = '_'.join(formatted_taxon_str_no_num.split(' '))
+
+        taxon_dict_formatted_with_num[each_16s] = formatted_taxon_str_with_numno_space
+        taxon_dict_formatted_no_num[each_16s] = formatted_taxon_str_no_num_no_space
+
+    output_file_1_handle = open(output_file_1, 'w')
+    output_file_2_handle = open(output_file_2, 'w')
+    for each_seq in taxon_dict_formatted_with_num:
+        output_file_1_handle.write('%s\t%s\n' % (each_seq, taxon_dict_formatted_with_num[each_seq]))
+        output_file_2_handle.write('%s\t%s\n' % (each_seq, taxon_dict_formatted_no_num[each_seq]))
+    output_file_1_handle.close()
+    output_file_2_handle.close()
+
+
+if __name__ == '__main__':
+
+    parser = argparse.ArgumentParser(usage=BLCA_op_parser_usage)
+    parser.add_argument('-in', required=True, help='BLCA output')
+    args = vars(parser.parse_args())
+    BLCA_op_parser(args)

biosak-1.123.7/BioSAK/BioSAK_config.py

@@ -0,0 +1,33 @@
+import os
+
+# extract path to the config file
+pwd_config_file = os.path.realpath(__file__)
+config_file_path = '/'.join(pwd_config_file.split('/')[:-1])
+
+# specify full path to corresponding executables at the right side of colon
+config_dict = {'config_file_path'       : config_file_path,
+               'prodigal'               : 'prodigal',
+               'hmmsearch'              : 'hmmsearch',
+               'hmmfetch'               : 'hmmfetch',
+               'hmmalign'               : 'hmmalign',
+               'hmmstat'                : 'hmmstat',
+               'mafft'                  : 'mafft',
+               'bowtie2'                : 'bowtie2',
+               'bowtie2_build'          : 'bowtie2-build',
+               'blastp'                 : 'blastp',
+               'blastn'                 : 'blastn',
+               'makeblastdb'            : 'makeblastdb',
+               'fasttree'               : 'FastTree',
+               'ranger_mac'             : '%s/Ranger-DTL-Dated.mac'           % config_file_path,
+               'ranger_linux'           : '%s/Ranger-DTL-Dated.linux'         % config_file_path,
+               'path_to_hmm'            : '%s/MetaCHIP_phylo.hmm'             % config_file_path,
+               'circos_HGT_R'           : '%s/MetaCHIP_circos_HGT.R'          % config_file_path,
+               'label_tree_R'           : '%s/label_tree.R'                   % config_file_path,
+               'cdd2cog_perl'           : '%s/cdd2cog.pl'                     % config_file_path,
+               'get_sankey_plot_R'      : '%s/sankey.R'              % config_file_path,
+               'compare_trees_R'        : '%s/compare_trees.R'                % config_file_path,
+               'PhyloBiAssoc_R'         : '%s/PhyloBiAssoc.R'                 % config_file_path,
+               'ko00001_keg'            : '%s/ko00001.keg'                    % config_file_path,
+               'MetaCyc_rxns_with_ec'   : '%s/MetaCyc_reactions_with_ec.txt'  % config_file_path
+               }
+