small bug fixes

README.md

@@ -25,7 +25,13 @@ GTDB-Tk makes use of the following 3rd party dependencies and assumes these are
 * [FastANI](https://github.com/ParBLiSS/FastANI) >= 1.0: Jain C, et al. 2017. High-throughput ANI Analysis of 90K Prokaryotic Genomes Reveals Clear Species Boundaries.<i>bioRxiv.</i> 256800.
 * [FastTree](http://www.microbesonline.org/fasttree/) >= 2.1.9: Price MN, et al. 2010 FastTree 2 -- Approximately Maximum-Likelihood Trees for Large Alignments. <i>PLoS ONE</i>, 5, e9490.
 
-GTDB-Tk also assumes the Python 2.7.x and Perl interpreters are on your system path.
+GTDB-Tk also assumes the Python 2.7.x and Perl interpreters are on your system path.    
+_NOTE_ :Perl interpreter requires Moose and IPC::Run modules. You need to make sure that the folder where perl modules (*.pm) are located is part the @inc variable.
+If it is not , you can set the PERL5LIB ( or PERLIB) environment variable the same way you set PATH environment variable. Every directory listed in this variable will be added to @inc.
+i.e:
+```
+export PERL5LIB=/path/to/moose/directory
+```
 
 GTDB-Tk requires ~70G+ of external data that need to be downloaded and unarchived (preferably in the same directory):
 ```

gtdbtk/VERSION

@@ -1,3 +1,9 @@
+0.0.5
+- stable version for pip 
+0.0.4b3
+- fastANI dependency fix
+0.0.4b2
+- fastANI dependency fix
 0.0.4b1
 - FastAni comparison bug fixing 
 0.0.4-beta

gtdbtk/classify.py

@@ -45,7 +45,7 @@ class Classify():
     def __init__(self, cpus=1):
         """Initialize."""
 
-        check_dependencies(['pplacer', 'guppy', 'fastani'])
+        check_dependencies(['pplacer', 'guppy', 'fastANI'])
 
         self.taxonomy_file = Config.TAXONOMY_FILE
 
@@ -93,7 +93,7 @@ def place_genomes(self,
                                                      pplacer_json_out,
                                                      user_msa_file,
                                                      pplacer_out)
-        #os.system(cmd)
+        os.system(cmd)
 
         # extract tree
         tree_file = os.path.join(out_dir, prefix + ".%s.classify.tree" % marker_set_id)
@@ -204,6 +204,8 @@ def run(self,
                 if Config.FASTANI_SPECIES_THRESHOLD < v.get("ani"):
                     suffixed_name = add_ncbi_prefix(v.get("ref_genome"))
                     taxa_str = ";".join(gtdb_taxonomy.get(suffixed_name))
+                    if taxa_str.endswith("s__"):
+                        taxa_str = taxa_str+v.get("ref_genome")
                     fout.write('%s\t%s\n' % (k, taxa_str))
                     fastani_dict[k]=v
                     redfout.write("{0}\tani\tNone\n".format(k))
@@ -585,15 +587,13 @@ def _calculate_fastani_distance(self,list_leaf,genomes):
             cmd = 'fastANI --ql {0} --rl {1} -o {2} > /dev/null 2>&1'.format(os.path.join(self.tmp_output_dir, 'query_list.txt'), 
                                                                            os.path.join(self.tmp_output_dir, 'ref_list.txt'), 
                                                                            os.path.join(self.tmp_output_dir, 'results.tab'))
-            #print cmd
             os.system(cmd)
 
             if not os.path.isfile(os.path.join(self.tmp_output_dir,'results.tab')):
                 raise
 
             dict_parser_distance = self._parse_fastani_results(os.path.join(self.tmp_output_dir,'results.tab'),list_leaf)
             shutil.rmtree(self.tmp_output_dir)
-            #print len(dict_parser_distance)
             return dict_parser_distance
 
         except:

gtdbtk/main.py

@@ -282,7 +282,7 @@ def parse_options(self, options):
 
             self.decorate(options)
         elif(options.subparser_name == 'classify_wf'):
-            check_dependencies(['prodigal', 'hmmalign', 'pplacer', 'guppy', 'fastani'])               
+            check_dependencies(['prodigal', 'hmmalign', 'pplacer', 'guppy', 'fastANI'])               
             self.identify(options)
 
             options.identify_dir = options.out_dir

scripts/trim_msa.py

@@ -49,6 +49,7 @@ def __init__(self):
 
     def run(self, msa, mask, marker_list, taxonomy_file,metadata_file, output):
         dict_marker ={}
+        print "readmsa"
         dict_genomes = read_fasta(msa,False)
 
         print len(dict_genomes)
@@ -99,18 +100,19 @@ def selectGenomes(self,list_genomes,taxonomy_file,metadata_file):
         dict_metadata = {}
         with open(metadata_file,'r') as mf:
             headers= mf.readline().strip().split("\t")
-            ncbi_type_strain_index = headers.index('ncbi_type_strain')
+            ncbi_type_strain_index = headers.index('ncbi_type_material')
             checkm_completeness_index =  headers.index('checkm_completeness')
             checkm_contamination_index = headers.index('checkm_contamination')
 
             for line in mf:
                 info = line.split('\t')
                 quality = float(info[checkm_completeness_index]) - 5*float(info[checkm_contamination_index])
-                if info[ncbi_type_strain_index] != '' and info[ncbi_type_strain_index] != 'yes' and info[ncbi_type_strain_index] != 'none':
-                    print info[0]
-                    print info[ncbi_type_strain_index]
-                    sys.exit()
-                dict_metadata[info[0]] = { "strain":info[ncbi_type_strain_index],
+                print info[ncbi_type_strain_index]
+                tm = False
+                if info[ncbi_type_strain_index] == 't':
+                    tm = True
+
+                dict_metadata[info[0]] = { "strain":tm,
                                           "quality":quality
                                           }
 
@@ -126,9 +128,9 @@ def selectGenomes(self,list_genomes,taxonomy_file,metadata_file):
                         else:
                             oldgid = dictgenusspecies.get(genusspecies)
 
-                            if dict_metadata[oldgid]['strain'] =='yes' and (dict_metadata[gid]['strain'] =='' or dict_metadata[gid]['strain'] == 'none'):
+                            if dict_metadata[oldgid]['strain'] is True and dict_metadata[gid]['strain'] is False:
                                 continue
-                            if dict_metadata[gid]['strain'] =='yes' and (dict_metadata[oldgid]['strain'] =='' or dict_metadata[oldgid]['strain'] == 'none'):
+                            if dict_metadata[gid]['strain'] is True and dict_metadata[oldgid]['strain'] is False:
                                 dictgenusspecies[genusspecies] = gid
                             elif dict_metadata[gid]['quality'] >= dict_metadata[oldgid]['quality']:
                                 dictgenusspecies[genusspecies] = gid