Added ssu_erroneous method and updated method for identifying taxonom…

…ic outliers.

MANIFEST.in

@@ -5,5 +5,6 @@ include README.rst
 include MANIFEST.in
 include bin refinem
 include refinem VERSION
+include *.txt
 recursive-include refinem *.py *.txt
-
+recursive-include docs *.txt

refinem/VERSION

@@ -1 +1 @@
-0.0.13
+0.0.14

refinem/__init__.py

@@ -0,0 +1,24 @@
+###############################################################################
+#                                                                             #
+#    This program is free software: you can redistribute it and/or modify     #
+#    it under the terms of the GNU General Public License as published by     #
+#    the Free Software Foundation, either version 3 of the License, or        #
+#    (at your option) any later version.                                      #
+#                                                                             #
+#    This program is distributed in the hope that it will be useful,          #
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of           #
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the            #
+#    GNU General Public License for more details.                             #
+#                                                                             #
+#    You should have received a copy of the GNU General Public License        #
+#    along with this program. If not, see <http://www.gnu.org/licenses/>.     #
+#                                                                             #
+###############################################################################
+
+import os
+
+def version():
+    """Read program version from file."""
+    import refinem
+    version_file = open(os.path.join(__path__[0], 'VERSION'))
+    return version_file.read().strip()

refinem/cluster.py

@@ -207,3 +207,72 @@ def dbscan(self, scaffold_stats, num_clusters, num_components, K, no_coverage, n
         """
 
         pass
+
+    def split(self, scaffold_stats, criteria1, criteria2, genome_file, output_dir):
+        """Split genome into two based ongenomic feature.
+
+        Parameters
+        ----------
+        scaffold_stats : ScaffoldStats
+            Statistics for individual scaffolds.
+        criteria1 : str
+            First criteria used for splitting genome.
+        criteria2 : str
+           Second criteria used for splitting genome.
+        genome_file : str
+            Sequences being clustered.
+        output_dir : str
+            Directory to write results.
+        """
+
+        seqs = seq_io.read(genome_file)
+
+        # calculate PCA if necessary
+        if 'pc' in criteria1 or 'pc' in criteria2:
+            self.logger.info('Performing PCA.')
+            signatures = GenomicSignature(K)
+            signature_matrix = []
+            seqs = seq_io.read(genome_file)
+            for seq_id, seq in seqs.iteritems():
+                stats = scaffold_stats.stats[seq_id]
+
+                signature_matrix.append(stats.signature)
+
+            pc, _variance = self.pca(signature_matrix)
+            for i, seq_id in enumerate(seqs):
+                scaffold_stats.stats[seq_id].pc1 = pc[i][0]
+                scaffold_stats.stats[seq_id].pc2 = pc[i][1]
+                scaffold_stats.stats[seq_id].pc3 = pc[i][2]
+
+        # split bin
+        genome_id = remove_extension(genome_file)
+        fout1 = open(os.path.join(output_dir, genome_id + '_c1.fna'), 'w')
+        fout2 = open(os.path.join(output_dir, genome_id + '_c2.fna'), 'w')
+
+        for seq_id, seq in seqs.iteritems():
+            stats = scaffold_stats.stats[seq_id]
+
+            meet_criteria = True
+            for criteria in [criteria1, criteria2]:
+                if 'gc' in criteria:
+                    v = eval(criteria.replace('gc', str(stats.gc)), {"__builtins__": {}})
+                elif 'coverage' in criteria:
+                    v = eval(criteria.replace('coverage', str(stats.coverage)), {"__builtins__": {}})
+                elif 'pc1' in criteria:
+                    v = eval(criteria.replace('pc1', str(stats.pc1)), {"__builtins__": {}})
+                elif 'pc2' in criteria:
+                    v = eval(criteria.replace('pc2', str(stats.pc2)), {"__builtins__": {}})
+                elif 'pc3' in criteria:
+                    v = eval(criteria.replace('pc3', str(stats.pc3)), {"__builtins__": {}})
+
+                meet_criteria = meet_criteria and v
+
+            if meet_criteria:
+                fout1.write('>' + seq_id + '\n')
+                fout1.write(seqs[seq_id] + '\n')
+            else:
+                fout2.write('>' + seq_id + '\n')
+                fout2.write(seqs[seq_id] + '\n')
+
+        fout1.close()
+        fout2.close()        

refinem/common.py

@@ -26,7 +26,6 @@
 
 import biolib.seq_io as seq_io
 
-
 def concatenate_gene_files(gene_files, concatenated_gene_file):
     """Combine all gene files into a single file.
 
@@ -47,7 +46,7 @@ def concatenate_gene_files(gene_files, concatenated_gene_file):
         genome_id = remove_extension(gf)
 
         for seq_id, seq in seq_io.read_seq(gf):
-            fout.write('>' + seq_id + '~' + genome_id + '\n')
+            fout.write('>' + genome_id + '~' + seq_id + '\n')
             if seq[-1] == '*':
                 seq = seq[0:-1]
             fout.write(seq + '\n')