multithread option added to mergepairs

README.rst

@@ -9,7 +9,7 @@ processing of amplicon sequencing data, **from raw sequences** to
 **OTU tables**, **taxonomy classification** and **phylogenetic tree**
 inference. The pipeline can be applied to a range of highly conserved
 genes/spacers, such as **16S rRNA gene**, **Internal Transcribed
-Spacer (ITS)** and **28S rRNA**. micca is an open-source, GPLv3-licensed
+Spacer (ITS)** **18S** and **28S rRNA**. micca is an open-source, GPLv3-licensed
 software.
 
 * `Homepage <http://micca.org/>`_
@@ -23,6 +23,7 @@ Key features:
   Torrent) and **overlapping paired-end** reads (Illumina MiSeq/HiSeq);
 * **multithread** de novo greedy, closed-reference, open-reference and swarm OTU
   picking protocols;
+* multithread denoising of Illumina reads;
 * **state-of-the-art taxonomic classification** algorithms (RDP and 
   consensus-based classifier);
 * fast and and memory efficient **NAST** multiple sequence alignment (MSA);

micca/api/_mergepairs.py

@@ -31,7 +31,7 @@
 
 def mergepairs(input_fns, output_fn, reverse_fn=None, notmerged_fwd_fn=None,
                notmerged_rev_fn=None, minovlen=32, maxdiffs=8, pattern="_R1",
-               repl="_R2", sep="_", nostagger=False):
+               repl="_R2", sep="_", nostagger=False, threads=1):
 
     if not isinstance(input_fns, list):
         raise ValueError("input_fns must be of type list")
@@ -60,7 +60,8 @@ def mergepairs(input_fns, output_fn, reverse_fn=None, notmerged_fwd_fn=None,
             fastq_minovlen=minovlen,
             fastq_maxdiffs=maxdiffs,
             fastq_allowmergestagger=not nostagger,
-            fastq_nostagger=nostagger)
+            fastq_nostagger=nostagger,
+            threads=threads)
     else:
         # output directory for temp files
         output_dir = os.path.dirname(output_fn)
@@ -112,7 +113,8 @@ def mergepairs(input_fns, output_fn, reverse_fn=None, notmerged_fwd_fn=None,
                     fastq_minovlen=minovlen,
                     fastq_maxdiffs=maxdiffs,
                     fastq_allowmergestagger=not nostagger,
-                    fastq_nostagger=nostagger)
+                    fastq_nostagger=nostagger,
+                    threads=threads)
             except micca.tp.vsearch.VSEARCHError as err:
                 warnings.warn("{}: VSEARCH error: {}, SKIP\n"
                               .format(input_fn_base, err))

micca/cmds/mergepairs.py

@@ -129,6 +129,9 @@ def main(argv):
                        help="write not merged forward reads.")
     group.add_argument('--notmerged-rev', metavar="FILE",
                        help="write not merged reverse reads.")
+    group.add_argument('-t', '--threads', default=1, type=int,
+                       help="number of threads to use (1 to 256, default "
+                       "%(default)s).")   
 
     args = parser.parse_args(argv)
 
@@ -147,7 +150,8 @@ def main(argv):
             pattern=args.pattern,
             repl=args.repl,
             sep=args.sep,
-            nostagger=args.nostagger)
+            nostagger=args.nostagger,
+            threads=args.threads)
     except Exception as err:
         sys.stderr.write("Error: {}\n".format(err))
         sys.exit(1)

micca/cmds/otu.py

@@ -150,20 +150,20 @@ def main(argv):
                         help="number of threads to use (1 to 256, default "
                         "%(default)s).")   
     group.add_argument('-g', '--greedy', default="dgc", choices=["dgc", "agc"],
-                        help="greedy clustering strategy, distance (DGC) or "
-                        "abundance-based (AGC) (for 'denovo_greedy' and "
-                        "'open_ref' clustering methods) (default %(default)s).")
+                       help="greedy clustering strategy, distance (DGC) or "
+                       "abundance-based (AGC) (for 'denovo_greedy' and "
+                       "'open_ref' clustering methods) (default %(default)s).")
     group.add_argument('-s', '--minsize', type=int,
-                        help="discard sequences with an abundance value "
-                        "smaller than MINSIZE after dereplication (>=1, "
-                        "default values are 2 for 'denovo_greedy' and "
-                        "'open_ref', 1 for 'denovo_swarm' and 8 for "
-                        "'denovo_unoise').")
+                       help="discard sequences with an abundance value "
+                       "smaller than MINSIZE after dereplication (>=1, "
+                       "default values are 2 for 'denovo_greedy' and "
+                       "'open_ref', 1 for 'denovo_swarm' and 8 for "
+                       "'denovo_unoise').")
     group.add_argument('-a', '--strand', default="both",
-                        choices=["both", "plus"],
-                        help="search both strands or the plus strand only "
-                        "(for 'closed_ref' and 'open_ref' clustering methods, "
-                        "default %(default)s).")
+                       choices=["both", "plus"],
+                       help="search both strands or the plus strand only "
+                       "(for 'closed_ref' and 'open_ref' clustering methods, "
+                       "default %(default)s).")
 
     # chimeras
     group_chim = parser.add_argument_group("Chimera removal specific options")

micca/tp/vsearch.py

@@ -227,11 +227,12 @@ def fastq_mergepairs(forward_fn, reverse_fn, fastaout_fn=None, fastqout_fn=None,
                      fastaout_notmerged_fwd_fn=None, fastaout_notmerged_rev_fn=None,
                      fastqout_notmerged_fwd_fn=None, fastqout_notmerged_rev_fn=None,
                      fastq_minovlen=10, fastq_maxdiffs=5,
-                     fastq_allowmergestagger=False, fastq_nostagger=True):
+                     fastq_allowmergestagger=False, fastq_nostagger=True,
+                     threads=1):
 
     params = ["--fastq_mergepairs", forward_fn, "--reverse", reverse_fn,
               "--fastq_maxdiffs", str(fastq_maxdiffs), "--fastq_minovlen",
-              str(fastq_minovlen)]
+              str(fastq_minovlen), "--threads", str(threads)]
 
     if fastaout_fn is not None:
         params.extend(["--fastaout", fastaout_fn])

scripts/micca

@@ -69,12 +69,12 @@ def main():
         stats         Report sequences stats
         filterstats   Report sequences stats relative to quality filtering
         filter        Filter sequences according to the expected error rate %%
-        otu           Assign similar sequences to OTUs (OTUs)
+        otu           Assign similar sequences to OTUs or SVs
         classify      Assign taxonomy
         msa           Multiple sequence alignment (MSA)
-        tree          Infer phylogenetic trees from alignments
+        tree          Infer phylogenetic trees from multiple alignments
         root          Reroot phylogenetic trees
-        tobiom        Convert micca output files into the BIOM format
+        tobiom        Convert micca output files into the BIOM (v1.0) format
         tablestats    Report OTU table summaries
         tablerare     Rarefy OTU tables
         tabletotax    Build tables for each taxonomic level

setup.py

@@ -21,7 +21,6 @@
     'Intended Audience :: Science/Research',
     'License :: OSI Approved :: GNU General Public License (GPL)',
     'Programming Language :: Python :: 2',
-    'Programming Language :: Python :: 3',
     'Programming Language :: C',
     'Programming Language :: C++',
     'Topic :: Scientific/Engineering :: Bio-Informatics',