--no-sv added

libs/qconfig.py

@@ -38,7 +38,7 @@
                "gene-thresholds= err-fpath= save-json gage eukaryote glimmer no-plots no-html no-check no-check-meta combined-ref no-gc help debug "\
                "ambiguity-usage= scaffolds threads= min-cluster= min-alignment= est-ref-size= use-all-alignments gene-finding "\
                "strict-NA meta labels= help-hidden no-snps fast max-ref-number= extensive-mis-size= plots-format= " \
-               "fragmented significant-part-size= unique-mapping " \
+               "fragmented significant-part-size= unique-mapping no-sv " \
                "references-list= sv-bedpe= reads1= reads2= memory-efficient silent version colors= ls=".split()
 short_options = "o:G:O:R:t:m:J:jehvda:c:ufl:Lx:i:s1:2:"
 
@@ -68,6 +68,7 @@
 no_check_meta = False  # for metaQUAST, without checking min-contig
 unique_mapping = False  # for metaQUAST only
 no_gc = False
+no_sv = False
 show_snps = True
 glimmer = False
 is_combined_ref = False
@@ -290,7 +291,7 @@ def usage(show_hidden=False, meta=False, short=True):
         print >> sys.stderr, "                                      This may significantly reduce memory consumption on large genomes."
         print >> sys.stderr, "-1  --reads1  <filename>              File with forward reads (in FASTQ format, may be gzipped). "
         print >> sys.stderr, "-2  --reads2  <filename>              File with reverse reads (in FASTQ format, may be gzipped). "
-        print >> sys.stderr, "                                      Reads are used for structural variant detection. "
+        print >> sys.stderr, "                                      Reads are used for structural variation detection and coverage histogram building in Icarus. "
         print >> sys.stderr, "    --sv-bedpe  <filename>            File with structural variations (in BEDPE format)"
         print >> sys.stderr, ""
         print >> sys.stderr, "Speedup options:"
@@ -299,6 +300,7 @@ def usage(show_hidden=False, meta=False, short=True):
         print >> sys.stderr, "    --no-html                         Do not build html reports and Icarus viewers"
         print >> sys.stderr, "    --no-snps                         Do not report SNPs (may significantly reduce memory consumption on large genomes)"
         print >> sys.stderr, "    --no-gc                           Do not compute GC% and GC-distribution"
+        print >> sys.stderr, "    --no-sv                           Do not run structural variation detection (make sense only if reads are specified)"
         print >> sys.stderr, "    --fast                            A combination of all speedup options except --no-check"
         if show_hidden:
             print >> sys.stderr, ""

libs/qutils.py

@@ -230,7 +230,7 @@ def is_exe(fpath):
 
 
 def is_non_empty_file(fpath):
-    return os.path.exists(fpath) and os.path.getsize(fpath) > 10
+    return fpath and os.path.exists(fpath) and os.path.getsize(fpath) > 10
 
 
 def cat_files(in_fnames, out_fname):

libs/reads_analyzer.py

@@ -180,11 +180,14 @@ def run_processing_reads(main_ref_fpath, meta_ref_fpaths, ref_labels, reads_fpat
     bed_fpath = bed_fpath or os.path.join(res_path, ref_name + '.bed')
     cov_fpath = os.path.join(res_path, ref_name + '.cov')
 
-    if is_non_empty_file(bed_fpath):
+    if qconfig.no_sv:
+        logger.info('  Will not search Structural Variations (--fast or --no-sv is specified)')
+        bed_fpath = None
+    elif is_non_empty_file(bed_fpath):
         logger.info('  Using existing BED-file: ' + bed_fpath)
     if is_non_empty_file(cov_fpath):
         logger.info('  Using existing reads coverage file: ' + cov_fpath)
-    if is_non_empty_file(bed_fpath) and is_non_empty_file(cov_fpath):
+    if (is_non_empty_file(bed_fpath) or qconfig.no_sv) and is_non_empty_file(cov_fpath):
         return bed_fpath, cov_fpath
 
     logger.info('  ' + 'Pre-processing reads...')
@@ -224,7 +227,7 @@ def run_processing_reads(main_ref_fpath, meta_ref_fpaths, ref_labels, reads_fpat
 
     if not is_non_empty_file(cov_fpath):
         cov_fpath = get_coverage(output_dirpath, ref_name, bam_fpath, err_path, cov_fpath)
-    if not is_non_empty_file(bed_fpath):
+    if not is_non_empty_file(bed_fpath) and not qconfig.no_sv:
         if meta_ref_fpaths:
             logger.info('  Splitting SAM-file by references...')
         headers = []
@@ -340,14 +343,15 @@ def run_processing_reads(main_ref_fpath, meta_ref_fpaths, ref_labels, reads_fpat
         if os.path.exists(trivial_deletions_fpath) and not is_non_empty_file(bed_fpath):
             shutil.copy(trivial_deletions_fpath, bed_fpath)
 
-    if is_non_empty_file(bed_fpath):
-        logger.main_info('  Structural variations are in ' + bed_fpath)
-    else:
-        if isfile(bed_fpath):
-            logger.main_info('  No structural variations were found.')
+    if not qconfig.no_sv:
+        if is_non_empty_file(bed_fpath):
+            logger.main_info('  Structural variations are in ' + bed_fpath)
         else:
-            logger.main_info('  Failed searching structural variations.')
-        bed_fpath = None
+            if isfile(bed_fpath):
+                logger.main_info('  No structural variations were found.')
+            else:
+                logger.main_info('  Failed searching structural variations.')
+            bed_fpath = None
     if is_non_empty_file(cov_fpath):
         logger.main_info('  Coverage distribution along the reference genome is in ' + cov_fpath)
     else:
@@ -426,7 +430,7 @@ def do(ref_fpath, contigs_fpaths, reads_fpaths, meta_ref_fpaths, output_dir, int
             logger.main_info('Failed searching structural variations')
             return None, None
 
-    if bed_fpath is None and not all_required_binaries_exist(manta_bin_dirpath, 'configManta.py'):
+    if not qconfig.no_sv and bed_fpath is None and not all_required_binaries_exist(manta_bin_dirpath, 'configManta.py'):
         # making
         if not os.path.exists(manta_build_dirpath):
             os.mkdir(manta_build_dirpath)

metaquast.py

@@ -514,6 +514,8 @@ def main(args):
             pass
         elif opt == '--no-gc':
             pass
+        elif opt == '--no-sv':
+            pass
         elif opt == '--no-plots':
             pass
         elif opt == '--no-html':

quast.py

@@ -572,10 +572,13 @@ def main(args):
 
         elif opt == '--no-gc':
             qconfig.no_gc = True
+        elif opt == '--no-sv':
+            qconfig.no_sv = True
 
         elif opt == '--fast':  # --no-gc, --no-plots, --no-snps
             #qconfig.no_check = True  # too risky to include
             qconfig.no_gc = True
+            qconfig.no_sv = True
             qconfig.show_snps = False
             qconfig.draw_plots = False
             qconfig.html_report = False