...

Author: Dom Laetsch

lib/BtCore.py

@@ -261,6 +261,9 @@ def parseHits(self, hitLibs):
             print BtLog.status_d['1'] % (hitLib.name, hitLib.f)
             # only accepts format 'seqID\ttaxID\tscore'
             for hitDict in BtIO.readTax(hitLib.f, set(self.dict_of_blobs)):
+                if ";" in hitDict['taxId']:
+                    hitDict['taxId'] = hitDict['taxId'].split(";")[0]
+                    print BtLog.warn['5'] % (hitDict['name'], hitLib)
                 self.set_of_taxIds.add(hitDict['taxId'])
                 self.dict_of_blobs[hitDict['name']].addHits(hitLib.name, hitDict)
 

lib/BtIO.py

@@ -220,6 +220,8 @@ def readTax(infile, set_of_blobs):
                     }
                 if hitDict['name'] not in set_of_blobs:
                     BtLog.error('19', hitDict['name'], infile)
+                if hitDict['taxId'] == 'N/A':
+                    BtLog.error('22', infile)
                 yield hitDict
 
 def parseColourDict(infile):

lib/BtLog.py

@@ -50,7 +50,8 @@ def progress(iteration, steps, max_value):
     '18' : '[ERROR:18]\t: Please provide a tax file in BLAST format.',
     '19' : '[ERROR:19]\t: Sequence %s in file %s is not part of the assembly.',
     '20' : '[ERROR:20]\t: Please add "clc_mapping_info" to you PATH variable.',
-    '21' : '[ERROR:21]\t: refcov FILE does not seem to have the right format.'
+    '21' : '[ERROR:21]\t: Refcov FILE does not seem to have the right format.',
+    '22' : '[ERROR:22]\t: Tax file %s seems to have no taxids.'
 
 }
 
@@ -59,7 +60,8 @@ def progress(iteration, steps, max_value):
     '1' : '[WARN]\t: %s not in colour file %s ...',
     '2' : '[WARN]\t: %s in file %s is not part of the assembly',
     '3' : '[WARN]\t: samtools flagstat reported %s mapped reads, %s mapped reads were parsed',
-    '4' : '[WARN]\t: No coverage data found in %s'
+    '4' : '[WARN]\t: No coverage data found in %s',
+    '5' : '[WARN]\t: Hit for sequence %s in tax file %s has multiple taxIds, only first one is used. '
 }
 status_d = {
     '1' : '[STATUS]\t: Parsing %s - %s',

lib/BtPlot.py

@@ -52,10 +52,10 @@ def parseRefCov(refcov_f):
     with open(refcov_f) as fh:
         for l in fh:
             try:
-                cov_lib, reads_mapped_ref, reads_unmapped_ref = l.split(",")
+                cov_lib, reads_total_ref, reads_mapped_ref = l.split(",")
                 refcov_dict[cov_lib] = {
-                                        'reads_mapped' : int(reads_mapped_ref), 
-                                        'reads_unmapped' : int(reads_unmapped_ref)
+                                        'reads_total' : int(reads_total_ref), 
+                                        'reads_mapped' : int(reads_mapped_ref)
                                        }
             except:
                 BtLog.error('21')
@@ -203,9 +203,9 @@ def write_stats(self):
         with open(out_f, 'w') as fh:
             for cov_lib in sorted(self.cov_libs):
                 fh.write("# %s - %s\n" % (self.out_f, cov_lib))
-                fh.write("{:<10}\t{:>10}{:>10}\t{:>10}\t{:<10}{:<10}\t{:<10}\t{:<5}\t{:<5}\t{:<10}\t{:<10}\t{:<10}\t{:<10}\n".format('Group', 'colour', 'count', 'visible (%)', 'span', 'visible(%)', 'n50', 'GC', 'GC (std)', 'cov_mean', 'cov_std', 'read map', 'read map (%)'))        
+                fh.write("{:<10}\t{:>10}{:>10}\t{:>10}\t{:<10}\t{:<10}\t{:<10}\t{:<5}\t{:<5}\t{:<10}\t{:<10}\t{:<10}\t{:<10}\n".format('Group', 'colour', 'count', 'visible (%)', 'span', 'visible(%)', 'n50', 'GC', 'GC (std)', 'cov_mean', 'cov_std', 'read map', 'read map (%)'))        
                 for stat in stats:
-                    fh.write("{:<10}\t{:>10}{:>10}\t{:>10}\t{:<10}{:<10}\t{:<10}\t{:<5}\t{:<5}\t{:<10}\t{:<10}\t{:<10}\t{:<10}\n".format(\
+                    fh.write("{:<10}\t{:>10}{:>10}\t{:>10}\t{:<10}\t{:<10}\t{:<10}\t{:<5}\t{:<5}\t{:<10}\t{:<10}\t{:<10}\t{:<10}\n".format(\
                             stat['name'], stat['colour'], stat['count_total'], stat['count_visible_perc'], stat['span_total'], \
                             stat['span_visible_perc'], stat['n50'], stat['gc_mean'], stat['gc_std'], stat['cov_mean'][cov_lib], \
                             stat['cov_std'][cov_lib], stat['reads_mapped'][cov_lib], stat['reads_mapped_perc'][cov_lib]))
@@ -302,7 +302,7 @@ def relabel_and_colour(self, colour_f, user_labels):
     def plotReadCov(self, refcov_dict):
         mat.rcParams.update({'font.size': 14})
         plot_data = {}
-        
+
         main_columns = 2
         if (refcov_dict):
             main_columns += 2
@@ -316,9 +316,9 @@ def plotReadCov(self, refcov_dict):
                 reads_total = self.cov_libs_total_reads_dict[cov_lib]
                 reads_unmapped = reads_total - self.stats['all']['reads_mapped'][cov_lib]
                 if cov_lib in refcov_dict:
-                    reads_mapped_ref = refcov_dict[cov_lib]['reads_mapped']
-                    reads_unmapped_ref = refcov_dict[cov_lib]['reads_unmapped'] 
-                    reads_total_ref = reads_mapped_ref + reads_unmapped_ref
+                    reads_total_ref = refcov_dict[cov_lib]['reads_total']
+                    reads_mapped_ref = refcov_dict[cov_lib]['reads_mapped'] 
+                    reads_unmapped_ref = reads_total_ref - reads_mapped_ref
                     main_plot.labels.append('Unmapped (ref)')
                     main_plot.values.append(reads_unmapped_ref/reads_total_ref)
                     main_plot.colours.append(DGREY)

plot.py

@@ -40,7 +40,7 @@
                                         ps, svg, svgz, tiff) [default: png]
         --noblobs                   Omit blobplot [default: False]
         --noreads                   Omit plot of reads mapping [default: False]
-        --refcov FILE               File containing number of "mapped" and "unmapped" reads 
+        --refcov FILE               File containing number of "total" and "mapped" reads 
                                     per coverage file. (e.g.: bam0,900,100). If provided, info
                                     will be used in read coverage plot(s). 
 """
@@ -108,8 +108,9 @@
         else:
             exclude_groups = exclude_groups
 
+    refcov_dict = {}
     if (refcov_f):
-        refcov_dict = BtPlot.parseRefCov(revcov)
+        refcov_dict = BtPlot.parseRefCov(refcov_f)
 
     # Load BlobDb
     print BtLog.status_d['9'] % blobdb_f
@@ -156,6 +157,8 @@
         out_f = "%s.%s.%s.p%s" % (title, hist_type, rank, max_group_plot)
         if out_prefix:
             out_f = "%s.%s" % (out_prefix, out_f)
+        if ignore_contig_length:
+            out_f = "%s.%s" % (out_f, "noscale")
         if c_index:
             out_f = "%s.%s" % (out_f, "c_index")
         if exclude_groups: