Minor fixes for some python2 bugs. Addressed #42. Fixes #41.

tombo/_version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-TOMBO_VERSION = '1.2.1'
+TOMBO_VERSION = '1.2.1b'

tombo/plot_commands.py

@@ -203,6 +203,12 @@ def plot_per_read_roc(
                 'stat':r.FloatVector(unzip_stats[0]),
                 'motif_match':r.BoolVector(unzip_stats[1])})
 
+    # python2 rpy2 ListVector can't take unicode keys
+    if sys.version_info[0] < 3:
+        conv_all_motif_stats_for_r = {}
+        for k, v in all_motif_stats_for_r.items():
+            conv_all_motif_stats_for_r[k.encode()] = v
+        all_motif_stats_for_r = conv_all_motif_stats_for_r
     all_motif_stats_for_r = r.ListVector(all_motif_stats_for_r)
 
     if VERBOSE: sys.stderr.write('Computing accuracy statistics.\n')
@@ -889,7 +895,7 @@ def plot_corrections(
 def plot_multi_corrections(
         f5_dirs1, corrected_group, basecall_subgroups, pdf_fn,
         num_reads_per_plot, num_regions, num_obs, include_orig_bcs,
-        genome_locations):
+        genome_locs):
     th._warning_message('The plot_multi_correction command may be deprecated ' +
                         'in future versions of Tombo.')
     num_regions = num_regions if num_regions % 2 == 0 else \
@@ -898,7 +904,7 @@ def plot_multi_corrections(
         f5_dirs1, corrected_group, basecall_subgroups)
     read_coverage = th.get_coverage(raw_read_coverage)
 
-    if genome_locations is None:
+    if genome_locs is None:
         coverage_regions = []
         for (chrm, strand), cs_coverage in read_coverage.items():
             reg_covs, reg_lens = zip(*[
@@ -923,16 +929,7 @@ def plot_multi_corrections(
                 'number of reads than requested.')
     else:
         if VERBOSE: sys.stderr.write('Parsing genome locations.\n')
-        parsed_locations = []
-        for chrm_pos_strand in genome_locations:
-            split_vals = chrm_pos_strand.replace('"', '').replace(
-                "'", "").split(':')[:3]
-            # default to plus strand if not specified
-            if len(split_vals) == 2:
-                parsed_locations.append((
-                    split_vals[0], split_vals[1], '+'))
-            else:
-                parsed_locations.append(split_vals)
+        parsed_locs = th.parse_genome_locations(genome_locs, default_strand='+')
         plot_locs = [
             ('{:03d}'.format(i), (chrm, int(pos) - 1, strand))
             for i, (chrm, pos, strand) in enumerate(parsed_locations)]
@@ -1480,22 +1477,14 @@ def plot_max_coverage(
 def plot_genome_locations(
         f5_dirs1, corrected_group, basecall_subgroups, pdf_fn,
         f5_dirs2, num_bases, overplot_thresh, overplot_type,
-        genome_locations, tb_model_fn, alt_model_fn, plot_default_stnd,
+        genome_locs, tb_model_fn, alt_model_fn, plot_default_stnd,
         plot_default_alt):
     if VERBOSE: sys.stderr.write('Parsing genome locations.\n')
-    # ignore strand for genome location plotting
-    genome_locations = [
-        chrm_pos.replace('"', '').replace("'", "").split(':')[:3]
-        for chrm_pos in genome_locations]
     # minus one here as all python internal coords are 0-based, but
     # genome is generally 1-based
     plot_intervals = []
-    for i, chrm_pos_strand in enumerate(genome_locations):
-        if len(chrm_pos_strand) == 2:
-            chrm, pos = chrm_pos_strand
-            strand = None
-        else:
-            chrm, pos, strand = chrm_pos_strand
+    for i, (chrm, pos, strand) in enumerate(
+            th.parse_genome_locations(genome_locs)):
         int_start = max(
             0, int(int(pos) - np.floor(num_bases / 2.0) - 1))
         plot_intervals.append(th.intervalData(
@@ -1527,19 +1516,12 @@ def plot_genome_locations(
 
 def plot_per_read_mods_genome_location(
         f5_dirs, corrected_group, basecall_subgroups, pdf_fn,
-        per_read_stats_fn, genome_locations, num_bases, num_reads, box_center,
+        per_read_stats_fn, genome_locs, num_bases, num_reads, box_center,
         fasta_fn):
     if VERBOSE: sys.stderr.write('Parsing genome locations.\n')
-    genome_locations = [
-        chrm_pos.replace('"', '').replace("'", "").split(':')[:3]
-        for chrm_pos in genome_locations]
     plot_intervals = []
-    for i, chrm_pos_strand in enumerate(genome_locations):
-        if len(chrm_pos_strand) == 2:
-            chrm, pos = chrm_pos_strand
-            strand = '+'
-        else:
-            chrm, pos, strand = chrm_pos_strand
+    for i, (chrm, pos, strand) in enumerate(th.parse_genome_locations(
+            genome_locs, default_strand='+')):
         int_start = max(
             0, int(int(pos) - np.floor(num_bases / 2.0) - 1) + 1)
         plot_intervals.append(th.intervalData(
@@ -2146,7 +2128,7 @@ def plot_main(args):
                  if 'num_obs' in args else None),]
     nread_opt = [('num_reads', args.num_reads
                   if 'num_reads' in args else None),]
-    glocs_opt = [('genome_locations', args.genome_locations
+    glocs_opt = [('genome_locs', args.genome_locations
                   if 'genome_locations' in args else None),]
     f5dirs2_opt = [('f5_dirs2', args.control_fast5_basedirs
                     if 'control_fast5_basedirs' in args else None),]

tombo/resquiggle.py

@@ -1128,8 +1128,7 @@ def resquiggle_all_reads(
         rsqgl_args = (
             proc_rsqgl_conns, std_ref, outlier_thresh, corr_grp, bio_samp_type,
             seg_params, sig_aln_params, obs_filter, index_q is None, const_scale)
-        rsqgl_process = Process(target=_resquiggle_worker, args=rsqgl_args,
-                                daemon=True)
+        rsqgl_process = Process(target=_resquiggle_worker, args=rsqgl_args)
         rsqgl_process.start()
 
     # now open mapping thread for each map connection created above

tombo/tombo_helper.py

@@ -128,6 +128,27 @@ def get_chrm_sizes(raw_read_coverage, raw_read_coverage2=None):
                 for chrm, strnd_sizes in
                 strand_chrm_sizes.items())
 
+def parse_genome_locations(genome_locs, default_strand=None):
+    parsed_locs = []
+    for chrm_pos_strand in genome_locs:
+        # strip off any quotes and return up to the first 3 values
+        split_vals = chrm_pos_strand.replace('"', '').replace(
+            "'", "").split(':')[:3]
+        # default to plus strand if not specified
+        if len(split_vals) == 1:
+            _error_message_and_exit(
+                'Invalid genome location provided: ' + chrm_pos_strand +
+                '\n\t\tTry adding quotation marks around specified genome ' +
+                'locations (especially for sequence identifiers with ' +
+                'special characters).')
+        elif len(split_vals) == 2:
+            parsed_locs.append((
+                split_vals[0], split_vals[1], default_strand))
+        else:
+            parsed_locs.append(split_vals)
+
+    return parsed_locs
+
 class TomboMotif(object):
     def _parse_motif(self, rev_comp_motif=False):
         """

tombo/tombo_stats.py

@@ -1276,7 +1276,8 @@ def calc_damp_fraction(self, cov_damp_counts):
         # on the fraction estimation as a binomial variable)
         damp_frac = (non_mod_counts + cov_damp_counts[0]) / (
             self.stats['valid_cov'] + sum(cov_damp_counts))
-        self.stats = append_fields(self.stats, 'damp_frac', damp_frac)
+        damp_name = 'damp_frac' if sys.version_info[0] > 2 else b'damp_frac'
+        self.stats = append_fields(self.stats, damp_name, damp_frac)
 
         return
 
@@ -2018,7 +2019,8 @@ def compute_read_stats(
         ctrl_cov = [ctrl_cov[pos] if pos in ctrl_cov else 0
                     for pos in reg_poss]
     else:
-        ctrl_cov = repeat(0, reg_poss.shape[0])
+        # convert to list since python2 repeat objects can't be pickled
+        ctrl_cov = list(repeat(0, reg_poss.shape[0]))
 
     return reg_base_stats, us_reg_poss, reg_cov, ctrl_cov, valid_cov