Bug fixes and cleanup from last commit.

megalodon/aggregate.py

@@ -256,7 +256,7 @@ def aggregate_stats(
         agg_vars = variants.AggVars(
             vars_db_fn, load_in_mem_indices=False)
         num_vars = agg_vars.num_uniq()
-        ref_names_and_lens = agg_vars.get_all_chrm_and_lens()
+        ref_names_and_lens = agg_vars.vars_db.get_all_chrm_and_lens()
         agg_vars.close()
         logger.info('Spawning variant aggregation processes.')
         # create process to collect var stats from workers
@@ -286,7 +286,7 @@ def aggregate_stats(
         mods_db_fn = mh.get_megalodon_fn(out_dir, mh.PR_MOD_NAME)
         agg_mods = mods.AggMods(mods_db_fn, load_in_mem_indices=False)
         num_mods = agg_mods.num_uniq()
-        ref_names_and_lens = agg_mods.get_all_chrm_and_lens()
+        ref_names_and_lens = agg_mods.mods_db.get_all_chrm_and_lens()
         agg_mods.close()
         logger.info('Spawning modified base aggregation processes.')
         # create process to collect mods stats from workers

megalodon/megalodon.py

@@ -1017,16 +1017,20 @@ def _main():
         args.processes, args.verbose_read_progress, args.suppress_progress,
         mods_info, args.database_safety, pr_ref_filts)
 
-    if aligner is not None: aligner.close()
+    if aligner is not None:
+        ref_fn = aligner.ref_fn
+        map_out_fmt = aligner.out_fmt
+        del aligner
+
     if mh.MAP_NAME in args.outputs:
         logger.info('Spawning process to sort mappings')
         map_p = post_process_mapping(
-            args.output_directory, aligner.out_fmt, aligner.ref_fn)
+            args.output_directory, map_out_fmt, ref_fn)
 
     if mh.WHATSHAP_MAP_NAME in args.outputs:
         logger.info('Spawning process to sort whatshap mappings')
         whatshap_sort_fn, whatshap_p = post_process_whatshap(
-            args.output_directory, aligner.out_fmt, aligner.ref_fn)
+            args.output_directory, map_out_fmt, ref_fn)
 
     if mh.VAR_NAME in args.outputs or mh.MOD_NAME in args.outputs:
         post_process_aggregate(

megalodon/mods.py

@@ -312,8 +312,13 @@ def get_chrm(self, chrm_id):
         return chrm
 
     def get_all_chrm_and_lens(self):
-        return tuple(map(tuple, zip(*self.cur.execute(
-            'SELECT chrm, chrm_len FROM chrm').fetchall())))
+        try:
+            return tuple(map(tuple, zip(*self.cur.execute(
+                'SELECT chrm, chrm_len FROM chrm').fetchall())))
+        except sqlite3.OperationalError:
+            raise mh.MegaError(
+                'Old megalodon database scheme detected. Please re-run ' +
+                'megalodon processing or downgrade megalodon installation.')
 
     def get_mod_base_data(self, mod_id):
         try:

megalodon/variants.py

@@ -340,8 +340,13 @@ def get_chrm(self, chrm_id):
         return chrm
 
     def get_all_chrm_and_lens(self):
-        return tuple(map(tuple, zip(*self.cur.execute(
-            'SELECT chrm, chrm_len FROM chrm').fetchall())))
+        try:
+            return tuple(map(tuple, zip(*self.cur.execute(
+                'SELECT chrm, chrm_len FROM chrm').fetchall())))
+        except sqlite3.OperationalError:
+            raise mh.MegaError(
+                'Old megalodon database scheme detected. Please re-run ' +
+                'megalodon processing or downgrade megalodon installation.')
 
     def get_alt_seq(self, alt_id):
         try:

scripts/run_aggregation.py

@@ -87,7 +87,7 @@ def main():
     args = get_parser().parse_args()
     log_suffix = ('aggregation' if args.output_suffix is None else
                   'aggregation.' + args.output_suffix)
-    logging.init_logger(args.output_directory, out_suffix=log_suffix)
+    logging.init_logger(args.megalodon_directory, out_suffix=log_suffix)
     logger = logging.get_logger()
 
     mod_agg_info = mods.AGG_INFO(
@@ -97,24 +97,22 @@ def main():
         logger.info('Loading model.')
         mod_names = backends.ModelInfo(mh.get_model_fn(
             args.taiyaki_model_filename)).mod_long_names
-    if args.reference is not None: logger.info('Loading reference.')
     valid_read_ids = None
     if args.read_ids_filename is not None:
         with open(args.read_ids_filename) as read_ids_fp:
             valid_read_ids = set(line.strip() for line in read_ids_fp)
     aggregate.aggregate_stats(
-        args.outputs, args.output_directory, args.processes,
+        args.outputs, args.megalodon_directory, args.processes,
         args.write_vcf_log_probs, args.heterozygous_factors,
         variants.HAPLIOD_MODE if args.haploid else variants.DIPLOID_MODE,
         mod_names, mod_agg_info, args.write_mod_log_probs,
         args.mod_output_formats, args.suppress_progress,
         valid_read_ids, args.output_suffix)
 
-    # note reference is required in order to annotate contigs for VCF writing
-    if mh.VAR_NAME in args.outputs and args.reference is not None:
+    if mh.VAR_NAME in args.outputs:
         logger.info('Sorting output variant file')
         variant_fn = mh.add_fn_suffix(
-            mh.get_megalodon_fn(args.output_directory, mh.VAR_NAME),
+            mh.get_megalodon_fn(args.megalodon_directory, mh.VAR_NAME),
             args.output_suffix)
         sort_variant_fn = mh.add_fn_suffix(variant_fn, 'sorted')
         variants.sort_variants(variant_fn, sort_variant_fn)