Merge pull request #202 from rhysnewell/fix-batch-read-type

fix: batch checks read type correctly
rhysnewell · Apr 28, 2024 · 9d97ef3 · 9d97ef3
2 parents bf90668 + 51cfd30
commit 9d97ef3
Show file tree

Hide file tree

Showing 3 changed files with 63 additions and 43 deletions.
diff --git a/aviary/__init__.py b/aviary/__init__.py
@@ -1 +1,25 @@
 __version__ = "0.9.0"
+
+
+# CONSTANTS
+LONG_READ_TYPES = ["ont", "ont_hq", "rs", "sq", "ccs", "hifi"]
+MEDAKA_MODELS = [
+    "r103_fast_g507", "r103_fast_snp_g507", "r103_fast_variant_g507", "r103_hac_g507", "r103_hac_snp_g507",
+    "r103_hac_variant_g507", "r103_min_high_g345", "r103_min_high_g360", "r103_prom_high_g360", "r103_prom_snp_g3210",
+    "r103_prom_variant_g3210", "r103_sup_g507", "r103_sup_snp_g507", "r103_sup_variant_g507", "r1041_e82_260bps_fast_g632",
+    "r1041_e82_260bps_fast_variant_g632", "r1041_e82_260bps_hac_g632", "r1041_e82_260bps_hac_variant_g632", "r1041_e82_260bps_sup_g632",
+    "r1041_e82_260bps_sup_variant_g632", "r1041_e82_400bps_fast_g615", "r1041_e82_400bps_fast_g632",
+    "r1041_e82_400bps_fast_variant_g615", "r1041_e82_400bps_fast_variant_g632", "r1041_e82_400bps_hac_g615",
+    "r1041_e82_400bps_hac_g632", "r1041_e82_400bps_hac_variant_g615", "r1041_e82_400bps_hac_variant_g632", "r1041_e82_400bps_sup_g615",
+    "r1041_e82_400bps_sup_variant_g615", "r104_e81_fast_g5015", "r104_e81_fast_variant_g5015", "r104_e81_hac_g5015",
+    "r104_e81_hac_variant_g5015", "r104_e81_sup_g5015", "r104_e81_sup_g610", "r104_e81_sup_variant_g610", "r10_min_high_g303",
+    "r10_min_high_g340", "r941_e81_fast_g514", "r941_e81_fast_variant_g514", "r941_e81_hac_g514", "r941_e81_hac_variant_g514",
+    "r941_e81_sup_g514", "r941_e81_sup_variant_g514", "r941_min_fast_g303", "r941_min_fast_g507", "r941_min_fast_snp_g507",
+    "r941_min_fast_variant_g507", "r941_min_hac_g507", "r941_min_hac_snp_g507", "r941_min_hac_variant_g507", "r941_min_high_g303",
+    "r941_min_high_g330", "r941_min_high_g340_rle", "r941_min_high_g344", "r941_min_high_g351", "r941_min_high_g360", "r941_min_sup_g507",
+    "r941_min_sup_snp_g507", "r941_min_sup_variant_g507", "r941_prom_fast_g303", "r941_prom_fast_g507", "r941_prom_fast_snp_g507",
+    "r941_prom_fast_variant_g507", "r941_prom_hac_g507", "r941_prom_hac_snp_g507", "r941_prom_hac_variant_g507", "r941_prom_high_g303",
+    "r941_prom_high_g330", "r941_prom_high_g344", "r941_prom_high_g360", "r941_prom_high_g4011", "r941_prom_snp_g303", "r941_prom_snp_g322",
+    "r941_prom_snp_g360", "r941_prom_sup_g507", "r941_prom_sup_snp_g507", "r941_prom_sup_variant_g507", "r941_prom_variant_g303",
+    "r941_prom_variant_g322", "r941_prom_variant_g360", "r941_sup_plant_g610", "r941_sup_plant_variant_g610"
+]
diff --git a/aviary/aviary.py b/aviary/aviary.py
@@ -19,7 +19,7 @@
 ###############################################################################
 import aviary.config.config as Config
 from aviary.modules.processor import Processor, process_batch
-from .__init__ import __version__
+from .__init__ import __version__, MEDAKA_MODELS, LONG_READ_TYPES
 __author__ = "Rhys Newell"
 __copyright__ = "Copyright 2022"
 __credits__ = ["Rhys Newell"]
@@ -478,34 +478,15 @@ def main():
              'reads, "ont" for Oxford Nanopore and "ont_hq" for Oxford Nanopore high quality reads (Guppy5+ or Q20) \n',
         dest='longread_type',
         default="ont",
-        choices=["ont","ont_hq", "rs", "sq", "ccs", "hifi"],
+        choices=LONG_READ_TYPES,
     )
 
     long_read_group.add_argument(
         '--medaka-model', '--medaka_model',
         help='Medaka model to use for polishing long reads. \n',
         dest='medaka_model',
         default="r941_min_hac_g507",
-        choices=[
-            "r103_fast_g507", "r103_fast_snp_g507", "r103_fast_variant_g507", "r103_hac_g507", "r103_hac_snp_g507",
-            "r103_hac_variant_g507", "r103_min_high_g345", "r103_min_high_g360", "r103_prom_high_g360", "r103_prom_snp_g3210",
-            "r103_prom_variant_g3210", "r103_sup_g507", "r103_sup_snp_g507", "r103_sup_variant_g507", "r1041_e82_260bps_fast_g632",
-            "r1041_e82_260bps_fast_variant_g632", "r1041_e82_260bps_hac_g632", "r1041_e82_260bps_hac_variant_g632", "r1041_e82_260bps_sup_g632",
-            "r1041_e82_260bps_sup_variant_g632", "r1041_e82_400bps_fast_g615", "r1041_e82_400bps_fast_g632",
-            "r1041_e82_400bps_fast_variant_g615", "r1041_e82_400bps_fast_variant_g632", "r1041_e82_400bps_hac_g615",
-            "r1041_e82_400bps_hac_g632", "r1041_e82_400bps_hac_variant_g615", "r1041_e82_400bps_hac_variant_g632", "r1041_e82_400bps_sup_g615",
-            "r1041_e82_400bps_sup_variant_g615", "r104_e81_fast_g5015", "r104_e81_fast_variant_g5015", "r104_e81_hac_g5015",
-            "r104_e81_hac_variant_g5015", "r104_e81_sup_g5015", "r104_e81_sup_g610", "r104_e81_sup_variant_g610", "r10_min_high_g303",
-            "r10_min_high_g340", "r941_e81_fast_g514", "r941_e81_fast_variant_g514", "r941_e81_hac_g514", "r941_e81_hac_variant_g514",
-            "r941_e81_sup_g514", "r941_e81_sup_variant_g514", "r941_min_fast_g303", "r941_min_fast_g507", "r941_min_fast_snp_g507",
-            "r941_min_fast_variant_g507", "r941_min_hac_g507", "r941_min_hac_snp_g507", "r941_min_hac_variant_g507", "r941_min_high_g303",
-            "r941_min_high_g330", "r941_min_high_g340_rle", "r941_min_high_g344", "r941_min_high_g351", "r941_min_high_g360", "r941_min_sup_g507",
-            "r941_min_sup_snp_g507", "r941_min_sup_variant_g507", "r941_prom_fast_g303", "r941_prom_fast_g507", "r941_prom_fast_snp_g507",
-            "r941_prom_fast_variant_g507", "r941_prom_hac_g507", "r941_prom_hac_snp_g507", "r941_prom_hac_variant_g507", "r941_prom_high_g303",
-            "r941_prom_high_g330", "r941_prom_high_g344", "r941_prom_high_g360", "r941_prom_high_g4011", "r941_prom_snp_g303", "r941_prom_snp_g322",
-            "r941_prom_snp_g360", "r941_prom_sup_g507", "r941_prom_sup_snp_g507", "r941_prom_sup_variant_g507", "r941_prom_variant_g303",
-            "r941_prom_variant_g322", "r941_prom_variant_g360", "r941_sup_plant_g610", "r941_sup_plant_variant_g610"
-        ]
+        choices=MEDAKA_MODELS
     )
 
     long_read_group.add_argument(
@@ -1109,7 +1090,7 @@ def main():
         type=str2bool,
         nargs='?',
         const=True,
-        default=True
+        default=False
     )
 
     batch_options.add_argument(
@@ -1136,6 +1117,14 @@ def main():
         default='95'
     )
 
+    batch_options.add_argument(
+        '--medaka-model', '--medaka_model',
+        help='Medaka model to use for polishing long reads. \n',
+        dest='medaka_model',
+        default="r941_min_hac_g507",
+        choices=MEDAKA_MODELS
+    )
+
     add_workflow_arg(
         batch_options,
         ['get_bam_indices', 'recover_mags', 'annotate', 'lorikeet'],

diff --git a/aviary/modules/processor.py b/aviary/modules/processor.py
@@ -35,13 +35,15 @@
 import logging
 import os
 import subprocess
+import copy
 from pathlib import Path
 from glob import glob
 
 # Local imports
 from snakemake import utils
 from snakemake.io import load_configfile
 from ruamel.yaml import YAML  # used for yaml reading with comments
+from aviary import LONG_READ_TYPES
 
 BATCH_HEADER=['sample', 'short_reads_1', 'short_reads_2', 'long_reads', 'long_read_type', 'assembly', 'coassemble']
 
@@ -555,36 +557,41 @@ def process_batch(args, prefix):
         s2 = check_batch_input(batch.iloc[i, 2], "none", split=True)
         l = check_batch_input(batch.iloc[i, 3], "none", split=True)
         l_type = check_batch_input(batch.iloc[i, 4], "ont", split=False)
+        if l_type not in LONG_READ_TYPES:
+            logging.error(f"Unknown long read type {l_type} specified.")
+            logging.error(f"Valid long read types: {LONG_READ_TYPES}")
+            sys.exit(1)
         assembly = check_batch_input(batch.iloc[i, 5], None, split=False)
         coassemble = check_batch_input(batch.iloc[i, 6], False, split=False)
-
+
+        new_args = copy.deepcopy(args)
         # update the value of args
-        args.output = f"{prefix}/{sample}"
-        runs.append(args.output)
-        args.pe1 = s1
-        args.pe2 = s2
+        new_args.output = f"{prefix}/{sample}"
+        runs.append(new_args.output)
+        new_args.pe1 = s1
+        new_args.pe2 = s2
 
-        args.longreads = l
-        args.longread_type = l_type
-        args.assembly = assembly
-        args.coassemble = coassemble
+        new_args.longreads = l
+        new_args.longread_type = l_type
+        new_args.assembly = assembly
+        new_args.coassemble = coassemble
 
         # ensure output folder exists
-        if not os.path.exists(args.output):
-            os.makedirs(args.output)
+        if not os.path.exists(new_args.output):
+            os.makedirs(new_args.output)
 
         # setup processor for this line
-        processor = Processor(args)
+        processor = Processor(new_args)
         processor.make_config()
 
-        processor.run_workflow(cores=int(args.n_cores),
-                               dryrun=args.dryrun,
-                               clean=args.clean,
-                               conda_frontend=args.conda_frontend,
-                               snakemake_args=args.cmds,
-                               rerun_triggers=args.rerun_triggers,
-                               profile=args.snakemake_profile,
-                               cluster_retries=args.cluster_retries,
+        processor.run_workflow(cores=int(new_args.n_cores),
+                               dryrun=new_args.dryrun,
+                               clean=new_args.clean,
+                               conda_frontend=new_args.conda_frontend,
+                               snakemake_args=new_args.cmds,
+                               rerun_triggers=new_args.rerun_triggers,
+                               profile=new_args.snakemake_profile,
+                               cluster_retries=new_args.cluster_retries,
                                write_to_script=write_to_script)
 
     if args.cluster: