From 3086bc7fe1bbff2f6d59dfa6318ea0985d1d2e32 Mon Sep 17 00:00:00 2001
From: Antonio Gonzalez <antgonza@gmail.com>
Date: Wed, 11 Sep 2024 10:29:45 -0600
Subject: [PATCH] BATCHSIZE = 25M

---
 qp_woltka/tests/test_woltka.py | 12 ++++++------
 qp_woltka/woltka.py            |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/qp_woltka/tests/test_woltka.py b/qp_woltka/tests/test_woltka.py
index 582cb98..7529834 100644
--- a/qp_woltka/tests/test_woltka.py
+++ b/qp_woltka/tests/test_woltka.py
@@ -147,7 +147,7 @@ def test_woltka_to_array_rep82(self):
             f'output={out_dir}\n',
             'bt2_cores=6\n',
             f'mxdx mux --file-map {out_dir}/files_list.tsv --batch '
-            '${SLURM_ARRAY_TASK_ID} --batch-size 600000 '
+            '${SLURM_ARRAY_TASK_ID} --batch-size 25000000 '
             '--paired-handling interleave | '
             'bowtie2 -p ${bt2_cores} -x '
             f'{database} --interleaved - --seed 42 --very-sensitive -k 16 '
@@ -155,8 +155,8 @@ def test_woltka_to_array_rep82(self):
             '--score-min "L,0,-0.05" --no-head --no-unal --no-exact-upfront '
             "--no-1mm-upfront | cut -f1-9 | sed \'s/$/\t*\t*/' | mxdx demux "
             f'--file-map {out_dir}/files_list.tsv '
-            '--batch ${SLURM_ARRAY_TASK_ID} --batch-size 600000 --output-base '
-            f'{out_dir}/alignments --extension sam.xz\n',
+            '--batch ${SLURM_ARRAY_TASK_ID} --batch-size 25000000 '
+            f'--output-base {out_dir}/alignments --extension sam.xz\n',
             'date\n']
         self.assertEqual(main, exp_main)
 
@@ -266,7 +266,7 @@ def test_woltka_to_array_wol(self):
             f'output={out_dir}\n',
             'bt2_cores=6\n',
             f'mxdx mux --file-map {out_dir}/files_list.tsv --batch '
-            '${SLURM_ARRAY_TASK_ID} --batch-size 600000 '
+            '${SLURM_ARRAY_TASK_ID} --batch-size 25000000 '
             '--paired-handling interleave | '
             'bowtie2 -p ${bt2_cores} -x '
             f'{database} --interleaved - --seed 42 --very-sensitive -k 16 '
@@ -274,8 +274,8 @@ def test_woltka_to_array_wol(self):
             '--score-min "L,0,-0.05" --no-head --no-unal --no-exact-upfront '
             "--no-1mm-upfront | cut -f1-9 | sed \'s/$/\t*\t*/' | mxdx demux "
             f'--file-map {out_dir}/files_list.tsv '
-            '--batch ${SLURM_ARRAY_TASK_ID} --batch-size 600000 --output-base '
-            f'{out_dir}/alignments --extension sam.xz\n',
+            '--batch ${SLURM_ARRAY_TASK_ID} --batch-size 25000000 '
+            f'--output-base {out_dir}/alignments --extension sam.xz\n',
             'date\n']
         self.assertEqual(main, exp_main)
 
diff --git a/qp_woltka/woltka.py b/qp_woltka/woltka.py
index b50e499..c30f3cc 100644
--- a/qp_woltka/woltka.py
+++ b/qp_woltka/woltka.py
@@ -33,7 +33,7 @@
 MERGE_MEMORY = '140g'
 SYNDNA_MEMORY = '190g'
 # setting so an iSeq run, generates 2 jobs
-BATCHSIZE = 600000
+BATCHSIZE = 25000000
 
 WALLTIME = '40:00:00'
 MERGE_WALLTIME = '30:00:00'