From a04293a5271176885ce7f876b6353b20da3f7b98 Mon Sep 17 00:00:00 2001
From: rzlim08 <37033997+rzlim08@users.noreply.github.com>
Date: Wed, 2 Oct 2024 13:35:10 -0700
Subject: [PATCH] [Bugfix] Fix subsample depth (#379)

* fix subsample depth

* add comment
---
 workflows/long-read-mngs/run.wdl | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/workflows/long-read-mngs/run.wdl b/workflows/long-read-mngs/run.wdl
index e1ffb2a1..1335edff 100644
--- a/workflows/long-read-mngs/run.wdl
+++ b/workflows/long-read-mngs/run.wdl
@@ -1280,7 +1280,9 @@ workflow czid_long_read_mngs {
         String library_type = "RNA"
         String guppy_basecaller_setting = "hac" # fast, hac, super
 
-        Int subsample_depth = 4000000 # should be 4x the number of reads desired
+        # The subsample_depth used to be 4000000 because to get 1 million reads we need to get 
+        # 4 * 1000000 lines. But since we switched to using seqtk, we only need to provide the total number of reads.
+        Int subsample_depth = 1000000 
 
         File minimap_host_db
         File minimap_human_db