From 8d1df2021036dfa060f58ea40ea7d016bdc70148 Mon Sep 17 00:00:00 2001
From: Chang Ye <yech1990@gmail.com>
Date: Wed, 1 May 2024 20:29:52 -0500
Subject: [PATCH] quick update

---
 cutseq/run.py  | 13 +++++++------
 pyproject.toml |  2 +-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/cutseq/run.py b/cutseq/run.py
index 7cae3b2..1405339 100644
--- a/cutseq/run.py
+++ b/cutseq/run.py
@@ -193,7 +193,7 @@ def __init__(self):
 
 BUILDIN_ADAPTERS = {
     # dsDNA ligation, A tailing method, do ot need to trim
-    "DSLIGATION": "AGTTCTACAGTCCGACGATCT>AGATCGGAAGAGCACACGTC",
+    "dsLIGATION": "AGTTCTACAGTCCGACGATCT>AGATCGGAAGAGCACACGTC",
     # Small RNA, double ligation method, without barcode
     # p5 - insert - p7
     # (Optional) trim 2nt on both end to increase quality
@@ -202,14 +202,14 @@ def __init__(self):
     # ref: https://www.nature.com/articles/nmeth0318-226c/figures/1
     "INLINE": "AGTTCTACAGTCCGACGATCNNNNN>NNNNN(ATCACG)AGATCGGAAGAGCACACGTC",
     # p5 - (random rt tail in TSO) - reverse insert - (random primer start?) - p7
-    "TAKARAV2": "ACACGACGCTCTTCCGATCTXXX<XXXAGATCGGAAGAGCACACGTC",
+    "TAKARAv2": "ACACGACGCTCTTCCGATCTXXX<XXXAGATCGGAAGAGCACACGTC",
     # p5 - (random rt tail in ligation) - reverse insert - (random primer start?) - p7
     "STRANDED": "ACACGACGCTCTTCCGATCTX<XXXAGATCGGAAGAGCACACGTC",
     # p5 - reverse insert - 14ntUMI - p7
     # 14nt UMI = (8 nt UMIs + 3 nt UMI linker + 3 nt from Pico v3 SMART UMI Adapter)
     # IMPORTANT: The UMI liker and UMI adapter can be different, even the 8nt UMI is the same. very weired.
     # NOTE: if insert is too short, also need to add -u -14 to trim readthrough in R1
-    "TAKARAV3": "ACACGACGCTCTTCCGATCTXXX<XXXXXXNNNNNNNNAGATCGGAAGAGCACACGTC",
+    "TAKARAv3": "ACACGACGCTCTTCCGATCTXXX<XXXXXXNNNNNNNNAGATCGGAAGAGCACACGTC",
     # eCLIP, SAC-seq, cDNA ligation method, with 6 nt UMI
     "eCLIP6": "ACACGACGCTCTTCCGATCTXX<XNNNNNNAGATCGGAAGAGCACACGTC",
     # eCLIP, SAC-seq, cDNA ligation method, with 10 nt UMI
@@ -223,9 +223,9 @@ def __init__(self):
     # https://www.idtdna.com/pages/products/next-generation-sequencing/workflow/xgen-ngs-library-preparation/methyl-seq-dna-library-kit#product-details
     # https://sfvideo.blob.core.windows.net/sitefinity/docs/default-source/technical-report/tail-trimming-for-better-data-technical-note.pdf?sfvrsn=135efe07_4
     # 10 bases from END of R1 10 bases from START of R2
-    "XGENMETHY": "ACACGACGCTCTTCCGATCTXXXXXX>XXXXXXXXXXAGATCGGAAGAGCACACGTC",
+    "xGENmethy": "ACACGACGCTCTTCCGATCTXXXXXX>XXXXXXXXXXAGATCGGAAGAGCACACGTC",
     # for snmC-seq, trim 15 bases
-    "XGENSNMC": "ACACGACGCTCTTCCGATCTXXXXXX>XXXXXXXXXXXXXXXAGATCGGAAGAGCACACGTC",
+    "xGENsnmc": "ACACGACGCTCTTCCGATCTXXXXXX>XXXXXXXXXXXXXXXAGATCGGAAGAGCACACGTC",
     # The general method for xGen / Swift kit, might be better than hard clip, TODO
     # '-a "C{20};e=0.5;o=1" -G "G{20};e=0.5;o=1"' might be better
     # "xGenDNA": "ACACGACGCTCTTCCGATCTXXX>(CCCCCCCCCCCCCCCCCCCC;noninternal;e=0.5;o=1)AGATCGGAAGAGCACACGTC",
@@ -808,11 +808,12 @@ def main():
 
     args = parser.parse_args()
 
+    _BUILDIN_ADAPTERS = {k.upper(): v for k, v in BUILDIN_ADAPTERS.items()}
     if args.adapter_name is not None:
         if args.adapter_scheme is not None:
             logging.info("Adapter scheme is provided, ignore adapter name.")
         else:
-            args.adapter_scheme = BUILDIN_ADAPTERS.get(args.adapter_name.upper())
+            args.adapter_scheme = _BUILDIN_ADAPTERS.get(args.adapter_name.upper())
             if args.adapter_scheme is None:
                 logging.error("Adapter name is not valid.")
                 sys.exit(1)
diff --git a/pyproject.toml b/pyproject.toml
index 4133e71..0059066 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cutseq"
-version = "0.0.31"
+version = "0.0.32"
 description = "Automatically cut adapter / barcode / UMI from NGS data"
 authors = ["Ye Chang <yech1990@gmail.com>"]
 license = "MIT"