From c87ae682b336169820715739071498150f0bc8d3 Mon Sep 17 00:00:00 2001
From: Xinpeng Zhang <84593788+Xinpeng021001@users.noreply.github.com>
Date: Fri, 24 Oct 2025 20:21:47 -0500
Subject: [PATCH] run_dbcan yml

---
 datasets/run_dbcan-database.yaml | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 datasets/run_dbcan-database.yaml

diff --git a/datasets/run_dbcan-database.yaml b/datasets/run_dbcan-database.yaml
new file mode 100644
index 000000000..5787942ff
--- /dev/null
+++ b/datasets/run_dbcan-database.yaml
@@ -0,0 +1,32 @@
+Name: run_dbcan CAZyme and CGC annotation database on AWS
+Description: Description: Database for use with run_dbcan (CAZyme and CGC annotation), including CAZyme, Transporter, Transcription factor, Signaling Transduction Protein, Sulfatase, Peptidase, and Polysaccharide utilization Loci.
+Documentation: https://run-dbcan.readthedocs.io/en/latest/
+Contact: xzhang55@huskers.unl.edu; hyi@stjude.org; yyin@unl.edu
+ManagedBy: Xinpeng Zhang; Haidong Yi; Yanbin Yin
+UpdateFrequency: This database will update annually and usually in July/August. 
+Tags:
+  - aws-pds
+  - metagenomics
+  - microbiome
+  - benchmark
+  - bioinformatics
+  - life sciences
+License: There are no restrictions on the use of this data.
+Resources:
+  - Description: run_dbcan CAZyme and CGC annotation database
+    ARN: NA #SHOULD BE CAHNGED
+    Region: us-west-2
+    Type: S3 Bucket
+    Explore:
+    - '[Browse Bucket](NA)' #SHOULD BE CHANGED
+DataAtWork:
+  Tutorials:
+  Tools & Applications:
+    - Title: run_dbcan
+      URL: https://run-dbcan.readthedocs.io/en/latest/
+      AuthorName: Xinpeng Zhang; Haidong Yi; Jinfang Zheng; Le Huang; Qiwei Ge; Yanbin Yin
+      AuthorURL: https://github.com/bcb-unl/run_dbcan
+  Publications:
+    - Title: "dbCAN3: automated carbohydrate-active enzyme and substrate annotation"
+      URL: https://doi.org/10.1093/nar/gkad328
+      AuthorName: Jinfang Zheng, Qiwei Ge, Yuchen Yan, Xinpeng Zhang, Le Huang, Yanbin Yin Author Notes