add doc. shenwei356#451

tetukas · Apr 7, 2024 · 307b11c · 307b11c
1 parent b459e6e
commit 307b11c
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,8 @@
 [![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v2.8.1/total.svg)](https://github.com/shenwei356/seqkit/releases/tag/v2.8.1)
     - `seqkit sana`:
         - Add support for IDs in separator (3rd) line. [#446](https://github.com/shenwei356/seqkit/pull/446), [#429](https://github.com/shenwei356/seqkit/issues/429), [#408](https://github.com/shenwei356/seqkit/issues/408)
+    - `seqkit subseq`:
+        - Add some docs to show how to keep the original order of sequences when extracting with BED: compress the input FASTA file. [#451](https://github.com/shenwei356/seqkit/issues/451)
 - [SeqKit v2.8.0](https://github.com/shenwei356/seqkit/releases/tag/v2.8.0) - 2024-01-31
 [![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v2.8.0/total.svg)](https://github.com/shenwei356/seqkit/releases/tag/v2.8.0)
     - `seqkit stats`:

diff --git a/README.md b/README.md
@@ -18,7 +18,7 @@ and
 [![Citation Badge](https://api.juleskreuer.eu/citation-badge.php?doi=10.1371/journal.pone.0163962)](https://scholar.google.com/citations?view_op=view_citation&hl=en&user=wHF3Lm8AAAAJ&citation_for_view=wHF3Lm8AAAAJ:zYLM7Y9cAGgC)
 - **Others**: [![check in Biotreasury](https://img.shields.io/badge/Biotreasury-collected-brightgreen)](https://biotreasury.rjmart.cn/#/tool?id=10081)  
 
-<img src="seqkit2.jpg" alt="Subcommands of SeqKit2" width="700"/>
+<a href="https://doi.org/10.1002/imt2.191"><img src="seqkit2.jpg" alt="Subcommands of SeqKit2" width="700"/></a>
 
 ## Features
 

diff --git a/doc/docs/usage.md b/doc/docs/usage.md
@@ -469,7 +469,10 @@ Usage
 get subsequences by region/gtf/bed, including flanking sequences.
 
 Attention:
-  1. Use "seqkit grep" for extract subsets of sequences.
+  1. When extracting with BED/GTF from plain text FASTA files, the order of output sequences
+     are random. To keep the order, just compress the FASTA file (input.fasta) and use the
+     compressed one (input.fasta.gz) as the input.
+  2. Use "seqkit grep" for extracting subsets of sequences.
      "seqtk subseq seqs.fasta id.txt" equals to
      "seqkit grep -f id.txt seqs.fasta"
 

diff --git a/seqkit/cmd/subseq.go b/seqkit/cmd/subseq.go
@@ -47,7 +47,10 @@ var subseqCmd = &cobra.Command{
 	Long: fmt.Sprintf(`get subsequences by region/gtf/bed, including flanking sequences.
 
 Attention:
-  1. Use "seqkit grep" for extract subsets of sequences.
+  1. When extracting with BED/GTF from plain text FASTA files, the order of output sequences
+     are random. To keep the order, just compress the FASTA file (input.fasta) and use the
+     compressed one (input.fasta.gz) as the input.
+  2. Use "seqkit grep" for extracting subsets of sequences.
      "seqtk subseq seqs.fasta id.txt" equals to
      "seqkit grep -f id.txt seqs.fasta"