add new flag --compress-level to set compression level. #320 . suppor…

…t bzip2 #361
shenwei356 · Mar 14, 2023 · 4081f4d · 4081f4d
1 parent d1e0ea2
commit 4081f4d
Show file tree

Hide file tree

Showing 8 changed files with 100 additions and 28 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,6 +1,8 @@
 - [SeqKit v2.4.0](https://github.com/shenwei356/seqkit/releases/tag/v2.4.0) - 2022-09-22
 [![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v2.4.0/total.svg)](https://github.com/shenwei356/seqkit/releases/tag/v2.4.0)
     - `seqkit`:
+        - support `bzip2` format. [#361](https://github.com/shenwei356/seqkit/issues/361)
+        - support setting compression level for `gzip`, `zstd`, and `bzip2` format via `--compress-level`. [#320](https://github.com/shenwei356/seqkit/issues/320)
         - the global flag `--infile-list` accepts stdin "-" now.
     - `seqkit locate`:
         - **do not remove embeded regions when searching with regular expressions**. [#368](https://github.com/shenwei356/seqkit/issues/368)

diff --git a/README.md b/README.md
@@ -27,7 +27,7 @@ and
 - **Easy to use** 
     - Ultrafast (see [technical-details](http://bioinf.shenwei.me/seqkit/usage/#technical-details-and-guides-for-use) and [benchmark](http://bioinf.shenwei.me/seqkit/benchmark))
     - Seamlessly parsing both FASTA and FASTQ formats
-    - Supporting (`gzip`/`xz`/`zstd` compressed) STDIN/STDOUT and input/output file, easily integrated in pipe
+    - Supporting (`gzip`/`xz`/`zstd`/`bzip2` compressed) STDIN/STDOUT and input/output file, easily integrated in pipe
     - Reproducible results (configurable rand seed in `sample` and `shuffle`)
     - Supporting custom sequence ID via regular expression
     - Supporting [Bash/Zsh completion](http://bioinf.shenwei.me/seqkit/download/#shell-completion)

diff --git a/doc/docs/usage.md b/doc/docs/usage.md
@@ -156,7 +156,7 @@ reproduced in different environments with same random seed.
 ``` text
 SeqKit -- a cross-platform and ultrafast toolkit for FASTA/Q file manipulation
 
-Version: 2.3.0
+Version: 2.4.0
 
 Author: Wei Shen <[email protected]>
 
@@ -172,6 +172,16 @@ larger than files generated by GNU gzip.
 Seqkit writes gzip files very fast, much faster than the multi-threaded pigz,
 therefore there's no need to pipe the result to gzip/pigz.
 
+Seqkit also supports reading and writing xz (.xz) and zstd (.zst) formats since v2.2.0.
+Bzip2 format is supported since v2.4.0.
+
+Compression level:
+  format   range   default  comment
+  gzip     1-9     5        https://github.com/klauspost/pgzip sets 5 as the default value.
+  xz       NA      NA       https://github.com/ulikunitz/xz does not support.
+  zstd     1-4     2        roughly equals to zstd 1, 3, 7, 11, respectively.
+  bzip     1-9     6        https://github.com/dsnet/compress
+
 Usage:
   seqkit [command]
 
@@ -202,7 +212,7 @@ Available Commands:
   sample          sample sequences by number or proportion
   sana            sanitize broken single line FASTQ files
   scat            real time recursive concatenation and streaming of fastx files
-  seq             transform sequences (extract ID, filter by length, remove gaps...)
+  seq             transform sequences (extract ID, filter by length, remove gaps, reverse complement...)
   shuffle         shuffle sequences
   sliding         extract subsequences in sliding windows
   sort            sort sequences by id/name/sequence/length
@@ -218,11 +228,12 @@ Available Commands:
 
 Flags:
       --alphabet-guess-seq-length int   length of sequence prefix of the first FASTA record based on which seqkit guesses the sequence type (0 for whole seq) (default 10000)
+      --compress-level int              compression level for gzip, zstd, xz and bzip2. type "seqkit -h" for the range and default value for each format (default -1)
   -h, --help                            help for seqkit
       --id-ncbi                         FASTA head is NCBI-style, e.g. >gi|110645304|ref|NC_002516.2| Pseud...
       --id-regexp string                regular expression for parsing ID (default "^(\\S+)\\s?")
       --infile-list string              file of input files list (one file per line), if given, they are appended to files from cli arguments
-  -w, --line-width int                  line width when outputing FASTA format (0 for no wrap) (default 60)
+  -w, --line-width int                  line width when outputting FASTA format (0 for no wrap) (default 60)
   -o, --out-file string                 out file ("-" for stdout, suffix .gz for gzipped out) (default "-")
       --quiet                           be quiet and do not show extra information
   -t, --seq-type string                 sequence type (dna|rna|protein|unlimit|auto) (for auto, it automatically detect by the first sequence) (default "auto")

diff --git a/go.mod b/go.mod
@@ -11,7 +11,7 @@ require (
 	github.com/dustin/go-humanize v1.0.0
 	github.com/fsnotify/fsnotify v1.5.4
 	github.com/iafan/cwalk v0.0.0-20210125030640-586a8832a711
-	github.com/klauspost/compress v1.15.12
+	github.com/klauspost/compress v1.16.3
 	github.com/klauspost/pgzip v1.2.5
 	github.com/logrusorgru/aurora v2.0.3+incompatible
 	github.com/mattn/go-colorable v0.1.13
@@ -23,7 +23,7 @@ require (
 	github.com/shenwei356/bwt v0.6.1
 	github.com/shenwei356/go-logging v0.0.0-20171012171522-c6b9702d88ba
 	github.com/shenwei356/util v0.5.1
-	github.com/shenwei356/xopen v0.2.2
+	github.com/shenwei356/xopen v0.3.1
 	github.com/smallfish/simpleyaml v0.1.0
 	github.com/spf13/cobra v1.5.0
 	github.com/tatsushid/go-prettytable v0.0.0-20141013043238-ed2d14c29939
@@ -36,7 +36,7 @@ replace github.com/miekg/dns v1.0.14 => github.com/miekg/dns v1.1.46
 require (
 	git.sr.ht/~sbinet/gg v0.3.1 // indirect
 	github.com/ajstarks/svgo v0.0.0-20211024235047-1546f124cd8b // indirect
-	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/dsnet/compress v0.0.1 // indirect
 	github.com/edsrzf/mmap-go v1.1.0 // indirect
 	github.com/go-fonts/liberation v0.2.0 // indirect
 	github.com/go-latex/latex v0.0.0-20210823091927-c0d11ff05a81 // indirect
@@ -49,11 +49,10 @@ require (
 	github.com/shenwei356/natsort v0.0.0-20220117010048-580176ad49fb // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
 	golang.org/x/crypto v0.0.0-20220919173607-35f4265a4bc0 // indirect
-	golang.org/x/image v0.5.0 // indirect
+	golang.org/x/image v0.0.0-20220902085622-e7cb96979f69 // indirect
 	golang.org/x/sys v0.0.0-20220919091848-fb04ddd9f9c8 // indirect
 	golang.org/x/term v0.0.0-20220919170432-7a66f970e087 // indirect
-	golang.org/x/text v0.7.0 // indirect
+	golang.org/x/text v0.3.7 // indirect
 	gonum.org/v1/plot v0.12.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
-	gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b // indirect
 )
diff --git a/go.sum b/go.sum
@@ -29,9 +29,11 @@ github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46t
 github.com/cznic/mathutil v0.0.0-20181122101859-297441e03548 h1:iwZdTE0PVqJCos1vaoKsclOGD3ADKpshg3SRtYBbwso=
 github.com/cznic/sortutil v0.0.0-20181122101858-f5f958428db8 h1:LpMLYGyy67BoAFGda1NeOBQwqlv7nUXpm+rIVHGxZZ4=
 github.com/cznic/sortutil v0.0.0-20181122101858-f5f958428db8/go.mod h1:q2w6Bg5jeox1B+QkJ6Wp/+Vn0G/bo3f1uY7Fn3vivIQ=
+github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
-github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dsnet/compress v0.0.1 h1:PlZu0n3Tuv04TzpfPbrnI0HW/YwodEXDS+oPKahKF0Q=
+github.com/dsnet/compress v0.0.1/go.mod h1:Aw8dCMJ7RioblQeTqt88akK31OvO8Dhf5JflhBbQEHo=
+github.com/dsnet/golib v0.0.0-20171103203638-1ea166775780/go.mod h1:Lj+Z9rebOhdfkVLjJ8T6VcRQv3SXugXy999NBtR9aFY=
 github.com/dustin/go-humanize v1.0.0 h1:VSnTsYCnlFHaM2/igO1h6X3HA71jcobQuxemgkq4zYo=
 github.com/dustin/go-humanize v1.0.0/go.mod h1:HtrtbFcZ19U5GC7JDqmcUSB87Iq5E25KnS6fMYU6eOk=
 github.com/edsrzf/mmap-go v1.1.0 h1:6EUwBLQ/Mcr1EYLE4Tn1VdW1A4ckqCQWZBw8Hr0kjpQ=
@@ -71,8 +73,10 @@ github.com/jung-kurt/gofpdf v1.0.0/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+
 github.com/jung-kurt/gofpdf v1.0.3-0.20190309125859-24315acbbda5/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
 github.com/jung-kurt/gofpdf v1.16.2/go.mod h1:1hl7y57EsiPAkLbOwzpzqgx1A30nQCk/YmFV8S2vmK0=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
-github.com/klauspost/compress v1.15.12 h1:YClS/PImqYbn+UILDnqxQCZ3RehC9N318SU3kElDUEM=
-github.com/klauspost/compress v1.15.12/go.mod h1:QPwzmACJjUTFsnSHH934V6woptycfrDDJnH7hvFVbGM=
+github.com/klauspost/compress v1.4.1/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A=
+github.com/klauspost/compress v1.16.3 h1:XuJt9zzcnaz6a16/OU53ZjWp/v7/42WcR5t2a0PcNQY=
+github.com/klauspost/compress v1.16.3/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
+github.com/klauspost/cpuid v1.2.0/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
 github.com/klauspost/pgzip v1.2.5 h1:qnWYvvKqedOF2ulHpMG72XQol4ILEJ8k2wwRl/Km8oE=
 github.com/klauspost/pgzip v1.2.5/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=
 github.com/kortschak/utter v0.0.0-20190412033250-50fe362e6560/go.mod h1:oDr41C7kH9wvAikWyFhr6UFr8R7nelpmCF5XR5rL7I8=
@@ -122,8 +126,8 @@ github.com/shenwei356/natsort v0.0.0-20220117010048-580176ad49fb h1:pb0RhpaADsFr
 github.com/shenwei356/natsort v0.0.0-20220117010048-580176ad49fb/go.mod h1:SiiGiRFyRtV7S9RamOrmQR5gpGIRhWJM1w0EtmuQ1io=
 github.com/shenwei356/util v0.5.1 h1:m3SjmJvIkEr7hQ1LyGGy5cgfQFSFOww2wmpZ0/hIiIM=
 github.com/shenwei356/util v0.5.1/go.mod h1:3tRAOfreWdgl/Zh1gE008h2lWocf5/YAxVSjgLKvd4k=
-github.com/shenwei356/xopen v0.2.2 h1:g1v3YjiIky9k6oN4qmnU1bDciAHnSrmOn2sMTE5pChY=
-github.com/shenwei356/xopen v0.2.2/go.mod h1:6EQUa6I7Zsl2GQKqcL9qGLrTzVE+oZyly+uhzovQYSk=
+github.com/shenwei356/xopen v0.3.1 h1:3pju0hVeRRnlpXC7s3aE/RVOhFB1S3qRJGN+eV85r3s=
+github.com/shenwei356/xopen v0.3.1/go.mod h1:6EQUa6I7Zsl2GQKqcL9qGLrTzVE+oZyly+uhzovQYSk=
 github.com/smallfish/simpleyaml v0.1.0 h1:5uAZdLAiHxS9cmzkOxg7lH0dILXKTD7uRZbAhyHmyU0=
 github.com/smallfish/simpleyaml v0.1.0/go.mod h1:gU3WdNn44dQVAbVHD2SrSqKKCvmzFApWD2UURhgEj1M=
 github.com/spf13/cobra v1.5.0 h1:X+jTBEBqF0bHN+9cSMgmfuvv2VHJ9ezmFNf9Y/XstYU=
@@ -175,9 +179,8 @@ golang.org/x/image v0.0.0-20210607152325-775e3b0c77b9/go.mod h1:023OzeP/+EPmXeap
 golang.org/x/image v0.0.0-20210628002857-a66eb6448b8d/go.mod h1:023OzeP/+EPmXeapQh35lcL3II3LrY8Ic+EFFKVhULM=
 golang.org/x/image v0.0.0-20211028202545-6944b10bf410/go.mod h1:023OzeP/+EPmXeapQh35lcL3II3LrY8Ic+EFFKVhULM=
 golang.org/x/image v0.0.0-20220302094943-723b81ca9867/go.mod h1:023OzeP/+EPmXeapQh35lcL3II3LrY8Ic+EFFKVhULM=
+golang.org/x/image v0.0.0-20220902085622-e7cb96979f69 h1:Lj6HJGCSn5AjxRAH2+r35Mir4icalbqku+CLUtjnvXY=
 golang.org/x/image v0.0.0-20220902085622-e7cb96979f69/go.mod h1:doUCurBvlfPMKfmIpRIywoHmhN3VyhnoFDbvIEWF4hY=
-golang.org/x/image v0.5.0 h1:5JMiNunQeQw++mMOz48/ISeNu3Iweh/JaZU8ZLqHRrI=
-golang.org/x/image v0.5.0/go.mod h1:FVC7BI/5Ym8R25iw5OLsgshdUBbT1h5jZTpA+mvAdZ4=
 golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
 golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCcRqshq8CkpyQDoeVncDDYHnLhea+o=
 golang.org/x/mobile v0.0.0-20201217150744-e6ae53a27f4f/go.mod h1:skQtrUTUwhdJvXM/2KKJzY8pDgNr9I/FOMqDVRPBUS4=
@@ -223,9 +226,8 @@ golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
-golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
-golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/tools v0.0.0-20180525024113-a5b4c53f6e8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190206041539-40960b6deb8e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -259,9 +261,8 @@ gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b h1:h8qDotaEPuJATrMmW04NCwg7v22aHH28wwpauUhK9Oo=
-gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 honnef.co/go/tools v0.1.3/go.mod h1:NgwopIslSNH47DimFoV78dnkksY2EFtX0ajyb3K/las=
 modernc.org/cc v1.0.0/go.mod h1:1Sk4//wdnYJiUIxnW8ddKpaOJCF37yAdqYnkxUpaYxw=
 modernc.org/golex v1.0.0/go.mod h1:b/QX9oBD/LhixY6NDh+IdGv17hgB+51fET1i2kPSmvk=

diff --git a/seqkit/cmd/helper.go b/seqkit/cmd/helper.go
@@ -238,23 +238,56 @@ type Config struct {
 	Quiet                  bool
 	AlphabetGuessSeqLength int
 	ValidateSeqLength      int
+	CompressionLevel       int
 }
 
 func getConfigs(cmd *cobra.Command) Config {
 	threads := getFlagPositiveInt(cmd, "threads")
 	if threads >= 1000 {
 		checkError(fmt.Errorf("are your seriously? %d threads? It will exhaust your RAM", threads))
 	}
+	outfile := getFlagString(cmd, "out-file")
+
+	level := getFlagInt(cmd, "compress-level")
+
+	f := strings.ToLower(outfile)
+	var ranges [3]int
+	var format string
+	checkCompressLevel := true
+	if strings.HasSuffix(f, ".gz") {
+		format = "gzip"
+		ranges = [3]int{1, 9, 5}
+	} else if strings.HasSuffix(f, ".xz") {
+		checkCompressLevel = false
+	} else if strings.HasSuffix(f, ".zst") {
+		format = "zstd"
+		ranges = [3]int{1, 4, 2}
+	} else if strings.HasSuffix(f, ".bz2") {
+		format = "bzip2"
+		ranges = [3]int{1, 9, 6}
+	} else {
+		checkCompressLevel = false
+	}
+	if checkCompressLevel {
+		if level == -1 {
+			level = ranges[2]
+		}
+		if level < ranges[0] || level > ranges[1] {
+			checkError(fmt.Errorf("compression level out of range for %s format (%d-%d): %d", format, ranges[0], ranges[1], level))
+		}
+	}
+	xopen.Level = level
 
 	return Config{
 		Alphabet:               getAlphabet(cmd, "seq-type"),
 		Threads:                threads,
 		LineWidth:              getFlagNonNegativeInt(cmd, "line-width"),
 		IDRegexp:               getIDRegexp(cmd, "id-regexp"),
 		IDNCBI:                 getFlagBool(cmd, "id-ncbi"),
-		OutFile:                getFlagString(cmd, "out-file"),
+		OutFile:                outfile,
 		Quiet:                  getFlagBool(cmd, "quiet"),
 		AlphabetGuessSeqLength: getFlagAlphabetGuessSeqLength(cmd, "alphabet-guess-seq-length"),
+		CompressionLevel:       level,
 	}
 
 }

diff --git a/seqkit/cmd/root.go b/seqkit/cmd/root.go
@@ -53,6 +53,14 @@ Seqkit writes gzip files very fast, much faster than the multi-threaded pigz,
 therefore there's no need to pipe the result to gzip/pigz.
 
 Seqkit also supports reading and writing xz (.xz) and zstd (.zst) formats since v2.2.0.
+Bzip2 format is supported since v2.4.0.
+
+Compression level:
+  format   range   default  comment
+  gzip     1-9     5        https://github.com/klauspost/pgzip sets 5 as the default value.
+  xz       NA      NA       https://github.com/ulikunitz/xz does not support.
+  zstd     1-4     2        roughly equals to zstd 1, 3, 7, 11, respectively.
+  bzip     1-9     6        https://github.com/dsnet/compress
 
 `, VERSION),
 }
@@ -90,6 +98,7 @@ func init() {
 	RootCmd.PersistentFlags().BoolP("quiet", "", false, "be quiet and do not show extra information")
 	RootCmd.PersistentFlags().IntP("alphabet-guess-seq-length", "", 10000, "length of sequence prefix of the first FASTA record based on which seqkit guesses the sequence type (0 for whole seq)")
 	RootCmd.PersistentFlags().StringP("infile-list", "", "", "file of input files list (one file per line), if given, they are appended to files from cli arguments")
+	RootCmd.PersistentFlags().IntP("compress-level", "", -1, `compression level for gzip, zstd, xz and bzip2. type "seqkit -h" for the range and default value for each format`)
 
 	RootCmd.CompletionOptions.DisableDefaultCmd = true
 	RootCmd.SetHelpCommand(&cobra.Command{Hidden: true})

diff --git a/seqkit/cmd/seq.go b/seqkit/cmd/seq.go
@@ -31,6 +31,7 @@ import (
 
 	// "runtime/debug"
 
+	"github.com/dsnet/compress/bzip2"
 	gzip "github.com/klauspost/pgzip"
 	"github.com/shenwei356/bio/seq"
 	"github.com/shenwei356/bio/seqio/fastx"
@@ -157,21 +158,27 @@ var seqCmd = &cobra.Command{
 			color = false
 		}
 
-		gzippedOutfile := strings.HasSuffix(strings.ToLower(outFile), ".gz")
-		xzOutfile := strings.HasSuffix(strings.ToLower(outFile), ".xz")
-		zstdOutfile := strings.HasSuffix(strings.ToLower(outFile), ".zst")
+		outFileLower := strings.ToLower(outFile)
+		gzippedOutfile := strings.HasSuffix(outFileLower, ".gz")
+		xzOutfile := strings.HasSuffix(outFileLower, ".xz")
+		zstdOutfile := strings.HasSuffix(outFileLower, ".zst")
+		bzip2Outfile := strings.HasSuffix(outFileLower, ".bz2")
 
 		var fh io.Writer
 		var outbw *bufio.Writer
 		var gw *gzip.Writer
 		var xw *xz.Writer
 		var zw *zstd.Encoder
+		var bz2 *bzip2.Writer
 
 		if color {
 			fh = seqCol.WrapWriter(outfh)
 			outbw = bufio.NewWriterSize(fh, bufSize)
 		} else if gzippedOutfile {
-			gw = gzip.NewWriter(outfh)
+			gw, err = gzip.NewWriterLevel(outfh, config.CompressionLevel)
+			if err != nil {
+				checkError(err)
+			}
 			outbw = bufio.NewWriterSize(gw, bufSize)
 		} else if xzOutfile {
 			xw, err = xz.NewWriter(outfh)
@@ -180,11 +187,17 @@ var seqCmd = &cobra.Command{
 			}
 			outbw = bufio.NewWriterSize(xw, bufSize)
 		} else if zstdOutfile {
-			zw, err = zstd.NewWriter(outfh)
+			zw, err = zstd.NewWriter(outfh, zstd.WithEncoderLevel(zstd.EncoderLevel(config.CompressionLevel)))
 			if err != nil {
 				checkError(err)
 			}
 			outbw = bufio.NewWriterSize(zw, bufSize)
+		} else if bzip2Outfile {
+			bz2, err = bzip2.NewWriter(outfh, &bzip2.WriterConfig{Level: config.CompressionLevel})
+			if err != nil {
+				checkError(err)
+			}
+			outbw = bufio.NewWriterSize(bz2, bufSize)
 		} else {
 			fh = outfh
 			outbw = bufio.NewWriterSize(fh, bufSize)
@@ -206,6 +219,10 @@ var seqCmd = &cobra.Command{
 				checkError(zw.Close())
 			}
 
+			if bzip2Outfile {
+				checkError(bz2.Close())
+			}
+
 			checkError(outfh.Close())
 		}()