Add cdhit module and package

common/cdhit.scm

+(define-module (common cdhit) 
+  #:use-module ((guix licenses) #:prefix license:)
+  #:use-module (guix packages)
+  #:use-module (guix download)
+  #:use-module (guix utils)
+  #:use-module (guix build utils)
+  #:use-module (guix build-system cmake)
+  #:use-module (guix build-system gnu)
+  #:use-module (gnu packages)
+  #:use-module (gnu packages algebra)
+  #:use-module (gnu packages image-processing)
+  #:use-module (gnu packages image)
+  #:use-module (gnu packages graphics)
+  #:use-module (gnu packages maths)
+  #:use-module (gnu packages mpi)
+  #:use-module (gnu packages python)
+  #:use-module (gnu packages python-xyz)
+  #:use-module (gnu packages compression)
+  #:use-module (gnu packages commencement)
+  #:use-module (gnu packages gcc)
+  #:use-module (gnu packages pkg-config)
+  #:use-module (gnu packages video)
+  #:use-module (gnu packages llvm)
+  #:use-module (gnu packages curl)
+  #:use-module (gnu packages pcre)
+  #:use-module (gnu packages geo)
+  #:use-module (gnu packages multiprecision))
+
+(define-public cdhit
+  (package
+    (name "cdhit")
+    (version "4.8.1")
+    (source (origin
+              (method url-fetch)
+              (uri (string-append "https://github.com/weizhongli/cdhit/archive/refs/tags/V" version ".tar.gz"))
+              (sha256
+               (base32
+                "0w0bnb6mfvn0xcvsilmv6qg3yhd6wy9h1vaysgy35d7bgbfkrg7q"))))
+    (build-system gnu-build-system)
+    (inputs
+      `(("zlib" ,zlib)))   
+    (arguments
+     `(#:make-flags
+        (list (string-append "PREFIX="
+                             (assoc-ref %outputs "out") "/bin"))
+       #:phases
+       (modify-phases %standard-phases
+         (delete 'check)
+         (replace 'configure
+           (lambda* (#:key outputs #:allow-other-keys)
+             (let* ((out (assoc-ref outputs "out")))
+               (mkdir-p (string-append out "/bin"))))))))
+    (synopsis "CD-HIT is a very widely used program for clustering and comparing protein or nucleotide sequences.")
+    (description "CD-HIT is very fast and can handle extremely large databases. CD-HIT helps to significantly reduce the computational and manual efforts in many sequence analysis tasks and aids in understanding the data structure and correct the bias within a dataset.")
+    (home-page "http://weizhong-lab.ucsd.edu/cd-hit/")
+    (license license:gpl3+)))
\ No newline at end of file