k-nucleotide Racket CS program
source code
#lang racket/base
;;; The Computer Language Benchmarks Game
;;; https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
;;; contributed by Matthew Flatt
(define (all-counts len dna)
(let ([table (make-hasheq)]
[seq (make-string len)])
(for ([s (in-range (- (string-length dna) len) -1 -1)])
(string-copy! seq 0 dna s (+ s len))
(let ([key (string->symbol seq)])
(let ([cnt (hash-ref table key 0)])
(hash-set! table key (add1 cnt)))))
table))
(define (write-freqs table)
(let* ([content (hash-map table cons)]
[total (exact->inexact (apply + (map cdr content)))])
(for ([a (sort content > #:key cdr)])
(printf "~a ~a\n"
(car a)
(real->decimal-string (* 100 (/ (cdr a) total)) 3)))))
(define (write-one-freq table key)
(let ([cnt (hash-ref table key 0)])
(printf "~a\t~a\n" cnt key)))
(define dna
(let ([in (current-input-port)])
;; Skip to ">THREE ..."
(regexp-match #rx#"(?m:^>THREE.*$)" in)
(let ([s (open-output-string)])
;; Copy everything but newlines to s:
(for ([l (in-bytes-lines in)])
(write-bytes l s))
;; Extract the string from s:
(string-upcase (get-output-string s)))))
;; 1-nucleotide counts:
(write-freqs (all-counts 1 dna))
(newline)
;; 2-nucleotide counts:
(write-freqs (all-counts 2 dna))
(newline)
;; Specific sequences:
(for ([seq '("GGT" "GGTA" "GGTATT" "GGTATTTTAATT" "GGTATTTTAATTTATAGT")])
(write-one-freq (all-counts (string-length seq) dna)
(string->symbol seq)))
notes, command-line, and program output
NOTES:
64-bit Ubuntu quad core
Welcome to Racket v7.7.0.4 [cs].
Thu, 07 May 2020 16:38:26 GMT
MAKE:
make: *** No rule to make target 'knucleotide.racketcs_run'. Stop.
0.07s to complete and log all make actions
COMMAND LINE:
/opt/src/racket-7.7.0.4-cs/bin/racket knucleotide.racketcs 0 < knucleotide-input25000000.txt
PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754
AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902
1471758 GGT
446535 GGTA
47336 GGTATT
893 GGTATTTTAATT
893 GGTATTTTAATTTATAGT