Add protein translation exercise (#297)

config.json

@@ -395,6 +395,14 @@
         "prerequisites": [],
         "difficulty": 2
       },
+      {
+        "slug": "protein-translation",
+        "name": "Protein Translation",
+        "uuid": "ab4b264c-3c04-4acb-bb0b-77c52e50f6a1",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 3
+      },
       {
         "slug": "proverb",
         "name": "Proverb",

exercises/practice/protein-translation/.docs/instructions.md

@@ -0,0 +1,45 @@
+# Instructions
+
+Translate RNA sequences into proteins.
+
+RNA can be broken into three nucleotide sequences called codons, and then translated to a polypeptide like so:
+
+RNA: `"AUGUUUUCU"` => translates to
+
+Codons: `"AUG", "UUU", "UCU"`
+=> which become a polypeptide with the following sequence =>
+
+Protein: `"Methionine", "Phenylalanine", "Serine"`
+
+There are 64 codons which in turn correspond to 20 amino acids; however, all of the codon sequences and resulting amino acids are not important in this exercise.
+If it works for one codon, the program should work for all of them.
+However, feel free to expand the list in the test suite to include them all.
+
+There are also three terminating codons (also known as 'STOP' codons); if any of these codons are encountered (by the ribosome), all translation ends and the protein is terminated.
+
+All subsequent codons after are ignored, like this:
+
+RNA: `"AUGUUUUCUUAAAUG"` =>
+
+Codons: `"AUG", "UUU", "UCU", "UAA", "AUG"` =>
+
+Protein: `"Methionine", "Phenylalanine", "Serine"`
+
+Note the stop codon `"UAA"` terminates the translation and the final methionine is not translated into the protein sequence.
+
+Below are the codons and resulting Amino Acids needed for the exercise.
+
+| Codon              | Protein       |
+| :----------------- | :------------ |
+| AUG                | Methionine    |
+| UUU, UUC           | Phenylalanine |
+| UUA, UUG           | Leucine       |
+| UCU, UCC, UCA, UCG | Serine        |
+| UAU, UAC           | Tyrosine      |
+| UGU, UGC           | Cysteine      |
+| UGG                | Tryptophan    |
+| UAA, UAG, UGA      | STOP          |
+
+Learn more about [protein translation on Wikipedia][protein-translation].
+
+[protein-translation]: https://en.wikipedia.org/wiki/Translation_(biology)

exercises/practice/protein-translation/.meta/config.json

@@ -0,0 +1,18 @@
+{
+  "authors": [
+    "Adrien-LUDWIG"
+  ],
+  "files": {
+    "solution": [
+      "protein-translation.rkt"
+    ],
+    "test": [
+      "protein-translation-test.rkt"
+    ],
+    "example": [
+      ".meta/example.rkt"
+    ]
+  },
+  "blurb": "Translate RNA sequences into proteins.",
+  "source": "Tyler Long"
+}

exercises/practice/protein-translation/.meta/example.rkt

@@ -0,0 +1,27 @@
+#lang racket
+
+(provide proteins)
+
+(define (empty-string? str) ((negate non-empty-string?) str))
+(define (string-length-3? str) (and (string? str) (= (string-length str) 3)))
+
+(define/contract (unsafe-translate protein)
+  (string-length-3? . -> . string?)
+  (case protein
+    [("AUG") "Methionine"]
+    [("UUU" "UUC") "Phenylalanine"]
+    [("UUA" "UUG") "Leucine"]
+    [("UCU" "UCC" "UCA" "UCG") "Serine"]
+    [("UAU" "UAC") "Tyrosine"]
+    [("UGU" "UGC") "Cysteine"]
+    [("UGG") "Tryptophan"]
+    [("UAA" "UAG" "UGA") ""]
+    [else (error "Invalid codon")]))
+
+(define (proteins strand)
+  (define (codon) (unsafe-translate (substring strand 0 3)))
+  (cond
+    [(zero? (string-length strand)) '()]
+    [(< (string-length strand) 3) (error "Incomplete RNA sequence can't translate")]
+    [else (cond [(empty-string? (codon)) '()]
+                [else (cons (codon) (proteins (substring strand 3)))])]))

exercises/practice/protein-translation/.meta/tests.toml

@@ -0,0 +1,100 @@
+# This is an auto-generated file.
+#
+# Regenerating this file via `configlet sync` will:
+# - Recreate every `description` key/value pair
+# - Recreate every `reimplements` key/value pair, where they exist in problem-specifications
+# - Remove any `include = true` key/value pair (an omitted `include` key implies inclusion)
+# - Preserve any other key/value pair
+#
+# As user-added comments (using the # character) will be removed when this file
+# is regenerated, comments can be added via a `comment` key.
+
+[2c44f7bf-ba20-43f7-a3bf-f2219c0c3f98]
+description = "Empty RNA sequence results in no proteins"
+
+[96d3d44f-34a2-4db4-84cd-fff523e069be]
+description = "Methionine RNA sequence"
+
+[1b4c56d8-d69f-44eb-be0e-7b17546143d9]
+description = "Phenylalanine RNA sequence 1"
+
+[81b53646-bd57-4732-b2cb-6b1880e36d11]
+description = "Phenylalanine RNA sequence 2"
+
+[42f69d4f-19d2-4d2c-a8b0-f0ae9ee1b6b4]
+description = "Leucine RNA sequence 1"
+
+[ac5edadd-08ed-40a3-b2b9-d82bb50424c4]
+description = "Leucine RNA sequence 2"
+
+[8bc36e22-f984-44c3-9f6b-ee5d4e73f120]
+description = "Serine RNA sequence 1"
+
+[5c3fa5da-4268-44e5-9f4b-f016ccf90131]
+description = "Serine RNA sequence 2"
+
+[00579891-b594-42b4-96dc-7ff8bf519606]
+description = "Serine RNA sequence 3"
+
+[08c61c3b-fa34-4950-8c4a-133945570ef6]
+description = "Serine RNA sequence 4"
+
+[54e1e7d8-63c0-456d-91d2-062c72f8eef5]
+description = "Tyrosine RNA sequence 1"
+
+[47bcfba2-9d72-46ad-bbce-22f7666b7eb1]
+description = "Tyrosine RNA sequence 2"
+
+[3a691829-fe72-43a7-8c8e-1bd083163f72]
+description = "Cysteine RNA sequence 1"
+
+[1b6f8a26-ca2f-43b8-8262-3ee446021767]
+description = "Cysteine RNA sequence 2"
+
+[1e91c1eb-02c0-48a0-9e35-168ad0cb5f39]
+description = "Tryptophan RNA sequence"
+
+[e547af0b-aeab-49c7-9f13-801773a73557]
+description = "STOP codon RNA sequence 1"
+
+[67640947-ff02-4f23-a2ef-816f8a2ba72e]
+description = "STOP codon RNA sequence 2"
+
+[9c2ad527-ebc9-4ace-808b-2b6447cb54cb]
+description = "STOP codon RNA sequence 3"
+
+[f4d9d8ee-00a8-47bf-a1e3-1641d4428e54]
+description = "Sequence of two protein codons translates into proteins"
+
+[dd22eef3-b4f1-4ad6-bb0b-27093c090a9d]
+description = "Sequence of two different protein codons translates into proteins"
+
+[d0f295df-fb70-425c-946c-ec2ec185388e]
+description = "Translate RNA strand into correct protein list"
+
+[e30e8505-97ec-4e5f-a73e-5726a1faa1f4]
+description = "Translation stops if STOP codon at beginning of sequence"
+
+[5358a20b-6f4c-4893-bce4-f929001710f3]
+description = "Translation stops if STOP codon at end of two-codon sequence"
+
+[ba16703a-1a55-482f-bb07-b21eef5093a3]
+description = "Translation stops if STOP codon at end of three-codon sequence"
+
+[4089bb5a-d5b4-4e71-b79e-b8d1f14a2911]
+description = "Translation stops if STOP codon in middle of three-codon sequence"
+
+[2c2a2a60-401f-4a80-b977-e0715b23b93d]
+description = "Translation stops if STOP codon in middle of six-codon sequence"
+
+[1e75ea2a-f907-4994-ae5c-118632a1cb0f]
+description = "Non-existing codon can't translate"
+
+[9eac93f3-627a-4c90-8653-6d0a0595bc6f]
+description = "Unknown amino acids, not part of a codon, can't translate"
+
+[9d73899f-e68e-4291-b1e2-7bf87c00f024]
+description = "Incomplete RNA sequence can't translate"
+
+[43945cf7-9968-402d-ab9f-b8a28750b050]
+description = "Incomplete RNA sequence can translate if valid until a STOP codon"

exercises/practice/protein-translation/protein-translation-test.rkt

@@ -0,0 +1,132 @@
+#lang racket/base
+
+(require "protein-translation.rkt")
+
+(module+ test
+  (require rackunit rackunit/text-ui)
+
+  (define suite
+    (test-suite
+     "protein-translation tests"
+
+     (test-equal? "Empty RNA sequence results in no proteins"
+                  (proteins "")
+                  '())
+
+     (test-equal? "Methionine RNA sequence"
+                  (proteins "AUG")
+                  '("Methionine"))
+
+     (test-equal? "Phenylalanine RNA sequence 1"
+                  (proteins "UUU")
+                  '("Phenylalanine"))
+
+     (test-equal? "Phenylalanine RNA sequence 2"
+                  (proteins "UUC")
+                  '("Phenylalanine"))
+
+     (test-equal? "Leucine RNA sequence 1"
+                  (proteins "UUA")
+                  '("Leucine"))
+
+     (test-equal? "Leucine RNA sequence 2"
+                  (proteins "UUG")
+                  '("Leucine"))
+
+     (test-equal? "Serine RNA sequence 1"
+                  (proteins "UCU")
+                  '("Serine"))
+
+     (test-equal? "Serine RNA sequence 2"
+                  (proteins "UCC")
+                  '("Serine"))
+
+     (test-equal? "Serine RNA sequence 3"
+                  (proteins "UCA")
+                  '("Serine"))
+
+     (test-equal? "Serine RNA sequence 4"
+                  (proteins "UCG")
+                  '("Serine"))
+
+     (test-equal? "Tyrosine RNA sequence 1"
+                  (proteins "UAU")
+                  '("Tyrosine"))
+
+     (test-equal? "Tyrosine RNA sequence 2"
+                  (proteins "UAC")
+                  '("Tyrosine"))
+
+     (test-equal? "Cysteine RNA sequence 1"
+                  (proteins "UGU")
+                  '("Cysteine"))
+
+     (test-equal? "Cysteine RNA sequence 2"
+                  (proteins "UGC")
+                  '("Cysteine"))
+
+     (test-equal? "Tryptophan RNA sequence"
+                  (proteins "UGG")
+                  '("Tryptophan"))
+
+     (test-equal? "STOP codon RNA sequence 1"
+                  (proteins "UAA")
+                  '())
+
+     (test-equal? "STOP codon RNA sequence 2"
+                  (proteins "UAG")
+                  '())
+
+     (test-equal? "STOP codon RNA sequence 3"
+                  (proteins "UGA")
+                  '())
+
+     (test-equal? "Sequence of two protein codons translates into proteins"
+                  (proteins "UUUUUU")
+                  '("Phenylalanine" "Phenylalanine"))
+
+     (test-equal? "Sequence of two different protein codons translates into proteins"
+                  (proteins "UUAUUG")
+                  '("Leucine" "Leucine"))
+
+     (test-equal? "Translate RNA strand into correct protein list"
+                  (proteins "AUGUUUUGG")
+                  '("Methionine" "Phenylalanine" "Tryptophan"))
+
+     (test-equal? "Translation stops if STOP codon at beginning of sequence"
+                  (proteins "UAGUGG")
+                  '())
+
+     (test-equal? "Translation stops if STOP codon at end of two-codon sequence"
+                  (proteins "UGGUAG")
+                  '("Tryptophan"))
+
+     (test-equal? "Translation stops if STOP codon at end of three-codon sequence"
+                  (proteins "AUGUUUUAA")
+                  '("Methionine" "Phenylalanine"))
+
+     (test-equal? "Translation stops if STOP codon in middle of three-codon sequence"
+                  (proteins "UGGUAGUGG")
+                  '("Tryptophan"))
+
+     (test-equal? "Translation stops if STOP codon in middle of six-codon sequence"
+                  (proteins "UGGUGUUAUUAAUGGUUU")
+                  '("Tryptophan" "Cysteine" "Tyrosine"))
+
+     (test-exn "Non-existing codon can't translate"
+               exn:fail?
+               (lambda () (proteins "AAA")))
+
+     (test-exn "Unknown amino acids, not part of a codon, can't translate"
+               exn:fail?
+               (lambda () (proteins "XYZ")))
+
+     (test-exn "Incomplete RNA sequence can't translate"
+               exn:fail?
+               (lambda () (proteins "AUGU")))
+
+     (test-equal? "Incomplete RNA sequence can translate if valid until a STOP codon"
+                  (proteins "UUCUUCUAAUGGU")
+                  '("Phenylalanine" "Phenylalanine"))))
+
+  (run-tests suite))

exercises/practice/protein-translation/protein-translation.rkt

@@ -0,0 +1,6 @@
+#lang racket
+
+(provide proteins)
+
+(define (proteins strand)
+  (error "Not implemented yet"))