Add protein-translation

config.json

@@ -344,6 +344,14 @@
         "prerequisites": [],
         "difficulty": 2
       },
+      {
+        "slug": "protein-translation",
+        "name": "Protein Translation",
+        "uuid": "7ba9bb49-551d-47a9-9662-f66560d9d0c4",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 2
+      },
       {
         "slug": "resistor-color",
         "name": "Resistor Color",

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": [
+    "BNAndras"
+  ],
+  "files": {
+    "solution": [
+      "source/protein_translation.d"
+    ],
+    "test": [
+      "source/protein_translation.d"
+    ],
+    "example": [
+      "example/protein_translation.d"
+    ]
+  },
+  "blurb": "Translate RNA sequences into proteins.",
+  "source": "Tyler Long"
+}

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

@@ -0,0 +1,105 @@
+# 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"
+
+[f6f92714-769f-4187-9524-e353e8a41a80]
+description = "Sequence of two non-STOP codons does not translate to a STOP codon"
+
+[1e75ea2a-f907-4994-ae5c-118632a1cb0f]
+description = "Non-existing codon can't translate"
+include = false
+
+[9eac93f3-627a-4c90-8653-6d0a0595bc6f]
+description = "Unknown amino acids, not part of a codon, can't translate"
+reimplements = "1e75ea2a-f907-4994-ae5c-118632a1cb0f"
+
+[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/dub.sdl

@@ -0,0 +1,2 @@
+name "protein-translation"
+buildRequirements "disallowDeprecations"

exercises/practice/protein-translation/example/protein_translation.d

@@ -0,0 +1,45 @@
+module protein_translation;
+
+import std.algorithm;
+import std.range;
+import std.conv;
+
+immutable string[string] availableProteins = [
+    "AUG": "Methionine",
+    "UUU": "Phenylalanine",
+    "UUC": "Phenylalanine",
+    "UUA": "Leucine",
+    "UUG": "Leucine",
+    "UCU": "Serine",
+    "UCC": "Serine",
+    "UCA": "Serine",
+    "UCG": "Serine",
+    "UAU": "Tyrosine",
+    "UAC": "Tyrosine",
+    "UGU": "Cysteine",
+    "UGC": "Cysteine",
+    "UGG": "Tryptophan",
+    "UAA": "STOP",
+    "UAG": "STOP",
+    "UGA": "STOP"
+];
+
+pure string[] proteins(immutable string strand)
+{
+    string[] codons = strand.chunks(3).map!(chunk => chunk.array.to!string).array;
+    string[] results = [];
+
+    foreach (codon; codons) {
+        if(codon!in availableProteins)
+            throw new Exception("Invalid codon");
+
+        string protein = availableProteins[codon];
+        if (protein == "STOP")
+            return results;
+
+        results ~= protein;
+    };
+
+    return results;
+}
+

exercises/practice/protein-translation/source/protein_translation.d

@@ -0,0 +1,110 @@
+module protein_translation;
+
+pure string[] proteins(immutable string rna)
+{
+    // implement this function
+}
+
+unittest
+{
+    import std.exception : assertThrown;
+
+    immutable int allTestsEnabled = 1;
+
+    // Empty RNA sequence results in no proteins
+    assert(proteins("") == []);
+
+    static if (allTestsEnabled)
+    {
+        // Methionine RNA sequence
+        assert(proteins("AUG") == ["Methionine"]);
+
+        // Phenylalanine RNA sequence 1
+        assert(proteins("UUU") == ["Phenylalanine"]);
+
+        // Phenylalanine RNA sequence 2
+        assert(proteins("UUC") == ["Phenylalanine"]);
+
+        // Leucine RNA sequence 1
+        assert(proteins("UUA") == ["Leucine"]);
+
+        // Leucine RNA sequence 2
+        assert(proteins("UUG") == ["Leucine"]);
+
+        // Serine RNA sequence 1
+        assert(proteins("UCU") == ["Serine"]);
+
+        // Serine RNA sequence 2
+        assert(proteins("UCC") == ["Serine"]);
+
+        // Serine RNA sequence 3
+        assert(proteins("UCA") == ["Serine"]);
+
+        // Serine RNA sequence 4
+        assert(proteins("UCG") == ["Serine"]);
+
+        // Tyrosine RNA sequence 1
+        assert(proteins("UAU") == ["Tyrosine"]);
+
+        // Tyrosine RNA sequence 2
+        assert(proteins("UAC") == ["Tyrosine"]);
+
+        // Cysteine RNA sequence 1
+        assert(proteins("UGU") == ["Cysteine"]);
+
+        // Cysteine RNA sequence 2
+        assert(proteins("UGC") == ["Cysteine"]);
+
+        // Tryptophan RNA sequence
+        assert(proteins("UGG") == ["Tryptophan"]);
+
+        // STOP codon RNA sequence 1
+        assert(proteins("UAA") == []);
+
+        // STOP codon RNA sequence 2
+        assert(proteins("UAG") == []);
+
+        // STOP codon RNA sequence 3
+        assert(proteins("UGA") == []);
+
+        // Sequence of two protein codons translates into proteins
+        assert(proteins("UUUUUU") == ["Phenylalanine", "Phenylalanine"]);
+
+        // Sequence of two different protein codons translates into proteins
+        assert(proteins("UUAUUG") == ["Leucine", "Leucine"]);
+
+        // Translate RNA strand into correct protein list
+        assert(proteins("AUGUUUUGG") == ["Methionine", "Phenylalanine", "Tryptophan"]);
+
+        // Translation stops if STOP codon at beginning of sequence
+        assert(proteins("UAGUGG") == []);
+
+        // Translation stops if STOP codon at end of two-codon sequence
+        assert(proteins("UGGUAG") == ["Tryptophan"]);
+
+        // Translation stops if STOP codon at end of three-codon sequence
+        assert(proteins("AUGUUUUAA") == ["Methionine", "Phenylalanine"]);
+
+        // Translation stops if STOP codon in middle of three-codon sequence
+        assert(proteins("UGGUAGUGG") == ["Tryptophan"]);
+
+        // Translation stops if STOP codon in middle of six-codon sequence
+        assert(proteins("UGGUGUUAUUAAUGGUUU") == ["Tryptophan", "Cysteine", "Tyrosine"]);
+
+        // Sequence of two non-STOP codons does not translate to a STOP codon
+        assert(proteins("AUGAUG") == ["Methionine", "Methionine"]);
+
+        // Non-existing codon can't translate
+        assertThrown(proteins("AAA"));
+
+        // Unknown amino acids, not part of a codon, can't translate
+        assertThrown(proteins("XYZ"));
+
+        // Incomplete RNA sequence can't translate
+        assertThrown(proteins("AUGU"));
+
+        // Incomplete RNA sequence can translate if valid until a STOP codon
+        assert(proteins("UUCUUCUAAUGGU") == ["Phenylalanine", "Phenylalanine"]);
+    }
+}
+