Add protein-translation exercise

concepts/dictionaries/.meta/config.json

@@ -0,0 +1,7 @@
+{
+    "blurb": "<todo>",
+    "authors": [
+        "misicnenad"
+    ],
+    "contributors": []
+}

concepts/dictionaries/about.md

@@ -0,0 +1 @@
+# Dictionaries

concepts/dictionaries/introduction.md

@@ -0,0 +1 @@
+# Introduction

concepts/dictionaries/links.json

@@ -0,0 +1 @@
+[]

config.json

@@ -226,9 +226,26 @@
         "slug": "sublist",
         "name": "Sublist",
         "uuid": "e62b1bb4-fb37-4dfe-ad81-e0fa5c494ba3",
-        "practices": ["arrays", "enums", "generics"],
+        "practices": [
+          "arrays",
+          "enums",
+          "generics"
+        ],
         "prerequisites": [],
         "difficulty": 3
+      },
+      {
+        "slug": "protein-translation",
+        "name": "Protein Translation",
+        "uuid": "d42e7a29-64b9-478b-8b2a-44fd002391fa",
+        "practices": [
+          "dictionaries",
+          "strings",
+          "felts",
+          "type-conversion"
+        ],
+        "prerequisites": [],
+        "difficulty": 8
       }
     ],
     "foregone": [
@@ -257,6 +274,11 @@
       "slug": "generics",
       "name": "Generic Types"
     },
+    {
+      "uuid": "7e7b772a-2b3e-47d7-96ef-807a4d5b3545",
+      "slug": "dictionaries",
+      "name": "Dictionaries"
+    },
     {
       "uuid": "de254443-42ee-4787-bc1e-3d0d2039c4f5",
       "slug": "booleans",

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 +1,19 @@
+{
+  "authors": [
+    "misicnenad"
+  ],
+  "files": {
+    "solution": [
+      "src/lib.cairo",
+      "Scarb.toml"
+    ],
+    "test": [
+      "src/tests.cairo"
+    ],
+    "example": [
+      ".meta/example.cairo"
+    ]
+  },
+  "blurb": "Translate RNA sequences into proteins.",
+  "source": "Tyler Long"
+}

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

@@ -0,0 +1,109 @@
+use core::dict::Felt252DictEntryTrait;
+use core::num::traits::zero::Zero;
+
+#[derive(Destruct)]
+struct CodonsInfo {
+    actual_codons: Felt252Dict<Nullable<ByteArray>>,
+}
+
+enum TranslateResult {
+    Invalid,
+    Stopped,
+    Ok
+}
+
+fn parse(pairs: Array<(felt252, ByteArray)>) -> CodonsInfo {
+    let mut pairs = pairs;
+    let mut actual_codons: Felt252Dict<Nullable<ByteArray>> = Default::default();
+    while let Option::Some((codon, name)) = pairs
+        .pop_front() {
+            actual_codons.insert(codon, NullableTrait::new(name));
+        };
+    CodonsInfo { actual_codons, }
+}
+
+#[generate_trait]
+impl CodonsInfoImpl of CodonsInfoTrait {
+    fn name_for(ref self: CodonsInfo, codon: felt252) -> ByteArray {
+        let (entry, _name) = self.actual_codons.entry(codon);
+        let name = _name.deref_or("");
+        let res = name.clone();
+        self.actual_codons = entry.finalize(NullableTrait::new(name));
+        res
+    }
+
+    fn of_rna(ref self: CodonsInfo, strand: ByteArray) -> Option<Array<ByteArray>> {
+        let mut result: Array<ByteArray> = array![];
+
+        let mut codon_index = 0;
+        let translate_result = loop {
+            if codon_index == strand.len() {
+                break TranslateResult::Ok;
+            }
+
+            if let Option::Some(codon) = strand.codon_chunk(codon_index) {
+                let name = self.name_for(codon);
+                if name == "" {
+                    break TranslateResult::Invalid;
+                } else if name == "stop codon" {
+                    break TranslateResult::Stopped;
+                }
+
+                result.append(name);
+                codon_index += 3;
+            } else {
+                break TranslateResult::Invalid;
+            }
+        };
+
+        match translate_result {
+            TranslateResult::Invalid => Option::None,
+            _ => Option::Some(result)
+        }
+    }
+}
+
+const TWO_POW_8: u32 = 0x100;
+const TWO_POW_16: u32 = 0x10000;
+
+#[generate_trait]
+impl CodonChunk of CodonChunkTrait {
+    /// Given a ByteArray, extracts a codon from a given index `from`.
+    /// Needs to extract 3 ByteArray characters and convert them to the appropriate
+    /// felt252 value. It does this by taking the characters' byte value and moving
+    /// their bits to the left depending on their position in the codon.
+    /// 
+    /// Example:
+    /// 1. Method call: "AUG".codon_chunk(0)
+    /// 2. Chars and their byte (hex) values:
+    ///    - "A" = 0x41
+    ///    - "U" = 0x55
+    ///    - "G" = 0x47 
+    /// 3. "A" is the leftmost character, so we "move" it 2 bytes to the left by
+    ///    multiplying it by 2^16 (hex value: 0x10000)
+    /// 4. "U" is the middle character, so we "move" it 1 byte to the left by
+    ///    multiplying it by 2^8 (hex value: 0x100)
+    /// 5. "G" is the rightmost character, so we leave it in place
+    /// 6. Codon = "A" * 2^16 + "U" * 2^8 + "G"
+    ///          = 0x41 * 0x10000 + 0x55 * 0x100 * 0x47
+    ///          = 0x415547
+    /// 7. (41)(55)(47) are hex values for (A)(U)(G)
+    /// 
+    /// Returns:
+    /// - Option::Some(codon) -> if the extraction was successful
+    /// - Option::None -> if the ByteArray was too short from the given index
+    fn codon_chunk(self: @ByteArray, from: usize) -> Option<felt252> {
+        if let Option::Some(char) = self.at(from + 2) {
+            let codon = char.into()
+                + self[from
+                + 1].into() * TWO_POW_8
+                + self[from].into() * TWO_POW_16;
+            Option::Some(codon.into())
+        } else {
+            Option::None
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests;

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/Scarb.toml

@@ -0,0 +1,4 @@
+[package]
+name = "protein_translation"
+version = "0.1.0"
+edition = "2023_11"