Add practice exercise: protein-translation

config.json

@@ -362,6 +362,14 @@
         "prerequisites": [],
         "difficulty": 8
       },
+      {
+        "slug": "protein-translation",
+        "name": "Protein Translation",
+        "uuid": "afebedda-e757-4811-825e-36be60fb8a4b",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 8
+      },
       {
         "slug": "rest-api",
         "name": "REST API",

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

@@ -0,0 +1,38 @@
+# Instructions
+
+Your job is to translate RNA sequences into proteins.
+
+RNA strands are made up of three-nucleotide sequences called **codons**.
+Each codon translates to an **amino acid**.
+When joined together, those amino acids make a protein.
+
+In the real world, there are 64 codons, which in turn correspond to 20 amino acids.
+However, for this exercise, you’ll only use a few of the possible 64.
+They are listed below:
+
+| Codon              | Amino Acid    |
+| ------------------ | ------------- |
+| 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          |
+
+For example, the RNA string “AUGUUUUCU” has three codons: “AUG”, “UUU” and “UCU”.
+These map to Methionine, Phenylalanine, and Serine.
+
+## “STOP” Codons
+
+You’ll note from the table above that there are three **“STOP” codons**.
+If you encounter any of these codons, ignore the rest of the sequence — the protein is complete.
+
+For example, “AUGUUUUCUUAAAUG” contains a STOP codon (“UAA”).
+Once we reach that point, we stop processing.
+We therefore only consider the part before it (i.e. “AUGUUUUCU”), not any further codons after it (i.e. “AUG”).
+
+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": [
+    "jimmytty"
+  ],
+  "files": {
+    "solution": [
+      "protein-translation.sql"
+    ],
+    "test": [
+      "protein-translation_test.sql"
+    ],
+    "example": [
+      ".meta/example.sql"
+    ]
+  },
+  "blurb": "Translate RNA sequences into proteins.",
+  "source": "Tyler Long"
+}

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

@@ -0,0 +1,70 @@
+DROP TABLE IF EXISTS dict;
+CREATE TEMPORARY TABLE dict (
+  codon      TEXT PRIMARY KEY,
+  amino_acid TEXT NOT NULL
+);
+INSERT INTO dict(codon, amino_acid)
+VALUES ('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'         );
+
+DROP TABLE IF EXISTS results;
+CREATE TEMPORARY TABLE results AS
+SELECT strand,
+       (WITH RECURSIVE translator (string, codon, amino_acid) AS (
+         VALUES (strand, '', '')
+         UNION ALL
+         SELECT SUBSTR(string, 4),
+                SUBSTR(string, 1, 3),
+                (SELECT amino_acid
+                   FROM dict
+                  WHERE dict.codon = SUBSTR(string, 1, 3))
+           FROM translator
+          WHERE string <> ''
+            AND amino_acid <> 'STOP'
+       )
+       SELECT
+         CASE
+         WHEN (SELECT 1
+                 FROM translator
+                WHERE amino_acid ISNULL)
+           THEN 'Invalid codon'
+         WHEN (SELECT COUNT(*) FILTER(WHERE amino_acid <> '') =
+                      COUNT(*) FILTER(WHERE amino_acid = 'STOP')
+                 FROM translator)
+           THEN ''
+         ELSE (SELECT GROUP_CONCAT(amino_acid, ', ')
+                 FROM translator
+                WHERE amino_acid NOT IN ('', 'STOP'))
+         END
+       ) result_or_error
+  FROM "protein-translation"
+;
+
+UPDATE "protein-translation" AS pt
+   SET error = result_or_error
+  FROM results re
+ WHERE pt.strand = re.strand
+   AND result_or_error = 'Invalid codon'
+;
+
+UPDATE "protein-translation" AS pt
+   SET result = result_or_error
+  FROM results re
+ WHERE pt.strand = re.strand
+   AND result_or_error <> 'Invalid codon'
+;

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/create_fixture.sql

@@ -0,0 +1,11 @@
+DROP TABLE IF EXISTS "protein-translation";
+CREATE TABLE "protein-translation" (
+  strand TEXT NOT NULL,
+  result TEXT         ,
+  error  TEXT
+);
+
+.mode csv
+.import ./data.csv "protein-translation"
+
+UPDATE "protein-translation" SET result = NULL, error = NULL;

exercises/practice/protein-translation/create_test_table.sql

@@ -0,0 +1,49 @@
+DROP TABLE IF EXISTS tests;
+CREATE TABLE IF NOT EXISTS tests (
+  -- uuid and description are taken from the test.toml file
+  uuid            TEXT PRIMARY KEY    ,
+  description     TEXT NOT NULL       ,
+  -- The following section is needed by the online test-runner
+  status          TEXT DEFAULT 'fail' ,
+  message         TEXT                ,
+  output          TEXT                ,
+  test_code       TEXT                ,
+  task_id         INTEGER DEFAULT NULL,
+  -- Here are columns for the actual tests
+  strand          TEXT NOT NULL       ,
+  expected_result TEXT                ,
+  expected_error  TEXT
+);
+
+INSERT INTO tests (uuid, description, strand, expected_result, expected_error)
+VALUES
+  ('2c44f7bf-ba20-43f7-a3bf-f2219c0c3f98', 'Empty RNA sequence results in no proteins', '', '', NULL),
+  ('96d3d44f-34a2-4db4-84cd-fff523e069be', 'Methionine RNA sequence', 'AUG', 'Methionine', NULL),
+  ('1b4c56d8-d69f-44eb-be0e-7b17546143d9', 'Phenylalanine RNA sequence 1', 'UUU', 'Phenylalanine', NULL),
+  ('81b53646-bd57-4732-b2cb-6b1880e36d11', 'Phenylalanine RNA sequence 2', 'UUC', 'Phenylalanine', NULL),
+  ('42f69d4f-19d2-4d2c-a8b0-f0ae9ee1b6b4', 'Leucine RNA sequence 1', 'UUA', 'Leucine', NULL),
+  ('ac5edadd-08ed-40a3-b2b9-d82bb50424c4', 'Leucine RNA sequence 2', 'UUG', 'Leucine', NULL),
+  ('8bc36e22-f984-44c3-9f6b-ee5d4e73f120', 'Serine RNA sequence 1', 'UCU', 'Serine', NULL),
+  ('5c3fa5da-4268-44e5-9f4b-f016ccf90131', 'Serine RNA sequence 2', 'UCC', 'Serine', NULL),
+  ('00579891-b594-42b4-96dc-7ff8bf519606', 'Serine RNA sequence 3', 'UCA', 'Serine', NULL),
+  ('08c61c3b-fa34-4950-8c4a-133945570ef6', 'Serine RNA sequence 4', 'UCG', 'Serine', NULL),
+  ('54e1e7d8-63c0-456d-91d2-062c72f8eef5', 'Tyrosine RNA sequence 1', 'UAU', 'Tyrosine', NULL),
+  ('47bcfba2-9d72-46ad-bbce-22f7666b7eb1', 'Tyrosine RNA sequence 2', 'UAC', 'Tyrosine', NULL),
+  ('3a691829-fe72-43a7-8c8e-1bd083163f72', 'Cysteine RNA sequence 1', 'UGU', 'Cysteine', NULL),
+  ('1b6f8a26-ca2f-43b8-8262-3ee446021767', 'Cysteine RNA sequence 2', 'UGC', 'Cysteine', NULL),
+  ('1e91c1eb-02c0-48a0-9e35-168ad0cb5f39', 'Tryptophan RNA sequence', 'UGG', 'Tryptophan', NULL),
+  ('e547af0b-aeab-49c7-9f13-801773a73557', 'STOP codon RNA sequence 1', 'UAA', '', NULL),
+  ('67640947-ff02-4f23-a2ef-816f8a2ba72e', 'STOP codon RNA sequence 2', 'UAG', '', NULL),
+  ('9c2ad527-ebc9-4ace-808b-2b6447cb54cb', 'STOP codon RNA sequence 3', 'UGA', '', NULL),
+  ('f4d9d8ee-00a8-47bf-a1e3-1641d4428e54', 'Sequence of two protein codons translates into proteins', 'UUUUUU', 'Phenylalanine, Phenylalanine', NULL),
+  ('dd22eef3-b4f1-4ad6-bb0b-27093c090a9d', 'Sequence of two different protein codons translates into proteins', 'UUAUUG', 'Leucine, Leucine', NULL),
+  ('d0f295df-fb70-425c-946c-ec2ec185388e', 'Translate RNA strand into correct protein list', 'AUGUUUUGG', 'Methionine, Phenylalanine, Tryptophan', NULL),
+  ('e30e8505-97ec-4e5f-a73e-5726a1faa1f4', 'Translation stops if STOP codon at beginning of sequence', 'UAGUGG', '', NULL),
+  ('5358a20b-6f4c-4893-bce4-f929001710f3', 'Translation stops if STOP codon at end of two-codon sequence', 'UGGUAG', 'Tryptophan', NULL),
+  ('ba16703a-1a55-482f-bb07-b21eef5093a3', 'Translation stops if STOP codon at end of three-codon sequence', 'AUGUUUUAA', 'Methionine, Phenylalanine', NULL),
+  ('4089bb5a-d5b4-4e71-b79e-b8d1f14a2911', 'Translation stops if STOP codon in middle of three-codon sequence', 'UGGUAGUGG', 'Tryptophan', NULL),
+  ('2c2a2a60-401f-4a80-b977-e0715b23b93d', 'Translation stops if STOP codon in middle of six-codon sequence', 'UGGUGUUAUUAAUGGUUU', 'Tryptophan, Cysteine, Tyrosine', NULL),
+  ('f6f92714-769f-4187-9524-e353e8a41a80', 'Sequence of two non-STOP codons does not translate to a STOP codon', 'AUGAUG', 'Methionine, Methionine', NULL),
+  ('9eac93f3-627a-4c90-8653-6d0a0595bc6f', 'Unknown amino acids, not part of a codon, can''t translate', 'XYZ', NULL, 'Invalid codon'),
+  ('9d73899f-e68e-4291-b1e2-7bf87c00f024', 'Incomplete RNA sequence can''t translate', 'AUGU', NULL, 'Invalid codon'),
+  ('43945cf7-9968-402d-ab9f-b8a28750b050', 'Incomplete RNA sequence can translate if valid until a STOP codon', 'UUCUUCUAAUGGU', 'Phenylalanine, Phenylalanine', NULL);

exercises/practice/protein-translation/data.csv

@@ -0,0 +1,30 @@
+"",,
+"AUG",,
+"UUU",,
+"UUC",,
+"UUA",,
+"UUG",,
+"UCU",,
+"UCC",,
+"UCA",,
+"UCG",,
+"UAU",,
+"UAC",,
+"UGU",,
+"UGC",,
+"UGG",,
+"UAA",,
+"UAG",,
+"UGA",,
+"UUUUUU",,
+"UUAUUG",,
+"AUGUUUUGG",,
+"UAGUGG",,
+"UGGUAG",,
+"AUGUUUUAA",,
+"UGGUAGUGG",,
+"UGGUGUUAUUAAUGGUUU",,
+"AUGAUG",,
+"XYZ",,
+"AUGU",,
+"UUCUUCUAAUGGU",,

exercises/practice/protein-translation/protein-translation.sql

@@ -0,0 +1,8 @@
+-- Schema:
+-- CREATE TABLE "protein-translation" (
+--   strand TEXT NOT NULL,
+--   result TEXT         ,
+--   error  TEXT
+-- );
+--
+-- Task: update the protein-translation and set the result or the error columns based on strand.