From 94a84673242d96ed71be6d11b5d4a6883d92e332 Mon Sep 17 00:00:00 2001 From: Eric Willigers Date: Sat, 11 May 2024 12:04:36 +1000 Subject: [PATCH] Add protein-translation exercise (#378) --- config.json | 11 ++ .../protein-translation/.docs/instructions.md | 45 +++++ .../protein-translation/.meta/config.json | 18 ++ .../protein-translation/.meta/example.el | 44 +++++ .../protein-translation/.meta/tests.toml | 102 ++++++++++++ .../protein-translation-test.el | 156 ++++++++++++++++++ .../protein-translation.el | 14 ++ 7 files changed, 390 insertions(+) create mode 100644 exercises/practice/protein-translation/.docs/instructions.md create mode 100644 exercises/practice/protein-translation/.meta/config.json create mode 100644 exercises/practice/protein-translation/.meta/example.el create mode 100644 exercises/practice/protein-translation/.meta/tests.toml create mode 100644 exercises/practice/protein-translation/protein-translation-test.el create mode 100644 exercises/practice/protein-translation/protein-translation.el diff --git a/config.json b/config.json index 86913445..a580df95 100644 --- a/config.json +++ b/config.json @@ -465,6 +465,17 @@ "math" ] }, + { + "slug": "protein-translation", + "name": "Protein Translation", + "uuid": "3201c23c-e2eb-4e1a-8a44-b56acac572f5", + "practices": [], + "prerequisites": [], + "difficulty": 3, + "topics": [ + "strings" + ] + }, { "slug": "series", "name": "Series", diff --git a/exercises/practice/protein-translation/.docs/instructions.md b/exercises/practice/protein-translation/.docs/instructions.md new file mode 100644 index 00000000..7dc34d2e --- /dev/null +++ b/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) diff --git a/exercises/practice/protein-translation/.meta/config.json b/exercises/practice/protein-translation/.meta/config.json new file mode 100644 index 00000000..bef5c3b6 --- /dev/null +++ b/exercises/practice/protein-translation/.meta/config.json @@ -0,0 +1,18 @@ +{ + "authors": [ + "keiravillekode" + ], + "files": { + "solution": [ + "protein-translation.el" + ], + "test": [ + "protein-translation-test.el" + ], + "example": [ + ".meta/example.el" + ] + }, + "blurb": "Translate RNA sequences into proteins.", + "source": "Tyler Long" +} diff --git a/exercises/practice/protein-translation/.meta/example.el b/exercises/practice/protein-translation/.meta/example.el new file mode 100644 index 00000000..255b7aff --- /dev/null +++ b/exercises/practice/protein-translation/.meta/example.el @@ -0,0 +1,44 @@ +;;; protein-translation.el --- Protein Translation (exercism) -*- lexical-binding: t; -*- + +;;; Commentary: + +;;; Code: + +(require 'cl-lib) + +(defun translate (codon) + (pcase codon + ("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" nil) + ("UAG" nil) + ("UGA" nil) + (otherwise (error "Invalid codon")))) + +(defun proteins (strand) + (let* ((len (length strand)) + (stop (- len (% len 3)))) + (cl-labels + ((recur (index) + (if (= index stop) + (unless (= index len) (error "Invalid codon")) + (let* ((next (+ index 3)) + (protein (translate (substring strand index next)))) + (when protein (cons protein (recur next))))))) + (recur 0)))) + +(provide 'protein-translation) +;;; protein-translation.el ends here + diff --git a/exercises/practice/protein-translation/.meta/tests.toml b/exercises/practice/protein-translation/.meta/tests.toml new file mode 100644 index 00000000..804b446e --- /dev/null +++ b/exercises/practice/protein-translation/.meta/tests.toml @@ -0,0 +1,102 @@ +# 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" +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" diff --git a/exercises/practice/protein-translation/protein-translation-test.el b/exercises/practice/protein-translation/protein-translation-test.el new file mode 100644 index 00000000..60575dbb --- /dev/null +++ b/exercises/practice/protein-translation/protein-translation-test.el @@ -0,0 +1,156 @@ +;;; protein-translation-test.el --- Tests for Protein Translation (exercism) -*- lexical-binding: t; -*- + +;;; Commentary: + +;;; Code: + + +(load-file "protein-translation.el") +(declare-function proteins "protein-translation.el" (strand)) + + +(ert-deftest empty-rna-sequence-results-in-no-proteins () + (should (equal '() + (proteins "")))) + + +(ert-deftest methionine-rna-sequence () + (should (equal '("Methionine") + (proteins "AUG")))) + + +(ert-deftest phenylalanine-rna-sequence-1 () + (should (equal '("Phenylalanine") + (proteins "UUU")))) + + +(ert-deftest phenylalanine-rna-sequence-2 () + (should (equal '("Phenylalanine") + (proteins "UUC")))) + + +(ert-deftest leucine-rna-sequence-1 () + (should (equal '("Leucine") + (proteins "UUA")))) + + +(ert-deftest leucine-rna-sequence-2 () + (should (equal '("Leucine") + (proteins "UUG")))) + + +(ert-deftest serine-rna-sequence-1 () + (should (equal '("Serine") + (proteins "UCU")))) + + +(ert-deftest serine-rna-sequence-2 () + (should (equal '("Serine") + (proteins "UCC")))) + + +(ert-deftest serine-rna-sequence-3 () + (should (equal '("Serine") + (proteins "UCA")))) + + +(ert-deftest serine-rna-sequence-4 () + (should (equal '("Serine") + (proteins "UCG")))) + + +(ert-deftest tyrosine-rna-sequence-1 () + (should (equal '("Tyrosine") + (proteins "UAU")))) + + +(ert-deftest tyrosine-rna-sequence-2 () + (should (equal '("Tyrosine") + (proteins "UAC")))) + + +(ert-deftest cysteine-rna-sequence-1 () + (should (equal '("Cysteine") + (proteins "UGU")))) + + +(ert-deftest cysteine-rna-sequence-2 () + (should (equal '("Cysteine") + (proteins "UGC")))) + + +(ert-deftest tryptophan-rna-sequence () + (should (equal '("Tryptophan") + (proteins "UGG")))) + + +(ert-deftest stop-codon-rna-sequence-1 () + (should (equal '() + (proteins "UAA")))) + + +(ert-deftest stop-codon-rna-sequence-2 () + (should (equal '() + (proteins "UAG")))) + + +(ert-deftest stop-codon-rna-sequence-3 () + (should (equal '() + (proteins "UGA")))) + + +(ert-deftest sequence-of-two-protein-codons-translates-into-proteins () + (should (equal '("Phenylalanine" "Phenylalanine") + (proteins "UUUUUU")))) + + +(ert-deftest sequence-of-two-different-protein-codons-translates-into-proteins () + (should (equal '("Leucine" "Leucine") + (proteins "UUAUUG")))) + + +(ert-deftest translate-rna-strand-into-correct-protein-list () + (should (equal '("Methionine" "Phenylalanine" "Tryptophan") + (proteins "AUGUUUUGG")))) + + +(ert-deftest translation-stops-if-stop-codon-at-beginning-of-sequence () + (should (equal '() + (proteins "UAGUGG")))) + + +(ert-deftest translation-stops-if-stop-codon-at-end-of-two-codon-sequence () + (should (equal '("Tryptophan") + (proteins "UGGUAG")))) + + +(ert-deftest translation-stops-if-stop-codon-at-end-of-three-codon-sequence () + (should (equal '("Methionine" "Phenylalanine") + (proteins "AUGUUUUAA")))) + + +(ert-deftest translation-stops-if-stop-codon-in-middle-of-three-codon-sequence () + (should (equal '("Tryptophan") + (proteins "UGGUAGUGG")))) + + +(ert-deftest translation-stops-if-stop-codon-in-middle-of-six-codon-sequence () + (should (equal '("Tryptophan" "Cysteine" "Tyrosine") + (proteins "UGGUGUUAUUAAUGGUUU")))) + + +(ert-deftest unknown-amino-acids-not-part-of-a-codon-cant-translate () + (should-error (proteins "XYZ"))) + + +(ert-deftest incomplete-rna-sequence-cant-translate () + (should-error (proteins "AUGU"))) + + +(ert-deftest incomplete-rna-sequence-can-translate-if-valid-until-a-stop-codon () + (should (equal '("Phenylalanine" "Phenylalanine") + (proteins "UUCUUCUAAUGGU")))) + + +(provide 'protein-translation-test) +;;; protein-translation-test.el ends here diff --git a/exercises/practice/protein-translation/protein-translation.el b/exercises/practice/protein-translation/protein-translation.el new file mode 100644 index 00000000..1d5f5366 --- /dev/null +++ b/exercises/practice/protein-translation/protein-translation.el @@ -0,0 +1,14 @@ +;;; protein-translation.el --- Protein Translation (exercism) -*- lexical-binding: t; -*- + +;;; Commentary: + +;;; Code: + + +(defun proteins (strand) + (error "Delete this S-Expression and write your own implementation")) + + +(provide 'protein-translation) +;;; protein-translation.el ends here +