Add protein translation exercise (#192)

config.json

@@ -343,6 +343,14 @@
         "practices": [],
         "prerequisites": [],
         "difficulty": 2
+      },
+      {
+        "slug": "protein-translation",
+        "name": "Protein Translation",
+        "uuid": "b61ac6a8-b40d-48ea-8a72-89608506c256",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 1
       }
     ]
   },

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": [
+    "kahgoh"
+  ],
+  "files": {
+    "solution": [
+      "src/protein-translation.lfe"
+    ],
+    "test": [
+      "test/protein-translation-tests.lfe"
+    ],
+    "example": [
+      ".meta/example.lfe"
+    ]
+  },
+  "blurb": "Translate RNA sequences into proteins.",
+  "source": "Tyler Long"
+}

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

@@ -0,0 +1,41 @@
+(defmodule protein-translation
+  (export (proteins 1)))
+
+(defun proteins 
+  ((strand) (when (!= (rem (length strand) 3) 0)) (tuple 'error "Invalid codon") )
+  ((strand) (translate strand '()))
+)
+
+(defun translate
+  (("" acc) (tuple 'ok acc))
+  ((strand acc) 
+    (case (codon (string:slice strand 0 3))
+      ((tuple 'ok codon) (translate (string:slice strand 3 (length strand)) (++ acc (list codon))))
+      ((tuple 'stop) (tuple 'ok acc))
+      (t t)
+    )
+  )
+)
+
+(defun codon (seq)
+  (case seq
+    ("AUG" (tuple 'ok 'Methionine))
+    ("UUU" (tuple 'ok 'Phenylalanine))
+    ("UUC" (tuple 'ok 'Phenylalanine))
+    ("UUA" (tuple 'ok 'Leucine))
+    ("UUG" (tuple 'ok 'Leucine))
+    ("UCU" (tuple 'ok 'Serine))
+    ("UCC" (tuple 'ok 'Serine))
+    ("UCA" (tuple 'ok 'Serine))
+    ("UCG" (tuple 'ok 'Serine))
+    ("UAU" (tuple 'ok 'Tyrosine))
+    ("UAC" (tuple 'ok 'Tyrosine))
+    ("UGU" (tuple 'ok 'Cysteine))
+    ("UGC" (tuple 'ok 'Cysteine))
+    ("UGG" (tuple 'ok 'Tryptophan))
+    ("UAA" (tuple 'stop))
+    ("UAG" (tuple 'stop))
+    ("UGA" (tuple 'stop))
+    (t (tuple 'error "Invalid codon"))
+  )
+)

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/Makefile

@@ -0,0 +1,21 @@
+ERL    := $(shell which erl)
+REBAR3 := $(shell which rebar3)
+
+null  :=
+space := $(null) #
+comma := ,
+
+ifeq ($(ERL),)
+  $(error Can't find Erlang executable 'erl')
+else ifeq ($(REBAR3),)
+  $(error Can't find rebar3)
+endif
+
+compile: ; $(REBAR3) compile
+
+clean: ; $(REBAR3) clean
+
+.PHONY: test
+test:
+	$(REBAR3) eunit \
+	-m $(subst $(space),$(comma),$(basename $(notdir $(wildcard test/*.lfe))))

exercises/practice/protein-translation/rebar.config

@@ -0,0 +1,11 @@
+{plugins, [{rebar3_lfe, "0.4.3"}]}.
+
+{provider_hooks, [{post, [{compile, {lfe, compile}}]}]}.
+
+{deps, [{lfe, "2.1.1"}]}.
+
+{profiles,
+ [{test,
+   [{eunit_compile_opts, [{src_dirs, ["src", "test"]}]},
+    {deps,
+     [{ltest, "0.13.3"}]}]}]}.

exercises/practice/protein-translation/rebar.lock

@@ -0,0 +1,8 @@
+{"1.2.0",
+[{<<"lfe">>,{pkg,<<"lfe">>,<<"2.1.1">>},0}]}.
+[
+{pkg_hash,[
+ {<<"lfe">>, <<"4A888B26172D198DC7A5AFEB897E8248AF7D56E1638D9C8249AAF933AE811B96">>}]},
+{pkg_hash_ext,[
+ {<<"lfe">>, <<"C484D3B655D40DED58BC41B17B22F173711C681BF36063A234A9BAA9506947E1">>}]}
+].

exercises/practice/protein-translation/src/protein-translation.app.src

@@ -0,0 +1,11 @@
+%% -*- erlang -*-
+{application, 'protein-translation',
+ [{description, "Translate RNA sequences into proteins."},
+  {vsn, "0.0.1"},
+  {modules,
+   ['raindrops']},
+  {registered, []},
+  {applications,
+   [kernel, stdlib]},
+  {included_applications, []},
+  {env, []}]}.

exercises/practice/protein-translation/src/protein-translation.lfe

@@ -0,0 +1,4 @@
+(defmodule protein-translation
+  (export (proteins 1)))
+
+; Please implement the 'proteins' function

exercises/practice/protein-translation/test/protein-translation-tests.lfe

@@ -0,0 +1,89 @@
+(defmodule protein-translation-tests
+  (behaviour ltest-unit)
+  (export all))
+
+(include-lib "ltest/include/ltest-macros.lfe")
+
+(deftest empty-rna-sequence-no-protein 
+  (is-equal (tuple 'ok '()) (protein-translation:proteins "")))
+
+(deftest methione-rna-sequence
+  (is-equal (tuple 'ok (list 'Methionine)) (protein-translation:proteins "AUG")))
+
+(deftest phenylalanine-rna-sequence-1
+  (is-equal (tuple 'ok (list 'Phenylalanine)) (protein-translation:proteins "UUU")))
+
+(deftest phenylalanine-rna-sequence-2
+  (is-equal (tuple 'ok (list 'Phenylalanine)) (protein-translation:proteins "UUC")))
+
+(deftest leucine-rna-sequence-1
+  (is-equal (tuple 'ok (list 'Leucine)) (protein-translation:proteins "UUA")))
+
+(deftest serine-rna-sequence-1
+  (is-equal (tuple 'ok (list 'Serine)) (protein-translation:proteins "UCU")))
+
+(deftest serine-rna-sequence-2
+  (is-equal (tuple 'ok (list 'Serine)) (protein-translation:proteins "UCC")))
+
+(deftest serine-rna-sequence-3
+  (is-equal (tuple 'ok (list 'Serine)) (protein-translation:proteins "UCA")))
+
+(deftest serine-rna-sequence-4
+  (is-equal (tuple 'ok (list 'Serine)) (protein-translation:proteins "UCG")))
+
+(deftest tyrosine-rna-sequence-1
+  (is-equal (tuple 'ok (list 'Tyrosine)) (protein-translation:proteins "UAU")))
+
+(deftest tyrosine-rna-sequence-2
+  (is-equal (tuple 'ok (list 'Tyrosine)) (protein-translation:proteins "UAC")))
+
+(deftest cysteine-rna-sequence-1
+  (is-equal (tuple 'ok (list 'Cysteine)) (protein-translation:proteins "UGU")))
+
+(deftest cysteine-rna-sequence-2
+  (is-equal (tuple 'ok (list 'Cysteine)) (protein-translation:proteins "UGC")))
+
+(deftest tryptophan-rna-sequence
+  (is-equal (tuple 'ok (list 'Tryptophan)) (protein-translation:proteins "UGG")))
+
+(deftest stop-codon-rna-sequence-1
+  (is-equal (tuple 'ok '()) (protein-translation:proteins "UAA")))
+
+(deftest stop-codon-rna-sequence-2
+  (is-equal (tuple 'ok '()) (protein-translation:proteins "UAG")))
+
+(deftest stop-codon-rna-sequence-3
+  (is-equal (tuple 'ok '()) (protein-translation:proteins "UGA")))
+
+(deftest sequence-of-two-proteins-codons-translates-into-proteins
+  (is-equal (tuple 'ok (list 'Phenylalanine 'Phenylalanine)) (protein-translation:proteins "UUUUUU")))
+
+(deftest sequence-of-two-different-protein-codons-translates-into-proteins
+  (is-equal (tuple 'ok (list 'Leucine 'Leucine)) (protein-translation:proteins "UUAUUG")))
+
+(deftest translate-rna-strand-into-correct-protein-list
+  (is-equal (tuple 'ok (list 'Methionine 'Phenylalanine 'Tryptophan)) (protein-translation:proteins "AUGUUUUGG")))
+
+(deftest translation-stops-if-stop-codon-at-beginning-of-sequence
+  (is-equal (tuple 'ok '()) (protein-translation:proteins "UAGUGG")))
+
+(deftest translation-stops-if-stop-codon-at-end-of-two-codon-sequence
+  (is-equal (tuple 'ok (list 'Tryptophan)) (protein-translation:proteins "UGGUAG")))
+
+(deftest translation-stops-if-stop-codon-at-end-of-three-codon-sequence
+  (is-equal (tuple 'ok (list 'Methionine 'Phenylalanine)) (protein-translation:proteins "AUGUUUUAA")))
+
+(deftest translation-stops-if-stop-codon-in-middle-of-three-codon-sequence
+  (is-equal (tuple 'ok (list 'Tryptophan)) (protein-translation:proteins "UGGUAGUGG")))
+
+(deftest translation-stops-if-stop-codon-in-middle-of-six-codon-sequence
+  (is-equal (tuple 'ok (list 'Tryptophan 'Cysteine 'Tyrosine)) (protein-translation:proteins "UGGUGUUAUUAAUGGUUU")))
+
+(deftest non-existing-condon-cant-translate
+  (is-equal (tuple 'error "Invalid codon") (protein-translation:proteins "AAA")))
+
+(deftest unknown-amino-acides-not-part-of-a-codon-cant-translate
+  (is-equal (tuple 'error "Invalid codon") (protein-translation:proteins "XYZ")))
+
+(deftest incomplete-rna-sequence-cant-translate
+  (is-equal (tuple 'error "Invalid codon") (protein-translation:proteins "AUGU")))