Skip to content

Commit 4938204

Browse files
authored
Add protein-translation (#270)
1 parent 0d55ecc commit 4938204

File tree

7 files changed

+333
-0
lines changed

7 files changed

+333
-0
lines changed

config.json

+8
Original file line numberDiff line numberDiff line change
@@ -344,6 +344,14 @@
344344
"prerequisites": [],
345345
"difficulty": 2
346346
},
347+
{
348+
"slug": "protein-translation",
349+
"name": "Protein Translation",
350+
"uuid": "7ba9bb49-551d-47a9-9662-f66560d9d0c4",
351+
"practices": [],
352+
"prerequisites": [],
353+
"difficulty": 2
354+
},
347355
{
348356
"slug": "resistor-color",
349357
"name": "Resistor Color",
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
# Instructions
2+
3+
Translate RNA sequences into proteins.
4+
5+
RNA can be broken into three nucleotide sequences called codons, and then translated to a polypeptide like so:
6+
7+
RNA: `"AUGUUUUCU"` => translates to
8+
9+
Codons: `"AUG", "UUU", "UCU"`
10+
=> which become a polypeptide with the following sequence =>
11+
12+
Protein: `"Methionine", "Phenylalanine", "Serine"`
13+
14+
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.
15+
If it works for one codon, the program should work for all of them.
16+
However, feel free to expand the list in the test suite to include them all.
17+
18+
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.
19+
20+
All subsequent codons after are ignored, like this:
21+
22+
RNA: `"AUGUUUUCUUAAAUG"` =>
23+
24+
Codons: `"AUG", "UUU", "UCU", "UAA", "AUG"` =>
25+
26+
Protein: `"Methionine", "Phenylalanine", "Serine"`
27+
28+
Note the stop codon `"UAA"` terminates the translation and the final methionine is not translated into the protein sequence.
29+
30+
Below are the codons and resulting Amino Acids needed for the exercise.
31+
32+
| Codon | Protein |
33+
| :----------------- | :------------ |
34+
| AUG | Methionine |
35+
| UUU, UUC | Phenylalanine |
36+
| UUA, UUG | Leucine |
37+
| UCU, UCC, UCA, UCG | Serine |
38+
| UAU, UAC | Tyrosine |
39+
| UGU, UGC | Cysteine |
40+
| UGG | Tryptophan |
41+
| UAA, UAG, UGA | STOP |
42+
43+
Learn more about [protein translation on Wikipedia][protein-translation].
44+
45+
[protein-translation]: https://en.wikipedia.org/wiki/Translation_(biology)
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
{
2+
"authors": [
3+
"BNAndras"
4+
],
5+
"files": {
6+
"solution": [
7+
"source/protein_translation.d"
8+
],
9+
"test": [
10+
"source/protein_translation.d"
11+
],
12+
"example": [
13+
"example/protein_translation.d"
14+
]
15+
},
16+
"blurb": "Translate RNA sequences into proteins.",
17+
"source": "Tyler Long"
18+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,105 @@
1+
# This is an auto-generated file.
2+
#
3+
# Regenerating this file via `configlet sync` will:
4+
# - Recreate every `description` key/value pair
5+
# - Recreate every `reimplements` key/value pair, where they exist in problem-specifications
6+
# - Remove any `include = true` key/value pair (an omitted `include` key implies inclusion)
7+
# - Preserve any other key/value pair
8+
#
9+
# As user-added comments (using the # character) will be removed when this file
10+
# is regenerated, comments can be added via a `comment` key.
11+
12+
[2c44f7bf-ba20-43f7-a3bf-f2219c0c3f98]
13+
description = "Empty RNA sequence results in no proteins"
14+
15+
[96d3d44f-34a2-4db4-84cd-fff523e069be]
16+
description = "Methionine RNA sequence"
17+
18+
[1b4c56d8-d69f-44eb-be0e-7b17546143d9]
19+
description = "Phenylalanine RNA sequence 1"
20+
21+
[81b53646-bd57-4732-b2cb-6b1880e36d11]
22+
description = "Phenylalanine RNA sequence 2"
23+
24+
[42f69d4f-19d2-4d2c-a8b0-f0ae9ee1b6b4]
25+
description = "Leucine RNA sequence 1"
26+
27+
[ac5edadd-08ed-40a3-b2b9-d82bb50424c4]
28+
description = "Leucine RNA sequence 2"
29+
30+
[8bc36e22-f984-44c3-9f6b-ee5d4e73f120]
31+
description = "Serine RNA sequence 1"
32+
33+
[5c3fa5da-4268-44e5-9f4b-f016ccf90131]
34+
description = "Serine RNA sequence 2"
35+
36+
[00579891-b594-42b4-96dc-7ff8bf519606]
37+
description = "Serine RNA sequence 3"
38+
39+
[08c61c3b-fa34-4950-8c4a-133945570ef6]
40+
description = "Serine RNA sequence 4"
41+
42+
[54e1e7d8-63c0-456d-91d2-062c72f8eef5]
43+
description = "Tyrosine RNA sequence 1"
44+
45+
[47bcfba2-9d72-46ad-bbce-22f7666b7eb1]
46+
description = "Tyrosine RNA sequence 2"
47+
48+
[3a691829-fe72-43a7-8c8e-1bd083163f72]
49+
description = "Cysteine RNA sequence 1"
50+
51+
[1b6f8a26-ca2f-43b8-8262-3ee446021767]
52+
description = "Cysteine RNA sequence 2"
53+
54+
[1e91c1eb-02c0-48a0-9e35-168ad0cb5f39]
55+
description = "Tryptophan RNA sequence"
56+
57+
[e547af0b-aeab-49c7-9f13-801773a73557]
58+
description = "STOP codon RNA sequence 1"
59+
60+
[67640947-ff02-4f23-a2ef-816f8a2ba72e]
61+
description = "STOP codon RNA sequence 2"
62+
63+
[9c2ad527-ebc9-4ace-808b-2b6447cb54cb]
64+
description = "STOP codon RNA sequence 3"
65+
66+
[f4d9d8ee-00a8-47bf-a1e3-1641d4428e54]
67+
description = "Sequence of two protein codons translates into proteins"
68+
69+
[dd22eef3-b4f1-4ad6-bb0b-27093c090a9d]
70+
description = "Sequence of two different protein codons translates into proteins"
71+
72+
[d0f295df-fb70-425c-946c-ec2ec185388e]
73+
description = "Translate RNA strand into correct protein list"
74+
75+
[e30e8505-97ec-4e5f-a73e-5726a1faa1f4]
76+
description = "Translation stops if STOP codon at beginning of sequence"
77+
78+
[5358a20b-6f4c-4893-bce4-f929001710f3]
79+
description = "Translation stops if STOP codon at end of two-codon sequence"
80+
81+
[ba16703a-1a55-482f-bb07-b21eef5093a3]
82+
description = "Translation stops if STOP codon at end of three-codon sequence"
83+
84+
[4089bb5a-d5b4-4e71-b79e-b8d1f14a2911]
85+
description = "Translation stops if STOP codon in middle of three-codon sequence"
86+
87+
[2c2a2a60-401f-4a80-b977-e0715b23b93d]
88+
description = "Translation stops if STOP codon in middle of six-codon sequence"
89+
90+
[f6f92714-769f-4187-9524-e353e8a41a80]
91+
description = "Sequence of two non-STOP codons does not translate to a STOP codon"
92+
93+
[1e75ea2a-f907-4994-ae5c-118632a1cb0f]
94+
description = "Non-existing codon can't translate"
95+
include = false
96+
97+
[9eac93f3-627a-4c90-8653-6d0a0595bc6f]
98+
description = "Unknown amino acids, not part of a codon, can't translate"
99+
reimplements = "1e75ea2a-f907-4994-ae5c-118632a1cb0f"
100+
101+
[9d73899f-e68e-4291-b1e2-7bf87c00f024]
102+
description = "Incomplete RNA sequence can't translate"
103+
104+
[43945cf7-9968-402d-ab9f-b8a28750b050]
105+
description = "Incomplete RNA sequence can translate if valid until a STOP codon"
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
name "protein-translation"
2+
buildRequirements "disallowDeprecations"
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
module protein_translation;
2+
3+
import std.algorithm;
4+
import std.range;
5+
import std.conv;
6+
7+
immutable string[string] availableProteins = [
8+
"AUG": "Methionine",
9+
"UUU": "Phenylalanine",
10+
"UUC": "Phenylalanine",
11+
"UUA": "Leucine",
12+
"UUG": "Leucine",
13+
"UCU": "Serine",
14+
"UCC": "Serine",
15+
"UCA": "Serine",
16+
"UCG": "Serine",
17+
"UAU": "Tyrosine",
18+
"UAC": "Tyrosine",
19+
"UGU": "Cysteine",
20+
"UGC": "Cysteine",
21+
"UGG": "Tryptophan",
22+
"UAA": "STOP",
23+
"UAG": "STOP",
24+
"UGA": "STOP"
25+
];
26+
27+
pure string[] proteins(immutable string strand)
28+
{
29+
string[] codons = strand.chunks(3).map!(chunk => chunk.array.to!string).array;
30+
string[] results = [];
31+
32+
foreach (codon; codons) {
33+
if(codon!in availableProteins)
34+
throw new Exception("Invalid codon");
35+
36+
string protein = availableProteins[codon];
37+
if (protein == "STOP")
38+
return results;
39+
40+
results ~= protein;
41+
};
42+
43+
return results;
44+
}
45+
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,110 @@
1+
module protein_translation;
2+
3+
pure string[] proteins(immutable string rna)
4+
{
5+
// implement this function
6+
}
7+
8+
unittest
9+
{
10+
import std.exception : assertThrown;
11+
12+
immutable int allTestsEnabled = 1;
13+
14+
// Empty RNA sequence results in no proteins
15+
assert(proteins("") == []);
16+
17+
static if (allTestsEnabled)
18+
{
19+
// Methionine RNA sequence
20+
assert(proteins("AUG") == ["Methionine"]);
21+
22+
// Phenylalanine RNA sequence 1
23+
assert(proteins("UUU") == ["Phenylalanine"]);
24+
25+
// Phenylalanine RNA sequence 2
26+
assert(proteins("UUC") == ["Phenylalanine"]);
27+
28+
// Leucine RNA sequence 1
29+
assert(proteins("UUA") == ["Leucine"]);
30+
31+
// Leucine RNA sequence 2
32+
assert(proteins("UUG") == ["Leucine"]);
33+
34+
// Serine RNA sequence 1
35+
assert(proteins("UCU") == ["Serine"]);
36+
37+
// Serine RNA sequence 2
38+
assert(proteins("UCC") == ["Serine"]);
39+
40+
// Serine RNA sequence 3
41+
assert(proteins("UCA") == ["Serine"]);
42+
43+
// Serine RNA sequence 4
44+
assert(proteins("UCG") == ["Serine"]);
45+
46+
// Tyrosine RNA sequence 1
47+
assert(proteins("UAU") == ["Tyrosine"]);
48+
49+
// Tyrosine RNA sequence 2
50+
assert(proteins("UAC") == ["Tyrosine"]);
51+
52+
// Cysteine RNA sequence 1
53+
assert(proteins("UGU") == ["Cysteine"]);
54+
55+
// Cysteine RNA sequence 2
56+
assert(proteins("UGC") == ["Cysteine"]);
57+
58+
// Tryptophan RNA sequence
59+
assert(proteins("UGG") == ["Tryptophan"]);
60+
61+
// STOP codon RNA sequence 1
62+
assert(proteins("UAA") == []);
63+
64+
// STOP codon RNA sequence 2
65+
assert(proteins("UAG") == []);
66+
67+
// STOP codon RNA sequence 3
68+
assert(proteins("UGA") == []);
69+
70+
// Sequence of two protein codons translates into proteins
71+
assert(proteins("UUUUUU") == ["Phenylalanine", "Phenylalanine"]);
72+
73+
// Sequence of two different protein codons translates into proteins
74+
assert(proteins("UUAUUG") == ["Leucine", "Leucine"]);
75+
76+
// Translate RNA strand into correct protein list
77+
assert(proteins("AUGUUUUGG") == ["Methionine", "Phenylalanine", "Tryptophan"]);
78+
79+
// Translation stops if STOP codon at beginning of sequence
80+
assert(proteins("UAGUGG") == []);
81+
82+
// Translation stops if STOP codon at end of two-codon sequence
83+
assert(proteins("UGGUAG") == ["Tryptophan"]);
84+
85+
// Translation stops if STOP codon at end of three-codon sequence
86+
assert(proteins("AUGUUUUAA") == ["Methionine", "Phenylalanine"]);
87+
88+
// Translation stops if STOP codon in middle of three-codon sequence
89+
assert(proteins("UGGUAGUGG") == ["Tryptophan"]);
90+
91+
// Translation stops if STOP codon in middle of six-codon sequence
92+
assert(proteins("UGGUGUUAUUAAUGGUUU") == ["Tryptophan", "Cysteine", "Tyrosine"]);
93+
94+
// Sequence of two non-STOP codons does not translate to a STOP codon
95+
assert(proteins("AUGAUG") == ["Methionine", "Methionine"]);
96+
97+
// Non-existing codon can't translate
98+
assertThrown(proteins("AAA"));
99+
100+
// Unknown amino acids, not part of a codon, can't translate
101+
assertThrown(proteins("XYZ"));
102+
103+
// Incomplete RNA sequence can't translate
104+
assertThrown(proteins("AUGU"));
105+
106+
// Incomplete RNA sequence can translate if valid until a STOP codon
107+
assert(proteins("UUCUUCUAAUGGU") == ["Phenylalanine", "Phenylalanine"]);
108+
}
109+
}
110+

0 commit comments

Comments
 (0)