-
-
Notifications
You must be signed in to change notification settings - Fork 184
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
2248b80
commit 8f30281
Showing
13 changed files
with
4,555 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
45 changes: 45 additions & 0 deletions
45
exercises/practice/protein-translation/.docs/instructions.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,20 @@ | ||
{ | ||
"authors": [ | ||
"ryanplusplus" | ||
], | ||
"files": { | ||
"solution": [ | ||
"protein_translation.c", | ||
"protein_translation.h" | ||
], | ||
"test": [ | ||
"test_protein_translation.c" | ||
], | ||
"example": [ | ||
".meta/example.c", | ||
".meta/example.h" | ||
] | ||
}, | ||
"blurb": "Translate RNA sequences into proteins.", | ||
"source": "Tyler Long" | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,62 @@ | ||
#include <string.h> | ||
#include "protein_translation.h" | ||
|
||
enum { codon_length = 3 }; | ||
|
||
typedef struct { | ||
const char *const codon; | ||
protein_t protein; | ||
bool stop; | ||
} protein_translation_t; | ||
|
||
static const protein_translation_t translations[] = { | ||
{ "AUG", Methionine, false }, | ||
{ "UUU", Phenylalanine, false }, | ||
{ "UUC", Phenylalanine, false }, | ||
{ "UUA", Leucine, false }, | ||
{ "UUG", Leucine, false }, | ||
{ "UCU", Serine, false }, | ||
{ "UCC", Serine, false }, | ||
{ "UCA", Serine, false }, | ||
{ "UCG", Serine, false }, | ||
{ "UAU", Tyrosine, false }, | ||
{ "UAC", Tyrosine, false }, | ||
{ "UGU", Cysteine, false }, | ||
{ "UGC", Cysteine, false }, | ||
{ "UGG", Tryptophan, false }, | ||
{ "UAA", 0, true }, | ||
{ "UAG", 0, true }, | ||
{ "UGA", 0, true }, | ||
}; | ||
static const size_t translation_count = | ||
sizeof(translations) / sizeof(translations[0]); | ||
|
||
proteins_t proteins(const char *const rna) | ||
{ | ||
proteins_t proteins = { .valid = true, .count = 0 }; | ||
|
||
size_t rna_length = strlen(rna); | ||
|
||
for (size_t i = 0; i < rna_length; i += codon_length) { | ||
bool found_codon = false; | ||
|
||
for (size_t j = 0; j < translation_count; j++) { | ||
if (strncmp(rna + i, translations[j].codon, codon_length) == 0) { | ||
if (translations[j].stop) { | ||
return proteins; | ||
} else { | ||
proteins.proteins[proteins.count++] = translations[j].protein; | ||
found_codon = true; | ||
break; | ||
} | ||
} | ||
} | ||
|
||
if (!found_codon) { | ||
proteins.valid = false; | ||
return proteins; | ||
} | ||
} | ||
|
||
return proteins; | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,27 @@ | ||
#ifndef PROTEIN_TRANSLATION_H | ||
#define PROTEIN_TRANSLATION_H | ||
|
||
#include <stdbool.h> | ||
#include <stddef.h> | ||
|
||
#define MAX_PROTEINS 10 | ||
|
||
typedef enum { | ||
Methionine, | ||
Phenylalanine, | ||
Leucine, | ||
Serine, | ||
Tyrosine, | ||
Cysteine, | ||
Tryptophan, | ||
} protein_t; | ||
|
||
typedef struct { | ||
bool valid; | ||
size_t count; | ||
protein_t proteins[MAX_PROTEINS]; | ||
} proteins_t; | ||
|
||
proteins_t proteins(const char *const rna); | ||
|
||
#endif |
100 changes: 100 additions & 0 deletions
100
exercises/practice/protein-translation/.meta/tests.toml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,37 @@ | ||
### If you wish to use extra libraries (math.h for instance), | ||
### add their flags here (-lm in our case) in the "LIBS" variable. | ||
|
||
LIBS = -lm | ||
|
||
### | ||
CFLAGS = -std=c99 | ||
CFLAGS += -g | ||
CFLAGS += -Wall | ||
CFLAGS += -Wextra | ||
CFLAGS += -pedantic | ||
CFLAGS += -Werror | ||
CFLAGS += -Wmissing-declarations | ||
CFLAGS += -DUNITY_SUPPORT_64 -DUNITY_OUTPUT_COLOR | ||
|
||
ASANFLAGS = -fsanitize=address | ||
ASANFLAGS += -fno-common | ||
ASANFLAGS += -fno-omit-frame-pointer | ||
|
||
.PHONY: test | ||
test: tests.out | ||
@./tests.out | ||
|
||
.PHONY: memcheck | ||
memcheck: ./*.c ./*.h | ||
@echo Compiling $@ | ||
@$(CC) $(ASANFLAGS) $(CFLAGS) test-framework/unity.c ./*.c -o memcheck.out $(LIBS) | ||
@./memcheck.out | ||
@echo "Memory check passed" | ||
|
||
.PHONY: clean | ||
clean: | ||
rm -rf *.o *.out *.out.dSYM | ||
|
||
tests.out: ./*.c ./*.h | ||
@echo Compiling $@ | ||
@$(CC) $(CFLAGS) test-framework/unity.c ./*.c -o tests.out $(LIBS) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
#include "protein_translation.h" |
27 changes: 27 additions & 0 deletions
27
exercises/practice/protein-translation/protein_translation.h
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,27 @@ | ||
#ifndef PROTEIN_TRANSLATION_H | ||
#define PROTEIN_TRANSLATION_H | ||
|
||
#include <stdbool.h> | ||
#include <stddef.h> | ||
|
||
#define MAX_PROTEINS 10 | ||
|
||
typedef enum { | ||
Methionine, | ||
Phenylalanine, | ||
Leucine, | ||
Serine, | ||
Tyrosine, | ||
Cysteine, | ||
Tryptophan, | ||
} protein_t; | ||
|
||
typedef struct { | ||
bool valid; | ||
size_t count; | ||
protein_t proteins[MAX_PROTEINS]; | ||
} proteins_t; | ||
|
||
proteins_t proteins(const char *const rna); | ||
|
||
#endif |
Oops, something went wrong.