Add protein-translation exercise (#165)
This commit is contained in:
Erik Schierboom
@@ -372,6 +372,14 @@
|
||||
"practices": [],
|
||||
"prerequisites": [],
|
||||
"difficulty": 3
|
||||
},
|
||||
{
|
||||
"slug": "protein-translation",
|
||||
"name": "Protein Translation",
|
||||
"uuid": "28d72a65-843a-4c31-bf74-c6e4f52a598e",
|
||||
"practices": [],
|
||||
"prerequisites": [],
|
||||
"difficulty": 3
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
45
exercises/practice/protein-translation/.docs/instructions.md
Normal file
45
exercises/practice/protein-translation/.docs/instructions.md
Normal file
@@ -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)
|
||||
18
exercises/practice/protein-translation/.meta/config.json
Normal file
18
exercises/practice/protein-translation/.meta/config.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"authors": [
|
||||
"erikschierboom"
|
||||
],
|
||||
"files": {
|
||||
"solution": [
|
||||
"protein-translation.8th"
|
||||
],
|
||||
"test": [
|
||||
"test.8th"
|
||||
],
|
||||
"example": [
|
||||
".meta/example.8th"
|
||||
]
|
||||
},
|
||||
"blurb": "Translate RNA sequences into proteins.",
|
||||
"source": "Tyler Long"
|
||||
}
|
||||
24
exercises/practice/protein-translation/.meta/example.8th
Normal file
24
exercises/practice/protein-translation/.meta/example.8th
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"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"
|
||||
} constant codon-protein-map
|
||||
|
||||
: >protein \ s -- s
|
||||
codon-protein-map swap caseof
|
||||
;
|
||||
|
||||
: >codons \ s -- a
|
||||
/[[:alpha:]]{1,3}/ r:+/
|
||||
;
|
||||
|
||||
: >proteins \ s -- a
|
||||
>codons a:new swap
|
||||
( >protein null? if nip break ;then
|
||||
dup "STOP" s:= if drop break else a:push then ) a:each! drop
|
||||
;
|
||||
102
exercises/practice/protein-translation/.meta/tests.toml
Normal file
102
exercises/practice/protein-translation/.meta/tests.toml
Normal file
@@ -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"
|
||||
173
exercises/practice/protein-translation/libs/exercism/test
Normal file
173
exercises/practice/protein-translation/libs/exercism/test
Normal file
@@ -0,0 +1,173 @@
|
||||
needs console/loaded
|
||||
|
||||
\ -----------------------------------------------------------------
|
||||
|
||||
ns: test
|
||||
|
||||
-1 var, test-count
|
||||
var tests-passed
|
||||
var tests-failed
|
||||
var tests-skipped
|
||||
true var, run-test
|
||||
|
||||
\ Some utility words
|
||||
|
||||
|
||||
: test-passed \ s x x -- \\ test name, expected value, actual value
|
||||
2drop
|
||||
1 tests-passed n:+!
|
||||
con:green con:onBlack . space " ... OK" . con:white con:onBlack cr
|
||||
;
|
||||
|
||||
: test-skipped \ s --
|
||||
1 tests-skipped n:+!
|
||||
con:cyan con:onBlack . space " ... SKIPPED" . con:white con:onBlack cr
|
||||
;
|
||||
|
||||
: test-failed \ s x x -- \\ test name, expected value, actual value
|
||||
1 tests-failed n:+!
|
||||
rot
|
||||
con:red con:onBlack . space " ... FAIL" . con:white con:onBlack cr
|
||||
" Actual: «" . . "»" . cr
|
||||
" Expected: «" . . "»" . cr cr
|
||||
;
|
||||
|
||||
: isword? \ x -- x f
|
||||
dup >kind ns:w n:=
|
||||
;
|
||||
|
||||
: run-test? \ -- T
|
||||
run-test @ if true else "RUN_ALL_TESTS" getenv n:>bool then
|
||||
;
|
||||
|
||||
\ Num passed + num skipped + num failed should == num tests
|
||||
: all-tests-run? \ -- T
|
||||
tests-passed @ tests-skipped @ tests-failed @ n:+ n:+
|
||||
test-count @ n:=
|
||||
;
|
||||
|
||||
\ returns true if x is a date, false otherwise
|
||||
: date? \ x -- x T
|
||||
dup >kind ns:d n:=
|
||||
;
|
||||
|
||||
\ adapted from 8th forum -- https://8th-dev.com/forum/index.php/topic,2745.0.html
|
||||
: eq? \ x x -- T
|
||||
\ are the items the same kind?
|
||||
2dup >kind swap >kind n:=
|
||||
!if 2drop false ;then
|
||||
|
||||
\ same kind: try different comparators
|
||||
number? if n:= ;then
|
||||
string? if s:= ;then
|
||||
array? if ' eq? a:= 2nip ;then
|
||||
map? if ' eq? m:= 2nip ;then
|
||||
date? if d:= ;then
|
||||
|
||||
\ otherwise fall back to 'lazy evaluation'
|
||||
l: =
|
||||
;
|
||||
|
||||
: eps_eq? \ n x x -- T
|
||||
\ are the items the same kind?
|
||||
2dup >kind swap >kind n:=
|
||||
!if 2drop false ;then
|
||||
number? !if 2drop false ;then
|
||||
rot n:~=
|
||||
;
|
||||
|
||||
: check-depth \ ... n -- ...
|
||||
dup>r
|
||||
n:1+ depth n:=
|
||||
!if
|
||||
con:red con:onBlack
|
||||
"PANIC: expected stack depth to be " . r> . cr
|
||||
"Stack is:" . cr
|
||||
.s cr
|
||||
255 die
|
||||
then
|
||||
rdrop
|
||||
;
|
||||
|
||||
\ -----------------------------------------------------------------
|
||||
|
||||
\ status report at end of run
|
||||
( all-tests-run?
|
||||
!if con:red con:onBlack "... FAIL - not all tests completed" . con:white con:onBlack cr then
|
||||
) onexit
|
||||
|
||||
\ Print a summary of the tests run
|
||||
( con:white con:onBlack
|
||||
test-count @ . space "tests planned - " .
|
||||
tests-passed @ . space "passed - " .
|
||||
tests-skipped @ . space "skipped - " .
|
||||
tests-failed @ . space "failed" . cr
|
||||
) onexit
|
||||
|
||||
\ -----------------------------------------------------------------
|
||||
\ The public-facing words
|
||||
\ -----------------------------------------------------------------
|
||||
|
||||
: equal? \ s x w -- | s w x --
|
||||
run-test? !if 2drop test-skipped ;; then
|
||||
isword? !if swap then
|
||||
w:exec
|
||||
3 check-depth
|
||||
2dup \ so test-failed can show actual and expected
|
||||
eq? if test-passed else test-failed then
|
||||
;
|
||||
|
||||
: approx_equal? \ s x w n -- | s w x n --
|
||||
run-test? !if 3drop test-skipped ;; then
|
||||
-rot isword? !if swap then
|
||||
w:exec
|
||||
4 check-depth
|
||||
3dup \ so test-failed can show actual and expected
|
||||
eps_eq?
|
||||
if rot drop test-passed else rot drop test-failed then
|
||||
;
|
||||
|
||||
: true? \ s w --
|
||||
run-test? !if drop test-skipped ;; then
|
||||
w:exec
|
||||
2 check-depth
|
||||
true swap dup \ so test-failed can show actual and expected
|
||||
if test-passed else test-failed then
|
||||
;
|
||||
|
||||
: false? \ s w --
|
||||
run-test? !if drop test-skipped ;; then
|
||||
w:exec
|
||||
2 check-depth
|
||||
false swap dup \ so test-failed can show actual and expected
|
||||
!if test-passed else test-failed then
|
||||
;
|
||||
|
||||
: null? \ s w --
|
||||
run-test? !if drop test-skipped ;; then
|
||||
w:exec
|
||||
2 check-depth
|
||||
null swap dup \ so test-failed can show actual and expected
|
||||
G:null? nip if test-passed else test-failed then
|
||||
;
|
||||
|
||||
: SKIP-REST-OF-TESTS false run-test ! ;
|
||||
|
||||
: tests \ n --
|
||||
test-count !
|
||||
;
|
||||
|
||||
\ Set the exit status:
|
||||
\ 0 = all OK
|
||||
\ 1 = not all tests were run (some error occurred)
|
||||
\ 2 = some tests failed
|
||||
: end-of-tests \ --
|
||||
all-tests-run?
|
||||
if
|
||||
tests-failed @ 0 n:= if 0 else 2 then
|
||||
else
|
||||
1
|
||||
then
|
||||
die
|
||||
;
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
: >proteins \ s -- a
|
||||
|
||||
;
|
||||
152
exercises/practice/protein-translation/test.8th
Normal file
152
exercises/practice/protein-translation/test.8th
Normal file
@@ -0,0 +1,152 @@
|
||||
"protein-translation.8th" f:include
|
||||
needs exercism/test
|
||||
with: test
|
||||
29 tests
|
||||
|
||||
"Empty RNA sequence results in no proteins"
|
||||
( "" >proteins )
|
||||
[]
|
||||
equal?
|
||||
|
||||
SKIP-REST-OF-TESTS
|
||||
|
||||
"Methionine RNA sequence"
|
||||
( "AUG" >proteins )
|
||||
["Methionine"]
|
||||
equal?
|
||||
|
||||
"Phenylalanine RNA sequence 1"
|
||||
( "UUU" >proteins )
|
||||
["Phenylalanine"]
|
||||
equal?
|
||||
|
||||
"Phenylalanine RNA sequence 2"
|
||||
( "UUC" >proteins )
|
||||
["Phenylalanine"]
|
||||
equal?
|
||||
|
||||
"Leucine RNA sequence 1"
|
||||
( "UUA" >proteins )
|
||||
["Leucine"]
|
||||
equal?
|
||||
|
||||
"Leucine RNA sequence 2"
|
||||
( "UUG" >proteins )
|
||||
["Leucine"]
|
||||
equal?
|
||||
|
||||
"Serine RNA sequence 1"
|
||||
( "UCU" >proteins )
|
||||
["Serine"]
|
||||
equal?
|
||||
|
||||
"Serine RNA sequence 2"
|
||||
( "UCC" >proteins )
|
||||
["Serine"]
|
||||
equal?
|
||||
|
||||
"Serine RNA sequence 3"
|
||||
( "UCA" >proteins )
|
||||
["Serine"]
|
||||
equal?
|
||||
|
||||
"Serine RNA sequence 4"
|
||||
( "UCG" >proteins )
|
||||
["Serine"]
|
||||
equal?
|
||||
|
||||
"Tyrosine RNA sequence 1"
|
||||
( "UAU" >proteins )
|
||||
["Tyrosine"]
|
||||
equal?
|
||||
|
||||
"Tyrosine RNA sequence 2"
|
||||
( "UAC" >proteins )
|
||||
["Tyrosine"]
|
||||
equal?
|
||||
|
||||
"Cysteine RNA sequence 1"
|
||||
( "UGU" >proteins )
|
||||
["Cysteine"]
|
||||
equal?
|
||||
|
||||
"Cysteine RNA sequence 2"
|
||||
( "UGC" >proteins )
|
||||
["Cysteine"]
|
||||
equal?
|
||||
|
||||
"Tryptophan RNA sequence"
|
||||
( "UGG" >proteins )
|
||||
["Tryptophan"]
|
||||
equal?
|
||||
|
||||
"STOP codon RNA sequence 1"
|
||||
( "UAA" >proteins )
|
||||
[]
|
||||
equal?
|
||||
|
||||
"STOP codon RNA sequence 2"
|
||||
( "UAG" >proteins )
|
||||
[]
|
||||
equal?
|
||||
|
||||
"STOP codon RNA sequence 3"
|
||||
( "UGA" >proteins )
|
||||
[]
|
||||
equal?
|
||||
|
||||
"Sequence of two protein codons translates into proteins"
|
||||
( "UUUUUU" >proteins )
|
||||
["Phenylalanine", "Phenylalanine"]
|
||||
equal?
|
||||
|
||||
"Sequence of two different protein codons translates into proteins"
|
||||
( "UUAUUG" >proteins )
|
||||
["Leucine", "Leucine"]
|
||||
equal?
|
||||
|
||||
"Translate RNA strand into correct protein list"
|
||||
( "AUGUUUUGG" >proteins )
|
||||
["Methionine", "Phenylalanine", "Tryptophan"]
|
||||
equal?
|
||||
|
||||
"Translation stops if STOP codon at beginning of sequence"
|
||||
( "UAGUGG" >proteins )
|
||||
[]
|
||||
equal?
|
||||
|
||||
"Translation stops if STOP codon at end of two-codon sequence"
|
||||
( "UGGUAG" >proteins )
|
||||
["Tryptophan"]
|
||||
equal?
|
||||
|
||||
"Translation stops if STOP codon at end of three-codon sequence"
|
||||
( "AUGUUUUAA" >proteins )
|
||||
["Methionine", "Phenylalanine"]
|
||||
equal?
|
||||
|
||||
"Translation stops if STOP codon in middle of three-codon sequence"
|
||||
( "UGGUAGUGG" >proteins )
|
||||
["Tryptophan"]
|
||||
equal?
|
||||
|
||||
"Translation stops if STOP codon in middle of six-codon sequence"
|
||||
( "UGGUGUUAUUAAUGGUUU" >proteins )
|
||||
["Tryptophan", "Cysteine", "Tyrosine"]
|
||||
equal?
|
||||
|
||||
"Unknown amino acids, not part of a codon, can't translate"
|
||||
( "XYZ" >proteins )
|
||||
null?
|
||||
|
||||
"Incomplete RNA sequence can't translate"
|
||||
( "AUGU" >proteins )
|
||||
null?
|
||||
|
||||
"Incomplete RNA sequence can translate if valid until a STOP codon"
|
||||
( "UUCUUCUAAUGGU" >proteins )
|
||||
["Phenylalanine", "Phenylalanine"]
|
||||
equal?
|
||||
|
||||
end-of-tests
|
||||
;with
|
||||
Reference in New Issue
Block a user