From e94ff2985cd6693cd0353008fdf52628b77ec468 Mon Sep 17 00:00:00 2001
From: Alberto Venturini <aventurini@gmail.com>
Date: Fri, 6 Sep 2024 12:32:54 +0200
Subject: [PATCH] Add Hamming Distance, Probability and Protein problems

---
 09_hamm/hamm.nim | 21 +++++++++++++
 10_iprb/iprb.nim | 38 +++++++++++++++++++++++
 11_prot/prot.nim | 80 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 139 insertions(+)
 create mode 100644 09_hamm/hamm.nim
 create mode 100644 10_iprb/iprb.nim
 create mode 100644 11_prot/prot.nim

diff --git a/09_hamm/hamm.nim b/09_hamm/hamm.nim
new file mode 100644
index 0000000..ea6e2f7
--- /dev/null
+++ b/09_hamm/hamm.nim
@@ -0,0 +1,21 @@
+import os
+import std/sequtils
+import std/streams
+
+template useStream(stream: Stream, body: untyped) =
+    if not isNil(stream):
+        try:
+            body
+        finally:
+            stream.close()
+
+proc hammingDist(s1, s2: string): int =
+    doAssert s1.len == s2.len
+    zip(s1, s2).countIt(it[0] != it[1])
+
+let fileName = paramStr(1)
+let fileStream = newFileStream(fileName)
+useStream(fileStream):
+    let s1 = readLine(fileStream)
+    let s2 = readLine(fileStream)
+    echo $hammingDist(s1, s2)
\ No newline at end of file
diff --git a/10_iprb/iprb.nim b/10_iprb/iprb.nim
new file mode 100644
index 0000000..28b6737
--- /dev/null
+++ b/10_iprb/iprb.nim
@@ -0,0 +1,38 @@
+import os
+import std/strutils
+
+let k = parseInt(paramStr(1))
+let m = parseInt(paramStr(2))
+let n = parseInt(paramStr(3))
+
+let T = k+m+n
+
+# Let "AA" be the case when we choose an individual with 2 dominant alleles,
+# "Aa" be the case when we choose an individual with 1 dominant and 1 recessive allele,
+# "aa" be the case when we choose an individual with 2 recessive alleles.
+#
+# Event probabilities:
+# p(AA) = k/T
+# p(Aa) = m/T
+# p(aa) = n/T
+# p(AA|AA) = (k-1)/(T-1)
+# p(Aa|AA) = m/(T-1)
+# and so on and so on.
+#
+# Choosing 2 individuals for mating is the combination of the probability events of choosing 2 individuals.
+# E.g., the probability of choosing two AA individuals is p(AA)*p(AA|AA) = (k/T)*((k-1)/(T-1))
+# Furthermore, for certain combinations, the probability that an offspring will display
+# the dominant phenotype is < 1. For example, when two Aa individuals mate, the probability of a dominant
+# phenotype is 0.75.
+
+let solution =
+    (k/T) * ((k-1)/(T-1)) +
+    (k/T) * (m/(T-1)) +
+    (k/T) * (n/(T-1)) +
+    (m/T) * (k/(T-1)) +
+    (m/T) * ((m-1)/(T-1)) * 0.75 +
+    (m/T) * (n/(T-1)) * 0.5 +
+    (n/T) * (k/(T-1)) +
+    (n/T) * (m/(T-1)) * 0.5
+
+echo $solution
\ No newline at end of file
diff --git a/11_prot/prot.nim b/11_prot/prot.nim
new file mode 100644
index 0000000..7fdf187
--- /dev/null
+++ b/11_prot/prot.nim
@@ -0,0 +1,80 @@
+import os
+import std/sequtils
+import std/streams
+import std/tables
+import std/enumutils
+import std/strutils
+
+template useStream(stream: Stream, body: untyped) =
+    if not isNil(stream):
+        try:
+            body
+        finally:
+            stream.close()
+
+type Codon = enum
+    UUU, CUU, AUU, GUU,
+    UUC, CUC, AUC, GUC,
+    UUA, CUA, AUA, GUA,
+    UUG, CUG, AUG, GUG,
+    UCU, CCU, ACU, GCU,
+    UCC, CCC, ACC, GCC,
+    UCA, CCA, ACA, GCA,
+    UCG, CCG, ACG, GCG,
+    UAU, CAU, AAU, GAU,
+    UAC, CAC, AAC, GAC,
+    UAA, CAA, AAA, GAA,
+    UAG, CAG, AAG, GAG,
+    UGU, CGU, AGU, GGU,
+    UGC, CGC, AGC, GGC,
+    UGA, CGA, AGA, GGA,
+    UGG, CGG, AGG, GGG
+
+type AminoAcid = enum
+    A, C, D, E, F, G, H, I,
+    K, L, M, N, P, Q, R,
+    S, T, V, W, Y, STOP
+
+let translationTable = {
+    UUU: F,    CUU: L, AUU: I, GUU: V,
+    UUC: F,    CUC: L, AUC: I, GUC: V,
+    UUA: L,    CUA: L, AUA: I, GUA: V,
+    UUG: L,    CUG: L, AUG: M, GUG: V,
+    UCU: S,    CCU: P, ACU: T, GCU: A,
+    UCC: S,    CCC: P, ACC: T, GCC: A,
+    UCA: S,    CCA: P, ACA: T, GCA: A,
+    UCG: S,    CCG: P, ACG: T, GCG: A,
+    UAU: Y,    CAU: H, AAU: N, GAU: D,
+    UAC: Y,    CAC: H, AAC: N, GAC: D,
+    UAA: STOP, CAA: Q, AAA: K, GAA: E,
+    UAG: STOP, CAG: Q, AAG: K, GAG: E,
+    UGU: C,    CGU: R, AGU: S, GGU: G,
+    UGC: C,    CGC: R, AGC: S, GGC: G,
+    UGA: STOP, CGA: R, AGA: R, GGA: G,
+    UGG: W,    CGG: R, AGG: R, GGG: G 
+}.toTable
+
+iterator codons(dna: string): Codon =
+    var i = 0
+    while i <= dna.len:
+        let codonStr = dna[i..i+2]
+        yield parseEnum[Codon](codonStr)
+        i += 3
+
+proc translate(codon: Codon): AminoAcid =
+    translationTable[codon]
+
+let fileName = paramStr(1)
+let fileStream = newFileStream(fileName)
+useStream(fileStream):
+    let codonStr = readLine(fileStream)
+
+    var aminoAcidStr = ""
+
+    for c in codons(codonStr):
+        let a = translate(c)
+        if a == STOP:
+            break
+        aminoAcidStr.add($a)
+
+    echo aminoAcidStr
\ No newline at end of file