Appendix D — Collections: Practice Problem Solutions

D.1 Solution to Problem C.1

gene_names = ["TP53", "BRCA1", "MDM2"]
print(gene_names[0])
print(gene_names[1])
print(gene_names[2])

TP53
BRCA1
MDM2

D.2 Solution to Problem C.2

bases = ["A", "T", "G", "C", "G", "C"]

first_three = bases[:3]
last_two = bases[-2:]

print(first_three)
print(last_two)

['A', 'T', 'G']
['G', 'C']

D.3 Solution to Problem C.3

genes = ["TP53", "BRCA1"]

genes.append("ATM")
genes.remove("BRCA1")

print(genes)

['TP53', 'ATM']

D.4 Solution to Problem C.4

gene_location = (2_345_678, 2_346_987)
print(gene_location)

(2345678, 2346987)

D.5 Solution to Problem C.5

gene_functions = {"TP53": "tumor suppression", "BRCA1": "DNA repair"}
print(gene_functions["TP53"])

tumor suppression

D.6 Solution to Problem C.6

gene_functions = {"TP53": "tumor suppression", "BRCA1": "DNA repair"}

result = gene_functions.get("MDM2", "Unknown")

print(result)

Unknown

D.7 Solution to Problem C.7

expression = [2.3, 3.1, 1.9]

for value in expression:
    print(value)

2.3
3.1
1.9

D.8 Solution to Problem C.8

sequence = "AAGCTTAA"
count = 0

for base in sequence:
    if base == "A":
        count += 1

print(count)

4

D.9 Solution to Problem C.9

genes = ["TP53", "BRCA1", "MDM2", "ATM"]
genes_with_A = []

for gene in genes:
    if "A" in gene:
        genes_with_A.append(gene)

print(genes_with_A)

['BRCA1', 'ATM']

D.10 Solution to Problem C.10

genes = ["TP53", "BRCA1", "MDM2"]

if "BRCA1" in genes:
    print("Found")
else:
    print("Not found")

Found

D.11 Solution to Problem C.11

samples = [
    ["Sample1", [1.1, 1.2, 1.3]],
    ["Sample2", [2.1, 2.2, 2.3]],
    ["Sample3", [3.1, 3.2, 3.3]],
]

print(samples[2][1][0])

3.1

Optional Extension

Here is one way that you could nested for loops with enumerate to print the values and their indices:

for sample_index, sample_data in enumerate(samples):
    sample_name, observations = sample_data
    for observation_index, observation in enumerate(observations):
        print(f"{sample_index}: {sample_name}; {observation_index}: {observation}")

0: Sample1; 0: 1.1
0: Sample1; 1: 1.2
0: Sample1; 2: 1.3
1: Sample2; 0: 2.1
1: Sample2; 1: 2.2
1: Sample2; 2: 2.3
2: Sample3; 0: 3.1
2: Sample3; 1: 3.2
2: Sample3; 2: 3.3

D.12 Solution to Problem C.12

gene_ids = ["nrdA", "nrdJ", "nrdD"]
products = ["Class I RNR", "Class II RNR", "Class III RNR"]

gene_products = {}

for gene_id, product in zip(gene_ids, products):
    gene_products[gene_id] = product

print(gene_products)

{'nrdA': 'Class I RNR', 'nrdJ': 'Class II RNR', 'nrdD': 'Class III RNR'}

D.13 Solution to Problem C.13

dna = "ATGCTTAC"

rna = ["U" if base == "T" else base for base in dna]

print(rna)

['A', 'U', 'G', 'C', 'U', 'U', 'A', 'C']

D.14 Solution to Problem C.14

from collections import defaultdict

sequence = "AAGCGAAGCT"
counts = defaultdict(int)

for base in sequence:
    counts[base] += 1

for base, count in counts.items():
    print(f"{base} => {count}")

A => 4
G => 3
C => 2
T => 1

D.15 Solution to Problem C.15

gene_info = {
    "nrdA": {"product": "Class I RNR", "location": {"start": 1023, "end": 3268}}
}

start = gene_info["nrdA"]["location"]["start"]
end = gene_info["nrdA"]["location"]["end"]

print(f"{start=}")
print(f"{end=}")

start=1023
end=3268

Optional Extension

Let’s add another gene to the dictionary and loop through it.

gene_info["new_gene"] = {
    "product": "Some Protein",
    "location": {"start": 5000, "end": 8000},
}

for gene_id, gene_data in gene_info.items():
    start = gene_data["location"]["start"]
    end = gene_data["location"]["end"]

    print(f"Gene={gene_id}; {start=}; {end=}")

Gene=nrdA; start=1023; end=3268
Gene=new_gene; start=5000; end=8000

D.16 Solution to Problem C.16

complement = {"A": "T", "T": "A", "G": "C", "C": "G"}

sequence = "AAAACCCGGT"
rev_comp = ""

for base in reversed(sequence):
    rev_comp += complement[base]

print(rev_comp)

ACCGGGTTTT

D.17 Solution to Problem C.17

BACTERIA_COUNT = 10
bacteria = [5] * BACTERIA_COUNT

for turn in range(10):
    print(f"Turn {turn}: {bacteria}")

    # Check if this is an even turn
    is_even_turn = turn % 2 == 0

    for i in range(BACTERIA_COUNT):
        # Check if this bacteria is at an even index
        is_even_index = i % 2 == 0

        # Even turns: even-indexed bacteria grow
        if is_even_turn and is_even_index:
            bacteria[i] += 1
        # Odd turns: odd-indexed bacteria shrink
        elif not is_even_turn and not is_even_index:
            bacteria[i] -= 1

print(f"At the end: {bacteria}")

Turn 0: [5, 5, 5, 5, 5, 5, 5, 5, 5, 5]
Turn 1: [6, 5, 6, 5, 6, 5, 6, 5, 6, 5]
Turn 2: [6, 4, 6, 4, 6, 4, 6, 4, 6, 4]
Turn 3: [7, 4, 7, 4, 7, 4, 7, 4, 7, 4]
Turn 4: [7, 3, 7, 3, 7, 3, 7, 3, 7, 3]
Turn 5: [8, 3, 8, 3, 8, 3, 8, 3, 8, 3]
Turn 6: [8, 2, 8, 2, 8, 2, 8, 2, 8, 2]
Turn 7: [9, 2, 9, 2, 9, 2, 9, 2, 9, 2]
Turn 8: [9, 1, 9, 1, 9, 1, 9, 1, 9, 1]
Turn 9: [10, 1, 10, 1, 10, 1, 10, 1, 10, 1]
At the end: [10, 0, 10, 0, 10, 0, 10, 0, 10, 0]