Python基本语法

变量和数据类型：

# 数字
integer = 42
floating = 3.14159
# 字符串
dna = "ATGCGCTAGCTA"
protein = 'MPLK'
# 字符串操作
print(len(dna))              # 长度
print(dna[0:3])              # 切片（前3个碱基）
print(dna.count("GC"))       # 计数
print(dna.replace("T", "U"))  # 替换（DNA转RNA）
print(dna.find("ATG"))       # 查找子串位置
# 列表（有序可变）
sequences = ["ATCG", "GCTA", "TAGC"]
sequences.append("CGAT")     # 添加元素
print(sequences[0])          # 访问
print(len(sequences))        # 长度
# 字典（键值对）
gene_expr = {
    "GAPDH": 25.3,
    "ACTB": 18.7,
    "TP53": 3.2
}
print(gene_expr["GAPDH"])    # 访问
gene_expr["BRCA1"] = 7.5     # 添加
# 元组（有序不可变）
coordinates = (100, 200)

控制流：

# 条件语句
gc_content = 0.55
if gc_content > 0.6:
    print("High GC")
elif gc_content > 0.4:
    print("Moderate GC")
else:
    print("Low GC")
# for循环
for seq in sequences:
    gc = (seq.count("G") + seq.count("C")) / len(seq)
    print(f"{seq}: GC={gc:.2%}")
# while循环
i = 0
while i < len(sequences):
    print(sequences[i])
    i += 1
# 列表推导式（Pythonic写法）
gc_values = [(s.count("G") + s.count("C")) / len(s) for s in sequences]

函数：

def calculate_gc_content(sequence):
    """计算DNA序列的GC含量"""
    sequence = sequence.upper()
    gc_count = sequence.count("G") + sequence.count("C")
    return gc_count / len(sequence)
# 调用
gc = calculate_gc_content("ATGCGCTAGCTA")
print(f"GC content: {gc:.2%}")
# 默认参数
def reverse_complement(seq, rna=False):
    """计算反向互补序列"""
    complement = {"A": "T", "T": "A", "G": "C", "C": "G",
                  "a": "t", "t": "a", "g": "c", "c": "g"}
    if rna:
        complement["A"] = "U"
        complement["a"] = "u"
    rc = "".join(complement.get(base, base) for base in reversed(seq))
    return rc
print(reverse_complement("ATGC"))       # GCAT
print(reverse_complement("ATGC", rna=True))  # GCAU

文件操作：

# 读取文件
with open("sequences.fasta", "r") as f:
    content = f.read()           # 读取全部
    lines = f.readlines()        # 读取为列表
# 写入文件
with open("output.txt", "w") as f:
    f.write("Hello\n")
# 逐行读取（推荐大文件使用）
with open("data.txt", "r") as f:
    for line in f:
        line = line.strip()      # 去除末尾换行符
        if line.startswith(">"):
            print(f"Header: {line}")