375_水体微生物组分析¶

# 步骤1：水样过滤（在采样现场进行）
# 先用5微米预滤膜去除大颗粒
filtration_prefilter="5um_prefilter"
filtration_main="0.2um_sterivex"

# 记录过滤体积（用于标准化）
echo "Sample: River_001" > sample_log.txt
echo "Volume filtered: 2000 mL" >> sample_log.txt
echo "Filter type: Sterivex 0.2um" >> sample_log.txt

# 步骤2：Sterivex 滤芯 DNA 提取（使用 PowerWater DNA 试剂盒）
# 向Sterivex注入裂解液，物理震荡，然后柱纯化

# 步骤3：质量检测
# 用 Qubit 检测DNA浓度（Nanodrop 在水样中不准）
echo "DNA concentration: 15 ng/uL" >> sample_log.txt
echo "Volume: 50 uL" >> sample_log.txt
echo "Total DNA: 750 ng" >> sample_log.txt

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import spearmanr

# 加载 OTU 丰度表和水质化学数据
otu_df   = pd.read_csv("water_otu_table.csv", index_col=0)   # 样本×OTU
chem_df  = pd.read_csv("water_chemistry.csv", index_col=0)   # 样本×化学指标

# 确保样本对齐
common = otu_df.index.intersection(chem_df.index)
otu_df  = otu_df.loc[common]    # 取公共样本
chem_df = chem_df.loc[common]

# 计算 Shannon 多样性
from skbio.diversity import alpha_diversity
shannon = alpha_diversity("shannon", otu_df.values, otu_df.index)
print("Shannon 多样性：\n", shannon.describe())

# 化学指标（溶解氧、pH、氮磷）与多样性的相关分析
results = []
for col in chem_df.columns:
    r, p = spearmanr(chem_df[col], shannon)    # Spearman 相关
    results.append({"指标": col, "r": round(r, 3), "p": round(p, 4)})

result_df = pd.DataFrame(results)
result_df["显著"] = result_df["p"] < 0.05    # 标记显著关联
print(result_df.sort_values("r", ascending=False))

# 可视化：溶解氧 vs Shannon
fig, ax = plt.subplots(figsize=(6, 4))
ax.scatter(chem_df["DO_mg_L"], shannon, alpha=0.7, color="steelblue")
ax.set_xlabel("溶解氧 (mg/L)")
ax.set_ylabel("Shannon 多样性指数")
ax.set_title("水体溶解氧与微生物多样性关系")
plt.tight_layout()
plt.savefig("DO_vs_shannon.pdf", dpi=300)

# 用 qPCR 定量大肠菌群（uidA 基因）
# 以下为引物信息（备查）：
# E.coli uidA-F: 5'-AAAACGGCAAGAAAAAGCAG-3'
# E.coli uidA-R: 5'-ACGCGTGGTTACAGTCTTGCG-3'

# qPCR 标准曲线制备（10倍梯度稀释）
echo "Standard curve dilutions:"
echo "STD1: 1e7 copies/uL"
echo "STD2: 1e6 copies/uL"
echo "STD3: 1e5 copies/uL"
echo "STD4: 1e4 copies/uL"
echo "STD5: 1e3 copies/uL"

# 计算每升水的大肠菌群数
# copies_per_mL = 10^(Ct * slope + intercept) * 稀释倍数
# copies_per_L = copies_per_mL * 1000 / 过滤体积(L)

python3 << 'EOF'
import numpy as np

# 标准曲线参数（从qPCR软件读取）
slope = -3.32         # 理想斜率约 -3.32（对应100% 效率）
intercept = 38.5      # 截距

# 样品Ct值
ct_values = [25.3, 25.1, 25.6]   # 三个技术重复

# 计算拷贝数（每微升）
copies_per_ul = [10**((ct - intercept) / slope) for ct in ct_values]
mean_copies = np.mean(copies_per_ul)

# 换算为每升水
elution_volume_ul = 50   # 洗脱体积50微升
filtered_volume_L = 2    # 过滤了2升水
copies_per_liter = mean_copies * elution_volume_ul / filtered_volume_L / 1000

print(f"大肠杆菌浓度：{copies_per_liter:.2e} copies/L")
# WHO 饮用水标准：大肠菌群检出量应为 0
EOF