提交饱和编辑的相关设计，及检验代码

2026-02-26 14:02:42 +08:00
commit cb556b47c0
36 changed files with 5437 additions and 0 deletions
--- a/filter.py
+++ b/filter.py
@@ -0,0 +1,87 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+import os
+import gzip
+from glob import glob
+
+import pandas as pd
+
+
+
+def amino_acid_to_codon(amino_acid):
+    """
+    简化的氨基酸到密码子转换函数
+
+    参数:
+        amino_acid (str): 单字母氨基酸代码
+
+    返回:
+        list: 可能的密码子列表
+    """
+    genetic_code = {
+        'A': ['GCT', 'GCC', 'GCA', 'GCG'],
+        'R': ['CGT', 'CGC', 'CGA', 'CGG', 'AGA', 'AGG'],
+        'N': ['AAT', 'AAC'],
+        'D': ['GAT', 'GAC'],
+        'C': ['TGT', 'TGC'],
+        'E': ['GAA', 'GAG'],
+        'Q': ['CAA', 'CAG'],
+        'G': ['GGT', 'GGC', 'GGA', 'GGG'],
+        'H': ['CAT', 'CAC'],
+        'I': ['ATT', 'ATC', 'ATA'],
+        'L': ['TTA', 'TTG', 'CTT', 'CTC', 'CTA', 'CTG'],
+        'K': ['AAA', 'AAG'],
+        'M': ['ATG'],
+        'F': ['TTT', 'TTC'],
+        'P': ['CCT', 'CCC', 'CCA', 'CCG'],
+        'S': ['TCT', 'TCC', 'TCA', 'TCG', 'AGT', 'AGC'],
+        'T': ['ACT', 'ACC', 'ACA', 'ACG'],
+        'W': ['TGG'],
+        'Y': ['TAT', 'TAC'],
+        'V': ['GTT', 'GTC', 'GTA', 'GTG'],
+        '*': ['TAA', 'TAG', 'TGA'],
+    }
+
+    return genetic_code.get(amino_acid.upper(), [])
+
+
+
+def main(ref, infile, outfile):
+    print(infile, outfile)
+    df = pd.read_excel(ref, 1)
+
+    keys = {}
+    for _, row in df.iterrows():
+        row = list(row)
+        for src in amino_acid_to_codon(row[1]):
+            keys[f"{src}_{row[2]}"] = 0
+
+    if os.path.dirname(outfile):
+        os.makedirs(os.path.dirname(outfile), exist_ok = True)
+
+    header = False
+    with gzip.open(outfile, "wt+") as w:
+        with gzip.open(infile, "rt") as r:
+            for line in r:
+                if not header:
+                    w.write(line.strip() + "\n")
+                    header = line.strip().split(",")
+                    continue
+
+                try:
+                    target = header.index("sequence_name")
+                except ValueError:
+                    target = header.index("Target_name")
+                
+                key = line.strip().split(",")[target]
+                key = key.split("_")[2:]
+                key = "_".join(key).strip('"')
+
+                if key in keys:
+                    w.write(line.strip() + "\n")
+
+
+if __name__ == '__main__':
+    from fire import Fire
+    Fire(main)
+