import sys import os f1 = open(sys.argv[1],"r") foutput = open(sys.argv[2],"w") dict = {} for line1 in f1: if '#' in line1: pass else: l1 = line1.rstrip() line = line1.rstrip().split("\t") GeneID = line[0] annotion = line[1:] dict[GeneID] = annotion foutput.write(GeneID + '_D1' + "\t" + annotion + "\n") f1.close() foutput.close()修改上述代码,在键后面增加字符串“_D1”
时间: 2024-01-02 13:03:51 浏览: 27
你想让我帮你修改这段代码,在键后面增加字符串“_D1”。可以这样修改:
```python
import sys
import os
f1 = open(sys.argv[1],"r")
foutput = open(sys.argv[2],"w")
dict = {}
for line1 in f1:
if '#' in line1:
pass
else:
l1 = line1.rstrip()
line = line1.rstrip().split("\t")
GeneID = line[0]
annotion = line[1:]
dict[GeneID+"_D1"] = annotion # 在键后面增加字符串“_D1”
foutput.write(GeneID + '_D1' + "\t" + "\t".join(annotion) + "\n") # 修改输出格式
f1.close()
foutput.close()
```
这样对于每个GeneID的键值后面都会增加字符串“_D1”,输出格式也做了相应的修改,把`annotion`列表中的元素用制表符`\t`拼接起来。
相关问题
import sys import os f1 = open(sys.argv[1],'r') f2 = open(sys.argv[2],'r') fout = open(sys.argv[3],'w') dic1 = {} for line1 in f1: tmp1 = line1.strip().split("\t") Gene_ID = tmp1[0] anno = tmp1[1:] dic1[Gene_ID] = anno dic2 = {} for line2 in f2: tmp2 = line2.strip().split("\t") Gene_ID = tmp2[0] gene_name = tmp2[1] dic2[Gene_ID] = gene_name for key in dic2: if key in dic1: fout.write(key + "\t" + gene_name + "\t" + anno + "\n") else: fout.write(key + "\t" + gene_name + "\t" + "NA" + "\n" ) f1.close() f2.close() fout.close(),修改fout处,实现将dic1的anno添加到dic2的键和值后一列
要将 `dic1` 的 `anno` 添加到 `dic2` 的键和值后一列,可以将 `fout.write()` 函数中的第三个参数改为 `gene_name + "\t" + dic1[key][0] + "\t" + dic1[key][1] + "\t" + dic1[key][2] + "\n"`,假设 `dic1` 中每个键对应的值有三个元素。修改后的代码如下:
```
import sys
import os
f1 = open(sys.argv[1],'r')
f2 = open(sys.argv[2],'r')
fout = open(sys.argv[3],'w')
dic1 = {}
for line1 in f1:
tmp1 = line1.strip().split("\t")
Gene_ID = tmp1[0]
anno = tmp1[1:]
dic1[Gene_ID] = anno
dic2 = {}
for line2 in f2:
tmp2 = line2.strip().split("\t")
Gene_ID = tmp2[0]
gene_name = tmp2[1]
dic2[Gene_ID] = gene_name
for key in dic2:
if key in dic1:
fout.write(key + "\t" + gene_name + "\t" + dic1[key][0] + "\t" + dic1[key][1] + "\t" + dic1[key][2] + "\n")
else:
fout.write(key + "\t" + gene_name + "\t" + "NA" + "\n" )
f1.close()
f2.close()
fout.close()
```
这样修改后,输出文件的格式为 `Gene_ID gene_name anno[0] anno[1] anno[2]`,其中 `anno[0]`、`anno[1]` 和 `anno[2]` 分别对应 `dic1` 中每个键对应的值的三个元素。
import sys import os f1 = open(sys.argv[1],'r') f2 = open(sys.argv[2],'r') f3 = open(sys.argv[3],'r') fout = open(sys.argv[4],'w') dic1 = {} for line1 in f1: tmp1 = line1.strip().split() Gene_ID = tmp1[0] # anno = tmp1[1:] # dic1[Gene_ID] = anno dic2 = {} for line2 in f2: tmp2 = line2.strip().split("\t") Gene_ID = tmp2[0] gene_name = tmp2[6] dic2[Gene_ID] = gene_name dic3 = {} for line3 in f3: tmp3 = line3.strip().split("\t") new_name = tmp3[0] raw_name = tmp3[1] dic3[new_name] = raw_name for key in dic2: if key in dic1: fout.write(key + "\t" + dic2[key] + "\n") else: fout.write(key + "\t" + dic2[key] + "\t" + "NA" + "\n" ) f1.close() f2.close() fout.close()修改代码,其中f1中只有一列数据,需要根据f1文件的内容去f2文件检索找到对应的第7列信息,由于第7列每行的字符串由逗号分割,需去掉逗号并进行换行成为新的一列,再根据新的一列信息去和f3第1列匹配,最后打印出f3中与匹配结果对应的第二列信息
import sys
import os
f1 = open(sys.argv[1],'r')
f2 = open(sys.argv[2],'r')
f3 = open(sys.argv[3],'r')
fout = open(sys.argv[4],'w')
dic2 = {}
for line2 in f2:
tmp2 = line2.strip().split("\t")
Gene_ID = tmp2[0]
gene_info = tmp2[6].replace(",", "\n")
dic2[Gene_ID] = gene_info
dic3 = {}
for line3 in f3:
tmp3 = line3.strip().split("\t")
new_name = tmp3[0]
raw_name = tmp3[1]
dic3[new_name] = raw_name
for line1 in f1:
Gene_ID = line1.strip()
if Gene_ID in dic2:
gene_info = dic2[Gene_ID].strip()
if gene_info in dic3:
fout.write(Gene_ID + "\t" + gene_info + "\t" + dic3[gene_info] + "\n")
else:
fout.write(Gene_ID + "\t" + gene_info + "\t" + "NA" + "\n")
else:
fout.write(Gene_ID + "\t" + "NA" + "\t" + "NA" + "\n")
f1.close()
f2.close()
fout.close()