Update Preinput_Merge.py

Preinput_Merge.py

@@ -1,6 +1,9 @@
+import re
+
 from tname import *
 from Rfile import *
 
+
 def Strip(seq_file):
     contents = j_reads(seq_file.name)
     ina = Name()
@@ -25,7 +28,7 @@ def Merge(smi_file, seq_file):
     smile = j_read(smi_file.name)
     smile = smile.strip("\n")
 
-    # 读取去掉空格后的文件
+    # 读取去掉换行后的文件
     contents = j_reads(seq_file.name)
 
     name = Name()
@@ -47,3 +50,34 @@ def Merge(smi_file, seq_file):
                 # 写入序列
                 f3.write(contents[i])
     return name
+
+
+def Merge_All(smi_file, seq_file):
+    smile = j_read(smi_file.name)
+    smile = smile.strip("\n")
+
+    # 读取去掉换行后的文件
+    contents = j_reads(seq_file.name)
+
+    name = Name()
+    name = name + r"kcat_input.tsv"  # 结果文件名称
+
+    with open(name, "a") as f3:
+        f3.write("Substrate Name	Substrate SMILES	Protein Sequence")
+        f3.write("\n")
+
+    for i in range(0, len(contents)):
+        if i % 2 == 1:
+            with open(name, "a") as f3:
+                # 写入索引
+                # f3.write(">seq" + str(int((i - 1) / 2)))
+                info = re.sub(' ', '_', contents[i - 1])
+                info = re.sub('\n', '', info)
+                f3.write(info)
+                f3.write("\t")
+                # 写入smile名称
+                f3.write(smile)
+                f3.write("\t")
+                # 写入序列
+                f3.write(contents[i])
+    return name