grammar correction and reformatting

Author: mark0428

README.md

@@ -50,7 +50,7 @@ Datasets for training and testing are stored in the `data` folder. Please specif
 
 ### User-Specified Data:
 
-AMPlify only accepts 20 standard amino acids. However, if the user specifies the stop codon with adding a asterisk character to the end of the peptide sequences, AMPlify would ignore the last character of the peptides and allow them to be participate in the training or inference stages.
+AMPlify only accepts the 20 standard amino acids. However, if the user specifies a stop codon by adding an asterisk character to the end of a peptide sequence, AMPlify will ignore the last character and allow the peptide to participate in the training or inference stage.
 
 ### Pre-trained sub-models
 

src/AMPlify.py

@@ -200,11 +200,12 @@ def main():
     valid_ix = []
     for i in range(len(peptide)):
         if len(peptide[i]) <= 200 and len(peptide[i]) >= 2:
-            if set(peptide[i])-set(aa) == set() or (set(peptide[i][:-1])-set(aa)==set() and peptide[i][-1]=='*'): # either does not contain nonstandard amino acids or the last character is '*'
+            if set(peptide[i])-set(aa) == set() or (set(peptide[i][:-1])-set(aa) == set() and peptide[i][-1] == '*'):
+                # either does not contain nonstandard amino acids or the last character is '*'
                 valid_ix.append(i)
 
     # select valid sequences for prediction
-    peptide_valid = [peptide[i] if peptide[i][-1]!="*" else peptide[i][:-1] for i in valid_ix]
+    peptide_valid = [peptide[i] if peptide[i][-1] != '*' else peptide[i][:-1] for i in valid_ix]
 
     # generate one-hot encoding input and pad sequences into MAX_LEN long
     X_seq_valid = one_hot_padding(peptide_valid, MAX_LEN)