added support for many fasta files

README.md

@@ -1,2 +1,2 @@
-# biomisc [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5762316.svg)](https://doi.org/10.5281/zenodo.5762316)
+# biomisc 
 collection of  miscellaneous command line bioinformatic scripts(see the wiki page for documentation and depedences) 

fasta_manipulation/fasta_formatter.py

@@ -1,19 +1,34 @@
 # python3
+import os
 import argparse
 from Bio import SeqIO
 import sys
 # input parameters
-ap = argparse.ArgumentParser(description="changes the width of sequences line in a FASTA file")
-ap.add_argument("-in", "--input", required=True, help="input fasta file")
-ap.add_argument("-out", "--output", required=True, help="output fasta file")
+ap = argparse.ArgumentParser(description="changes the width of sequences line in 1 or many FASTA files")
+ap.add_argument("-in", "--input", required=False, help="input fasta file")
+ap.add_argument("-out", "--output", required=False, help="output fasta file")
 ap.add_argument("-width", "--width", required=False, type=int, default=80, help="number of characters per line. Default 80")
+ap.add_argument("-pro", "--program", required=False, type=int, default=1, help="program to choose. 1) one input/output fasta file, 2) many input/output fasta files. Default is 1")
 args = vars(ap.parse_args())
 # main
 # create function to split the input sequence based on a specific number of characters
-def split_every_width(s): return [s[i:i+args['width']] for i in range(0,len(s),args['width'])]
-# export to a new fasta file
-sys.stdout = open(args['output'], 'a')
-for record in SeqIO.parse(args['input'],'fasta'):
-	print(">"+record.id)
-	print('\n'.join(split_every_width(str(record.seq)))) # add characters in new line after the number of characters surpasses the input width 
-sys.stdout.close()
+def split_every_width(s,w): return [s[i:i+w] for i in range(0,len(s),w)]
+# choose program
+if args['program'] == 1:
+    # export to a new fasta file
+    sys.stdout = open(args['output'], 'a')
+    for record in SeqIO.parse(args['input'],'fasta'):
+            print(">"+record.id)
+            print('\n'.join(split_every_width(str(record.seq), args['width']))) # add characters in new line after the number of characters surpasses the input width 
+    sys.stdout.close()
+else:
+    # import each fasta file from the working directory
+    for filename in sorted(os.listdir(str(os.getcwd()))):
+        if filename.endswith(".fa") or filename.endswith(".fasta"):
+            # export to new fasta files with the user imported width value
+            sys.stdout = open(''.join([filename.split(".")[0],"_","w",str(args['width']),".fasta"]), 'a')
+            for record in SeqIO.parse(filename,'fasta'):
+                    print(">"+record.id)
+                    print('\n'.join(split_every_width(str(record.seq), args['width']))) # add characters in new line after the number of characters surpasses the input width 
+            sys.stdout.close()
+

fasta_manipulation/fasta_formatter_many_fasta.py

@@ -0,0 +1,24 @@
+# python3
+import os
+import argparse
+from Bio import SeqIO
+import sys
+# input parameters
+ap = argparse.ArgumentParser(description="changes the width of sequences line in multiple FASTA file by specifying either the width")
+ap.add_argument("-w", "--width", required=False, type=int, default=80, help="number of characters per line. Default 80")
+args = vars(ap.parse_args())
+# main
+# create function to split the input sequence based on a specific number of characters
+def split_every_width(s,w): return [s[i:i+w] for i in range(0,len(s),w)]
+# setup empty list 
+names = []
+# import each fasta file from the working directory
+for filename in sorted(os.listdir(str(os.getcwd()))):
+    if filename.endswith(".fa") or filename.endswith(".fasta"):
+        # export to new fasta files with the user imported width value
+        sys.stdout = open(''.join([filename.split(".")[0],"_","w",str(args['width']),".fasta"]), 'a')
+        for record in SeqIO.parse(filename,'fasta'):
+                print(">"+record.id)
+                print('\n'.join(split_every_width(str(record.seq), args['width']))) # add characters in new line after the number of characters surpasses the input width 
+        sys.stdout.close()
+