support of multiple width values 1 per fasta

README.md

@@ -1,4 +1,4 @@
-# bioinfo_gui_scripts [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5795514.svg)](https://doi.org/10.5281/zenodo.5795514)
+# bioinfo_gui_scripts 
 python scripts that can be easily transformed to gui programs for wet lab scientists to use(see the wiki page for documentation and depedences)
 ## GUI stadalone programs(.exe)
 1. DSSP statistics GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4838997.svg)](https://doi.org/10.5281/zenodo.4838997)
@@ -15,7 +15,7 @@ python scripts that can be easily transformed to gui programs for wet lab scient
 12. tab to fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5703366.svg)](https://doi.org/10.5281/zenodo.5703366)
 13. single-fastas to tabular GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5672075.svg)](https://doi.org/10.5281/zenodo.5672075)
 14. tabular file to single-fastas GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5652249.svg)](https://doi.org/10.5281/zenodo.5652249)
-15. fasta formatter GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5786883.svg)](https://doi.org/10.5281/zenodo.5786883)
+15. fasta formatter GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5799390.svg)](https://doi.org/10.5281/zenodo.5799390)
 16. chain pdb to fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5706468.svg)](https://doi.org/10.5281/zenodo.5706468)
 17. subset pdb to fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5725658.svg)](https://doi.org/10.5281/zenodo.5725658)
 18. trim fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5794123.svg)](https://doi.org/10.5281/zenodo.5794123)

fasta_manipulation/fasta_formatter_gui.py

@@ -2,16 +2,18 @@
 import os
 from gooey import *
 from Bio import SeqIO
+import pandas as pd
 import sys
 # input parameters
 @Gooey(required_cols=0, program_name= 'fasta formatter', header_bg_color= '#DCDCDC', terminal_font_color= '#DCDCDC', terminal_panel_color= '#DCDCDC')
 def main():
     ap = GooeyParser(description="changes the width of sequences line in 1 or many FASTA files")
     ap.add_argument("-in", "--input", required=False, widget="FileChooser", help="input fasta file")
+    ap.add_argument("-txt", "--txt", required=False, widget="FileChooser", help="input txt file with 2 columns 1) file name (without extension), 2) width")
     ap.add_argument("-out", "--output", required=False, widget="FileSaver", help="output fasta file")
     ap.add_argument("-dir", "--directory", required=False, type=str, widget='DirChooser', help="directory to search for fasta files")
     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")
+    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, 3) .txt file with fasta file names and width for each file. Default is 1")
     args = vars(ap.parse_args())
     # main
     # create function to split the input sequence based on a specific number of characters
@@ -24,16 +26,30 @@ def split_every_width(s,w): return [s[i:i+w] for i in range(0,len(s),w)]
                 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:
+    elif args['program'] == 2:
         # import each fasta file from the working directory
-        for filename in sorted(os.listdir(os.chdir(args['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()
+    else:
+        df = pd.read_csv(args['txt'], header=None, sep="\t")
+        # select ids and widths columns, convert to lists
+        headers = df.iloc[:,0].values.tolist()
+        widths = df.iloc[:,1].values.tolist()
+        # iter elements on pairs to export to fasta
+        for (a,b) in zip(headers, widths):
+            # export to new fasta files with the user imported width value
+            sys.stdout = open(''.join([str(a),"_","w",str(b),".fasta"]), 'a')
+            for record in SeqIO.parse(''.join([str(a),".fasta"]),'fasta'):
+                print(">"+record.id)
+                print('\n'.join(split_every_width(str(record.seq), int(b)))) # add characters in new line after the number of characters surpasses the input width 
+            sys.stdout.close()
 
+
 if __name__ == '__main__':
     main()