tabular and multi/single fasta conversion

README.md

@@ -5,11 +5,15 @@ python scripts that can be easily transformed to gui programs for wet lab scient
 2. DSSP statistics by chain GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4891916.svg)](https://doi.org/10.5281/zenodo.4891916)
 3. DSSP tabular by chain GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4839987.svg)](https://doi.org/10.5281/zenodo.4839987)
 4. add adapters by pair GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5201840.svg)](https://doi.org/10.5281/zenodo.5201840)
-5. Extract or remove sequences from fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5213003.svg)](https://doi.org/10.5281/zenodo.5213003)
+5. extract or remove sequences from fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5703246.svg)](https://doi.org/10.5281/zenodo.5703246)
 6. FASTA subset by length GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5218645.svg)](https://doi.org/10.5281/zenodo.5218645)
 7. select header or fasta by aa GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5218741.svg)](https://doi.org/10.5281/zenodo.5218741)
 8. amino acids content multifasta calculator GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5275827.svg)](https://doi.org/10.5281/zenodo.5275827)
 9. pdbs secondary structure statistics GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5348006.svg)](https://doi.org/10.5281/zenodo.5348006)
 10. add adapters on single-fastas GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5559117.svg)](https://doi.org/10.5281/zenodo.5559117)
 11. Trim multi-fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5565197.svg)](https://doi.org/10.5281/zenodo.5565197)
-12. Trim single-fastas GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5565299.svg)](https://doi.org/10.5281/zenodo.5565299)
+12. Trim single-fastas GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5565299.svg)](https://doi.org/10.5281/zenodo.5565299)
+13. fasta to tab GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5699003.svg)](https://doi.org/10.5281/zenodo.5699003)
+14. tab to fasta GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5703366.svg)](https://doi.org/10.5281/zenodo.5703366)
+15. single-fastas to tabular GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5672075.svg)](https://doi.org/10.5281/zenodo.5672075)
+16. tabular file to single-fastas GUI: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5652249.svg)](https://doi.org/10.5281/zenodo.5652249)

fasta_manipulation/extract_or_remove_seqs_from_fasta_gui.py

@@ -1,13 +1,15 @@
 # python3
 from gooey import *
 from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.SeqRecord import SeqRecord
 # input parameters
-@Gooey(required_cols=3, program_name= 'extract or remove sequences from fasta', header_bg_color= '#DCDCDC', terminal_font_color= '#DCDCDC', terminal_panel_color= '#DCDCDC')
+@Gooey(required_cols=2, program_name= 'extract or remove sequences from fasta', header_bg_color= '#DCDCDC', terminal_font_color= '#DCDCDC', terminal_panel_color= '#DCDCDC')
 def main():
     ap = GooeyParser(description="use a txt file with fasta headers to extract or remove sequences from fasta file")
     ap.add_argument("-in", "--input", required=True, widget='FileChooser', help="input fasta file")
-    ap.add_argument("-out", "--output", required=True, widget='FileSaver', help="output fasta file")
-    ap.add_argument("-pro", "--program",type=int, default=1, required=False, help="choose to exract or remove(1. extract, 2. remove. Defaults to 1)")
+    ap.add_argument("-out", "--output", required=False, widget='FileSaver', help="output fasta file")
+    ap.add_argument("-pro", "--program",type=int, default=1, required=False, help="choose to exract or remove( 1) extract, 2) remove, 3) extract and export as single-fasta files, 4) remove and export as single-fasta files. Defaults to 1)")
     ap.add_argument("-headers", "--headers", required=True, widget='FileChooser', help="file with fasta headers to retrieve the output fasta sequences")
     args = vars(ap.parse_args())
     # main
@@ -27,12 +29,26 @@ def main():
                 if seq.id in wanted:
                     SeqIO.write([seq], f, "fasta")
     # remove
-    elif program == 2:
+    if program == 2:
         fasta_sequences = SeqIO.parse(open(args['input']),'fasta')
         with open(args['output'], "w") as f:
             for seq in fasta_sequences:
                 if seq.id not in wanted:
                     SeqIO.write([seq], f, "fasta")
+    # extract and export as single-fasta files
+    if program == 3:
+        fasta_sequences = SeqIO.parse(open(args['input']),'fasta')
+        for seq in fasta_sequences:
+            if seq.id in wanted:
+                record = SeqRecord(Seq(str(seq.seq)),id=str(seq.id),description="")
+                SeqIO.write(record, "".join([str(seq.id),".fasta"]), "fasta")
+    # remove and export as single-fasta files
+    if program == 4:
+        fasta_sequences = SeqIO.parse(open(args['input']),'fasta')
+        for seq in fasta_sequences:
+            if seq.id not in wanted:
+                record = SeqRecord(Seq(str(seq.seq)),id=str(seq.id),description="")
+                SeqIO.write(record, "".join([str(seq.id),".fasta"]), "fasta")
 
 if __name__ == '__main__':
     main()

fasta_manipulation/singlefastas_to_tab_gui.py

@@ -0,0 +1,33 @@
+# python3
+from gooey import * 
+import os
+from Bio import SeqIO
+import pandas as pd
+# imput parameters
+@Gooey(required_cols=2, program_name='single-fastas to tabular txt file', header_bg_color= '#DCDCDC', terminal_font_color= '#DCDCDC', terminal_panel_color= '#DCDCDC')
+def main():
+	ap = GooeyParser()
+	ap.add_argument("-dir", "--directory", required=True, type=str, widget='DirChooser', help="directory to search for fasta files")
+	ap.add_argument("-out","--output", required=True, widget='FileSaver', help="output txt file")
+	args = vars(ap.parse_args())
+# main
+	seqs = []
+	ids = [] # setup empty lists
+# import each fasta file from the working directory
+	for filename in sorted(os.listdir(os.chdir(args['directory']))):
+		if filename.endswith(".fa") or filename.endswith(".fasta"):
+			for record in SeqIO.parse(filename, "fasta"):
+				ids.append(record.id)
+				seqs.append(record.seq)
+# put the 2 list in a data frame of 2 columns
+	dfasta = pd.DataFrame()
+	dfasta['id'] = ids
+	dfasta['seq'] = seqs
+# export data frame to a tabular txt file
+	with open(args['output'], 'a') as f:
+	    f.write(
+	        dfasta.to_csv(header = False, index = False, sep= "\t", line_terminator= '\n')
+	    )
+
+if __name__ == '__main__':
+    main()

fasta_manipulation/tab_to_fasta_gui.py

@@ -4,12 +4,12 @@
 # input parameters
 @Gooey(required_cols=2, program_name='tab to fasta', header_bg_color= '#DCDCDC', terminal_font_color= '#DCDCDC', terminal_panel_color= '#DCDCDC')
 def main():
-  ap = GooeyParser(description="converts a tabular file with identifier and sequence, into a fasta file")
-  ap.add_argument("-in", "--input", required=True, widget='FileChooser', help="input tab seperated file")
-  ap.add_argument("-out", "--output", required=True, widget='FileSaver', help="output fasta file")                                                                  
-  args = vars(ap.parse_args())
-  # main
-  count = SeqIO.convert(args['input'], "tab", args['output'], "fasta")
+    ap = GooeyParser(description="converts a tabular file with identifier and sequence, into a fasta file")
+    ap.add_argument("-in", "--input", required=True, widget='FileChooser', help="input tab seperated file")
+    ap.add_argument("-out", "--output", required=True, widget='FileSaver', help="output fasta file")                                                                  
+    args = vars(ap.parse_args())
+    # main
+    count = SeqIO.convert(args['input'], "tab", args['output'], "fasta")
 
 if __name__ == '__main__':
     main()

fasta_manipulation/tab_to_singlefastas_gui.py

@@ -0,0 +1,25 @@
+# python3
+import itertools
+from gooey import *
+from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.SeqRecord import SeqRecord
+import pandas as pd
+# input arguments
+@Gooey(required_cols=1, program_name='tabular to single-fasta files', header_bg_color= '#DCDCDC', terminal_font_color= '#DCDCDC', terminal_panel_color= '#DCDCDC')
+def main():
+    ap = GooeyParser(description="convert each row of a tabular file with the fasta headers and sequences in each row in single-fasta files")
+    ap.add_argument("-in", "--input", required=True, widget="FileChooser", help="input txt file")
+    args = vars(ap.parse_args())
+	# main
+    df = pd.read_csv(args['input'], header=None, sep="\t")
+	# select ids and sequence columns, convert to lists
+    headers = df.iloc[:,0].values.tolist()
+    sequences = df.iloc[:,1].values.tolist()
+	# iter elements on pairs to export to single-fasta files
+    for (ids, seq) in zip(headers, sequences):
+		    seq_for_fasta=SeqRecord(Seq(str(seq)),id=str(ids),description="")
+		    SeqIO.write(seq_for_fasta, "".join([str(ids),".fasta"]), "fasta")
+
+if __name__ == '__main__':
+    main()