Minor fixes

Author: albidgy

flic_src/modules/extract_fasta.py

@@ -1,6 +1,7 @@
 import os
 from collections import defaultdict
 
+
 D_OF_COMPLEMENT = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G', 'N': 'N', '-': '-'}
 
 
@@ -107,10 +108,8 @@ def extract_transcripts_seq(file_isoform_coords, d_of_gene_coords, d_of_fasta, o
             transcript_seq = d_of_fasta[chrom][start:stop]
             correct_transcript_seq = change_introns_to_gap(transcript_seq, splice_sites, start)
             # add 5'- and 3'-gaps
-            correct_transcript_seq = (['-'] * compare_starts_ends(start, d_of_gene_coords[gene_id][
-                0])) + correct_transcript_seq
-            correct_transcript_seq = correct_transcript_seq + (
-                    ['-'] * compare_starts_ends(stop, d_of_gene_coords[gene_id][1]))
+            correct_transcript_seq = (['-'] * compare_starts_ends(start, d_of_gene_coords[gene_id][0])) + correct_transcript_seq
+            correct_transcript_seq = correct_transcript_seq + (['-'] * compare_starts_ends(stop, d_of_gene_coords[gene_id][1]))
 
             if orientation == '-':
                 correct_transcript_seq = complement(correct_transcript_seq)

flic_src/modules/make_genes_from_iso.py

@@ -197,7 +197,7 @@ def read_annot_file(annot_file):
     return d_of_annot_genes
 
 
-def intersection_with_genes(gene_coords, d_of_ref):
+def intersection_with_genes(gene_coords, d_of_ref, counter_unassigned_genes):
     start_gene, stop_gene = gene_coords
 
     for key, gene_id in d_of_ref.items():
@@ -211,10 +211,11 @@ def intersection_with_genes(gene_coords, d_of_ref):
 
         if prop_intersection >= 0.8:
             return gene_id
-    return 'unassigned_gene'
+    return f'unassigned_gene_{str(counter_unassigned_genes)}'
 
 
 def move_geneids_from_annot(annot_file, genes_file, out_dir):
+    counter_unassigned_genes = 1
     out_fname = f'{out_dir}final_results/{os.path.basename(genes_file)}'
     os.mkdir(f'{out_dir}final_results/')
 
@@ -229,8 +230,11 @@ def move_geneids_from_annot(annot_file, genes_file, out_dir):
             start = int(line_l[2])
             stop = int(line_l[4])
 
-            gene_id = intersection_with_genes((start, stop), d_annot_file[chrom_and_orientation])
+            gene_id = intersection_with_genes((start, stop), d_annot_file[chrom_and_orientation],
+                                              counter_unassigned_genes)
             line_l.append(gene_id)
+            if gene_id.startswith('unassigned_gene_'):
+                counter_unassigned_genes += 1
 
             with open(out_fname, 'a') as ouf:
                 ouf.write('\t'.join(line_l) + '\n')

flic_src/run_flic.py

@@ -64,7 +64,7 @@ def run_tool():
 
     cagefightr_res_dir = find_start_polya.find_starts_polya(bam_dir, arguments.ref_fasta,
                                                             arguments.output_dir)
-    dirs_for_delete.append(os.path.split(os.path.abspath(cagefightr_res_dir)))
+    dirs_for_delete.append(os.path.split(os.path.abspath(cagefightr_res_dir))[0])
 
     for changed_splice_file in os.listdir(changed_splice_sites_dir):
         iso_dir = make_iso.create_isoforms(cagefightr_res_dir, changed_splice_sites_dir,

setup.py

@@ -7,7 +7,7 @@
     author='Alexandra Kasianova',
     author_email='[email protected]',
     url='https://github.com/albidgy/FLIC',
-    description='A tool for reconstruction of splicing isoform from transcription start site to polyA site',
+    description='A tool for isoform reconstruction based on long reads',
     license='MIT',
     install_requires=['joblib', 'networkx', 'numpy'],
     packages=['flic_src', 'flic_src/modules', 'flic_src/scripts'],