fix bugs

LabShengLi · Jun 12, 2023 · d1a7fd5 · d1a7fd5
1 parent 54300b9
commit d1a7fd5
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 4 deletions.
diff --git a/modules/ENVCHECK.nf b/modules/ENVCHECK.nf
@@ -80,7 +80,9 @@ process ENVCHECK {
 			## for folder, use ln, note this is a link to a folder
 			## find_dir=$( readlink -f !{reference_genome} )
 			## Copy reference genome, avoid singularity/docker access out data problem
-			cp -f -L !{reference_genome}/*   !{params.GENOME_DIR}/
+			## cp -f -L !{reference_genome}/*   !{params.GENOME_DIR}/
+			find !{reference_genome}/ -maxdepth 1 -type f  | \
+				parallel -j0 cp -f -L {} !{params.GENOME_DIR}/
 		else
 			echo "### ERROR: not recognized reference_genome=!{reference_genome}"
 			exit -1

diff --git a/utils/modbam2bed_extract_read_cpg.py b/utils/modbam2bed_extract_read_cpg.py
@@ -57,13 +57,21 @@ def process_modbam2bed(input_bam, chr_list, reference_fasta, output_bed, canon_t
                                 continue
                             ### Filter out CpG sites
                             if ref_strand == "+":
-                                reference_base = reference_fasta.fetch(chr_name, ref_pos, ref_pos + 2).upper()
+                                try:
+                                    reference_base = reference_fasta.fetch(chr_name, ref_pos, ref_pos + 2).upper()
+                                except:
+                                    continue
                             elif ref_strand == "-":
                                 # For "-" strand, get the reverse complement of the reference sequence
-                                reference_base = reverse_complement(
-                                    reference_fasta.fetch(chr_name, ref_pos - 1, ref_pos + 1)).upper()
+                                try:
+                                    reference_base = reverse_complement(
+                                        reference_fasta.fetch(chr_name, ref_pos - 1, ref_pos + 1)).upper()
+                                except:
+                                    continue
                             else:
+                                reference_base = "NANA"
                                 print("ref_strand is not correct!")
+
                             if reference_base in ['CG' or 'GC']:
                                 if prob_mod < canon_threshold:  # Extract canon_read and label as 0
                                     # read_data.append([chr_name, ref_pos, ref_pos + 1, read_id, prob_mod, ref_strand, 0])