Filter on viral contig length

sunbeam-labs · Oct 19, 2023 · 3049472 · 3049472
1 parent 5ce1491
commit 3049472
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/sbx_virus_id.smk b/sbx_virus_id.smk
@@ -228,7 +228,7 @@ rule virsorter:
         "envs/virsorter_env.yml"
     shell:
         """
-        virsorter run -w {params.out_dir} -i {input.contigs} -j {threads} all
+        virsorter run -w {params.out_dir} -i {input.contigs} --min-length 1000 -j {threads} all
         """
 
 

diff --git a/scripts/filter_virsorter_contigs.py b/scripts/filter_virsorter_contigs.py
@@ -0,0 +1,6 @@
+from sunbeamlib.parse import parse_fasta, write_fasta
+
+# This does nothing but I'm leaving it in case we want to add custom filtering here later
+with open(snakemake.input.contigs) as f_contigs, open(snakemake.output[0], "w") as f_out:
+    for header_str, seq_str in parse_fasta(f_contigs):
+        write_fasta((header_str, seq_str), f_out)