Update embed script to remove Other types

zellerlab · Mar 17, 2022 · 3cac963 · 3cac963
1 parent ac9faf6
commit 3cac963
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/src/embed/__main__.py b/src/embed/__main__.py
@@ -135,9 +135,9 @@ def load_mibig_records(path):
  Bio.SeqIO.write(record, gbk, "genbank")
  Bio.SeqIO.write(record, fna, "fasta")
 
- types = ";".join(sorted(mibig_meta[bgc_id]["biosyn_class"]))
+ types = ";".join(sorted(ty for ty in mibig_meta[bgc_id]["biosyn_class"] if ty != "Other"))
  if types == "Nucleoside": # fix bad annotation of BGC0000880 in MIBiG 1.3 JSON
- types = "Other" 
+ types = "Unknown"
  print(record.id, bgc_id, insert_loc, insert_loc + len(bgc_gbk), types, file=tsv, sep="\t")
 
  print("Skipped", n_skipped, "GenBank records that were not in metadata")

diff --git a/src/embed/requirements.txt b/src/embed/requirements.txt
@@ -0,0 +1,2 @@
+biopython >=1.79
+tqdm >=2