fix bug in make_plasmid_summary which was messing up references

README.md

@@ -13,7 +13,7 @@ config:
   layout: elk
 ---
 flowchart LR
-SnapGene ==> Plasmids[17k+ plasmids]
+SnapGene ==> Plasmids[~14k plasmids]
 AddGene ==> Plasmids
 Plasmids ==> Sites[extracted att sites]
 Plasmids ==> SequenceFeatures[extracted sequence features]

make_feature_dict.py

@@ -51,6 +51,8 @@
 import json
 from Bio import SeqIO
 from Bio.SeqFeature import SeqFeature
+import warnings
+from tqdm import tqdm
 
 
 def main(plasmid_summary_file, plasmid_site_dict_file, output_file):
@@ -60,7 +62,7 @@ def main(plasmid_summary_file, plasmid_site_dict_file, output_file):
     with open(plasmid_site_dict_file) as f:
         plasmid_site_dict = json.load(f)
 
-    for plasmid in plasmid_summary:
+    for plasmid in tqdm(plasmid_summary, desc="Extracting plasmid features"):
         # If no att sites, skip and remove from plasmid summary
         if len(plasmid_site_dict[plasmid["file"]]) == 0:
             plasmid_summary.remove(plasmid)
@@ -70,8 +72,10 @@ def main(plasmid_summary_file, plasmid_site_dict_file, output_file):
             with open(plasmid["file"], "br") as f:
                 record = SeqIO.read(f, "snapgene")
         elif plasmid["source"] == "addgene":
-            with open(plasmid["file"], "r") as f:
-                record = SeqIO.read(f, "genbank")
+            with warnings.catch_warnings():
+                warnings.simplefilter("ignore")
+                with open(plasmid["file"], "r") as f:
+                    record = SeqIO.read(f, "genbank")
         features: list[SeqFeature] = record.features
         plasmid["att_sites"] = list(sorted(plasmid_site_dict[plasmid["file"]].keys()))
         plasmid["features"] = set()

make_plasmid_site_dict.py

@@ -19,6 +19,8 @@
 import json
 import re
 import glob
+import warnings
+from tqdm import tqdm
 
 
 def main(input_folder, output_file):
@@ -29,11 +31,13 @@ def main(input_folder, output_file):
 
     out_dict = dict()
 
-    for file in files:
+    for file in tqdm(files, desc="Processing plasmid files"):
         plasmid_dict = dict()
 
         file_format = "snapgene" if file.split(".")[-1] == "dna" else "genbank"
-        plasmid_record = SeqIO.read(file, file_format)
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore")
+            plasmid_record = SeqIO.read(file, file_format)
 
         # Find att sites
         for feature in plasmid_record.features:

make_plasmid_summary.py

@@ -31,18 +31,23 @@ def main(
     input_folder, output_file, all_gateway_plasmids, addgene_kits, addgene_articles
 ):
     addgene_id2name = dict()
+    addgene_id2reference_id = dict()
     with open(all_gateway_plasmids) as f:
         for line in f:
             addgene_id, name = line.strip().split("\t")[:2]
             addgene_id2name[addgene_id] = name
+            reference_id = line.strip().split("\t")[2:]
+            addgene_id2reference_id[addgene_id] = (
+                reference_id[0] if len(reference_id) > 0 else None
+            )
 
-    addgene_id2references = dict()
+    reference_id2reference_links = dict()
     with open(addgene_articles) as f:
         for line in f:
             ls = line.strip().split("\t")
             addgene_id = ls[0]
             references = ls[1:]
-            addgene_id2references[addgene_id] = references
+            reference_id2reference_links[addgene_id] = references
 
     addgene_id2kit = dict()
     with open(addgene_kits) as f:
@@ -75,8 +80,12 @@ def main(
             plasmid_dict["plasmid_name"] = addgene_id2name[addgene_id]
             plasmid_dict["sequence-type"] = basename.split(".")[1]
             plasmid_dict["addgene_id"] = addgene_id
-            if addgene_id in addgene_id2references:
-                plasmid_dict["references"] = addgene_id2references[addgene_id]
+            if addgene_id in addgene_id2reference_id:
+                reference_id = addgene_id2reference_id[addgene_id]
+                if reference_id is not None:
+                    plasmid_dict["references"] = reference_id2reference_links[
+                        reference_id
+                    ]
             else:
                 plasmid_dict["references"] = []
             if addgene_id in addgene_id2kit:

pyproject.toml

@@ -11,6 +11,7 @@ python = "^3.12"
 biopython = "^1.84"
 pydna = "^5.2.0"
 pandas = "^2.2.3"
+tqdm = "^4.67.0"
 
 
 [tool.poetry.group.playwright.dependencies]