Merge branch 'main' into stable

CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## [2.2.1](https://github.com/brsynth/rpfbagr/tree/2.2.1) (2022-08-25)
+
+[Full Changelog](https://github.com/brsynth/rpfbagr/compare/2.2.0...2.2.1)
+
 ## [2.2.0](https://github.com/brsynth/rpfbagr/tree/2.2.0) (2022-08-24)
 
 [Full Changelog](https://github.com/brsynth/rpfbagr/compare/2.1.0...2.2.0)

src/rpfbagr/__main__.py

@@ -1,11 +1,8 @@
 import argparse
-import getpass
 import logging
 import os
 import sys
-import tempfile
 
-os.environ["XDG_CACHE_HOME"] = tempfile.TemporaryDirectory().name
 from rpfbagr.medium import associate_flux_env, load_medium
 from rpfbagr.metabolic import gene_ko, gene_ou
 from rpfbagr.preprocess import build_model, genes_annotate, save_results
@@ -158,18 +155,6 @@ def main():
         logger.debug("Create out directory: %s")
         os.makedirs(os.path.dirname(args.output_file_tsv))
 
-    try:
-        getpass.getuser()
-    except Exception as e:
-        if args.email:
-            os.environ["USERNAME"] = args.email
-        else:
-            logger.error(str(e))
-            logger.error(
-                "A login name must be provided for Cameo with --email argument"
-            )
-            parser.exit(1)
-
     # Load model
     logger.info("Build model")
     model = build_model(
@@ -225,7 +210,7 @@ def main():
     if res is not None:
         if args.email and args.strategy == "ko":
             logger.info("Perform gene annotation")
-            res = genes_annotate(model=model, df=res, email=args.email)
+            res = genes_annotate(model=model, df=res, email=args.email, logger=logger)
         logger.info("Save results")
         if args.output_file_csv:
             save_results(res, path=args.output_file_csv, sep=",")

src/rpfbagr/_version.py

@@ -1,2 +1,2 @@
 __app_name__ = "rpfbagr"
-__version__ = "2.2.0"
+__version__ = "2.2.1"

src/rpfbagr/preprocess.py

@@ -1,5 +1,6 @@
 import ast
 import logging
+import time
 from typing import Dict
 
 import pandas as pd
@@ -44,10 +45,16 @@ def build_model(
     return model
 
 
-def genes_annotate(model: Model, df: pd.DataFrame, email: str) -> pd.DataFrame:
+def genes_annotate(
+    model: Model,
+    df: pd.DataFrame,
+    email: str,
+    logger: logging.Logger,
+) -> pd.DataFrame:
 
     if df.empty:
         return df
+    is_ncbi_error = False
     Entrez.email = email
     cache: Dict[str, str] = {}
     for ix in df.index:
@@ -64,26 +71,30 @@ def genes_annotate(model: Model, df: pd.DataFrame, email: str) -> pd.DataFrame:
                 model_gene = model.genes.get_by_id(gene)
                 ncbi_gene = model_gene.annotation.get("ncbigene", "")
                 if gene not in cache.keys():
-                    if ncbi_gene == "":
-                        label = gene
-                    else:
-                        hd = Entrez.esummary(db="gene", id=ncbi_gene)
-                        rec = Entrez.read(hd, validate=False)
-                        rec = rec.get("DocumentSummarySet", {})
-                        rec = rec.get("DocumentSummary", [])
-                        label = gene
-                        if len(rec) > 0:
-                            name = rec[0].get("Name", "")
-                            name = name.replace(",", "")
-                            desc = rec[0].get("Description", "")
-                            desc = desc.replace(",", "")
-                            syn = rec[0].get("OtherAliases", "")
-                            syn = syn.replace(",", "")
-                            label = "%s=%s - %s" % (name, syn, desc)
+                    label = gene
+                    if ncbi_gene != "":
+                        try:
+                            hd = Entrez.esummary(db="gene", id=ncbi_gene)
+                            rec = Entrez.read(hd, validate=False)
+                            rec = rec.get("DocumentSummarySet", {})
+                            rec = rec.get("DocumentSummary", [])
+                            if len(rec) > 0:
+                                name = rec[0].get("Name", "")
+                                name = name.replace(",", "")
+                                desc = rec[0].get("Description", "")
+                                desc = desc.replace(",", "")
+                                syn = rec[0].get("OtherAliases", "")
+                                syn = syn.replace(",", "")
+                                label = "%s=%s - %s" % (name, syn, desc)
+                            time.sleep(2)
+                        except Exception:
+                            is_ncbi_error = True
                     cache[gene] = label
                 labels.append(cache[gene])
             labels_groups.append("(%s)" % (",".join(labels),))
         df.at[ix, "genes_annotation"] = ",".join(labels_groups)
+    if is_ncbi_error:
+        logger.warning("NCBI annotation failing for some items")
     return df