Updating EUKulele to v2.0.7

AlexanderLabWHOI · Dec 5, 2023 · 9758d60 · 9758d60
1 parent 7281263
commit 9758d60
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 12 deletions.
diff --git a/recipe/meta.yaml b/recipe/meta.yaml
@@ -1,6 +1,6 @@
 package:
   name: eukulele
-  version: 2.0.5
+  version: 2.0.7
 
 build:
   noarch: python
@@ -28,7 +28,6 @@ requirements:
     - pytest-cov
     - pytest-xdist
     - blast
-#    - busco==4.1.4
     - diamond 
     - transdecoder
     - wget
@@ -52,7 +51,6 @@ requirements:
     - pytest-cov
     - pytest-xdist
     - blast 
- #   - busco==4.0.6 
     - diamond 
     - transdecoder
     - wget

diff --git a/src/EUKulele/EUKulele_main.py b/src/EUKulele/EUKulele_main.py
@@ -236,8 +236,12 @@ def main(args_in):
             prot_tab = os.path.join(reference_dir, "prot-map.json")
         f = open(os.path.join(output_dir, "README_DB.txt"), "a")
         e = datetime.datetime.now()
+        filename = os.path.join(os.path.dirname(os.path.realpath(__file__)),
+                                "static", "VERSION")
+        file_read = open(filename, "r")
+        f.write("The version of EUKulele was "+str(file_read.read())+".\n")
         f.write("Time finished was " + str(e) + " for database " + \
-                str(args.database.lower()))
+                str(args.database.lower())+"\n")
 
         ## Next, see whether there is a subdirectory of reference
         ## directory containing folder for our DB name

diff --git a/src/EUKulele/tax_placement.py b/src/EUKulele/tax_placement.py
@@ -130,16 +130,12 @@ def match_maker(dd, consensus_cutoff, consensus_proportion, tax_dict, use_counts
 
     ambiguous = 0 # we assume unambiguous
     md = dd.bitscore.max() * consensus_proportion #0.97 
-    #dd.bitscore.max() #dd.pident.max()
     transcript_name = set(list(dd["qseqid"]))
     if len(transcript_name) > 1:
         print("More than 1 transcript name included in the group.", flush = True)
     transcript_name = list(transcript_name)[0]
     ds = list(set(dd[dd.bitscore>=md]['ssqid_TAXID']))
     counts = list(set(dd[dd.bitscore>=md]['counts']))
-    #maxpident = md #max(list(set(dd[dd.pident==md]['pident'])))
-    #ds = list(set(dd[dd.bitscore==md]['ssqid_TAXID']))
-    #counts = list(set(dd[dd.bitscore==md]['counts']))
     maxpident = max(list(set(dd[dd.bitscore>=md]['pident'])))
 
     if len(counts) >= 1:
@@ -150,7 +146,10 @@ def match_maker(dd, consensus_cutoff, consensus_proportion, tax_dict, use_counts
                         # most specific taxonomic level assigned
     if len(ds)==1:
         if ds[0] not in tax_dict:
-            return pd.DataFrame(columns=['transcript_name','classification_level',
+            return pd.DataFrame([[transcript_name, assignment,\
+                              "MissingFromTaxDict", "MissingFromTaxDict", md,\
+                              chosen_count, ambiguous]],
+                                columns=['transcript_name','classification_level',
                                          'full_classification','classification',
                                          'max_pid','counts','ambiguous'])
         full_classification = str(tax_dict[ds[0]]).split(";")[0:level]
@@ -163,9 +162,11 @@ def match_maker(dd, consensus_cutoff, consensus_proportion, tax_dict, use_counts
         full_classification_0 = []
         for d in ds:
             if d not in tax_dict:
-                return(pd.DataFrame(columns=['transcript_name','classification_level',
-                                             'full_classification','classification',
-                                             'max_pid','counts','ambiguous']))
+                classification_0.append("MissingFromTaxDict")
+                full_classification_0.append("MissingFromTaxDict")
+                #return(pd.DataFrame(columns=['transcript_name','classification_level',
+                #                             'full_classification','classification',
+                #                             'max_pid','counts','ambiguous']))
             d_full_class = str(tax_dict[str(d)]).split(";")[0:level]
             classification_0.append(d_full_class[len(d_full_class) - 1])
                         # the most specific taxonomic level we can classify by