Merge pull request #17 from mtisza1/update5

to v3.3.2, Update5

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cenotetaker3"
-version = "3.3.1"
+version = "3.3.2"
 authors = [
   { name="Mike Tisza", email="[email protected]" },
 ]

src/cenote/cenotetaker3.py

@@ -12,7 +12,7 @@
 import string
 import re
 import logging
-from distutils.spawn import find_executable
+from shutil import which
 
 def str2bool(v):
     if isinstance(v, bool):
@@ -79,7 +79,7 @@ def cenotetaker3():
 
     parentpath = Path(pathname).parents[1]
 
-    __version__ = "3.3.1"
+    __version__ = "3.3.2"
 
     Def_CPUs = os.cpu_count()
 
@@ -381,10 +381,12 @@ def check_ct3_dbs():
     ### check dependencies
     def is_tool(name):
         """Check whether `name` is on PATH."""
-        return find_executable(name) is not None
+        return which(name) is not None
 
-    tool_dep_list = ['samtools', 'minimap2', 'tRNAscan-SE', 'seqkit', 'hhblits', 
-                     'bedtools', 'phanotate.py', 'mmseqs']
+    tool_dep_list = ['samtools', 'minimap2', 
+                     'tRNAscan-SE', 'seqkit', 
+                     'hhblits', 'bedtools', 
+                     'phanotate.py', 'mmseqs']
 
     for tool in tool_dep_list:
         if not is_tool(tool):
@@ -395,12 +397,17 @@ def is_tool(name):
     reqs = subprocess.check_output([sys.executable, '-m', 'pip', 'freeze'])
     installed_packages = [r.decode().split('==')[0] for r in reqs.split()]
 
-    python_dep_list = ['pyhmmer', 'numpy', 'pandas', 'biopython', 'pyrodigal-gv']
+    python_dep_list = ['pyhmmer', 'numpy', 'pandas', 'biopython', 'pyrodigal']
 
     for pydep in python_dep_list:
         if pydep not in installed_packages:
             logger.warning(f"{pydep} not found in installed python packages. Exiting.")
             sys.exit() 
+
+    if not 'pyrodigal-gv' in installed_packages:
+        if not 'pyrodigal_gv' in installed_packages:
+            logger.warning(f"pyrodigal-gv not found in installed python packages. Exiting.")
+            sys.exit() 
 
     ## check run_title suitability
     if re.search(r'^[a-zA-Z0-9_]+$', str(args.run_title)) and \

src/cenote/python_modules/prune_virus_coords1.py

@@ -192,7 +192,7 @@ def left_cutoff(position, groupframe):
             row1["Position start"] == 0 and \
             row1["Position stop"] != (total_len + 1):
 
-                ddf = ["Chunk_" + str(i1), 
+                ddf = ["C" + str(i1), 
                        row1["Position start"], 
                        right_cutoff(row2["Window midpoint"], group)]
                 ddf_list.append(ddf)
@@ -206,11 +206,11 @@ def left_cutoff(position, groupframe):
                 rico = right_cutoff(row2["Window midpoint"], group)
 
                 if rico > leco:
-                    ddf = ["Chunk_" + str(i1), 
+                    ddf = ["C" + str(i1), 
                         left_cutoff(row1["Window midpoint"], group), 
                         right_cutoff(row2["Window midpoint"], group)]
                 else:
-                     ddf = ["Chunk_" + str(i1), row1["Window midpoint"], row2["Window midpoint"]]
+                     ddf = ["C" + str(i1), row1["Window midpoint"], row2["Window midpoint"]]
 
                 ddf_list.append(ddf)
 
@@ -219,7 +219,7 @@ def left_cutoff(position, groupframe):
             row1["Position start"] != 0 and \
             row1["Position stop"] == (total_len + 1):
 
-                ddf = ["Chunk_" + str(i1), 
+                ddf = ["C" + str(i1), 
                        left_cutoff(row1["Window midpoint"], group), 
                        row2["Position stop"]]
                 ddf_list.append(ddf)
@@ -230,7 +230,7 @@ def left_cutoff(position, groupframe):
         if merged_df.iloc[0,1] == '+' and \
             merged_df.iloc[0,2] == 0 and \
             merged_df.iloc[0,3] == (total_len + 1): #if first column last(2nd row) == last -1 then its one chunk
-                rep_list = [('Chunk_0', '0', (total_len+1))]
+                rep_list = [('C0', '0', (total_len+1))]
                 ddf_list = rep_list
         else:
                 ddf_list = ddf_list

src/cenote/python_modules/virus_summary.py

@@ -137,7 +137,7 @@
 
 summary_list = []
 for name, group in grouped_df:
-    if "Chunk" in str(name[2]):
+    if "C" in str(name[2]):
         outname = "@".join([name[0], name[2]])
     else:
         outname = name[0]