include test data

src/Afanc/_version.py

@@ -1 +1 @@
-__version__="v0.7-alpha"
+__version__="0.8a-alpha"

src/Afanc/autodatabase/assemblyQC.py

@@ -15,7 +15,20 @@ def mash(args, taxon_id, fastas):
     """
 
     mashdist_out = path.abspath(f"{taxon_id}_mashdist.txt")
-    mash_sketchline = f"mash sketch -o ref {' '.join(fastas)}"
+
+    ## WORKING SKETCHBLOCK ##
+    # for fa in fastas:
+    #     mash_sketchline = f"mash sketch -o ref {fa}"
+    #     command(mash_sketchline, "MASH").run_comm_quiet(0, args.stdout, args.stderr)
+    #
+    # mash_distline = f"mash dist *msh> {mashdist_out}"
+    # command(mash_distline, "MASH").run_comm_quiet(0, args.stdout, args.stderr)
+
+    ## OLD SKETCHBLOCK ##
+    ## take only the first 1000 fastas for mash distance
+    ## this is to avoid max args OS errors
+    ## not ideal, but if large numbers of assemblies exist for a single tip level taxa, then it could be further split
+    mash_sketchline = f"mash sketch -o ref {' '.join(fastas[:500])}"
     mash_distline = f"mash dist ref.msh ref.msh > {mashdist_out}"
     command(mash_sketchline, "MASH").run_comm_quiet(0, args.stdout, args.stderr)
     command(mash_distline, "MASH").run_comm_quiet(0, args.stdout, args.stderr)
@@ -101,6 +114,6 @@ def fastaMove(args, calcArray, tax, modeVal, modeRange):
     # write to file list of high quality assemblies
     cleanList = str(tax[0]) + "_clean.txt"
     with open(cleanList, "w") as file_out:
-        for elem in cleanFasta:
-            move(elem, args.cleanFasta_WDir)
-            # file_out.write("%s\n" % elem)
+        for fasta in cleanFasta:
+            move(fasta, args.cleanFasta_WDir)
+            file_out.write(f"{fasta}\n")

src/Afanc/autodatabase/runFuncs.py

@@ -178,6 +178,7 @@ def makeK2db(args):
 def makeKronaChart(args):
     from Afanc.utilities.runCommands import command
 
+    ## TODO: Fix this module for custom taxonomy
     subprocessID = "KRONA"
     vprint(
         subprocessID,

src/Afanc/autodatabase/taxadd.py

@@ -37,10 +37,9 @@ def addTaxon(taxname, mother_clade_taxid, names_df, nodes_df):
     to the database.
     """
 
-    ## max_taxid increased by a factor of 10 to it's length - 1
-    ## this should avoid future conflicts
+    ## max_taxid increased by 1
     max_taxid = max(names_df[0])
-    taxid = max_taxid + ( 10**(len(str(max_taxid))-1) )
+    taxid = int(max_taxid + 1)
 
     ## hacky way of dealing with this, but anything above species level should not be getting introduced into the tax db anyway
     if taxname.count(" ")>1:
@@ -88,7 +87,7 @@ def getTaxidNames(taxname, mother_clade, names_df, nodes_df):
     ## block for dealing with taxon missing from the ncbi taxonomy database
     if taxid == None:
 
-        print(f"Cannot find {taxname} in ncbi taxonomy database.")
+        # print(f"Cannot find {taxname} in ncbi taxonomy database.")
 
         ###  TAXADD BLOCK  ###
         ### IN DEVELOPMENT ###
@@ -97,13 +96,13 @@ def getTaxidNames(taxname, mother_clade, names_df, nodes_df):
         if mother_clade != None:
             ## find taxid for the mother clade
             mother_clade_unformatted = mother_clade.replace("_", " ")
-            print(f"Attempting to find {mother_clade_unformatted} in ncbi taxonomy database...", end=" ")
+            # print(f"Attempting to find {mother_clade_unformatted} in ncbi taxonomy database...", end=" ")
             mother_taxid = search_taxon(mother_clade_unformatted, names_df)
 
             ## if no taxon exists for the mother clade, find taxid for the genus
             if mother_taxid == None:
                 genus = mother_clade.split("_")[0]
-                print(f"Attempting to find {genus} in ncbi taxonomy database...")
+                # print(f"Attempting to find {genus} in ncbi taxonomy database...")
                 genus_taxid = search_taxon(genus, names_df)
 
                 ## if the genus does not exist within the ncbi taxonomy database, then call a fail
@@ -112,18 +111,18 @@ def getTaxidNames(taxname, mother_clade, names_df, nodes_df):
 
                 ## else if the genus does exist within the database, add both the mother and daughter taxa
                 else:
-                    print(f"Found {genus_taxid}.", end="\n")
+                    # print(f"Found {genus_taxid}.", end="\n")
                     mother_taxid, names_df, nodes_df = addTaxon(mother_clade_unformatted, genus_taxid, names_df, nodes_df)
                     taxid, names_df, nodes_df = addTaxon(taxname, mother_taxid, names_df, nodes_df)
 
             else:
-                print(f"Found {mother_taxid}.", end="\n")
+                # print(f"Found {mother_taxid}.", end="\n")
                 taxid, names_df, nodes_df = addTaxon(taxname, mother_taxid, names_df, nodes_df)
 
         ## if no mother clade is given, try to find the genus in the taxonomy database
         else:
             genus = taxname.split(" ")[0]
-            print(f"Attempting to find genus {genus} in ncbi taxonomy database...", end=" ")
+            # print(f"Attempting to find genus {genus} in ncbi taxonomy database...", end=" ")
             genus_taxid = search_taxon(genus, names_df)
 
             ## if the genus does not exist within the ncbi taxonomy database, then call a fail
@@ -132,7 +131,7 @@ def getTaxidNames(taxname, mother_clade, names_df, nodes_df):
 
             ## else if the genus does exist within the database, add both the mother and daughter taxa
             else:
-                print(f"Found {genus_taxid}.", end="\n")
+                # print(f"Found {genus_taxid}.", end="\n")
                 taxid, names_df, nodes_df = addTaxon(taxname, genus_taxid, names_df, nodes_df)
 
 

src/Afanc/parser.py

@@ -99,9 +99,9 @@ def initLogFiles(args):
 
 parser_autodb.add_argument('-n', '--ncbi_date',
     type=checkDate,
-    default="2020-05-01",
+    default="2022-05-01",
     action='store',
-    help='The date of NCBI taxonomy to download. Must be of the form YYYY-05-MM. Default=2020-05-01.')
+    help='The date of NCBI taxonomy to download. Must be of the form YYYY-05-MM. Default=2022-05-01.')
 
 parser_autodb.add_argument('-m', '--mode_range',
     type=float,

src/Afanc/screen/report/parseK2report.py

@@ -3,7 +3,6 @@
 from os import path
 
 from Afanc.screen.tree import Tree
-from Afanc.utilities.generalUtils import gendbdict
 
 
 def parseK2line(line):
@@ -186,6 +185,10 @@ def parseK2reportMain(args, dbdict):
 
     base_nodes, root_node = readK2report(report_path)
     best_hits = find_best_hit(root_node, args.pct_threshold, args.num_threshold, args.local_threshold)
+
+    if len(best_hits) == 0:
+        return None
+
     out_json = makeJson(best_hits, args.output_prefix, args.reportsDir, args.pct_threshold, args.num_threshold, args.local_threshold, dbdict)
 
     return out_json