fixing up species #210 and added new env var for mlst #214

Author: kristyhoran

bohra/bohra.nf

@@ -85,6 +85,7 @@ workflow {
     READ_ANALYSIS ( reads_pe )
     read_stats = READ_ANALYSIS.out.read_stats
     reads_pe = READ_ANALYSIS.out.reads_pe
+    // println reads_pe.view()
     results = results.concat( read_stats)
     versions = READ_ANALYSIS.out.version_seqkit_reads
     versions = versions.concat( READ_ANALYSIS.out.version_kmc )
@@ -208,7 +209,8 @@ workflow {
             reads = reads_pe.filter { cfg,files -> cfg.control != 'control' }.map { cfg, files -> tuple(cfg.id, cfg, files) }
             // 
             asm_tmp = asm.filter { cfg,files -> cfg.control != 'control' }.map { cfg, files -> tuple(cfg.id, cfg , files) }
-            // println reads.view()
+            println reads.view()
+            println asm_tmp.view()
             sequences = reads.join(asm_tmp, remainder:true).map( v -> { v.size() == 4 ? v[1] ? [v[1],v[2]] : [v[2],v[3]]  : [v[1],v[2]]} )
 
         } 

bohra/environments/mlst.yml

@@ -2,6 +2,6 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - mlst>=2.32.2
+  - mlst>=2.35
   - csvtk
   - pandas

bohra/launcher/BohraTyping.py

@@ -48,12 +48,16 @@ def _missing_reads(input_table: pd.DataFrame) -> bool:
 
 def _setup_typing_args(kwargs:dict, command:dict, mtb:False) -> dict:
 
-    typing_dbs = ["blast_db", "data_dir", "mobsuite_db"]
+    # typing_dbs = ["mlst_dbdir", "mobsuite_db"]
+    typing_dbs = {
+        "blastdb": f"{kwargs['mlst_dbdir']}/blast/mlst.fa",
+        "datadir":f"{kwargs['mlst_dbdir']}/pubmlst",
+        "mobsuite_db": f"{kwargs['mobsuite_db']}"}
     input_table = _open_input_file(kwargs['input_file'])
     command = _setup_assembly_args(kwargs, command, mtb)
     command['modules'].append('typing')
     for d in typing_dbs:
-        db = _check_databases(path = kwargs[d], dtbtype = d)
+        db = _check_databases(path = typing_dbs[d], dtbtype = d)
         command["params"].append(db)
 
     exclude = eval(kwargs['mlst_exclude'])

bohra/launcher/Utils.py

@@ -412,15 +412,15 @@ def _get_run_cmd_options() -> dict:
         "amr_typing": [
 
             {
-                "name":"blast_db",
-                "help":"Path to the mlst blast_db, defaults to what is installed in the environment.",
-                "default":f"{os.getenv('BLAST_DB', '')}"
-            },
-            {
-                "name":"data_dir",
-                "help":"Path to the mlst datadir, defaults to what is installed in the environment.",
-                "default":f"{os.getenv('PUBMLST_DB','')}"
-            },
+                "name":"mlst_dbdir",
+                "help":"Path to the mlst blast and publmlst, defaults to what is installed in the environment.",
+                "default":f"{os.getenv('MLST_DBDIR', '')}"
+            },
+            # {
+            #     "name":"data_dir",
+            #     "help":"Path to the mlst datadir, defaults to what is installed in the environment.",
+            #     "default":f"{os.getenv('PUBMLST_DB','')}"
+            # },
             {
                 "name":"mlst_exclude",
                 "short_name":"-me",

bohra/modules/collation/bin/collate_kraken2.py

@@ -26,7 +26,11 @@
 try:
     sp = pd.read_csv(f"{sys.argv[2]}", sep = "\t", header = None, names = ["perc","cumulative",'direct','rank','taxon_id','name'])
     sp['name'] = sp['name'].apply(lambda x: x.strip())
-    uc = sp[sp['rank'] == "U"]['perc'].values[0]
+    uc = sp[sp['rank'] == "U"]
+    if uc.shape[0] == 0:
+        uc = 0
+    else:
+        uc = uc['perc'].values[0]
     print(uc)
     spc = sp[sp['rank'] == "S"].sort_values(['perc'], ascending = False).head(3)
     print(spc)
@@ -42,8 +46,10 @@
         levs = levs +1
 
     df = pd.DataFrame(res, index = [0])
-    print(df[["Isolate","Unclassified (%)","Match 1","Detected_1 (%)","Match 2","Detected_2 (%)","Match 3","Detected_3 (%)"]])
-    df[["Isolate","Unclassified (%)","Match 1","Detected_1 (%)","Match 2","Detected_2 (%)","Match 3","Detected_3 (%)"]].to_csv(f"{sys.argv[3]}", sep = "\t", index = False)
+    cols = ["Isolate","Unclassified (%)","Match 1","Detected_1 (%)","Match 2","Detected_2 (%)","Match 3","Detected_3 (%)"]
+    cols = [i for i in cols if i in df.columns.tolist()]
+    print(df[cols])
+    df[cols].to_csv(f"{sys.argv[3]}", sep = "\t", index = False)
 except Exception as e:
     print(f"Something has gone wrong opening the kraken report: {e}")