fix linting/formatting

src/dnaapler/__init__.py

@@ -9,10 +9,13 @@
 from loguru import logger
 
 from dnaapler.utils.all import all_process_MMseqs2_output_and_reorient
-from dnaapler.utils.bulk import bulk_process_MMseqs2_output_and_reorient, run_bulk_MMseqs2
+from dnaapler.utils.bulk import (
+    bulk_process_MMseqs2_output_and_reorient,
+    run_bulk_MMseqs2,
+)
 from dnaapler.utils.cds_methods import (
-    run_MMseqs2_based_method,
     run_largest,
+    run_MMseqs2_based_method,
     run_mystery,
     run_nearest,
 )
@@ -24,7 +27,7 @@
     end_dnaapler,
     get_version,
     print_citation,
-    run_autocomplete
+    run_autocomplete,
 )
 from dnaapler.utils.validation import (
     check_evalue,
@@ -527,15 +530,14 @@ def custom(
     custom_database = os.path.join(db_dir, "custom_db")
 
     makeMMseqs2db = ExternalTool(
-            tool="mmseqs",
-            input=f"createdb {custom_db_fasta}",
-            output=f" {custom_database}",
-            logdir=logdir,
-        )
+        tool="mmseqs",
+        input=f"createdb {custom_db_fasta}",
+        output=f" {custom_database}",
+        logdir=logdir,
+    )
 
     ExternalTool.run_tool(makeMMseqs2db, ctx)
 
-
     # runs and processes MMseqs2
     MMseqs2_success = run_MMseqs2_based_method(
         ctx, input, output, prefix, gene, evalue, threads
@@ -787,11 +789,11 @@ def bulk(
             custom_database = os.path.join(db_dir, "custom_db")
 
             makeMMseqs2db = ExternalTool(
-            tool="mmseqs",
-            input=f"createdb {custom_db_fasta}",
-            output=f" {custom_database}",
-            logdir=logdir,
-        )
+                tool="mmseqs",
+                input=f"createdb {custom_db_fasta}",
+                output=f" {custom_database}",
+                logdir=logdir,
+            )
 
             ExternalTool.run_tool(makeMMseqs2db, ctx)
 

src/dnaapler/utils/all.py

@@ -35,10 +35,10 @@ def all_process_MMseqs2_output_and_reorient(
     :return:
     """
 
-    # define colnames - keep the same colnames as BLAST for ease 
+    # define colnames - keep the same colnames as BLAST for ease
     # matches the MMseqs2 ones to make subbing MMseqs2 for BLAST as easy as possible
     # MMseqs2_columns = "query,qlen,target,tlen,alnlen,qstart,qend,tstart,tend,fident,nident,gapopen,mismatch,evalue,bits,qaln,taln"
-        
+
     col_list = [
         "qseqid",
         "qlen",

src/dnaapler/utils/bulk.py

@@ -11,6 +11,7 @@
 from dnaapler.utils.processing import reorient_single_record_bulk
 from dnaapler.utils.validation import validate_custom_db_fasta
 
+
 def run_bulk_MMseqs2(
     ctx,
     input: Path,
@@ -69,7 +70,7 @@ def run_bulk_MMseqs2(
         # matches the MMseqs2 ones to make subbing MMseqs2 for BLAST as easy as possible
         MMseqs2_columns = "query,qlen,target,tlen,alnlen,qstart,qend,tstart,tend,fident,nident,gapopen,mismatch,evalue,bits,qaln,taln"
         db = os.path.join(DNAAPLER_DB, db_name)
-           
+
     elif gene == "custom":
         # validates custom fasta input for database
         validate_custom_db_fasta(Path(custom_db))
@@ -90,19 +91,18 @@ def run_bulk_MMseqs2(
 
         db = custom_database
 
-
     MMseqs2 = ExternalTool(
-            tool="mmseqs easy-search",
-            input=f"{input} {db}",
-            output=f"{MMseqs2_output_file}",
-            params=f"{MMseqs2_output_tmpdir} --search-type 2  --threads {threads} -e {evalue} --format-output {MMseqs2_columns}",
-            logdir=logdir,
-        )
+        tool="mmseqs easy-search",
+        input=f"{input} {db}",
+        output=f"{MMseqs2_output_file}",
+        params=f"{MMseqs2_output_tmpdir} --search-type 2  --threads {threads} -e {evalue} --format-output {MMseqs2_columns}",
+        logdir=logdir,
+    )
 
     ExternalTool.run_tool(MMseqs2, ctx)
     from dnaapler.utils.util import remove_directory
-    remove_directory(MMseqs2_output_tmpdir)
 
+    remove_directory(MMseqs2_output_tmpdir)
 
 
 def bulk_process_MMseqs2_output_and_reorient(

src/dnaapler/utils/cds_methods.py

@@ -231,22 +231,20 @@ def run_MMseqs2_based_method(
     # matches the blast ones to make subbing MMseqs2 for BLAST as easy as possible
     MMseqs2_columns = "query,qlen,target,tlen,alnlen,qstart,qend,tstart,tend,fident,nident,gapopen,mismatch,evalue,bits,qaln,taln"
 
-
     db = os.path.join(DNAAPLER_DB, db_name)
     if gene == "custom":
         db = os.path.join(output, "custom_db", "custom_db")
 
     # run MMseqs2 easy-search
     MMseqs2 = ExternalTool(
-            tool="mmseqs easy-search",
-            input=f"{input} {db}",
-            output=f"{MMseqs2_output_file}",
-            params=f"{MMseqs2_output_tmpdir} --search-type 2  --threads {threads} -e {evalue} --format-output {MMseqs2_columns}",
-            logdir=logdir,
-        )
+        tool="mmseqs easy-search",
+        input=f"{input} {db}",
+        output=f"{MMseqs2_output_file}",
+        params=f"{MMseqs2_output_tmpdir} --search-type 2  --threads {threads} -e {evalue} --format-output {MMseqs2_columns}",
+        logdir=logdir,
+    )
 
     ExternalTool.run_tool(MMseqs2, ctx)
-
 
     # reorient the genome based on the MMseqs22 hit
     output_processed_file = os.path.join(output, f"{prefix}_reoriented.fasta")
@@ -289,26 +287,26 @@ def run_MMseqs2_based_method_bulk(
     MMseqs2_output_tmpdir = Path(f"{output}/tmp_MMseqs2_output")
     MMseqs2_output_file = Path(f"{output}/{prefix}_MMseqs2_output.txt")
     # matches the blast ones to make subbing MMseqs2 for BLAST as easy as possible
-    # qaln and taln are the translated alignments 
+    # qaln and taln are the translated alignments
     MMseqs2_columns = "query,qlen,target,tlen,alnlen,qstart,qend,tstart,tend,fident,nident,gapopen,mismatch,evalue,bits,qaln,taln"
 
     db = os.path.join(DNAAPLER_DB, db_name)
     if gene == "custom":
         db = os.path.join(output, "custom_db", "custom_db")
 
-
     # MMSeqs2 easy-search
     MMseqs2 = ExternalTool(
-            tool="mmseqs easy-search ",
-            input=f"{input} {db}",
-            output=f"{MMseqs2_output_file}",
-            params=f"{MMseqs2_output_tmpdir} --search-type 2 --threads {threads} -e {evalue} --format-output {MMseqs2_columns}",
-            logdir=logdir,
-        )
+        tool="mmseqs easy-search ",
+        input=f"{input} {db}",
+        output=f"{MMseqs2_output_file}",
+        params=f"{MMseqs2_output_tmpdir} --search-type 2 --threads {threads} -e {evalue} --format-output {MMseqs2_columns}",
+        logdir=logdir,
+    )
 
     ExternalTool.run_tool(MMseqs2, ctx)
 
     from dnaapler.utils.util import remove_directory
+
     remove_directory(MMseqs2_output_tmpdir)
 
     # reorient the genome based on the MMseqs2 hit
@@ -318,4 +316,3 @@ def run_MMseqs2_based_method_bulk(
     )
 
     return MMseqs2_success
-

src/dnaapler/utils/external_tools.py

@@ -42,7 +42,7 @@ def command_as_str(self) -> str:
 
     @staticmethod
     def _build_command(tool: str, input: str, output: str, params: str) -> List[str]:
-        command = f"{tool} {input} {output} {params}"# this is how mmseqs does it
+        command = f"{tool} {input} {output} {params}"  # this is how mmseqs does it
         print(command)
         escaped_command = shlex.split(command)
         return escaped_command

src/dnaapler/utils/processing.py

@@ -29,7 +29,7 @@ def process_MMseqs2_output_and_reorient(
 
     # define colnames
     col_list = [
-        "qseqid",     
+        "qseqid",
         "qlen",
         "sseqid",
         "slen",
@@ -88,7 +88,9 @@ def process_MMseqs2_output_and_reorient(
     # https://github.com/gbouras13/dnaapler/issues/44
 
     else:
-        if MMseqs2_df["qseq"][0][0] in ["M", "V", "L"] and (MMseqs2_df["sstart"][0] == 1):
+        if MMseqs2_df["qseq"][0][0] in ["M", "V", "L"] and (
+            MMseqs2_df["sstart"][0] == 1
+        ):
             reorient_sequence(MMseqs2_df, input, out_file, gene, overlapping_orf=False)
         else:  # this will reorient the sequence with the orf that overlaps the tophit by the most
             # warn if the top hit doesnt begin with a valid start codon

src/dnaapler/utils/util.py

@@ -3,11 +3,11 @@
 """
 
 import os
+import shutil
 import subprocess as sp
 import sys
 import time
 from pathlib import Path
-import shutil
 
 import click
 import pyrodigal
@@ -119,7 +119,6 @@ def check_mmseqs2_version():
     message = "Checking MMseqs2 installation."
     logger.info(message)
     try:
-
         process = sp.Popen(["mmseqs"], stdout=sp.PIPE, stderr=sp.STDOUT)
         mmseqs_out, _ = process.communicate()
         mmseqs_out = mmseqs_out.decode()
@@ -129,7 +128,7 @@ def check_mmseqs2_version():
                 break
         else:
             raise ValueError("MMseqs2 version not found")
-        
+
         mmseqs_major_version = int(mmseqs_version.split(".")[0])
         mmseqs_minor_version = mmseqs_version.split(".")[1]
 
@@ -139,7 +138,7 @@ def check_mmseqs2_version():
 
         if mmseqs_major_version != 15:
             logger.error("MMseqs2 is the wrong version. Please install v15.6f452")
-        if mmseqs_minor_version != '6f452':
+        if mmseqs_minor_version != "6f452":
             logger.error("MMseqs2 is the wrong version. Please install v15.6f452")
 
         logger.info("MMseqs2 version is ok.")
@@ -226,6 +225,7 @@ def check_duplicate_headers(fasta_file: Path) -> None:
             header_set.add(header)
     # if it finished it will be fine
 
+
 def remove_directory(dir_path: Path) -> None:
     """
     Remove a directory and all its contents if it exists.
@@ -237,4 +237,4 @@ def remove_directory(dir_path: Path) -> None:
         None
     """
     if dir_path.exists():
-        shutil.rmtree(dir_path)
+        shutil.rmtree(dir_path)

tests/test_dnaapler.py

@@ -167,7 +167,9 @@ def test_process_MMseqs2_output_and_reorient_invalid_MMseqs2_file(self):
 
     def test_process_MMseqs2_output_and_reorient_already_oriented(self):
         # Test scenario where the MMseqs2 output suggests the contig is already oriented correctly
-        MMseqs2_file = os.path.join(test_data, "SAOMS1_MMseqs2_output_already_oriented.txt")
+        MMseqs2_file = os.path.join(
+            test_data, "SAOMS1_MMseqs2_output_already_oriented.txt"
+        )
         input = os.path.join(test_data, "SAOMS1.fasta")
         output = os.path.join(test_data, "fake_reoriented.fasta")
         gene = "terL"
@@ -272,5 +274,3 @@ def test_evalue_nearest(self):
         ctx = "1"
         param = "2"
         val = validate_choice_autocomplete(ctx, param, value)
-
-

tests/test_overall.py

@@ -384,7 +384,6 @@ def test_bulk_phage_with_chrom(self):
             cmd = f"dnaapler bulk -m chromosome -i {input_fasta} -o {outdir} -t 1 -f"
             exec_command(cmd)
 
-
     def test_all_autocomplete_mystery_too_small(self):
         """test all where the autocompletion mystery fails as the contig has < 4 CDS"""
         with self.assertRaises(RuntimeError):