mgnify-pipelines-toolkit 1.0.6__py3-none-any.whl → 1.0.8__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py

@@ -401,12 +401,10 @@ def retrieve_regions(
         region_counter = defaultdict(int)
 
         regions_to_remove = []
-
         for model, value in multiregion_matches.items():
             marker_gene = determine_marker_gene(determine_domain(model))
             for region in value:
                 region_counter[f"{marker_gene}.{region}"] += 1
-
         for region, count in region_counter.items():
             if count < MIN_SEQ_COUNT:
                 regions_to_remove.append(region)
@@ -421,6 +419,8 @@ def retrieve_regions(
         for model, value in multiregion_matches.items():
             new_value = []
             for region in value:
+                if region == "":
+                    continue
                 marker_gene = determine_marker_gene(determine_domain(model))
                 full_region = f"{marker_gene}.{region}"
                 if full_region not in regions_to_remove:
@@ -463,6 +463,9 @@ def retrieve_regions(
             for key, value in temp_seq_counter.items():
                 seq_per_variable_region_count.setdefault(key, 0)
                 seq_per_variable_region_count[key] += value
+        else:
+            logging.info("No output will be produced - the run is ambiguous.")
+            continue
 
     json_outfile = "{}.json".format(outfile_prefix)
     tsv_outfile = "{}.tsv".format(outfile_prefix)

mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_cazys.py

@@ -52,7 +52,7 @@ def main():
 
 def load_gff(gff):
     genome_gff_lines = dict()
-    with fileinput.hook_compressed(gff, "rt") as gff:
+    with fileinput.hook_compressed(gff, "r", encoding="utf-8") as gff:
         for line in gff:
             if line.startswith("##FASTA"):
                 return genome_gff_lines
@@ -81,7 +81,7 @@ def load_gff(gff):
 def print_gff(overview_file, outfile, dbcan_version, substrates, genome_gff_lines):
     with open(outfile, "w") as file_out:
         file_out.write("##gff-version 3\n")
-        with fileinput.hook_compressed(overview_file, "rt") as file_in:
+        with fileinput.hook_compressed(overview_file, "r", encoding="utf-8") as file_in:
             for line in file_in:
                 if line.startswith("MGYG") or line.startswith("ERZ"):
                     (
@@ -151,7 +151,7 @@ def print_gff(overview_file, outfile, dbcan_version, substrates, genome_gff_line
 
 def load_substrates(hmm_path):
     substrates = dict()
-    with fileinput.hook_compressed(hmm_path, "rt") as file_in:
+    with fileinput.hook_compressed(hmm_path, "r", encoding="utf-8") as file_in:
         header = next(file_in)
         header_fields = header.strip().split("\t")
         substrate_idx = header_fields.index("Substrate")

mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_clusters.py

@@ -49,7 +49,7 @@ def main():
 
 def load_cgcs(standard_path):
     cgc_locations = dict()
-    with fileinput.hook_compressed(standard_path, "rt") as file_in:
+    with fileinput.hook_compressed(standard_path, "r", encoding="utf-8") as file_in:
         for line in file_in:
             if not line.startswith("CGC#"):
                 cgc, _, contig, _, start, end, _, _ = line.strip().split("\t")
@@ -72,7 +72,7 @@ def print_gff(standard_path, outfile, dbcan_version, substrates, cgc_locations):
     with open(outfile, "w") as file_out:
         file_out.write("##gff-version 3\n")
         cgcs_printed = list()
-        with fileinput.hook_compressed(standard_path, "rt") as file_in:
+        with fileinput.hook_compressed(standard_path, "r", encoding="utf-8") as file_in:
             for line in file_in:
                 if not line.startswith("CGC#"):
                     cgc, gene_type, contig, prot_id, start, end, strand, protein_fam = (
@@ -107,7 +107,7 @@ def print_gff(standard_path, outfile, dbcan_version, substrates, cgc_locations):
 
 def load_substrates(substrate_path):
     substrates = dict()
-    with fileinput.hook_compressed(substrate_path, "rt") as file_in:
+    with fileinput.hook_compressed(substrate_path, "r", encoding="utf-8") as file_in:
         for line in file_in:
             if not line.startswith("#"):
                 parts = line.strip().split("\t")

{mgnify_pipelines_toolkit-1.0.6.dist-info → mgnify_pipelines_toolkit-1.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.6
+Version: 1.0.8
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0

{mgnify_pipelines_toolkit-1.0.6.dist-info → mgnify_pipelines_toolkit-1.0.8.dist-info}/RECORD

@@ -4,7 +4,7 @@ mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py,sha256=8qmb57E2XBrw
 mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py,sha256=2-URxvcl13_8O9bUmoa3-KMPSvdTaLbxfFDY-ycs_4M,5316
 mgnify_pipelines_toolkit/analysis/amplicon/assess_inflection_point_mcp.py,sha256=cRoHPM-VB_L3NWYgkNWuyzqIqhzwHJuU3-6BiiS2lnw,7553
 mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py,sha256=RAdqakH05Qt_LG9jlV7P2M90o5KmlAXmDFQ4X51NIBE,5387
-mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=EqfaATb5agvtQOhJqrb2YS6OxtCXvxC-q_05UzvDYug,19926
+mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=x8GmhFPT2ElAcBMeyLEBw3zYxI75fYL0xVHUPSyhw7c,20100
 mgnify_pipelines_toolkit/analysis/amplicon/find_mcp_inflection_points.py,sha256=vC3nKxggnSljfw4HNkugXbXfGvLx7XnryEE7eEGqfqs,3552
 mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=soTewFddtebW-EcejGh9whs3cBLWJrGCYdPc0KukoAw,8756
 mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=BLqhflblUegCvuQic16PrFXfIXlFWmGkmWJyl4wJoLQ,5040
@@ -21,8 +21,8 @@ mgnify_pipelines_toolkit/analysis/assembly/gff_file_utils.py,sha256=_4J31wAjK5B1
 mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py,sha256=_iaTBvMKbQDi_02_QuSPqLJ_rC37ruxiPHv5lLQmI-w,5480
 mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=eay9e3Xdc8XxnlC_4SHHjN89k-M9i_cFMc2lI_ZFxqY,5596
 mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py,sha256=uex2T6GagtYFBIc39-Xm4SFHL06KAQ5v0_loOmY_eaw,4289
-mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_cazys.py,sha256=5lbVSWRZoi61cKvuolzUJlhUBzpx8DgWMH0Vzw1HcHA,7748
-mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_clusters.py,sha256=i4uYdqY6y2ee72vl0sLkHeJvigHGKJMzdyR3HEIK1Mk,5930
+mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_cazys.py,sha256=KaJHOKfbIurbD1iiMssjdAaSAT8Nv-_ZUFwxkLqukAE,7799
+mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_clusters.py,sha256=DYZhChGD49M-zAtGkCmNHXDoVTnd5Qy6amG-oePO8Ek,5981
 mgnify_pipelines_toolkit/analysis/assembly/summarise_antismash_bgcs.py,sha256=eRAQ0vFbqnWreiBdtFuwLKve9WwYwv9dYQtD1pumaZs,10776
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py,sha256=TPaKlYkoy37_XgYNOskWCCoXtPNku_k5ygSeK4fT1VQ,6689
 mgnify_pipelines_toolkit/analysis/assembly/summarise_sanntis_bgcs.py,sha256=65szj-H8Hxy_eXy3TyTs48EhPJbJ2w1skHlVbH2YeVM,4538
@@ -48,9 +48,9 @@ mgnify_pipelines_toolkit/schemas/schemas.py,sha256=pnH8LUH8i2ACNvFNWyG-n-eIHZcI5
 mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=lgYIR1S4crURY7C7nFtgE6QMV4u4zCNsUrVkcRnsEEo,3996
 mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=aS9bWrC9CP7tpxoEVg6eEYt18-pmjG7fJl5Mchz4YOU,798
-mgnify_pipelines_toolkit-1.0.6.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.0.6.dist-info/METADATA,sha256=b9Hoo0e0xVvL4erImJgt_7gtbb-5Yx8TZNlf9KZcQIY,5810
-mgnify_pipelines_toolkit-1.0.6.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
-mgnify_pipelines_toolkit-1.0.6.dist-info/entry_points.txt,sha256=T8soGT2to8c_qafw-0itqCn4sjOnxlfaNWHIaHz4H54,3416
-mgnify_pipelines_toolkit-1.0.6.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.0.6.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.0.8.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.0.8.dist-info/METADATA,sha256=1hUZYUS7S2wdpK1zQdj4gVYhpUvn_-LjHi8iGb9LQ30,5810
+mgnify_pipelines_toolkit-1.0.8.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+mgnify_pipelines_toolkit-1.0.8.dist-info/entry_points.txt,sha256=T8soGT2to8c_qafw-0itqCn4sjOnxlfaNWHIaHz4H54,3416
+mgnify_pipelines_toolkit-1.0.8.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.0.8.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.0.6.dist-info → mgnify_pipelines_toolkit-1.0.8.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.0)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any