mgnify-pipelines-toolkit 0.2.2__py3-none-any.whl → 1.0.1__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py

@@ -0,0 +1,240 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import argparse
+from collections import defaultdict
+import pathlib
+import logging
+import requests
+
+import pandas as pd
+import pyfastx
+
+logging.basicConfig(level=logging.DEBUG)
+
+URL = "https://www.ebi.ac.uk/ena/portal/api/search?result"
+RUNS_URL = f"{URL}=read_run&fields=secondary_study_accession,sample_accession&limit=10&format=json&download=false"
+SAMPLES_URL = f"{URL}=sample&fields=lat,lon,collection_date,depth&limit=10&format=json&download=false"
+HEADERS = {"Accept": "application/json"}
+
+
+def parse_args():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-i",
+        "--input_path",
+        required=True,
+        type=str,
+        help="Directory where ASV files are.",
+    )
+    parser.add_argument(
+        "-r",
+        "--runs",
+        required=True,
+        type=str,
+        help="Path to CSV file containing successful analyses generated by the pipeline (columns: `run, status`)",
+    )
+    parser.add_argument(
+        "-o", "--output", required=True, type=str, help="Path to output directory."
+    )
+
+    args = parser.parse_args()
+
+    input_path = args.input_path
+    runs = args.runs
+    output = args.output
+
+    return input_path, runs, output
+
+
+def get_metadata_from_run_acc(run_acc):
+
+    query = f"{RUNS_URL}&includeAccessions={run_acc}"
+    res_run = requests.get(query, headers=HEADERS)
+
+    if res_run.status_code != 200:
+        logging.error(f"Data not found for run {run_acc}")
+        return False
+
+    sample_acc = res_run.json()[0]["sample_accession"]
+
+    query = f"{SAMPLES_URL}&includeAccessions={sample_acc}"
+    res_sample = requests.get(query, headers=HEADERS)
+
+    full_res_dict = res_run.json()[0] | res_sample.json()[0]
+
+    fields_to_clean = ["lat", "lon", "depth"]
+
+    for field in fields_to_clean:
+        val = full_res_dict[field]
+        if val == "":
+            full_res_dict[field] = "NA"
+
+    if full_res_dict["collection_date"] == "":
+        full_res_dict["collectionDate"] = "NA"
+    else:
+        full_res_dict["collectionDate"] = full_res_dict["collection_date"]
+
+    del full_res_dict["collection_date"]
+
+    res_df = pd.DataFrame(full_res_dict, index=[0])
+    res_df.columns = [
+        "RunID",
+        "SampleID",
+        "StudyID",
+        "decimalLongitude",
+        "depth",
+        "decimalLatitude",
+        "collectionDate",
+    ]
+
+    return res_df
+
+
+def get_all_metadata_from_runs(runs):
+
+    run_metadata_dict = defaultdict(dict)
+
+    for run in runs:
+        res_df = get_metadata_from_run_acc(run)
+        if res_df is not False:
+            run_metadata_dict[run] = res_df
+
+    return run_metadata_dict
+
+
+def cleanup_taxa(df):
+
+    df.pop("Kingdom")
+    cleaned_df = df.rename(columns={"Superkingdom": "Kingdom", "asv": "ASVID"})
+
+    ranks = ["Kingdom", "Phylum", "Class", "Order", "Family", "Genus", "Species"]
+
+    for rank in ranks:
+        cleaned_df[rank] = cleaned_df[rank].apply(
+            lambda x: x.split("__")[1] if pd.notnull(x) else "NA"
+        )
+
+    for rank in ranks:
+        cleaned_df[rank] = cleaned_df[rank].apply(lambda x: x if x != "" else "NA")
+
+    cleaned_df = cleaned_df[
+        [
+            "ASVID",
+            "StudyID",
+            "SampleID",
+            "RunID",
+            "decimalLongitude",
+            "decimalLatitude",
+            "depth",
+            "collectionDate",
+            "Kingdom",
+            "Phylum",
+            "Class",
+            "Order",
+            "Family",
+            "Genus",
+            "Species",
+            "ASVSeq",
+        ]
+    ]
+
+    return cleaned_df
+
+
+def get_asv_dict(runs_df, root_path):
+
+    asv_dict = {}
+    for i in range(0, len(runs_df)):
+        run_acc = runs_df.loc[i, "run"]
+        status = runs_df.loc[i, "status"]
+
+        if status != "all_results":
+            continue
+
+        tax_file = sorted(
+            list(
+                (pathlib.Path(root_path) / run_acc / "asv").glob(
+                    "*_DADA2-SILVA_asv_tax.tsv"
+                )
+            )
+        )[0]
+        count_files = sorted(
+            list(pathlib.Path(f"{root_path}/{run_acc}/asv").glob("*S-V*/*.tsv"))
+        )
+
+        asv_fasta_file = sorted(
+            list(pathlib.Path(f"{root_path}/{run_acc}/asv").glob("*_asv_seqs.fasta"))
+        )[0]
+        fasta = pyfastx.Fasta(str(asv_fasta_file), build_index=False)
+        asv_fasta_dict = {name: seq for name, seq in fasta}
+        asv_fasta_df = pd.DataFrame(asv_fasta_dict, index=["ASVSeq"]).transpose()
+        asv_fasta_df["asv"] = asv_fasta_df.index
+        run_tax_df = pd.read_csv(tax_file, sep="\t")
+
+        count_dfs = []
+
+        for count_file in count_files:
+            count_df = pd.read_csv(count_file, sep="\t")
+            count_dfs.append(count_df)
+
+        all_ampregions_count_df = pd.concat(count_dfs)
+        merged_df = all_ampregions_count_df.merge(
+            run_tax_df, left_on="asv", right_on="ASV"
+        )
+        merged_df.pop("ASV")
+        run_col = [run_acc] * len(merged_df)
+        merged_df["RunID"] = run_col
+        merged_df = merged_df.merge(asv_fasta_df, on="asv")
+        asv_dict[run_acc] = merged_df
+
+    return asv_dict
+
+
+def main():
+
+    input_path, runs, output = parse_args()
+
+    root_path = pathlib.Path(input_path)
+
+    if not root_path.exists():
+        logging.error(f"Results path does not exist: {root_path}")
+        exit(1)
+
+    runs_df = pd.read_csv(runs, names=["run", "status"])
+
+    all_runs = runs_df.run.to_list()
+    run_metadata_dict = get_all_metadata_from_runs(all_runs)
+    asv_dict = get_asv_dict(runs_df, root_path)
+
+    all_merged_df = []
+
+    for run in all_runs:
+        if run in asv_dict.keys() and run in run_metadata_dict.keys():
+            run_asv_data = asv_dict[run]
+            run_metadata = run_metadata_dict[run]
+            run_merged_result = run_metadata.merge(run_asv_data, on="RunID")
+            all_merged_df.append(run_merged_result)
+
+    final_df = pd.concat(all_merged_df, ignore_index=True)
+    final_df = cleanup_taxa(final_df)
+
+    final_df.to_csv(f"{output}_dwcready.csv", index=False, na_rep="NA")
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/analysis/shared/get_subunits.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.py

@@ -1,7 +1,9 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
+import shutil
+from shutil import SameFileError
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -33,6 +35,7 @@ from mgnify_pipelines_toolkit.schemas.schemas import (
     AmpliconNonINSDCPassedRunsSchema,
     TaxonSchema,
     PR2TaxonSchema,
+    validate_dataframe,
 )
 
 logging.basicConfig(level=logging.DEBUG)
@@ -127,9 +130,9 @@ def parse_one_tax_file(
     # Two different schemas used for validation depending on the database
     # because PR2 schema has different taxonomic ranks than the standard
     if len(long_tax_ranks) == 8:
-        TaxonSchema(res_df)
+        validate_dataframe(res_df, TaxonSchema, str(tax_file))
     elif len(long_tax_ranks) == 9:
-        PR2TaxonSchema(res_df)
+        validate_dataframe(res_df, PR2TaxonSchema, str(tax_file))
 
     res_df["full_taxon"] = res_df.iloc[:, 1:].apply(
         lambda x: ";".join(x).strip(";"), axis=1
@@ -205,9 +208,7 @@ def generate_db_summary(
                 amp_region_dict[amp_region].append(amp_region_df)
 
         for amp_region, amp_region_dfs in amp_region_dict.items():
-            if (
-                len(amp_region_dfs) > 1
-            ):  # Need at least two analyses with this amp_region to bother with the summary
+            if amp_region_dfs:
                 amp_res_df = amp_region_dfs[0]
                 for amp_df in amp_region_dfs[1:]:
                     amp_res_df = amp_res_df.join(amp_df, how="outer")
@@ -319,9 +320,7 @@ def summarise_analyses(
             if tax_file:
                 tax_files[run_acc] = tax_file
 
-        if (
-            len(tax_files) > 1
-        ):  # If at least two analyses have results from the current DB, generate a study-level summary for it
+        if tax_files:
             generate_db_summary(db_label, tax_files, output_prefix)
 
 
@@ -356,12 +355,12 @@ def merge_summaries(analyses_dir: str, output_prefix: str) -> None:
     :type output_prefix: str
     """
 
-    # TODO: The way we grab all the summaries might change depending on how the prefect side does things
     all_study_summaries = glob.glob(f"{analyses_dir}/*_study_summary.tsv")
 
     summaries_dict = organise_study_summaries(all_study_summaries)
 
     for db_label, summaries in summaries_dict.items():
+        merged_summary_name = f"{output_prefix}_{db_label}_study_summary.tsv"
         if len(summaries) > 1:
             res_df = pd.read_csv(summaries[0], sep="\t", index_col=0)
             for summary in summaries[1:]:
@@ -372,10 +371,18 @@ def merge_summaries(analyses_dir: str, output_prefix: str) -> None:
 
             res_df = res_df.reindex(sorted(res_df.columns), axis=1)
             res_df.to_csv(
-                f"{output_prefix}_{db_label}_study_summary.tsv",
+                merged_summary_name,
                 sep="\t",
                 index_label="taxonomy",
             )
+        elif len(summaries) == 1:
+            logging.info(
+                f"Only one summary ({summaries[0]}) so will use that as {merged_summary_name}"
+            )
+            try:
+                shutil.copyfile(summaries[0], merged_summary_name)
+            except SameFileError:
+                pass
 
 
 if __name__ == "__main__":

mgnify_pipelines_toolkit/constants/db_labels.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/constants/regex_fasta_header.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/constants/tax_ranks.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/constants/thresholds.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/constants/var_region_coordinates.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/schemas/schemas.py

@@ -1,7 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -14,11 +13,15 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import logging
 import re
 
 from enum import Enum
-from typing import ClassVar, Optional
+from typing import ClassVar, Optional, Type
+
+import pandas as pd
 import pandera as pa
+from pandera.typing.common import DataFrameBase
 
 from pydantic import (
     Field,
@@ -215,3 +218,18 @@ class PR2TaxonSchema(pa.DataFrameModel):
 
         dtype = PydanticModel(PR2TaxonRecord)
         coerce = True
+
+
+def validate_dataframe(
+    df: pd.DataFrame, schema: Type[pa.DataFrameModel], df_metadata: str
+) -> DataFrameBase:
+    """
+    Validate a pandas dataframe using a pandera schema.
+    df_metadata will be shown in logs on failure: example, the TSV filename from which the df was read.
+    """
+    try:
+        dfs = schema.validate(df, lazy=True)
+    except pa.errors.SchemaErrors as e:
+        logging.error(f"{schema.__name__} validation failure for {df_metadata}")
+        raise e
+    return dfs

mgnify_pipelines_toolkit/utils/fasta_to_delimited.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

mgnify_pipelines_toolkit/utils/get_mpt_version.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright 2024 EMBL - European Bioinformatics Institute
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

{mgnify_pipelines_toolkit-0.2.2.dist-info → mgnify_pipelines_toolkit-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mgnify_pipelines_toolkit
-Version: 0.2.2
+Version: 1.0.1
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -19,6 +19,7 @@ Requires-Dist: requests==2.32.3
 Requires-Dist: click==8.1.7
 Requires-Dist: pandera==0.22.1
 Requires-Dist: pyfastx>=2.2.0
+Requires-Dist: intervaltree==3.1.0
 Provides-Extra: tests
 Requires-Dist: pytest==7.4.0; extra == "tests"
 Requires-Dist: pytest-md==0.2.0; extra == "tests"

mgnify_pipelines_toolkit-1.0.1.dist-info/RECORD

@@ -0,0 +1,48 @@
+mgnify_pipelines_toolkit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py,sha256=8qmb57E2XBrwqo6YcJYyvPyuaIMu82Ifho7yyyUdnSM,6572
+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/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
+mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=Bmc4Yu8inpT6AVTG1zwxp9F9mknIDLY33-UuFdaZuq0,3756
+mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=Wu4tRtuRkgd3hoeuwPl_E5ghxIW7e_1vrcvFGWv_U4A,3173
+mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=yLpzkRJXAeXRUNgz60zopEwHcdprM2UDjquE-GkrFys,1722
+mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py,sha256=K6gniytuItq5WzHLi1BsaUCOdP4Zm0_ZzW2_ns7-BTI,11114
+mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=HarDM6ay0MbyDfGGjmxP8epjsXciAJHOmqe8G64gLuM,4258
+mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py,sha256=wXrw1B-z4hOu5oA27Vp1WYxGP2Mk6ZY4i_T5jDZgek0,6954
+mgnify_pipelines_toolkit/analysis/assembly/combined_gene_caller_merge.py,sha256=Pq-9RSt3RCxzDMQVW1VHlHF4NtpVwCWFbg2CMkvpZZc,19089
+mgnify_pipelines_toolkit/analysis/assembly/generate_gaf.py,sha256=2T4T7aXMGPac-LZUXJF3lOUzZZF50dAKkKTSaO-4idQ,3587
+mgnify_pipelines_toolkit/analysis/assembly/gff_annotation_utils.py,sha256=IlkeP4DuN7rXJIHa7o2sONHAXLhV9nGP-5Y1_0u8YQo,31393
+mgnify_pipelines_toolkit/analysis/assembly/gff_file_utils.py,sha256=8kv_6KWznOVRkeAtghLf4pxKPhAqdn36LOK4MsTz9hU,3282
+mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py,sha256=uUIo97gmzO2zzN-pYF5paIzeHWBsmmjFp7zGAhf4PKY,5021
+mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=5D-9rB3omTxKwZuS_WjgyjsaaSPNnvZoXeThofWrK7k,5452
+mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py,sha256=07CbJdpo-Gy2aglCFiu2mHbkY18pYMlLFLPnYoD7tyk,5839
+mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py,sha256=hggPqv9QawWAccm5tmru4VF9VnQAHF5LCXnqyLw_BWI,6727
+mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py,sha256=ye0Jka6_lNn4dQGb2QG3YT46y7QK0QvyaIitIaS8JVQ,4026
+mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=NhX6cSLu9QB9I5JKNUJwJVMmcRcbG-0MJCEgDJ5DxtE,4777
+mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=EH5RyzesLqsonnTQbSDs7kAOV6IskS4oyqZYlex1tAY,1934
+mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py,sha256=6Ck2NhwRWw66GctUtKDdPT5fwJhWFR_YOZq-Vxwoa8A,1996
+mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=7-U0DN1joVu0ifLOoDUK2Pfqy8rb1RDKT6khVg3jky0,5559
+mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py,sha256=sKAo_rKEyVAZXSaIFMkpSoYZxiWwXMA3XDA6Z-hbHgg,7904
+mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.py,sha256=OOqKaQmKGAya6_BZgfcWBZSVlmZ918PQTVMv6KwGIns,13827
+mgnify_pipelines_toolkit/constants/db_labels.py,sha256=omPINMylAjO2PxeFhSk2MbYNcGZH3P82optSlMey3dw,858
+mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=7nEOODQq35y9wx9YnvJuo29oBpwTpXg_kIbf_t7N4TQ,1093
+mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=G-xrc9b8zdmPTaOICD2b3RCVeFAEOVkfRkIfotQ7gek,1193
+mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=kMq__kOJcbiwsgolkdvb-XLo3WMnJdEXgedjUyMOYjI,1081
+mgnify_pipelines_toolkit/constants/thresholds.py,sha256=guDE7c4KrVJEfg_AcO_cQoJM6LGGaRlmo_U2i8d4N7g,1157
+mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=0bM4MwarFiM5yTcp5AbAmQ0o-q-gWy7kknir9zJ9R0A,1312
+mgnify_pipelines_toolkit/schemas/schemas.py,sha256=pnH8LUH8i2ACNvFNWyG-n-eIHZcI5O9UDYulkh43mec,7692
+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-1.0.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.0.1.dist-info/METADATA,sha256=3xW9nS84AonTMO6tWU03fii6CqyV5-oa7pa4XrlYvWE,6181
+mgnify_pipelines_toolkit-1.0.1.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+mgnify_pipelines_toolkit-1.0.1.dist-info/entry_points.txt,sha256=MsQXFdzL_dd7-2V6kHtA-QCf_iSQ-FmDcB9nZMLzJ98,2301
+mgnify_pipelines_toolkit-1.0.1.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.0.1.dist-info/RECORD,,

{mgnify_pipelines_toolkit-0.2.2.dist-info → mgnify_pipelines_toolkit-1.0.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.2)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-0.2.2.dist-info → mgnify_pipelines_toolkit-1.0.1.dist-info}/entry_points.txt

@@ -3,8 +3,9 @@ add_rhea_chebi_annotation = mgnify_pipelines_toolkit.analysis.assembly.add_rhea_
 are_there_primers = mgnify_pipelines_toolkit.analysis.amplicon.are_there_primers:main
 assess_inflection_point_mcp = mgnify_pipelines_toolkit.analysis.amplicon.assess_inflection_point_mcp:main
 assess_mcp_proportions = mgnify_pipelines_toolkit.analysis.amplicon.assess_mcp_proportions:main
-cgc_merge = mgnify_pipelines_toolkit.analysis.assembly.cgc_merge:combine_main
 classify_var_regions = mgnify_pipelines_toolkit.analysis.amplicon.classify_var_regions:main
+combined_gene_caller_merge = mgnify_pipelines_toolkit.analysis.assembly.combined_gene_caller_merge:main
+dwc_summary_generator = mgnify_pipelines_toolkit.analysis.assembly.dwc_summary_generator:main
 fasta_to_delimited = mgnify_pipelines_toolkit.utils.fasta_to_delimited:main
 fastq_suffix_header_check = mgnify_pipelines_toolkit.analysis.shared.fastq_suffix_header_check:main
 find_mcp_inflection_points = mgnify_pipelines_toolkit.analysis.amplicon.find_mcp_inflection_points:main