mgnify-pipelines-toolkit 0.2.1__py3-none-any.whl → 1.0.0__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py

@@ -0,0 +1,243 @@
+#!/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 json
+import pathlib
+import logging
+
+import pandas as pd
+import pyfastx
+
+from mgnify_pipelines_toolkit.constants.thresholds import MAJORITY_MARKER_PROPORTION
+
+logging.basicConfig(level=logging.DEBUG)
+
+
+def parse_args():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-i",
+        "--input_path",
+        required=True,
+        type=str,
+        help="Input directory containing amplicon analysis pipeline results",
+    )
+    parser.add_argument(
+        "-r",
+        "--runs",
+        required=True,
+        type=str,
+        help="CSV file containing successful analyses generated by the pipeline",
+    )
+    parser.add_argument(
+        "-p", "--prefix", required=True, type=str, help="Prefix for the output file"
+    )
+
+    args = parser.parse_args()
+
+    input_path = args.input_path
+    runs = args.runs
+    prefix = args.prefix
+
+    return input_path, runs, prefix
+
+
+def get_read_count(read_path):
+
+    fasta = pyfastx.Fasta(read_path, build_index=False)
+    read_count = sum(1 for _ in fasta)
+
+    return read_count
+
+
+def add_markergene(root_path, run_acc, markergene_dict, markergene):
+
+    if markergene != "ITS":
+
+        bacterial_ssu = list(
+            pathlib.Path(f"{root_path}/{run_acc}/sequence-categorisation").glob(
+                f"*{markergene}*bacteria*"
+            )
+        )
+        archaeal_ssu = list(
+            pathlib.Path(f"{root_path}/{run_acc}/sequence-categorisation").glob(
+                f"*{markergene}*archaea*"
+            )
+        )
+        eukarya_ssu = list(
+            pathlib.Path(f"{root_path}/{run_acc}/sequence-categorisation").glob(
+                f"*{markergene}*eukarya*"
+            )
+        )
+
+        markergene_dict[markergene] = defaultdict()
+        markergene_dict[markergene]["Bacteria"] = defaultdict()
+        markergene_dict[markergene]["Archaea"] = defaultdict()
+        markergene_dict[markergene]["Eukarya"] = defaultdict()
+
+        markergene_dict[markergene] = add_read_count_to_markergene(
+            markergene_dict[markergene], bacterial_ssu, "Bacteria"
+        )
+        markergene_dict[markergene] = add_read_count_to_markergene(
+            markergene_dict[markergene], archaeal_ssu, "Archaea"
+        )
+        markergene_dict[markergene] = add_read_count_to_markergene(
+            markergene_dict[markergene], eukarya_ssu, "Eukarya"
+        )
+    else:
+        its = list(
+            pathlib.Path(f"{root_path}/{run_acc}/sequence-categorisation").glob("*ITS*")
+        )
+        markergene_dict["ITS"] = defaultdict()
+        markergene_dict["ITS"]["Eukarya"] = defaultdict()
+        markergene_dict["ITS"] = add_read_count_to_markergene(
+            markergene_dict["ITS"], its, "Eukarya"
+        )
+
+    return markergene_dict
+
+
+def add_read_count_to_markergene(marker_gene_dict, marker, label):
+
+    if marker:
+        read_count = get_read_count(str(marker[0]))
+        marker_gene_dict[label]["read_count"] = read_count
+    else:
+        marker_gene_dict[label]["read_count"] = 0
+
+    return marker_gene_dict
+
+
+def main():
+
+    input_path, runs, prefix = 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"])
+
+    # Marker gene study summary
+    markergene_dict = defaultdict(dict)
+    for i in range(0, len(runs_df)):
+        run_acc = runs_df.loc[i, "run"]
+        markergene_dict[run_acc]["marker_genes"] = defaultdict(dict)
+        markergene_dict[run_acc]["marker_genes"] = add_markergene(
+            root_path, run_acc, markergene_dict[run_acc]["marker_genes"], "SSU"
+        )
+        markergene_dict[run_acc]["marker_genes"] = add_markergene(
+            root_path, run_acc, markergene_dict[run_acc]["marker_genes"], "LSU"
+        )
+        markergene_dict[run_acc]["marker_genes"] = add_markergene(
+            root_path, run_acc, markergene_dict[run_acc]["marker_genes"], "ITS"
+        )
+
+        total_read_counts = sum(
+            [
+                markergene["read_count"]
+                for markergene in markergene_dict[run_acc]["marker_genes"][
+                    "SSU"
+                ].values()
+            ]
+        )
+        total_read_counts += sum(
+            [
+                markergene["read_count"]
+                for markergene in markergene_dict[run_acc]["marker_genes"][
+                    "LSU"
+                ].values()
+            ]
+        )
+        total_read_counts += sum(
+            [
+                markergene["read_count"]
+                for markergene in markergene_dict[run_acc]["marker_genes"][
+                    "ITS"
+                ].values()
+            ]
+        )
+
+        for markergene in markergene_dict[run_acc]["marker_genes"].keys():
+            read_count = 0
+            for domain in markergene_dict[run_acc]["marker_genes"][markergene].keys():
+                read_count += markergene_dict[run_acc]["marker_genes"][markergene][
+                    domain
+                ]["read_count"]
+                proportion = read_count / float(total_read_counts)
+                markergene_dict[run_acc]["marker_genes"][markergene][domain][
+                    "majority_marker"
+                ] = (proportion >= MAJORITY_MARKER_PROPORTION)
+
+    if markergene_dict:
+        with open(f"{prefix}_markergene_study_summary.json", "w") as fw:
+            fw.write(json.dumps(markergene_dict, indent=4))
+    else:
+        logging.warning(
+            "Marker gene data empty for some reason. No summary file created."
+        )
+
+    # Amplified region study summary (only available if ASV results present)
+
+    ampregion_dict = defaultdict(dict)
+    for i in range(0, len(runs_df)):
+        run_status = runs_df.loc[i, "status"]
+        if run_status == "no_asvs":
+            continue
+
+        run_acc = runs_df.loc[i, "run"]
+        ampregion_dict[run_acc]["amplified_regions"] = []
+
+        amp_regions = sorted(
+            list(pathlib.Path(f"{root_path}/{run_acc}/asv").glob("*S-V*/*.tsv"))
+        )
+
+        for amp_region_path in amp_regions:
+            amp_dict = defaultdict()
+            amp_region = str(amp_region_path).split("/")[-2]
+            marker_gene = amp_region.split("-")[0]
+            amp_region = "-".join(amp_region.split("-")[1:])
+
+            amp_region_df = pd.read_csv(amp_region_path, sep="\t")
+            asv_count = len(amp_region_df)
+            read_count = amp_region_df.loc[:, "count"].sum()
+
+            amp_dict["marker_gene"] = marker_gene
+            amp_dict["amplified_region"] = amp_region
+            amp_dict["asv_count"] = int(
+                asv_count
+            )  # casting needed for JSON serialising
+            amp_dict["read_count"] = int(
+                read_count
+            )  # casting needed for JSON serialising
+
+            ampregion_dict[run_acc]["amplified_regions"].append(amp_dict)
+
+    if ampregion_dict:
+        with open(f"{prefix}_ampregion_study_summary.json", "w") as fw:
+            fw.write(json.dumps(ampregion_dict, indent=4))
+    else:
+        logging.warning("No amplified region data found. No summary file created.")
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.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/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.
@@ -25,3 +25,10 @@ MAX_INTERNAL_PRIMER_PROPORTION = 0.2
 
 # used by library_strategy_checker in analysis.shared
 MIN_AMPLICON_STRATEGY_CHECK = 0.30
+
+# used by markergene_study_summary in analysis.shared
+MAJORITY_MARKER_PROPORTION = 0.45
+
+# used by gff_toolkit in analysis.assembly
+EVALUE_CUTOFF_IPS = 1e-10
+EVALUE_CUTOFF_EGGNOG = 1e-10

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 +1,7 @@
 #!/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/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-0.2.1.dist-info → mgnify_pipelines_toolkit-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mgnify_pipelines_toolkit
-Version: 0.2.1
+Version: 1.0.0
 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"
@@ -30,6 +31,7 @@ Requires-Dist: regex==2023.12.25; extra == "tests"
 Requires-Dist: requests==2.32.3; extra == "tests"
 Requires-Dist: click==8.1.7; extra == "tests"
 Requires-Dist: pandera==0.22.1; extra == "tests"
+Requires-Dist: pyfastx>=2.2.0; extra == "tests"
 Provides-Extra: dev
 Requires-Dist: mgnify_pipelines_toolkit[tests]; extra == "dev"
 Requires-Dist: pre-commit==3.8.0; extra == "dev"

mgnify_pipelines_toolkit-1.0.0.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=SosRFtW2PWr3dzvLEvYHQFZgGFX0LkQe30sGl3ozThA,13685
+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=Iwps_YtOrIzCuADBgjjJU5VSKb4G0OQZLJfvwRNGN3A,7103
+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-1.0.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.0.0.dist-info/METADATA,sha256=46IhEb_9fA1DuCMiQDWyc3yv4EcoZ9KhZ77hWBmjHjA,6181
+mgnify_pipelines_toolkit-1.0.0.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+mgnify_pipelines_toolkit-1.0.0.dist-info/entry_points.txt,sha256=cTTjlAPQafv9uLrsV4PUGWZgU61qaY8j6uvu0FEpO4A,2309
+mgnify_pipelines_toolkit-1.0.0.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.0.0.dist-info/RECORD,,

{mgnify_pipelines_toolkit-0.2.1.dist-info → mgnify_pipelines_toolkit-1.0.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-0.2.1.dist-info → mgnify_pipelines_toolkit-1.0.0.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:combine_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
@@ -16,9 +17,10 @@ library_strategy_check = mgnify_pipelines_toolkit.analysis.shared.library_strate
 make_asv_count_table = mgnify_pipelines_toolkit.analysis.amplicon.make_asv_count_table:main
 mapseq2biom = mgnify_pipelines_toolkit.analysis.shared.mapseq2biom:main
 mapseq_to_asv_table = mgnify_pipelines_toolkit.analysis.amplicon.mapseq_to_asv_table:main
+markergene_study_summary = mgnify_pipelines_toolkit.analysis.shared.markergene_study_summary:main
 primer_val_classification = mgnify_pipelines_toolkit.analysis.amplicon.primer_val_classification:main
 remove_ambiguous_reads = mgnify_pipelines_toolkit.analysis.amplicon.remove_ambiguous_reads:main
 rev_comp_se_primers = mgnify_pipelines_toolkit.analysis.amplicon.rev_comp_se_primers:main
 standard_primer_matching = mgnify_pipelines_toolkit.analysis.amplicon.standard_primer_matching:main
-study_summary_generator = mgnify_pipelines_toolkit.analysis.shared.study_summary_generator:main
+study_summary_generator = mgnify_pipelines_toolkit.analysis.shared.study_summary_generator:cli
 summarise_goslims = mgnify_pipelines_toolkit.analysis.assembly.summarise_goslims:main