mgnify-pipelines-toolkit 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/assembly/gff_file_utils.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Copyright 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 csv
+
+
+def write_results_to_file(
+    outfile, header, main_gff_extended, fasta, ncrnas, trnas, crispr_annotations
+):
+    with open(outfile, "w") as file_out:
+        file_out.write("\n".join(header) + "\n")
+        contig_list = list(main_gff_extended.keys())
+        # check if there are any contigs that don't have CDS; if so add them in
+        contig_list = check_for_additional_keys(
+            ncrnas, trnas, crispr_annotations, contig_list
+        )
+        for contig in contig_list:
+            sorted_pos_list = sort_positions(
+                contig, main_gff_extended, ncrnas, trnas, crispr_annotations
+            )
+            for pos in sorted_pos_list:
+                for my_dict in (ncrnas, trnas, crispr_annotations, main_gff_extended):
+                    if contig in my_dict and pos in my_dict[contig]:
+                        for line in my_dict[contig][pos]:
+                            if type(line) is str:
+                                file_out.write(f"{line}\n")
+                            else:
+                                for element in line:
+                                    file_out.write(element)
+        for line in fasta:
+            file_out.write(f"{line}\n")
+
+
+def sort_positions(contig, main_gff_extended, ncrnas, trnas, crispr_annotations):
+    sorted_pos_list = list()
+    for my_dict in (main_gff_extended, ncrnas, trnas, crispr_annotations):
+        if contig in my_dict:
+            sorted_pos_list += list(my_dict[contig].keys())
+    return sorted(list(set(sorted_pos_list)))
+
+
+def check_for_additional_keys(ncrnas, trnas, crispr_annotations, contig_list):
+    for my_dict in (ncrnas, trnas, crispr_annotations):
+        dict_keys = set(my_dict.keys())
+        absent_keys = dict_keys - set(contig_list)
+        if absent_keys:
+            contig_list = contig_list + list(absent_keys)
+    return contig_list
+
+
+def print_pseudogene_report(pseudogene_report_dict, pseudogene_report_file):
+    with open(pseudogene_report_file, "w") as file_out:
+        writer = csv.writer(file_out, delimiter="\t", lineterminator="\n")
+        # Print header
+        writer.writerow(
+            [
+                "ID",
+                "Pseudogene according to Bakta/Prokka",
+                "Pseudogene according to Pseudofinder",
+                "AntiFam hit",
+            ]
+        )
+
+        all_keys = ["gene_caller", "pseudofinder", "antifams"]
+        for protein, attributes in pseudogene_report_dict.items():
+            # Fill in missing attributes with False
+            line = [protein] + [str(attributes.get(key, False)) for key in all_keys]
+            writer.writerow(line)

mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py

@@ -0,0 +1,170 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Copyright 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 gff_annotation_utils import get_ncrnas, get_trnas, load_annotations, load_crispr
+from gff_file_utils import write_results_to_file, print_pseudogene_report
+
+
+def main(
+    gff,
+    ipr_file,
+    eggnog_file,
+    sanntis_file,
+    crispr_file,
+    amr_file,
+    antismash_file,
+    gecco_file,
+    dbcan_file,
+    defense_finder_file,
+    pseudofinder_file,
+    rfam_file,
+    trnascan_file,
+    outfile,
+    pseudogene_report_file,
+):
+    # load annotations and add them to existing CDS
+    # here header contains leading GFF lines starting with "#",
+    # main_gff_extended is a dictionary that contains GFF lines with added in additional annotations
+    # fasta is the fasta portion of the original GFF file
+    # pseudogene_report_dict is the information on detected pseudogene which can be optionally printed
+    # to a separate output file
+    header, main_gff_extended, fasta, pseudogene_report_dict = load_annotations(
+        gff,
+        eggnog_file,
+        ipr_file,
+        sanntis_file,
+        amr_file,
+        antismash_file,
+        gecco_file,
+        dbcan_file,
+        defense_finder_file,
+        pseudofinder_file,
+    )
+    ncrnas = {}
+    if rfam_file:
+        ncrnas = get_ncrnas(rfam_file)
+    trnas = {}
+    if trnascan_file:
+        trnas = get_trnas(trnascan_file)
+    crispr_annotations = {}
+    if crispr_file:
+        crispr_annotations = load_crispr(crispr_file)
+
+    write_results_to_file(outfile, header, main_gff_extended, fasta, ncrnas, trnas, crispr_annotations)
+    if pseudogene_report_file:
+        print_pseudogene_report(pseudogene_report_dict, pseudogene_report_file)
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        description="The script extends a user-provided base GFF annotation file by incorporating "
+                    "information extracted from the user-provided outputs of supplementary annotation tools.",
+    )
+    parser.add_argument(
+        "-g",
+        dest="gff_input",
+        required=True,
+        help="GFF input file containing the base annotation",
+    )
+    parser.add_argument(
+        "-i",
+        dest="ips",
+        help="InterProScan annotation results (TSV)",
+        required=False,
+    )
+    parser.add_argument(
+        "-e",
+        dest="eggnog",
+        help="EggNOG mapper annotation results (TSV)",
+        required=False,
+    )
+    parser.add_argument(
+        "-s",
+        dest="sanntis",
+        help="SanntiS results",
+        required=False,
+    )
+    parser.add_argument(
+        "-c",
+        dest="crispr",
+        help="CRISPRCasFinder results for the cluster rep (pre-filtered high quality GFF)",
+        required=False,
+    )
+    parser.add_argument(
+        "-a",
+        dest="amr",
+        help="The TSV file produced by AMRFinderPlus",
+        required=False,
+    )
+    parser.add_argument(
+        "--antismash",
+        help="The GFF file produced by AntiSMASH post-processing script",
+        required=False,
+    )
+    parser.add_argument(
+        "--gecco",
+        help="The GFF file produced by GECCO",
+        required=False,
+    )
+    parser.add_argument(
+        "--dbcan",
+        help="The GFF file produced by dbCAN post-processing script",
+        required=False,
+    )
+    parser.add_argument(
+        "--defense-finder",
+        help="The GFF file produced by Defense Finder post-processing script",
+        required=False,
+    )
+    parser.add_argument(
+        "--pseudofinder",
+        help="The GFF file produced by the Pseudofinder post-processing script",
+        required=False,
+    )
+    parser.add_argument("-r", dest="rfam", help="Rfam results", required=False)
+    parser.add_argument(
+        "-t", dest="trnascan", help="tRNAScan-SE results", required=False
+    )
+    parser.add_argument("-o", dest="outfile", help="Outfile name", required=True)
+    parser.add_argument(
+        "--pseudogene-report", help="Pseudogene report filename", required=False
+    )
+
+    return parser.parse_args()
+
+
+if __name__ == '__main__':
+    args = parse_args()
+    main(
+        args.gff_input,
+        args.ips,
+        args.eggnog,
+        args.sanntis,
+        args.crispr,
+        args.amr,
+        args.antismash,
+        args.gecco,
+        args.dbcan,
+        args.defense_finder,
+        args.pseudofinder,
+        args.rfam,
+        args.trnascan,
+        args.outfile,
+        args.pseudogene_report,
+         )

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/constants/thresholds.py

@@ -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-0.2.0.dist-info → mgnify_pipelines_toolkit-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mgnify_pipelines_toolkit
-Version: 0.2.0
+Version: 0.2.2
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -18,6 +18,7 @@ Requires-Dist: regex==2023.12.25
 Requires-Dist: requests==2.32.3
 Requires-Dist: click==8.1.7
 Requires-Dist: pandera==0.22.1
+Requires-Dist: pyfastx>=2.2.0
 Provides-Extra: tests
 Requires-Dist: pytest==7.4.0; extra == "tests"
 Requires-Dist: pytest-md==0.2.0; extra == "tests"
@@ -29,6 +30,7 @@ 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-0.2.0.dist-info → mgnify_pipelines_toolkit-0.2.2.dist-info}/RECORD

@@ -1,9 +1,9 @@
 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=ySMZkgRSg-dnh6HMAE_1Vx8_EvJj7AiHJ2FcCaXKI-s,6448
-mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py,sha256=P_BM3GTB1KKKDb5chDK7-6cP6KORJef7i8ub-XLDtM0,5289
+mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py,sha256=9ScTh7uAIEBRDt61oG4inu9yezEzP1T2DgFWitaq4Po,6567
+mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py,sha256=Hfp5P89Sx6QE5oAxdNmuDwySG9FII3x4H5RFEXgnbF4,5311
 mgnify_pipelines_toolkit/analysis/amplicon/assess_inflection_point_mcp.py,sha256=hVkg8-tdLLf1Ewy9hor-H9zsyi-n8dnuj_shTQ5_rrM,7548
-mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py,sha256=aNucaUnYejl2Not4YLMBSzyYWGYJvYwLPZcFE94TIDc,5355
+mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py,sha256=xdnois8ilj4wuyDSc8xfIclVpcqaygCliVjEgnFDdi0,5382
 mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=kIuE2wo3FaFZw2-HRGxstKz29FyGuhqVDRhf_vPZgsA,19921
 mgnify_pipelines_toolkit/analysis/amplicon/find_mcp_inflection_points.py,sha256=EnsIrPGigsy8jVnjYgSECihhuquSJTgCi-k6fhusKYM,3547
 mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=ICFR8Ci_VofQFykasiSWwOwL_SH64PVcROoenw5jifE,8751
@@ -11,11 +11,14 @@ mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=9QI6o85
 mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=d_Mco92RRUXSq5-5oFlXC0ZO83kbxwOREoCCyA2glDc,3751
 mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=8vwH6PY-XwMZhaUo08tOwdFsoREfNumvvDawTb9Y98U,3168
 mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=19NgCYE12bEvRBVibhZtZywwRiMdiBUBJjzL4by3_qo,1717
-mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py,sha256=RDPsaWKf0wIDwvCHXyRCh2zSJf3y9E7uOhHjaAeX8bY,11099
-mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=69iK8vtG5xFgYQ-KJiSQlaxuhSoxzcO59eNLyDS3nm0,4323
+mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py,sha256=8xCjkCMtLuBWZ74AUu7tw0uXQRII3jD3n12PX-Xd9y4,11109
+mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=8GRjqDVQLU6cutn-40wVuEz_PxlnjCz33YJ0PUpObIc,4253
 mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py,sha256=OODl3XhLvksvG5RZn1iHZlg9L3DXiWIkyxJ6o-y6oeg,6949
 mgnify_pipelines_toolkit/analysis/assembly/cgc_merge.py,sha256=u6r_1GRGgBAJQvU_t5Rtl3ZYjTtGJGd5yHCobtL9ob0,15405
 mgnify_pipelines_toolkit/analysis/assembly/generate_gaf.py,sha256=U1Ls3O0CQmukmoyUwEAEN11jHUKuCdS-qVkr5ai243I,3582
+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=vsYaFJ_cmbo6DXlWs_X8wpZJfMQOq1CrLX4-3owmYjI,5447
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py,sha256=RthgLO3YTO_JGMC7Nx2JDrowXRimnOtVUDkM1l31rt4,5834
 mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -24,20 +27,21 @@ mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=xl5HduWtGPWiI9yq
 mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=DTX7S1P_BkGPEeDkbmUn1YoB247hpdNIe5rdFdRYDdA,1929
 mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py,sha256=XV1vjkjIHhzouM1k5hu_51XK_mgC_EOOGDN3mx4LOvc,1991
 mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=exzWyuK0YxDiVSu4WX2H7g-uT5Y00w_EmrFqSHjRObU,5554
+mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py,sha256=sKAo_rKEyVAZXSaIFMkpSoYZxiWwXMA3XDA6Z-hbHgg,7904
 mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.py,sha256=aWD-1B_fJg4rYZj2p8t8CUZdG1lDSo-oeFtLvjLgsak,13680
 mgnify_pipelines_toolkit/constants/db_labels.py,sha256=_2sGzTlfX7unGqkLylQFEUWNPQ8NZnQMtzlfVFuWtyU,853
 mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=dCP3u_Qo-JMk3aqVapkqEbVUGE06jBQmUH6bB3bT8k0,1088
 mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=_2UTWfHKJyyFkIRQIPM2wDf-QkRTdLJ4xsA6gAkY9f4,1188
 mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=63dQlW7jAjLPOSCT670QCS5WhTp13vwaHqfmFYbKMyg,1076
-mgnify_pipelines_toolkit/constants/thresholds.py,sha256=zz8paGQfZAU8tT-RbSGpzZ1Aopf77yEs97BAblHH5fk,964
+mgnify_pipelines_toolkit/constants/thresholds.py,sha256=7PuGhYPHBTJc-hwyOgnfmkfslWX-rQyLWeJVG_E6SGY,1152
 mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=jbOB_bTnW2TRjmdF7IS1A7nNOLt-lGnGyVXUHu0TmvQ,1307
 mgnify_pipelines_toolkit/schemas/schemas.py,sha256=fd2xCoA1Ty-XaMG9U_gxNcBokHiYENbA85n9YTsqbpU,7098
 mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=GbNT7clHso21w_1PbPpWKVRd5bNs_MDbGXt8XVIGl2o,3991
 mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=zsQ4TuR4vpqYa67MgIdopdscsS0DVJdy4enRe1nCjSs,793
-mgnify_pipelines_toolkit-0.2.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-0.2.0.dist-info/METADATA,sha256=TR0FyKtC0Xyj0zvDCPiYsI6bGbZI9GkQ8fiC1WWomEk,6068
-mgnify_pipelines_toolkit-0.2.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-mgnify_pipelines_toolkit-0.2.0.dist-info/entry_points.txt,sha256=60Nov738JAon-uZXUqqjOGy4TXxgS4xtxqYhAi12HY0,2084
-mgnify_pipelines_toolkit-0.2.0.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-0.2.0.dist-info/RECORD,,
+mgnify_pipelines_toolkit-0.2.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-0.2.2.dist-info/METADATA,sha256=7YtKMV_tE60N9c7H2ZXTmitIBGuULAjFn-IsyO-zg8M,6146
+mgnify_pipelines_toolkit-0.2.2.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+mgnify_pipelines_toolkit-0.2.2.dist-info/entry_points.txt,sha256=ThsGYkuzeFRfs2NB1Z1EJ_EtfPDKrZ4lHL8AvXDRq1k,2181
+mgnify_pipelines_toolkit-0.2.2.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-0.2.2.dist-info/RECORD,,

{mgnify_pipelines_toolkit-0.2.0.dist-info → mgnify_pipelines_toolkit-0.2.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (75.8.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-0.2.0.dist-info → mgnify_pipelines_toolkit-0.2.2.dist-info}/entry_points.txt

@@ -16,9 +16,10 @@ 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