mgnify-pipelines-toolkit 1.1.0__py3-none-any.whl → 1.1.1__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/{shared → amplicon}/study_summary_generator.py

@@ -257,7 +257,7 @@ def organise_study_summaries(all_study_summaries: List[str]) -> defaultdict[List
 @cli.command(
     "summarise",
     options_metavar="-r <runs> -a <analyses_dir> -p <output_prefix>",
-    short_help="Generate study-level analysis summaries.",
+    short_help="Generate study-level summaries of amplicon analysis results.",
 )
 @click.option(
     "-r",
@@ -327,7 +327,7 @@ def summarise_analyses(
 @cli.command(
     "merge",
     options_metavar="-a <analyses_dir> -p <output_prefix>",
-    short_help="Merge multiple study-level analysis summaries.",
+    short_help="Merge multiple study-level summaries of amplicon analysis.",
 )
 @click.option(
     "-a",

mgnify_pipelines_toolkit/analysis/assembly/study_summary_generator.py

@@ -0,0 +1,605 @@
+#!/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 click
+from functools import reduce
+import glob
+import logging
+from pathlib import Path
+from typing import Literal
+
+import pandas as pd
+
+from mgnify_pipelines_toolkit.schemas.schemas import (
+    CompletedAnalysisSchema,
+    TaxonSchema,
+    GOSummarySchema,
+    InterProSummarySchema,
+    KOSummarySchema,
+    SanntisSummarySchema,
+    AntismashSummarySchema,
+    PFAMSummarySchema,
+    KEGGModulesSummarySchema,
+    GOStudySummarySchema,
+    InterProStudySummarySchema,
+    TaxonomyStudySummarySchema,
+    KOStudySummarySchema,
+    SanntisStudySummarySchema,
+    AntismashStudySummarySchema,
+    PFAMStudySummarySchema,
+    KEGGModulesStudySummarySchema,
+    validate_dataframe,
+)
+
+logging.basicConfig(
+    level=logging.DEBUG, format="%(asctime)s - %(levelname)s - %(message)s"
+)
+
+# Keys are the original column names in the input files,
+# values are the standardised column names used in the generated study summary files
+# Note: "Count" or "count" column should be excluded
+GO_COLUMN_NAMES = {
+    "go": "GO",
+    "term": "description",
+    "category": "category",
+}
+
+INTERPRO_COLUMN_NAMES = {
+    "interpro_accession": "IPR",
+    "description": "description",
+}
+
+SANNTIS_COLUMN_NAMES = {
+    "nearest_mibig": "nearest_mibig",
+    "nearest_mibig_class": "nearest_mibig_class",
+    "description": "description",
+}
+
+ANTISMASH_COLUMN_NAMES = {
+    "label": "label",
+    "description": "description",
+}
+
+KEGG_COLUMN_NAMES = {
+    "ko": "KO",
+    "description": "description",
+}
+
+PFAM_COLUMN_NAMES = {
+    "pfam": "PFAM",
+    "description": "description",
+}
+
+KEGG_MODULES_COLUMN_NAMES = {
+    "module_accession": "module_accession",
+    "pathway_name": "pathway_name",
+    "pathway_class": "pathway_class",
+}
+
+# this mapping allows using 'for' cycle later to process all summary types in one way
+SUMMARY_TYPES_MAP = {
+    "go": {
+        "folder": "functional-annotation/go",
+        "column_names": GO_COLUMN_NAMES,
+        "schema": GOSummarySchema,
+        "study_schema": GOStudySummarySchema,
+    },
+    "goslim": {
+        "folder": "functional-annotation/go",
+        "column_names": GO_COLUMN_NAMES,
+        "schema": GOSummarySchema,
+        "study_schema": GOStudySummarySchema,
+    },
+    "interpro": {
+        "folder": "functional-annotation/interpro",
+        "column_names": INTERPRO_COLUMN_NAMES,
+        "schema": InterProSummarySchema,
+        "study_schema": InterProStudySummarySchema,
+    },
+    "ko": {
+        "folder": "functional-annotation/kegg",
+        "column_names": KEGG_COLUMN_NAMES,
+        "schema": KOSummarySchema,
+        "study_schema": KOStudySummarySchema,
+    },
+    "sanntis": {
+        "folder": "pathways-and-systems/sanntis",
+        "column_names": SANNTIS_COLUMN_NAMES,
+        "schema": SanntisSummarySchema,
+        "study_schema": SanntisStudySummarySchema,
+    },
+    "antismash": {
+        "folder": "pathways-and-systems/antismash",
+        "column_names": ANTISMASH_COLUMN_NAMES,
+        "schema": AntismashSummarySchema,
+        "study_schema": AntismashStudySummarySchema,
+    },
+    "pfam": {
+        "folder": "functional-annotation/pfam",
+        "column_names": PFAM_COLUMN_NAMES,
+        "schema": PFAMSummarySchema,
+        "study_schema": PFAMStudySummarySchema,
+    },
+    "kegg_modules": {
+        "folder": "pathways-and-systems/kegg-modules",
+        "column_names": KEGG_MODULES_COLUMN_NAMES,
+        "schema": KEGGModulesSummarySchema,
+        "study_schema": KEGGModulesStudySummarySchema,
+    },
+}
+
+# The taxonomy file is a tab-separated file without any header
+# containing of following columns:
+TAXONOMY_COLUMN_NAMES = [
+    "Count",
+    "Superkingdom",
+    "Kingdom",
+    "Phylum",
+    "Class",
+    "Order",
+    "Family",
+    "Genus",
+    "Species",
+]
+
+OUTPUT_SUFFIX = "summary.tsv"
+
+
+@click.group()
+def cli():
+    pass
+
+
+def check_files_exist(file_list: list[Path]) -> None:
+    """
+    Check that all files in the given list exist on disk.
+
+    :param file_list: List of file paths to check.
+    :raises FileNotFoundError: If any file does not exist.
+    """
+    missing_files = [str(path) for path in file_list if not path.is_file()]
+    if missing_files:
+        raise FileNotFoundError(
+            f"The following required files are missing: {', '.join(missing_files)}"
+        )
+
+
+def generate_taxonomy_summary(
+    file_dict: dict[str, Path],
+    output_file_name: str,
+    outdir: Path = None,
+) -> None:
+    """
+    Generate a combined study-level taxonomic classification summary from multiple input
+    assembly-level summary files.
+
+    :param file_dict: Dictionary mapping assembly accession to its taxonomy file.
+    :param output_file_name: Output path for the output summary file.
+    :param outdir: Optional output directory for the results.
+
+    Example of the taxonomy file:
+    23651	sk__Bacteria
+    4985	sk__Archaea	k__Thermoproteati	p__Nitrososphaerota
+    882	sk__Archaea	k__Nanobdellati	p__	c__	o__	f__	g__	s__Candidatus Pacearchaeota archaeon
+    """
+    check_files_exist(list(file_dict.values()))
+
+    tax_dfs = []
+    for assembly_acc, path in file_dict.items():
+        df = pd.read_csv(path, sep="\t", names=TAXONOMY_COLUMN_NAMES).fillna("")
+
+        # Note: schema validation will fail if the taxonomy file is empty
+        df = validate_dataframe(df, TaxonSchema, str(path))
+
+        # Combine all taxonomic ranks in the classification into a single string
+        df["full_taxon"] = (
+            df[TAXONOMY_COLUMN_NAMES[1:]].agg(";".join, axis=1).str.strip(";")
+        )
+
+        # Create a new DataFrame with taxonomy as index and count as the only column
+        result = df[["Count", "full_taxon"]].set_index("full_taxon")
+        result.columns = [assembly_acc]
+        tax_dfs.append(result)
+
+    summary_df = pd.concat(tax_dfs, axis=1)
+    summary_df = summary_df.fillna(0).astype(int).sort_index()
+
+    outfile = output_file_name
+    if outdir:
+        outfile = outdir / output_file_name
+
+    summary_df.to_csv(outfile, sep="\t", index_label="taxonomy")
+
+
+def generate_functional_summary(
+    file_dict: dict[str, Path],
+    column_names: dict[str, str],
+    output_prefix: str,
+    label: Literal[
+        "go", "goslim", "interpro", "ko", "sanntis", "antismash", "pfam", "kegg_modules"
+    ],
+    outdir: Path = None,
+) -> None:
+    """
+    Generate a combined study-level functional annotation summary from multiple input
+    assembly-level summary files.
+
+    :param file_dict: Dictionary mapping assembly accession to its summary file path.
+    :param column_names: Dictionary mapping original column names to standard column names.
+    :param output_prefix: Prefix for the output summary file.
+    :param label: Label for the functional annotation type
+    (expected one of ["go", "goslim", "interpro", "ko", "sanntis", "antismash", "pfam", "kegg_modules"]).
+    :param outdir: Optional output directory for the results.
+
+    In the input files, column orders may vary, but the following columns are expected:
+    GO summary input file:
+    go	term	category	count
+    GO:0016020	membrane	cellular_component	30626
+    GO:0005524	ATP binding	molecular_function	30524
+
+    InterPro summary input file:
+    interpro_accession	description	count
+    IPR036291	NAD(P)-binding domain superfamily	16503
+    IPR019734	Tetratricopeptide repeat	14694
+
+    KEGG summary input file:
+    ko      description	count
+    K01552  energy-coupling factor transport system ATP-binding protein [EC:7.-.-.-]	562
+    K18889  ATP-binding cassette, subfamily B, multidrug efflux pump	537
+    K15497  molybdate/tungstate transport system ATP-binding protein [EC:7.3.2.5 7.3.2.6]	517
+
+    Sanntis summary input file:
+    nearest_mibig	nearest_mibig_class	description	count
+    BGC0000787	Saccharide	Carbohydrate-based natural products (e.g., aminoglycoside antibiotics)	1
+    BGC0000248	Polyketide	Built from iterative condensation of acetate units derived from acetyl-CoA	3
+    BGC0001327	NRP Polyketide	Nonribosomal Peptide Polyketide	2
+
+    Antismash summary input file:
+    label	description	count
+    terpene	Terpene	16
+    betalactone	Beta-lactone containing protease inhibitor	8
+    T1PKS	Type I PKS (Polyketide synthase)	3
+
+    PFAM summary input file:
+    pfam	description	count
+    PF00265	Thymidine kinase	457
+    PF01852	START domain	368
+    PF13756	Stimulus-sensing domain	397
+
+    KEGG modules summary input file:
+    module_accession	completeness	pathway_name	pathway_class	matching_ko	missing_ko
+    M00986	100.0	Sulfur reduction, sulfur => sulfide	Pathway modules; Energy metabolism; Sulfur metabolism	K18367
+    M00163	83.33	Photosystem I	Pathway modules; Energy metabolism; Photosynthesis	K02689,K02690,K02691,K02692,K02694	K02693
+    M00615	50.0	Nitrate assimilation	Signature modules; Module set; Metabolic capacity	K02575	M00531
+    """
+    check_files_exist(list(file_dict.values()))
+
+    output_file_name = f"{output_prefix}_{label}_{OUTPUT_SUFFIX}"
+
+    original_col_names = list(column_names.keys())
+    renamed_col_names = list(column_names.values())
+    value_col_name = "completeness" if label == "kegg_modules" else "count"
+
+    dfs = []
+    for assembly_acc, filepath in file_dict.items():
+        try:
+            df = pd.read_csv(filepath, sep="\t")
+        except pd.errors.EmptyDataError:
+            logging.warning(f"File {filepath.resolve()} is empty. Skipping.")
+            continue
+
+        schema = SUMMARY_TYPES_MAP[label]["schema"]
+        df = validate_dataframe(df, schema, str(filepath))
+
+        # Extract only relevant columns
+        df = df[original_col_names + [value_col_name]].copy()
+
+        # Rename columns: metadata columns are renamed according to column_names dict, "count"/"completeness" -> assembly acc
+        df.rename(columns={**column_names, value_col_name: assembly_acc}, inplace=True)
+        dfs.append(df)
+
+    if not dfs:
+        logging.warning(
+            f"No valid files with functional annotation summary were found. Skipping creation of {output_file_name}."
+        )
+        return
+
+    # Merge all dataframes on the renamed metadata columns
+    merged_df = reduce(
+        lambda left, right: pd.merge(left, right, on=renamed_col_names, how="outer"),
+        dfs,
+    )
+
+    # Fill missing values appropriately, convert completeness percentages to float, counts to integers
+    value_columns = [col for col in merged_df.columns if col not in renamed_col_names]
+    fill_value = 0.0 if label == "kegg_modules" else 0
+    dtype = float if label == "kegg_modules" else int
+    merged_df[value_columns] = merged_df[value_columns].fillna(fill_value).astype(dtype)
+
+    # Reorder columns: merge keys first, then sorted assembly accessions
+    merged_df = merged_df[renamed_col_names + sorted(value_columns)]
+
+    outfile = output_file_name
+    if outdir:
+        outfile = outdir / output_file_name
+
+    merged_df.to_csv(outfile, sep="\t", index=False)
+
+
+@cli.command(
+    "summarise",
+    options_metavar="-a <assemblies> -s <study_dir> -p <output_prefix>",
+    short_help="Generate study-level summaries for assembly analysis results.",
+)
+@click.option(
+    "-a",
+    "--assemblies",
+    required=True,
+    help="CSV file containing successful analyses generated by the pipeline",
+    type=click.Path(exists=True, path_type=Path, dir_okay=False),
+)
+@click.option(
+    "-s",
+    "--study_dir",
+    required=True,
+    help="Input directory to where all the individual analyses subdirectories for summarising",
+    type=click.Path(exists=True, path_type=Path, file_okay=False),
+)
+@click.option(
+    "-p",
+    "--output_prefix",
+    required=True,
+    help="Prefix for generated summary files",
+    type=str,
+)
+@click.option(
+    "-o",
+    "--outdir",
+    required=False,
+    help="Directory for the output files, by default it will use the current working directory.",
+    type=click.Path(exists=True, path_type=Path, file_okay=False),
+)
+def summarise_analyses(
+    assemblies: Path, study_dir: Path, output_prefix: str, outdir: Path
+) -> None:
+    """
+    Generate study-level summaries for successfully proccessed assemblies.
+
+    :param assemblies: Path to a file listing completed assembly accessions and their status.
+    :param study_dir: Path to the directory containing analysis results for each assembly.
+    :param output_prefix: Prefix for the generated summary files.
+    """
+    logging.info(f"Reading assembly list from {assemblies.resolve()}")
+    assemblies_df = pd.read_csv(assemblies, names=["assembly", "status"])
+    CompletedAnalysisSchema(assemblies_df)
+    assembly_list = assemblies_df["assembly"].tolist()
+    logging.info("Assembly list was read successfully.")
+
+    def get_file_paths(subdir: str, filename_template: str) -> dict[str, Path]:
+        """
+        Construct file paths for each assembly given a subdirectory and filename template.
+        Template must contain {acc} as a placeholder.
+        """
+        return {
+            acc: study_dir / acc / subdir / filename_template.format(acc=acc)
+            for acc in assembly_list
+        }
+
+    logging.info("Start processing of assembly-level summaries.")
+
+    logging.info(
+        "Generating taxonomy summary from assembly-level summaries <accession>.krona.txt"
+    )
+    generate_taxonomy_summary(
+        get_file_paths("taxonomy", "{acc}.krona.txt.gz"),
+        f"{output_prefix}_taxonomy_{OUTPUT_SUFFIX}",
+        outdir=outdir,
+    )
+
+    for summary_type, config in SUMMARY_TYPES_MAP.items():
+        logging.info(
+            f"Generating study-level {summary_type.capitalize()} summary from file <accession>_{summary_type}_summary.tsv.gz"
+        )
+        generate_functional_summary(
+            get_file_paths(config["folder"], f"{{acc}}_{summary_type}_summary.tsv.gz"),
+            config["column_names"],
+            output_prefix,
+            summary_type,
+            outdir=outdir,
+        )
+    logging.info("Assembly-level summaries were generated successfully.")
+    logging.info("Done.")
+
+
+@cli.command(
+    "merge",
+    options_metavar="-a <study_dir> -p <output_prefix>",
+    short_help="Merge multiple study-level summaries of assembly analysis.",
+)
+@click.option(
+    "-s",
+    "--study_dir",
+    required=True,
+    help="Input directory to where all the individual analyses subdirectories for merging",
+    type=click.Path(exists=True, file_okay=False),
+)
+@click.option(
+    "-p",
+    "--output_prefix",
+    required=True,
+    help="Prefix for generated merged summary files",
+    type=str,
+)
+def merge_summaries(study_dir: str, output_prefix: str) -> None:
+    """
+    Merge multiple study-level summary files into combined summary files.
+
+    :param study_dir: Path to the directory containing study-level summary files.
+    :param output_prefix: Prefix for the output merged summary files.
+    """
+
+    def get_file_paths(summary_type: str) -> list[str]:
+        return glob.glob(f"{study_dir}/*_{summary_type}_{OUTPUT_SUFFIX}")
+
+    logging.info("Generating combined assembly-level summaries")
+    logging.info("Parsing summary files for taxonomic classification")
+    merge_taxonomy_summaries(
+        get_file_paths("taxonomy"), f"{output_prefix}_taxonomy_{OUTPUT_SUFFIX}"
+    )
+
+    for summary_type, config in SUMMARY_TYPES_MAP.items():
+        logging.info(f"Parsing summary files for {summary_type.capitalize()}.")
+        column_names = config["column_names"]
+        merge_functional_summaries(
+            get_file_paths(summary_type),
+            list(column_names.values()),
+            output_prefix,
+            summary_type,
+        )
+    logging.info("Merged assembly-level summaries were generated successfully.")
+    logging.info("Done.")
+
+
+def merge_taxonomy_summaries(summary_files: list[str], output_file_name: str) -> None:
+    """
+    Merge multiple taxonomy study-level summary files into a single study-level summary.
+
+    :param summary_files: List of paths to taxonomy summary files, each containing
+                        taxonomic classifications and counts for an individual analysis.
+    :param output_file_name: Output path for the merged taxonomy summary.
+
+    Example of input taxonomy summary file:
+    taxonomy	ERZ1049444	ERZ1049446
+    sk__Eukaryota;k__Metazoa;p__Chordata	2	10
+    sk__Eukaryota;k__Metazoa;p__Chordata;c__Mammalia;o__Primates	118	94
+    """
+    if not summary_files:
+        raise FileNotFoundError(
+            "The required taxonomic classification summary files are missing. Exiting."
+        )
+
+    summary_dfs = []
+    for file in summary_files:
+        df = pd.read_csv(file, sep="\t", index_col=0)
+        df = validate_dataframe(df, TaxonomyStudySummarySchema, file)
+        summary_dfs.append(df)
+    merged_df = pd.concat(summary_dfs, axis=1)
+    merged_df = merged_df.fillna(0).astype(int)
+
+    # Reorder columns: taxonomy first, then sorted assembly accessions
+    merged_df = merged_df[sorted(merged_df.columns)]
+    merged_df = merged_df.sort_index()
+
+    merged_df.to_csv(
+        output_file_name,
+        sep="\t",
+        index_label="taxonomy",
+    )
+
+
+def merge_functional_summaries(
+    summary_files: list[str],
+    merge_keys: list[str],
+    output_prefix: str,
+    label: Literal[
+        "go", "goslim", "interpro", "ko", "sanntis", "antismash", "pfam", "kegg_modules"
+    ],
+) -> None:
+    """
+    Merge multiple functional study-level summary files into a single study-level summary.
+
+    :param summary_files: List of paths to functional summary files, each containing
+                        annotation terms and counts for an individual analysis.
+    :param merge_keys: List of column names to merge on (e.g. term ID, description).
+    :param output_prefix: Prefix for the generated output file.
+    :param label: Label describing the functional annotation type
+    (expected one of ["go", "goslim", "interpro", "ko", "sanntis", "antismash", "pfam", "kegg_modules"]).
+
+    In the input files, column orders may vary, but the following columns are expected:
+    GO summary input:
+    GO	description	category	ERZ1049444	ERZ1049446
+    GO:0016020	membrane	cellular_component	30626	673
+    GO:0005524	ATP binding	molecular_function	30524	2873
+
+    Example of InterPro summary input:
+    IPR	description	ERZ1049444	ERZ1049446
+    IPR036291	NAD(P)-binding domain superfamily	16503	13450
+    IPR019734	Tetratricopeptide repeat	14694	11021
+
+    KEGG summary input:
+    GO	description	category	ERZ1049440	ERZ1049443
+    GO:0003677	DNA binding	molecular_function	6125	16417
+    GO:0055085	transmembrane transport	biological_process	144	13926
+
+    Sanntis summary input:
+    nearest_mibig	nearest_mibig_class	description	ERZ1049440	ERZ1049443
+    BGC0001356	RiPP	Ribosomally synthesised and Post-translationally modified Peptide	230	185
+    BGC0001432	NRP Polyketide	Nonribosomal Peptide Polyketide	0	8
+
+    Antismash summary input:
+    label	description	ERZ1049440	ERZ1049443
+    NRPS	Non-ribosomal peptide synthetase	368	0
+    arylpolyene	Aryl polyene	149	447
+
+    PFAM summary input:
+    PFAM	description	ERZ1049440	ERZ1049443
+    PF24718	HTH-like domain	468	1
+    PF06039	Malate:quinone oxidoreductase (Mqo)	490	21
+
+    KEGG modules summary input:
+    module_accession	pathway_name	pathway_class	ERZ1049440	ERZ1049443
+    M00109	C21-Steroid hormone biosynthesis, progesterone => cortisol/cortisone	Pathway modules; Lipid metabolism; Sterol biosynthesis	38.9	0.0
+    M00153	Cytochrome bd ubiquinol oxidase	Pathway modules; Energy metabolism; ATP synthesis	44.7	84.4
+    """
+    output_file_name = f"{output_prefix}_{label}_{OUTPUT_SUFFIX}"
+
+    if not summary_files:
+        logging.warning(
+            f"Skipping creation of {output_file_name} because no summaries were found for this type of functional annotation."
+        )
+        return
+
+    validation_schema = SUMMARY_TYPES_MAP[label]["study_schema"]
+
+    dfs = []
+    for filepath in summary_files:
+        df = pd.read_csv(filepath, sep="\t")
+        df = validate_dataframe(df, validation_schema, filepath)
+        dfs.append(df)
+
+    if len(dfs) == 1:
+        merged_df = dfs[0]
+    else:
+        merged_df = reduce(
+            lambda left, right: pd.merge(left, right, on=merge_keys, how="outer"), dfs
+        )
+
+    # Identify non-key columns (i.e. counts)
+    value_columns = [col for col in merged_df.columns if col not in merge_keys]
+
+    # Fill NaNs and set dtype accordingly
+    fill_value = 0.0 if label == "kegg_modules" else 0
+    dtype = float if label == "kegg_modules" else int
+    merged_df[value_columns] = merged_df[value_columns].fillna(fill_value).astype(dtype)
+
+    # Reorder columns
+    merged_df = merged_df[merge_keys + sorted(value_columns)]
+
+    merged_df.to_csv(output_file_name, sep="\t", index=False)
+
+
+if __name__ == "__main__":
+    cli()

mgnify_pipelines_toolkit/analysis/assembly/summarise_antismash_bgcs.py

@@ -155,7 +155,7 @@ def parse_args():
     description = (
         "antiSMASH output summary generator. "
         "Script takes regions from GFF and counts its appearance in annotation. "
-        "Output columns contain classID, descriptions and count. "
+        "Output columns contain label, descriptions and count. "
         f"Descriptions were taken from pre-parsed glossary provided on antiSMASH website. "
         f"Current script supports antiSMASH results for version {ANTISMASH_VERSION} and older."
     )
@@ -202,15 +202,15 @@ def main():
         df = pd.DataFrame(dict_list)
         df = df[df["product"].notna()]
         df_grouped = (
-            df.groupby(["product"]).size().reset_index(name="Count")
-        ).sort_values(by="Count", ascending=False)
+            df.groupby(["product"]).size().reset_index(name="count")
+        ).sort_values(by="count", ascending=False)
 
         df_grouped = df_grouped.rename(
             columns={
                 "product": "label",
             }
         )
-        df_grouped["Description"] = df_grouped["label"].apply(
+        df_grouped["description"] = df_grouped["label"].apply(
             lambda x: ",".join(
                 [
                     DESCRIPTIONS.get(cls.strip().lower(), cls.strip())
@@ -218,11 +218,7 @@ def main():
                 ]
             )
         )
-        df_grouped = df_grouped[["label", "Description", "Count"]]
-        df_grouped = df_grouped.rename(columns={
-            "Description": "description",
-            "Count": "count"
-        })
+        df_grouped = df_grouped[["label", "description", "count"]]
         df_grouped.to_csv(output_filename, sep="\t", index=False)
 
 

mgnify_pipelines_toolkit/analysis/assembly/summarise_sanntis_bgcs.py

@@ -75,38 +75,40 @@ def main():
                 entry_dict[key] = value
             dict_list.append(entry_dict)
 
-            # Convert to DataFrame
+        # Convert to DataFrame
         df = pd.DataFrame(dict_list)
         df = df.rename(
             columns={
-                "nearest_MiBIG": "nearest_MIBiG",
-                "nearest_MiBIG_class": "nearest_MIBiG_class",
+                "nearest_MiBIG": "nearest_mibig",
+                "nearest_MiBIG_class": "nearest_mibig_class",
             }
         )
         df_grouped = (
-            df.groupby(["nearest_MIBiG", "nearest_MIBiG_class"])
+            df.groupby(["nearest_mibig", "nearest_mibig_class"])
             .size()
-            .reset_index(name="Count")
+            .reset_index(name="count")
         )
-        df_grouped = df_grouped.sort_values(by="Count", ascending=False)
+        df_grouped = df_grouped.sort_values(by="count", ascending=False)
 
         df_desc = pd.DataFrame(
-            list(DESCRIPTIONS.items()), columns=["MIBiG_class", "Description"]
+            list(DESCRIPTIONS.items()), columns=["mibig_class", "description"]
         )
-        df_desc = df_desc.set_index("MIBiG_class")
+        df_desc = df_desc.set_index("mibig_class")
         df_merged = df_grouped.merge(
-            df_desc, left_on="nearest_MIBiG_class", right_index=True, how="left"
+            df_desc, left_on="nearest_mibig_class", right_index=True, how="left"
         )
-        df_merged["Description"] = df_merged.apply(
-            lambda row: row["nearest_MIBiG_class"].replace(
-                "NRP", df_desc.loc["NRP"]["Description"]
-            )
-            if pd.isna(row["Description"]) and "NRP" in row["nearest_MIBiG_class"]
-            else row["Description"],
+        df_merged["description"] = df_merged.apply(
+            lambda row: (
+                row["nearest_mibig_class"].replace(
+                    "NRP", df_desc.loc["NRP"]["description"]
+                )
+                if pd.isna(row["description"]) and "NRP" in row["nearest_mibig_class"]
+                else row["description"]
+            ),
             axis=1,
         )
         df_merged = df_merged[
-            ["nearest_MIBiG", "nearest_MIBiG_class", "Description", "Count"]
+            ["nearest_mibig", "nearest_mibig_class", "description", "count"]
         ]
         df_merged = df_merged.rename(columns={
             "Description": "description",

mgnify_pipelines_toolkit/schemas/schemas.py

@@ -17,10 +17,11 @@ import logging
 import re
 
 from enum import Enum
-from typing import ClassVar, Optional, Type
+from typing import ClassVar, Optional, Type, Literal
 
 import pandas as pd
 import pandera as pa
+from pandera.typing import Series
 from pandera.typing.common import DataFrameBase
 
 from pydantic import (
@@ -110,6 +111,354 @@ class AmpliconPassedRunsSchema(pa.DataFrameModel):
         coerce = True
 
 
+class CompletedAnalysisRecord(BaseModel):
+    """Class defining a Pydantic model for a single "row" of an successfully analysed assemblies file."""
+
+    assembly: str = Field(
+        ...,
+        description="Assembly accession",
+        examples=["ERZ789012"],
+        pattern=r"ERZ\d{6,}",
+    )
+    status: Literal["success"] = Field(
+        ...,
+        description="Pipeline output for whether this assembly's analysis succeeded or not",
+    )
+
+
+class CompletedAnalysisSchema(pa.DataFrameModel):
+    """Class modelling a Pandera dataframe schema that uses the CompletedAnalysisSchema class as dtype.
+    This is what actually validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    assembly: Series[str]
+
+    @pa.check("assembly")
+    def accessions_unique(self, series: Series[str]) -> Series[bool]:
+        return ~series.duplicated()
+
+    class Config:
+        """Config with dataframe-level data type."""
+
+        dtype = PydanticModel(CompletedAnalysisRecord)
+        coerce = True
+
+
+class InterProSummaryRecord(BaseModel):
+    """Model of a row in the InterPro summary file."""
+
+    count: int = Field(
+        ..., ge=0, description="Number of hits for the InterPro accession"
+    )
+    interpro_accession: str = Field(
+        ...,
+        description="InterPro accession ID",
+        examples=["IPR123456"],
+        pattern=r"IPR\d{6}",
+    )
+    description: str = Field(..., description="Description of the InterPro domain")
+
+
+class GOSummaryRecord(BaseModel):
+    """Model of a row in the GO summary file."""
+
+    go: str = Field(
+        ...,
+        description="GO term identifier",
+        examples=["GO:1234567"],
+        pattern=r"GO:\d{7}",
+    )
+    term: str = Field(..., description="GO term name")
+    category: str = Field(
+        ...,
+        description="GO category",
+        examples=["biological_process", "molecular_function", "cellular_component"],
+    )
+    count: int = Field(..., ge=0, description="Number of times the GO term is observed")
+
+
+class BaseSummarySchema(pa.DataFrameModel):
+    """Base schema for summary files."""
+
+    @staticmethod
+    def is_unique(series: Series[str]) -> Series[bool]:
+        return ~series.duplicated()
+
+
+class InterProSummarySchema(BaseSummarySchema):
+    """Schema for InterPro summary file validation."""
+
+    interpro_accession: Series[str]
+
+    @pa.check("interpro_accession")
+    def interpro_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(InterProSummaryRecord)
+        coerce = True
+
+
+class GOSummarySchema(BaseSummarySchema):
+    """Schema for GO or GOslim summary file validation."""
+
+    go: Series[str]
+
+    @pa.check("go")
+    def go_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(GOSummaryRecord)
+        coerce = True
+
+
+class SanntisSummaryRecord(BaseModel):
+    """Model of a row in the Sanntis assembly-level summary file."""
+
+    nearest_mibig: str = Field(
+        ...,
+        description="The accession ID of the closest matching biosynthetic gene cluster (BGC) in the MIBiG database",
+        examples=["BGC0000073"],
+        pattern=r"BGC\d{7}",
+    )
+    nearest_mibig_class: str = Field(
+        ...,
+        description="The biosynthetic class of the nearest MIBiG BGC",
+        examples=["Polyketide"],
+    )
+    description: str = Field(
+        ...,
+        description="A brief summary of the biosynthetic process or type of metabolite associated with the nearest MIBiG cluster",
+    )
+
+    count: int = Field(
+        ..., ge=0, description="Number of times the MIBiG entry is observed"
+    )
+
+
+class AntismashSummaryRecord(BaseModel):
+    """Model of a row in the Antismash summary file."""
+
+    label: str = Field(
+        ...,
+        description="Biosynthetic class or label assigned by Antismash based on sequence similarity to known biosynthetic gene clusters.",
+        examples=["RiPP-like", "T1PKS", "terpene"],
+    )
+    description: str = Field(
+        ...,
+        description="Brief explanation of the biosynthetic class, often indicating compound type or functional characteristics.",
+        examples=["Type I PKS (Polyketide synthase)", "Redox-cofactors such as PQQ"],
+    )
+    count: int = Field(
+        ...,
+        ge=0,
+        description="Number of BGCs (biosynthetic gene clusters) in the dataset assigned to this label.",
+    )
+
+
+class KOSummaryRecord(BaseModel):
+    """Model of a row in the KEGG summary file."""
+
+    ko: str = Field(
+        ...,
+        description="KEGG Orthology (KO) identifier representing a functional gene or pathway component.",
+        examples=["K07547", "K04874", "K19946"],
+        pattern=r"K\d{5,}",
+    )
+    description: str = Field(
+        ...,
+        description="Name or function of the KO, sometimes including EC numbers and protein families.",
+        examples=["optineurin", "MFS transporter, POT/PTR family"],
+    )
+    count: int = Field(
+        ...,
+        ge=0,
+        description="Number of times this KO identifier is observed in the dataset.",
+    )
+
+
+class PFAMSummaryRecord(BaseModel):
+    """Model of a row in the PFAM summary file."""
+
+    pfam: str = Field(
+        ...,
+        description="PFAM accession identifier representing a protein domain or family.",
+        examples=["PF00265", "PF01956", "PF00673"],
+        pattern=r"PF\d{5}",
+    )
+    description: str = Field(
+        ...,
+        description="Description of the protein domain or family associated with the PFAM ID.",
+        examples=["Thymidine kinase", "Integral membrane protein EMC3/TMCO1-like"],
+    )
+    count: int = Field(
+        ...,
+        ge=0,
+        description="Number of times the PFAM domain is observed in the dataset.",
+    )
+
+
+class KEGGModulesSummaryRecord(BaseModel):
+    """Model of a row in the KEGG Modules summary file."""
+
+    module_accession: str = Field(
+        ...,
+        description="KEGG Module identifier representing a specific metabolic pathway or module.",
+        examples=["M00123", "M00234"],
+        pattern=r"M\d{5}",
+    )
+    completeness: float = Field(
+        ...,
+        ge=0,
+        description="Completeness score of the KEGG Module, indicating the extent to which the module is present in the metagenome.",
+    )
+    pathway_name: str = Field(
+        ...,
+        description="Name of the metabolic pathway associated with the KEGG Module.",
+        examples=["Sulfur reduction, sulfur => sulfide"],
+    )
+    pathway_class: str = Field(
+        ...,
+        description="Biosynthetic class or category associated with the KEGG Module, semi colon separated.",
+        examples=["Pathway modules; Energy metabolism; Photosynthesis"],
+    )
+
+
+class SanntisSummarySchema(BaseSummarySchema):
+    nearest_mibig: Series[str]
+
+    @pa.check("nearest_mibig")
+    def mibig_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(SanntisSummaryRecord)
+        coerce = True
+
+
+class AntismashSummarySchema(BaseSummarySchema):
+    label: Series[str]
+
+    @pa.check("label")
+    def class_names_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(AntismashSummaryRecord)
+        coerce = True
+
+
+class KOSummarySchema(BaseSummarySchema):
+    ko: Series[str]
+
+    @pa.check("ko")
+    def ko_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(KOSummaryRecord)
+        coerce = True
+
+
+class PFAMSummarySchema(BaseSummarySchema):
+    pfam: Series[str]
+
+    @pa.check("pfam")
+    def pfam_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(PFAMSummaryRecord)
+        coerce = True
+
+
+class KEGGModulesSummarySchema(BaseSummarySchema):
+    module_accession: Series[str]
+
+    @pa.check("module_accession")
+    def module_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+    class Config:
+        dtype = PydanticModel(KEGGModulesSummaryRecord)
+        coerce = True
+
+
+class BaseStudySummarySchema(BaseSummarySchema):
+    """Base schema for study summary files with ERZ* columns and count checks."""
+
+    @pa.check(regex=r"^ERZ\d+")
+    def count_columns_are_non_negative(self, s: Series[int]) -> Series[bool]:
+        return s >= 0
+
+    class Config:
+        strict = False  # allow extra ERZ* columns not declared above
+
+
+class GOStudySummarySchema(BaseStudySummarySchema):
+    GO: Series[str] = pa.Field(str_matches=r"^GO:\d{7}$")
+    description: Series[str]
+    category: Series[str]
+
+    @pa.check("GO")
+    def go_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class InterProStudySummarySchema(BaseStudySummarySchema):
+    IPR: Series[str] = pa.Field(str_matches=r"^IPR\d{6}$")
+    description: Series[str]
+
+    @pa.check("IPR")
+    def interpro_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class AntismashStudySummarySchema(BaseStudySummarySchema):
+    label: Series[str]
+
+    @pa.check("label")
+    def class_names_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class SanntisStudySummarySchema(BaseStudySummarySchema):
+    nearest_mibig: Series[str]
+
+    @pa.check("nearest_mibig")
+    def mibig_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class KOStudySummarySchema(BaseStudySummarySchema):
+    KO: Series[str]
+
+    @pa.check("KO")
+    def ko_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class PFAMStudySummarySchema(BaseStudySummarySchema):
+    PFAM: Series[str]
+
+    @pa.check("PFAM")
+    def pfam_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class KEGGModulesStudySummarySchema(BaseStudySummarySchema):
+    module_accession: Series[str]
+
+    @pa.check("module_accession")
+    def module_ids_unique(self, series: Series[str]) -> Series[bool]:
+        return self.is_unique(series)
+
+
+class TaxonomyStudySummarySchema(BaseStudySummarySchema):
+    pass
+
+
 class AmpliconNonINSDCPassedRunsSchema(pa.DataFrameModel):
     """Class modelling the same dataframe schema as the preceding one, except with no INSDC validation.
     Uses the AmpliconNonINSDCSPassedRunsRecord as a dtype to achieve this.
@@ -145,7 +494,11 @@ class TaxRank(RootModel):
     def rank_structure_validity_check(cls, taxrank: str) -> bool:
         taxrank_list = taxrank.split("__")
         rank = taxrank_list[0]
-        if rank != "" and rank != "Unclassified" and rank not in cls.valid_tax_ranks:
+        if (
+            rank != ""
+            and rank.capitalize() != "Unclassified"
+            and rank not in cls.valid_tax_ranks
+        ):
             raise ValueError(f"Invalid taxonomy rank {rank}.")
 
         return taxrank

{mgnify_pipelines_toolkit-1.1.0.dist-info → mgnify_pipelines_toolkit-1.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.1.0
+Version: 1.1.1
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -8,7 +8,7 @@ Keywords: bioinformatics,pipelines,metagenomics
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: biopython>=1.85

{mgnify_pipelines_toolkit-1.1.0.dist-info → mgnify_pipelines_toolkit-1.1.1.dist-info}/RECORD

@@ -12,6 +12,7 @@ mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=B
 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/amplicon/study_summary_generator.py,sha256=epVClL10QcllL8yu7YGjx0rXNVHL2GxHi-Ek0MOjsjo,13859
 mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=NZSNY2bqs_TQyz8riDqiEFPLKcwTgzh1C7DeVHT6V8Q,4366
 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
@@ -23,9 +24,10 @@ mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=eay9e3Xdc8XxnlC_4S
 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=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/study_summary_generator.py,sha256=J4cIWaFyWihqo2JtaOR531aXtVxIfOi_hcwZZw-vP8g,21252
+mgnify_pipelines_toolkit/analysis/assembly/summarise_antismash_bgcs.py,sha256=jUeA7I12YrtIqnm3hUxpdgsWfa2pP1ALGjb9OMKPcgY,10643
 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
+mgnify_pipelines_toolkit/analysis/assembly/summarise_sanntis_bgcs.py,sha256=1wblLbZl521digIUWoqneAu15gErzvN_oC--5T_xUdw,4582
 mgnify_pipelines_toolkit/analysis/genomes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/shared/convert_cmscan_to_cmsearch_tblout.py,sha256=kAGU5kQyj-Hlcdx32i-xOJSuHYYUDj-kqnyYHMohHGc,4477
@@ -36,7 +38,6 @@ mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=EH5RyzesL
 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/ncrna.py,sha256=a_5hWp446S7BhRbe_JcydFgZM7sgPLuMlaiBvKWN_XM,1928
 mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=7nEOODQq35y9wx9YnvJuo29oBpwTpXg_kIbf_t7N4TQ,1093
@@ -44,13 +45,13 @@ mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=G-xrc9b8zdmPTaOI
 mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=kMq__kOJcbiwsgolkdvb-XLo3WMnJdEXgedjUyMOYjI,1081
 mgnify_pipelines_toolkit/constants/thresholds.py,sha256=V_xDBk0RhS3hHeWqOacKzth2gM6zJABRPgwHy-Ciqfk,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/schemas/schemas.py,sha256=pyDZvCuWbwccQF0D7c5BN1vv36wQdgcAUXU43_zAu74,18164
 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-1.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.1.0.dist-info/METADATA,sha256=ZBar6psIFlDE7DNfuDFjeX0HLKsgMwFn6ZW_ifMqEww,5810
-mgnify_pipelines_toolkit-1.1.0.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
-mgnify_pipelines_toolkit-1.1.0.dist-info/entry_points.txt,sha256=T8soGT2to8c_qafw-0itqCn4sjOnxlfaNWHIaHz4H54,3416
-mgnify_pipelines_toolkit-1.1.0.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.1.0.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.1.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.1.1.dist-info/METADATA,sha256=E86Tp9qJuQUrkNIklK4PEATQ4ovZfhRbgMKVTyxGSx0,5811
+mgnify_pipelines_toolkit-1.1.1.dist-info/WHEEL,sha256=wXxTzcEDnjrTwFYjLPcsW_7_XihufBwmpiBeiXNBGEA,91
+mgnify_pipelines_toolkit-1.1.1.dist-info/entry_points.txt,sha256=JSjuxAr71MTeSUPPpno22wmZYgVO-gbsXfDkgWKkF7A,3533
+mgnify_pipelines_toolkit-1.1.1.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.1.1.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.1.0.dist-info → mgnify_pipelines_toolkit-1.1.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.0)
+Generator: setuptools (80.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-1.1.0.dist-info → mgnify_pipelines_toolkit-1.1.1.dist-info}/entry_points.txt

@@ -1,7 +1,9 @@
 [console_scripts]
 add_rhea_chebi_annotation = mgnify_pipelines_toolkit.analysis.assembly.add_rhea_chebi_annotation:main
+amplicon_study_summary_generator = mgnify_pipelines_toolkit.analysis.amplicon.study_summary_generator:cli
 antismash_gff_builder = mgnify_pipelines_toolkit.analysis.assembly.antismash_gff_builder:main
 are_there_primers = mgnify_pipelines_toolkit.analysis.amplicon.are_there_primers:main
+assembly_study_summary_generator = mgnify_pipelines_toolkit.analysis.assembly.study_summary_generator:cli
 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
 classify_var_regions = mgnify_pipelines_toolkit.analysis.amplicon.classify_var_regions:main
@@ -31,7 +33,6 @@ process_dbcan_clusters = mgnify_pipelines_toolkit.analysis.assembly.process_dbca
 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:cli
 summarise_antismash_bgcs = mgnify_pipelines_toolkit.analysis.assembly.summarise_antismash_bgcs:main
 summarise_goslims = mgnify_pipelines_toolkit.analysis.assembly.summarise_goslims:main
 summarise_sanntis_bgcs = mgnify_pipelines_toolkit.analysis.assembly.summarise_sanntis_bgcs:main