mgnify-pipelines-toolkit 1.1.0__py3-none-any.whl → 1.1.2__py3-none-any.whl

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-1.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.1.0
+Version: 1.1.2
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -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-1.1.2.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
@@ -21,11 +22,12 @@ mgnify_pipelines_toolkit/analysis/assembly/gff_file_utils.py,sha256=_4J31wAjK5B1
 mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py,sha256=_iaTBvMKbQDi_02_QuSPqLJ_rC37ruxiPHv5lLQmI-w,5480
 mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=eay9e3Xdc8XxnlC_4SHHjN89k-M9i_cFMc2lI_ZFxqY,5596
 mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py,sha256=uex2T6GagtYFBIc39-Xm4SFHL06KAQ5v0_loOmY_eaw,4289
-mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_cazys.py,sha256=KaJHOKfbIurbD1iiMssjdAaSAT8Nv-_ZUFwxkLqukAE,7799
+mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_cazys.py,sha256=5m5AwWEKidJx1FI0y93AFka7z0zEE8dBf1ofgP8TV_Y,7108
 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=eNichqFFmfPsa2J10IUm_PemVs9fBhbKa2vpDqEvJNU,21791
+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-1.1.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.1.2.dist-info/METADATA,sha256=5ByyTshLjj3V5NYnqFinX0ROLb9GmST0m_CltiUdBiY,5811
+mgnify_pipelines_toolkit-1.1.2.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
+mgnify_pipelines_toolkit-1.1.2.dist-info/entry_points.txt,sha256=JSjuxAr71MTeSUPPpno22wmZYgVO-gbsXfDkgWKkF7A,3533
+mgnify_pipelines_toolkit-1.1.2.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.1.2.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.1.0.dist-info → mgnify_pipelines_toolkit-1.1.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.0)
+Generator: setuptools (80.3.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-1.1.0.dist-info → mgnify_pipelines_toolkit-1.1.2.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