mgnify-pipelines-toolkit 0.1.8__py3-none-any.whl → 0.2.0__py3-none-any.whl

mgnify_pipelines_toolkit/schemas/schemas.py

@@ -0,0 +1,217 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Copyright 2024 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 re
+
+from enum import Enum
+from typing import ClassVar, Optional
+import pandera as pa
+
+from pydantic import (
+    Field,
+    BaseModel,
+    field_validator,
+    RootModel,
+)
+from pandera.engines.pandas_engine import PydanticModel
+
+from mgnify_pipelines_toolkit.constants.tax_ranks import (
+    SHORT_TAX_RANKS,
+    SHORT_PR2_TAX_RANKS,
+)
+
+
+class INSDCRunAccession(RootModel):
+    """Class for modelling for INSDC-specific run accessions.
+    Essentially is just a special string with regex-based validation of the accession.
+    """
+
+    # RootModel example:
+    # https://stackoverflow.com/questions/78393675/how-to-make-a-custom-type-inheriting-from-uuid-work-as-a-pydantic-model
+
+    root: str = Field(
+        unique=True,
+        description="The run needs to be a valid ENA accession",
+        examples=["ERR123456", "DRR789012", "SRR345678"],
+    )
+
+    @field_validator("root", mode="after")
+    @classmethod
+    def run_validity_check(cls, run: str) -> bool:
+        """Checks that the run string matches the regex code of an INSDC run accession.
+        Throws a `ValueError` exception if not, which is what Pydantic prefers for validation errors.
+        """
+
+        run_accession_regex = "(E|D|S)RR[0-9]{6,}"
+        regex_res = re.match(run_accession_regex, run)
+
+        if regex_res is None:
+            raise ValueError(
+                f"Accession `{run}` does not fit INSDC format [ERR*,SRR*,DRR*]."
+            )
+
+        return run
+
+
+class AmpliconResultTypes(str, Enum):
+    """Class that models the two allowed statuses for successful amplicon analysis runs.
+    Pydantic validates Enums very simply without needing to declare a new function.
+    """
+
+    all_results = "all_results"
+    no_asvs = "no_asvs"
+
+
+class AmpliconPassedRunsRecord(BaseModel):
+    """Class defining a Pydantic model for a single "row" of an amplicon passed runs file.
+    Uses the previous two classes.
+    """
+
+    run: INSDCRunAccession
+    status: AmpliconResultTypes
+
+
+class AmpliconNonINSDCSPassedRunsRecord(BaseModel):
+    """Class modeling a very similar model as the preceding one, but with no INSDC-validation.
+    This is achieved by replacing the type of the runs with just a simple string so no validation
+    happens.
+    """
+
+    run: str
+    status: AmpliconResultTypes
+
+
+# This is the schema for the whole DF
+class AmpliconPassedRunsSchema(pa.DataFrameModel):
+    """Class modelling a Pandera dataframe schema that uses the AmpliconPassedRunsRecord class as dtype.
+    This is what actually validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    class Config:
+        """Config with dataframe-level data type."""
+
+        dtype = PydanticModel(AmpliconPassedRunsRecord)
+        coerce = True
+
+
+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.
+    """
+
+    class Config:
+        """Config with dataframe-level data type."""
+
+        dtype = PydanticModel(AmpliconNonINSDCSPassedRunsRecord)
+        coerce = True
+
+
+class TaxRank(RootModel):
+    """Class for modelling a single Taxonomic Rank.
+    Essentially is just a special string with validation of the structure:
+    `${rank}__${taxon}`
+    Where `${rank}` is one of the allowed short ranks defined by the imported
+    `SHORT_TAX_RANKS` and `SHORT_PR2_TAX_RANKS` variables.
+    And `${taxon}` is the actual taxon for that rank (this isn't validated).
+    It will also validate if the whole string is the permitted "Unclassified".
+    """
+
+    valid_tax_ranks: ClassVar = SHORT_TAX_RANKS + SHORT_PR2_TAX_RANKS
+
+    root: str = Field(
+        unique=True,
+        description="A single taxon in a taxonomy record",
+        examples=["sk__Bacteria", "p__Bacillota", "g__Tundrisphaera"],
+    )
+
+    @field_validator("root", mode="after")
+    @classmethod
+    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:
+            raise ValueError(f"Invalid taxonomy rank {rank}.")
+
+        return taxrank
+
+
+# TODO: see if we can simplify the declaration of two Taxon classes by using one of these solutions
+# None of the solutions have a model-only way of doing it, but worth considering maybe
+# https://stackoverflow.com/questions/76537360/initialize-one-of-two-pydantic-models-depending-on-an-init-parameter
+
+
+class Taxon(BaseModel):
+    """Class for modelling an entire Taxon or taxonomic assignment.
+    All of the ranks are optional, to model for the taxon being "Unclassified".
+    """
+
+    Superkingdom: Optional[TaxRank] = None
+    Kingdom: Optional[TaxRank] = None
+    Phylum: Optional[TaxRank] = None
+    Class: Optional[TaxRank] = None
+    Order: Optional[TaxRank] = None
+    Family: Optional[TaxRank] = None
+    Genus: Optional[TaxRank] = None
+    Species: Optional[TaxRank] = None
+
+
+class PR2Taxon(Taxon):
+    """Class for modelling the same thing as the preceding class, but for PR2 ranks."""
+
+    Domain: Optional[TaxRank] = None
+    Supergroup: Optional[TaxRank] = None
+    Division: Optional[TaxRank] = None
+    Subdivision: Optional[TaxRank] = None
+
+
+class TaxonRecord(Taxon):
+    """Class for modelling a single taxon record in a taxonomy file.
+    It inherits the Taxon class, and simply adds a Count field, modelling the read counts
+    for that particular Taxon record.
+    """
+
+    Count: int
+
+
+class PR2TaxonRecord(PR2Taxon):
+    """Class for modelling the same thing as the preceding class, but for PR2 ranks."""
+
+    Count: int
+
+
+# This is the schema for the whole DF
+class TaxonSchema(pa.DataFrameModel):
+    """Class modelling a Pandera dataframe schema that uses the TaxonRecord class as dtype.
+    This is what actually validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    class Config:
+        """Config with dataframe-level data type."""
+
+        dtype = PydanticModel(TaxonRecord)
+        coerce = True
+
+
+class PR2TaxonSchema(pa.DataFrameModel):
+    """Class modelling the same dataframe schema as the preceding one, except for the PR2 taxonomy.
+    Uses the PR2TaxonSchema as a dtype to achieve this.
+    """
+
+    class Config:
+        """Config with dataframe-level data type."""
+
+        dtype = PydanticModel(PR2TaxonRecord)
+        coerce = True

{mgnify_pipelines_toolkit-0.1.8.dist-info → mgnify_pipelines_toolkit-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: mgnify_pipelines_toolkit
-Version: 0.1.8
+Version: 0.2.0
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -11,24 +11,30 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: biopython ==1.82
-Requires-Dist: numpy ==1.26.0
-Requires-Dist: pandas ==2.0.2
-Requires-Dist: regex ==2023.12.25
-Provides-Extra: dev
-Requires-Dist: mgnify-pipelines-toolkit[tests] ; extra == 'dev'
-Requires-Dist: pre-commit ==3.8.0 ; extra == 'dev'
-Requires-Dist: black ==24.8.0 ; extra == 'dev'
-Requires-Dist: flake8 ==7.1.1 ; extra == 'dev'
-Requires-Dist: pep8-naming ==0.14.1 ; extra == 'dev'
+Requires-Dist: biopython==1.82
+Requires-Dist: numpy==1.26.0
+Requires-Dist: pandas==2.0.2
+Requires-Dist: regex==2023.12.25
+Requires-Dist: requests==2.32.3
+Requires-Dist: click==8.1.7
+Requires-Dist: pandera==0.22.1
 Provides-Extra: tests
-Requires-Dist: pytest ==7.4.0 ; extra == 'tests'
-Requires-Dist: pytest-md ==0.2.0 ; extra == 'tests'
-Requires-Dist: pytest-workflow ==2.0.1 ; extra == 'tests'
-Requires-Dist: biopython ==1.82 ; extra == 'tests'
-Requires-Dist: pandas ==2.0.2 ; extra == 'tests'
-Requires-Dist: numpy ==1.26.0 ; extra == 'tests'
-Requires-Dist: regex ==2023.12.25 ; extra == 'tests'
+Requires-Dist: pytest==7.4.0; extra == "tests"
+Requires-Dist: pytest-md==0.2.0; extra == "tests"
+Requires-Dist: pytest-workflow==2.0.1; extra == "tests"
+Requires-Dist: biopython==1.82; extra == "tests"
+Requires-Dist: pandas==2.0.2; extra == "tests"
+Requires-Dist: numpy==1.26.0; extra == "tests"
+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"
+Provides-Extra: dev
+Requires-Dist: mgnify_pipelines_toolkit[tests]; extra == "dev"
+Requires-Dist: pre-commit==3.8.0; extra == "dev"
+Requires-Dist: black==24.8.0; extra == "dev"
+Requires-Dist: flake8==7.1.1; extra == "dev"
+Requires-Dist: pep8-naming==0.14.1; extra == "dev"
 
 # mgnify-pipelines-toolkit
 

{mgnify_pipelines_toolkit-0.1.8.dist-info → mgnify_pipelines_toolkit-0.2.0.dist-info}/RECORD

@@ -12,23 +12,32 @@ mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=d
 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/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/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
 mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py,sha256=H5ccd1e_e5dk8vhVOvHLK1lknYbRPbnqPjULCYnU0FQ,4021
 mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=xl5HduWtGPWiI9yqsjQ3itIzwHSxF2ig5KgjLXmj9EE,4772
 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/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=VaHL4mbof_9Gl7Ca3b2UkqjRqjAAvBYqprfbchae480,942
+mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=63dQlW7jAjLPOSCT670QCS5WhTp13vwaHqfmFYbKMyg,1076
 mgnify_pipelines_toolkit/constants/thresholds.py,sha256=zz8paGQfZAU8tT-RbSGpzZ1Aopf77yEs97BAblHH5fk,964
 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-0.1.8.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-0.1.8.dist-info/METADATA,sha256=Uf-ukd_8rWTprPyipZQXTy4ZKdpxNezdwwPNwtNFbRk,5859
-mgnify_pipelines_toolkit-0.1.8.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-mgnify_pipelines_toolkit-0.1.8.dist-info/entry_points.txt,sha256=tCZ7ijAgfIn47xXGxNtoZbHTDyUfHjUzjXg-NBRlj6g,1646
-mgnify_pipelines_toolkit-0.1.8.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-0.1.8.dist-info/RECORD,,
+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-0.1.8.dist-info → mgnify_pipelines_toolkit-0.2.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-0.1.8.dist-info → mgnify_pipelines_toolkit-0.2.0.dist-info}/entry_points.txt

@@ -1,11 +1,14 @@
 [console_scripts]
+add_rhea_chebi_annotation = mgnify_pipelines_toolkit.analysis.assembly.add_rhea_chebi_annotation:main
 are_there_primers = mgnify_pipelines_toolkit.analysis.amplicon.are_there_primers:main
 assess_inflection_point_mcp = mgnify_pipelines_toolkit.analysis.amplicon.assess_inflection_point_mcp:main
 assess_mcp_proportions = mgnify_pipelines_toolkit.analysis.amplicon.assess_mcp_proportions:main
+cgc_merge = mgnify_pipelines_toolkit.analysis.assembly.cgc_merge:combine_main
 classify_var_regions = mgnify_pipelines_toolkit.analysis.amplicon.classify_var_regions:main
 fasta_to_delimited = mgnify_pipelines_toolkit.utils.fasta_to_delimited:main
 fastq_suffix_header_check = mgnify_pipelines_toolkit.analysis.shared.fastq_suffix_header_check:main
 find_mcp_inflection_points = mgnify_pipelines_toolkit.analysis.amplicon.find_mcp_inflection_points:main
+generate_gaf = mgnify_pipelines_toolkit.analysis.assembly.generate_gaf:main
 get_mpt_version = mgnify_pipelines_toolkit.utils.get_mpt_version:main
 get_subunits = mgnify_pipelines_toolkit.analysis.shared.get_subunits:main
 get_subunits_coords = mgnify_pipelines_toolkit.analysis.shared.get_subunits_coords:main
@@ -17,3 +20,5 @@ primer_val_classification = mgnify_pipelines_toolkit.analysis.amplicon.primer_va
 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
+summarise_goslims = mgnify_pipelines_toolkit.analysis.assembly.summarise_goslims:main