mgnify-pipelines-toolkit 1.2.6__py3-none-any.whl → 1.2.8__py3-none-any.whl

mgnify_pipelines_toolkit/constants/db_labels.py

@@ -19,3 +19,9 @@ TAXDB_LABELS = ["SILVA-SSU", "SILVA-LSU", "PR2", "UNITE", "ITSoneDB"]
 
 # taxonomy_summary for ASV method
 ASV_TAXDB_LABELS = ["DADA2-SILVA", "DADA2-PR2"]
+
+# taxonomy_summary labels for Raw Reads Analysis Pipeline
+RRAP_TAXDB_LABELS = ["silva-ssu", "silva-lsu", "motus"]
+
+# function_summary labels for Raw Reads Analysis Pipeline
+RRAP_FUNCDB_LABELS = ["pfam"]

mgnify_pipelines_toolkit/constants/tax_ranks.py

@@ -35,7 +35,8 @@ _PR2_TAX_RANKS = [
     "Genus",
     "Species",
 ]
+_MOTUS_TAX_RANKS = ["Kingdom", "Phylum", "Class", "Order", "Family", "Genus", "Species"]
 
 SHORT_TAX_RANKS = ["sk", "k", "p", "c", "o", "f", "g", "s"]
-
+SHORT_MOTUS_TAX_RANKS = ["k", "p", "c", "o", "f", "g", "s"]
 SHORT_PR2_TAX_RANKS = ["d", "sg", "dv", "sdv", "c", "o", "f", "g", "s"]

mgnify_pipelines_toolkit/schemas/schemas.py

@@ -16,7 +16,7 @@
 import logging
 import re
 
-from enum import Enum
+from enum import StrEnum
 from typing import ClassVar, Optional, Type, Literal
 
 import pandas as pd
@@ -35,6 +35,7 @@ from pandera.engines.pandas_engine import PydanticModel
 from mgnify_pipelines_toolkit.constants.tax_ranks import (
     SHORT_TAX_RANKS,
     SHORT_PR2_TAX_RANKS,
+    SHORT_MOTUS_TAX_RANKS,
 )
 
 
@@ -70,7 +71,7 @@ class INSDCRunAccession(RootModel):
         return run
 
 
-class AmpliconResultTypes(str, Enum):
+class AmpliconResultTypes(StrEnum):
     """Class that models the two allowed statuses for successful amplicon analysis runs.
     Pydantic validates Enums very simply without needing to declare a new function.
     """
@@ -545,7 +546,7 @@ class TaxonRecord(Taxon):
 class PR2TaxonRecord(PR2Taxon):
     """Class for modelling the same thing as the preceding class, but for PR2 ranks."""
 
-    Count: int
+    count: int = Field(alias="Count")
 
 
 # This is the schema for the whole DF
@@ -573,6 +574,154 @@ class PR2TaxonSchema(pa.DataFrameModel):
         coerce = True
 
 
+class RawReadsStatusTypes(StrEnum):
+    """Class that models the four allowed statuses for successful raw reads analysis runs.
+    Pydantic validates Enums very simply without needing to declare a new function.
+    """
+
+    all_results = "all_results"
+    no_reads = "no_reads"
+    all_empty_results = "all_empty_results"
+    some_empty_results = "some_empty_results"
+
+
+class RawReadsPassedRunsRecord(BaseModel):
+    """Class defining a Pydantic model for a single "row" of a raw-reads pipeline passed runs file.
+    Uses the previous nine classes.
+    """
+
+    run: INSDCRunAccession
+    status: RawReadsStatusTypes
+
+
+class RawReadsNonINSDCSPassedRunsRecord(RawReadsPassedRunsRecord):
+    """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
+
+
+# This is the schema for the whole DF
+class RawReadsPassedRunsSchema(pa.DataFrameModel):
+    """Class modelling a Pandera dataframe schema that uses the RawReadsPassedRunsRecord 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(RawReadsPassedRunsRecord)
+        coerce = True
+
+
+class RawReadsNonINSDCPassedRunsSchema(pa.DataFrameModel):
+    """Class modelling the same dataframe schema as the preceding one, except with no INSDC validation.
+    Uses the RawReadsNonINSDCSPassedRunsRecord as a dtype to achieve this.
+    """
+
+    class Config:
+        """Config with dataframe-level data type."""
+
+        dtype = PydanticModel(RawReadsNonINSDCSPassedRunsRecord)
+        coerce = True
+
+
+class MotusTaxRank(RootModel):
+    """Class for modelling a single Taxonomic Rank in mOTUs output.
+    Essentially is just a special string with validation of the structure:
+    `${rank}__${taxon}`
+    Where `${rank}` is one of the allowed short ranks defined by the imported
+    `SHORT_MOTUS_TAX_RANKS` variables.
+    And `${taxon}` is the actual taxon for that rank (this isn't validated).
+    It will also validate if the whole string is the permitted "unassigned" or "unclassified".
+    """
+
+    valid_tax_ranks: ClassVar = SHORT_MOTUS_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 not rank.capitalize() in {"Unclassified", "Unassigned"}
+            and rank not in cls.valid_tax_ranks
+        ):
+            raise ValueError(f"Invalid taxonomy rank {rank}.")
+
+        return taxrank
+
+
+class MotusTaxon(BaseModel):
+    """Class for modelling an entire MotusTaxon or mOTUs taxonomic assignment.
+    All of the ranks are optional, to model for the taxon being "Unclassified" or "Unassigned".
+    """
+
+    Kingdom: Optional[MotusTaxRank] = None
+    Phylum: Optional[MotusTaxRank] = None
+    Class: Optional[MotusTaxRank] = None
+    Order: Optional[MotusTaxRank] = None
+    Family: Optional[MotusTaxRank] = None
+    Genus: Optional[MotusTaxRank] = None
+    Species: Optional[MotusTaxRank] = None
+
+
+class MotusTaxonRecord(MotusTaxon):
+    """Class for modelling a single taxon record in a mOTUs taxonomy file.
+    It inherits the MotusTaxon class, and simply adds a Count field, modelling the read counts
+    for that particular MotusTaxon record.
+    """
+
+    count: int = Field(alias="Count")
+
+
+class MotusTaxonSchema(pa.DataFrameModel):
+    """Class modelling a Pandera dataframe schema that uses the MotusTaxonRecord 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(MotusTaxonRecord)
+        coerce = True
+
+
+class FunctionProfileRecord(BaseModel):
+    """Class for modelling a single taxon record in a functional profile file.
+    It models the read counts and coverage depth/breadth of each function (gene/protein)
+    for each specific record.
+    """
+
+    read_count: int
+    coverage_depth: float
+    coverage_breadth: float
+
+    class Config:
+        validate_by_name = True
+
+
+class FunctionProfileSchema(pa.DataFrameModel):
+    """Class modelling a Pandera dataframe schema that uses the FunctionProfileRecord 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(FunctionProfileRecord)
+        coerce = True
+
+
 def validate_dataframe(
     df: pd.DataFrame, schema: Type[pa.DataFrameModel], df_metadata: str
 ) -> DataFrameBase:

{mgnify_pipelines_toolkit-1.2.6.dist-info → mgnify_pipelines_toolkit-1.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.2.6
+Version: 1.2.8
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0

{mgnify_pipelines_toolkit-1.2.6.dist-info → mgnify_pipelines_toolkit-1.2.8.dist-info}/RECORD

@@ -1,7 +1,7 @@
 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/classify_var_regions.py,sha256=8yFhmHQXVDPXvRX8oWSANV3VMu0X-zNnz12u1fcGwTE,20649
-mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=ohguvrMSg7GuiiZ5aHj1DvCnfThKFUG4s13LUSMM0mo,8892
+mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=-g1FDwdEndWH9VvYLmc_NEs2l204kKjMHk65wag8T_s,8891
 mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=BLqhflblUegCvuQic16PrFXfIXlFWmGkmWJyl4wJoLQ,5040
 mgnify_pipelines_toolkit/analysis/amplicon/permute_primers.py,sha256=1aGOJX9tC7M1rnd0U2PeJ681sUo02wxk7_ycJqeVt6s,2216
 mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=-W_QmdmKAIqVC5n-RS8LX11hEQM4xdp5r1jkITB1CI8,5256
@@ -22,30 +22,31 @@ mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_clusters.py,sha2
 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=1wblLbZl521digIUWoqneAu15gErzvN_oC--5T_xUdw,4582
+mgnify_pipelines_toolkit/analysis/assembly/summarise_sanntis_bgcs.py,sha256=lxe7R2RQFyNCzEm6YuNRrqKZLZOUPq5W1P23Pt2sKBU,4570
 mgnify_pipelines_toolkit/analysis/genomes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/analysis/rawreads/study_summary_generator.py,sha256=ltyNHwzaZZkK1ScH2vV2QV1eUXTHQUMYyadJwO-zSQY,16028
 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
-mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py,sha256=hggPqv9QawWAccm5tmru4VF9VnQAHF5LCXnqyLw_BWI,6727
+mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py,sha256=RaFopUjJI4UO1ttnSEHj7iUXpAL5-2FTbDXlhOmNy0s,25534
 mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py,sha256=ye0Jka6_lNn4dQGb2QG3YT46y7QK0QvyaIitIaS8JVQ,4026
 mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=UrU0CpZj3pfHZWI7Uuhv2a_C0JsO8pnVErY0sWGgNdw,4920
 mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=EH5RyzesLqsonnTQbSDs7kAOV6IskS4oyqZYlex1tAY,1934
 mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py,sha256=6Ck2NhwRWw66GctUtKDdPT5fwJhWFR_YOZq-Vxwoa8A,1996
 mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=7-U0DN1joVu0ifLOoDUK2Pfqy8rb1RDKT6khVg3jky0,5559
 mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py,sha256=sKAo_rKEyVAZXSaIFMkpSoYZxiWwXMA3XDA6Z-hbHgg,7904
-mgnify_pipelines_toolkit/constants/db_labels.py,sha256=omPINMylAjO2PxeFhSk2MbYNcGZH3P82optSlMey3dw,858
+mgnify_pipelines_toolkit/constants/db_labels.py,sha256=12mksTtAwTE1smLnemdoItxGw1AmtJPOzbnW2aGj0u0,1062
 mgnify_pipelines_toolkit/constants/ncrna.py,sha256=a_5hWp446S7BhRbe_JcydFgZM7sgPLuMlaiBvKWN_XM,1928
 mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=G-xrc9b8zdmPTaOICD2b3RCVeFAEOVkfRkIfotQ7gek,1193
-mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=kMq__kOJcbiwsgolkdvb-XLo3WMnJdEXgedjUyMOYjI,1081
+mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=ekZN5OcMBhDRcj7XB_27wQ8fEnmAqMJc4aQ3pv4BRmI,1229
 mgnify_pipelines_toolkit/constants/thresholds.py,sha256=1AMBmoHBR0WjXZpkwJ7_Q-gfJtHXuCA4tZ-uvPhF0Xc,1085
 mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=0bM4MwarFiM5yTcp5AbAmQ0o-q-gWy7kknir9zJ9R0A,1312
-mgnify_pipelines_toolkit/schemas/schemas.py,sha256=pyDZvCuWbwccQF0D7c5BN1vv36wQdgcAUXU43_zAu74,18164
+mgnify_pipelines_toolkit/schemas/schemas.py,sha256=he9igC80YTR32v1e5NslwTgtdVySmnXwK9iY9IBPNBg,23133
 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-1.2.6.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.2.6.dist-info/METADATA,sha256=5XvhGHG2Zc5p8PNmR5ZYHUuRG1G6IIWT67t_FxkXkus,5775
-mgnify_pipelines_toolkit-1.2.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mgnify_pipelines_toolkit-1.2.6.dist-info/entry_points.txt,sha256=sHDxlHizt_iZPtkNp0EDuohDGvC4O12B57JtpUmHwYk,3123
-mgnify_pipelines_toolkit-1.2.6.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.2.6.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.2.8.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.2.8.dist-info/METADATA,sha256=RkF31O7GjADzb2k96oZxbyWOmDvN1bKzIThNTb0e7Qg,5775
+mgnify_pipelines_toolkit-1.2.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mgnify_pipelines_toolkit-1.2.8.dist-info/entry_points.txt,sha256=7TJ8GgbKoX1xnQsOdWwMvwhIv4uuHCx7pMxKmZabPOs,3228
+mgnify_pipelines_toolkit-1.2.8.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.2.8.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.2.6.dist-info → mgnify_pipelines_toolkit-1.2.8.dist-info}/entry_points.txt

@@ -6,7 +6,7 @@ assembly_study_summary_generator = mgnify_pipelines_toolkit.analysis.assembly.st
 classify_var_regions = mgnify_pipelines_toolkit.analysis.amplicon.classify_var_regions:main
 combined_gene_caller_merge = mgnify_pipelines_toolkit.analysis.assembly.combined_gene_caller_merge:main
 convert_cmscan_to_cmsearch_tblout = mgnify_pipelines_toolkit.analysis.shared.convert_cmscan_to_cmsearch_tblout:main
-dwc_summary_generator = mgnify_pipelines_toolkit.analysis.shared.dwc_summary_generator:main
+dwc_summary_generator = mgnify_pipelines_toolkit.analysis.shared.dwc_summary_generator:cli
 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
 generate_gaf = mgnify_pipelines_toolkit.analysis.assembly.generate_gaf:main
@@ -27,6 +27,7 @@ permute_primers = mgnify_pipelines_toolkit.analysis.amplicon.permute_primers:mai
 primer_val_classification = mgnify_pipelines_toolkit.analysis.amplicon.primer_val_classification:main
 process_dbcan_cazys = mgnify_pipelines_toolkit.analysis.assembly.process_dbcan_result_cazys:main
 process_dbcan_clusters = mgnify_pipelines_toolkit.analysis.assembly.process_dbcan_result_clusters:main
+rawreads_study_summary_generator = mgnify_pipelines_toolkit.analysis.rawreads.study_summary_generator:cli
 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
 summarise_antismash_bgcs = mgnify_pipelines_toolkit.analysis.assembly.summarise_antismash_bgcs:main