Restructure codebase

This PR changes the locations of code files (or code) to make the structure look more logical. 

Changes:
- move runbigscape.py to bigscape folder
- move podp antismash downloader to antismash folder
- rename folder pairedomics to strain
- move strain related modules to strain folder
- move utils functions to related modules
- remove unused and empty class GNPSLoader

src/nplinker/arranger.py

@@ -6,19 +6,19 @@
 from jsonschema import validate
 import nplinker.globals as globals
 from nplinker.config import config
-from nplinker.genomics import generate_mappings_genome_id_bgc_id
+from nplinker.genomics.antismash import podp_download_and_extract_antismash_data
+from nplinker.genomics.bigscape.runbigscape import run_bigscape
 from nplinker.genomics.mibig import download_and_extract_mibig_metadata
+from nplinker.genomics.utils import generate_mappings_genome_id_bgc_id
 from nplinker.globals import GENOME_BGC_MAPPINGS_FILENAME
 from nplinker.globals import GENOME_STATUS_FILENAME
 from nplinker.globals import STRAIN_MAPPINGS_FILENAME
 from nplinker.metabolomics.gnps import GNPSDownloader
 from nplinker.metabolomics.gnps import GNPSExtractor
-from nplinker.pairedomics import podp_download_and_extract_antismash_data
-from nplinker.pairedomics.runbigscape import run_bigscape
-from nplinker.pairedomics.strain_mappings_generator import podp_generate_strain_mappings
 from nplinker.schemas import STRAIN_MAPPINGS_SCHEMA
 from nplinker.schemas import USER_STRAINS_SCHEMA
 from nplinker.schemas import validate_podp_json
+from nplinker.strain.utils import podp_generate_strain_mappings
 from nplinker.utils import download_url
 from nplinker.utils import list_dirs
 from nplinker.utils import list_files

src/nplinker/genomics/__init__.py

@@ -1,21 +1,11 @@
 import logging
-from .abc import BGCLoaderBase
 from .bgc import BGC
 from .gcf import GCF
-from .utils import add_bgc_to_gcf
-from .utils import add_strain_to_bgc
-from .utils import generate_mappings_genome_id_bgc_id
-from .utils import get_mibig_from_gcf
 
 
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 
 __all__ = [
-    "BGCLoaderBase",
     "BGC",
     "GCF",
-    "add_bgc_to_gcf",
-    "add_strain_to_bgc",
-    "generate_mappings_genome_id_bgc_id",
-    "get_mibig_from_gcf",
 ]

src/nplinker/genomics/antismash/__init__.py

@@ -2,8 +2,18 @@
 from .antismash_downloader import download_and_extract_antismash_data
 from .antismash_loader import AntismashBGCLoader
 from .antismash_loader import parse_bgc_genbank
+from .podp_antismash_downloader import GenomeStatus
+from .podp_antismash_downloader import get_best_available_genome_id
+from .podp_antismash_downloader import podp_download_and_extract_antismash_data
 
 
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 
-__all__ = ["AntismashBGCLoader", "parse_bgc_genbank", "download_and_extract_antismash_data"]
+__all__ = [
+    "download_and_extract_antismash_data",
+    "AntismashBGCLoader",
+    "parse_bgc_genbank",
+    "GenomeStatus",
+    "get_best_available_genome_id",
+    "podp_download_and_extract_antismash_data",
+]

src/nplinker/genomics/bigscape/__init__.py

@@ -1,7 +1,8 @@
 import logging
 from .bigscape_loader import BigscapeGCFLoader
+from .runbigscape import run_bigscape
 
 
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 
-__all__ = ["BigscapeGCFLoader"]
+__all__ = ["BigscapeGCFLoader", "run_bigscape"]

src/nplinker/pairedomics/runbigscape.py → src/nplinker/genomics/bigscape/runbigscape.py

@@ -2,7 +2,7 @@
 import subprocess
 import sys
 from os import PathLike
-from ..logconfig import LogConfig
+from ...logconfig import LogConfig
 
 
 logger = LogConfig.getLogger(__name__)

src/nplinker/genomics/gcf.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 from typing import TYPE_CHECKING
 from nplinker.logconfig import LogConfig
-from nplinker.strain_collection import StrainCollection
+from nplinker.strain import StrainCollection
 
 
 if TYPE_CHECKING:

src/nplinker/genomics/utils.py

@@ -6,9 +6,12 @@
 from nplinker.globals import GENOME_BGC_MAPPINGS_FILENAME
 from nplinker.logconfig import LogConfig
 from nplinker.schemas import GENOME_BGC_MAPPINGS_SCHEMA
-from nplinker.strain_collection import StrainCollection
+from nplinker.schemas import validate_podp_json
+from nplinker.strain import StrainCollection
 from nplinker.utils import list_dirs
 from nplinker.utils import list_files
+from ..genomics.antismash.podp_antismash_downloader import GenomeStatus
+from ..genomics.antismash.podp_antismash_downloader import get_best_available_genome_id
 from .bgc import BGC
 from .gcf import GCF
 
@@ -179,3 +182,128 @@ def get_mibig_from_gcf(gcfs: list[GCF]) -> tuple[list[BGC], StrainCollection]:
                 if bgc.strain is not None:
                     mibig_strains_in_use.add(bgc.strain)
     return mibig_bgcs_in_use, mibig_strains_in_use
+
+
+# ------------------------------------------------------------------------------
+# Functions to extract mappings for genomics side:
+# strain_id <-> original_geonme_id <-> resolved_genome_id <-> bgc_id
+# ------------------------------------------------------------------------------
+def extract_mappings_strain_id_original_genome_id(
+    podp_project_json_file: str | PathLike
+) -> dict[str, set[str]]:
+    """Extract mappings "strain id <-> original genome id".
+
+    Args:
+        podp_project_json_file: The path to the PODP project
+            JSON file.
+
+    Returns:
+        Key is strain id and value is a set of original genome ids.
+
+    Notes:
+        The `podp_project_json_file` is the project JSON file downloaded from
+        PODP platform. For example, for project MSV000079284, its json file is
+        https://pairedomicsdata.bioinformatics.nl/api/projects/4b29ddc3-26d0-40d7-80c5-44fb6631dbf9.4.
+    """
+    mappings_dict = {}
+    with open(podp_project_json_file, "r") as f:
+        json_data = json.load(f)
+
+    validate_podp_json(json_data)
+
+    for record in json_data["genomes"]:
+        strain_id = record["genome_label"]
+        genome_id = get_best_available_genome_id(record["genome_ID"])
+        if genome_id is None:
+            logger.warning("Failed to extract genome ID from genome with label %s", strain_id)
+            continue
+        if strain_id in mappings_dict:
+            mappings_dict[strain_id].add(genome_id)
+        else:
+            mappings_dict[strain_id] = {genome_id}
+    return mappings_dict
+
+
+def extract_mappings_original_genome_id_resolved_genome_id(
+    genome_status_json_file: str | PathLike
+) -> dict[str, str]:
+    """Extract mappings "original_genome_id <-> resolved_genome_id".
+
+    Args:
+        genome_status_json_file: The path to the genome status
+            JSON file.
+
+    Returns:
+        Key is original genome id and value is resolved genome id.
+
+    Notes:
+        The `genome_status_json_file` is usually generated by the
+        `podp_download_and_extract_antismash_data` function with
+        a default file name defined in `nplinker.globals.GENOME_STATUS_FILENAME`.
+    """
+    gs_mappings_dict = GenomeStatus.read_json(genome_status_json_file)
+    return {gs.original_id: gs.resolved_refseq_id for gs in gs_mappings_dict.values()}
+
+
+def extract_mappings_resolved_genome_id_bgc_id(
+    genome_bgc_mappings_file: str | PathLike
+) -> dict[str, set[str]]:
+    """Extract mappings "resolved_genome_id <-> bgc_id".
+
+    Args:
+        genome_bgc_mappings_file: The path to the genome BGC
+            mappings JSON file.
+
+    Returns:
+        Key is resolved genome id and value is a set of BGC ids.
+
+    Notes:
+        The `genome_bgc_mappings_file` is usually generated by the
+        `generate_mappings_genome_id_bgc_id` function with a default file name
+        defined in `nplinker.globals.GENOME_BGC_MAPPINGS_FILENAME`.
+    """
+    with open(genome_bgc_mappings_file, "r") as f:
+        json_data = json.load(f)
+
+    # validate the JSON data
+    validate(json_data, GENOME_BGC_MAPPINGS_SCHEMA)
+
+    return {mapping["genome_ID"]: set(mapping["BGC_ID"]) for mapping in json_data["mappings"]}
+
+
+def get_mappings_strain_id_bgc_id(
+    mappings_strain_id_original_genome_id: dict[str, set[str]],
+    mappings_original_genome_id_resolved_genome_id: dict[str, str],
+    mappings_resolved_genome_id_bgc_id: dict[str, set[str]],
+) -> dict[str, set[str]]:
+    """Get mappings "strain_id <-> bgc_id".
+
+    Args:
+        mappings_strain_id_original_genome_id: Mappings
+            "strain_id <-> original_genome_id".
+        mappings_original_genome_id_resolved_genome_id: Mappings
+            "original_genome_id <-> resolved_genome_id".
+        mappings_resolved_genome_id_bgc_id: Mappings
+            "resolved_genome_id <-> bgc_id".
+
+    Returns:
+        Key is strain id and value is a set of BGC ids.
+
+    See Also:
+        `extract_mappings_strain_id_original_genome_id`: Extract mappings
+            "strain_id <-> original_genome_id".
+        `extract_mappings_original_genome_id_resolved_genome_id`: Extract mappings
+            "original_genome_id <-> resolved_genome_id".
+        `extract_mappings_resolved_genome_id_bgc_id`: Extract mappings
+            "resolved_genome_id <-> bgc_id".
+    """
+    mappings_dict = {}
+    for strain_id, original_genome_ids in mappings_strain_id_original_genome_id.items():
+        bgc_ids = set()
+        for original_genome_id in original_genome_ids:
+            resolved_genome_id = mappings_original_genome_id_resolved_genome_id[original_genome_id]
+            if (bgc_id := mappings_resolved_genome_id_bgc_id.get(resolved_genome_id)) is not None:
+                bgc_ids.update(bgc_id)
+        if bgc_ids:
+            mappings_dict[strain_id] = bgc_ids
+    return mappings_dict

src/nplinker/loader.py

@@ -2,27 +2,27 @@
 from deprecated import deprecated
 from nplinker import globals
 from nplinker.config import config
-from nplinker.genomics import add_bgc_to_gcf
-from nplinker.genomics import add_strain_to_bgc
-from nplinker.genomics import get_mibig_from_gcf
 from nplinker.genomics.antismash import AntismashBGCLoader
 from nplinker.genomics.bigscape import BigscapeGCFLoader
 from nplinker.genomics.mibig import MibigLoader
+from nplinker.genomics.utils import add_bgc_to_gcf
+from nplinker.genomics.utils import add_strain_to_bgc
+from nplinker.genomics.utils import get_mibig_from_gcf
 from nplinker.globals import GNPS_ANNOTATIONS_FILENAME
 from nplinker.globals import GNPS_DEFAULT_PATH
 from nplinker.globals import GNPS_MOLECULAR_FAMILY_FILENAME
 from nplinker.globals import GNPS_SPECTRA_FILENAME
 from nplinker.globals import STRAIN_MAPPINGS_FILENAME
 from nplinker.globals import STRAINS_SELECTED_FILENAME
 from nplinker.logconfig import LogConfig
-from nplinker.metabolomics import add_annotation_to_spectrum
-from nplinker.metabolomics import add_spectrum_to_mf
-from nplinker.metabolomics import add_strains_to_spectrum
 from nplinker.metabolomics.gnps import GNPSAnnotationLoader
 from nplinker.metabolomics.gnps import GNPSMolecularFamilyLoader
 from nplinker.metabolomics.gnps import GNPSSpectrumLoader
-from nplinker.strain_collection import StrainCollection
-from nplinker.strain_loader import load_user_strains
+from nplinker.metabolomics.utils import add_annotation_to_spectrum
+from nplinker.metabolomics.utils import add_spectrum_to_mf
+from nplinker.metabolomics.utils import add_strains_to_spectrum
+from nplinker.strain import StrainCollection
+from nplinker.strain.utils import load_user_strains
 
 
 try:

src/nplinker/metabolomics/__init__.py

@@ -1,9 +1,6 @@
 import logging
 from .molecular_family import MolecularFamily
 from .spectrum import Spectrum
-from .utils import add_annotation_to_spectrum
-from .utils import add_spectrum_to_mf
-from .utils import add_strains_to_spectrum
 
 
 logging.getLogger(__name__).addHandler(logging.NullHandler())
@@ -12,7 +9,4 @@
 __all__ = [
     "MolecularFamily",
     "Spectrum",
-    "add_annotation_to_spectrum",
-    "add_spectrum_to_mf",
-    "add_strains_to_spectrum",
 ]

src/nplinker/metabolomics/abc.py

@@ -1,20 +1,24 @@
 from abc import ABC
 from abc import abstractmethod
 from collections.abc import Sequence
-from nplinker.metabolomics import MolecularFamily
-from nplinker.metabolomics import Spectrum
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from .molecular_family import MolecularFamily
+    from .spectrum import Spectrum
 
 
 class SpectrumLoaderBase(ABC):
     @property
     @abstractmethod
-    def spectra(self) -> Sequence[Spectrum]:
+    def spectra(self) -> Sequence["Spectrum"]:
         ...
 
 
 class MolecularFamilyLoaderBase(ABC):
     @abstractmethod
-    def get_mfs(self, keep_singleton: bool) -> Sequence[MolecularFamily]:
+    def get_mfs(self, keep_singleton: bool) -> Sequence["MolecularFamily"]:
         """Get MolecularFamily objects.
 
         Args:

src/nplinker/metabolomics/gnps/gnps_molecular_family_loader.py

@@ -1,8 +1,8 @@
 import csv
 from os import PathLike
-from nplinker.metabolomics import MolecularFamily
 from nplinker.metabolomics.abc import MolecularFamilyLoaderBase
 from nplinker.utils import is_file_format
+from ..molecular_family import MolecularFamily
 
 
 class GNPSMolecularFamilyLoader(MolecularFamilyLoaderBase):

src/nplinker/metabolomics/molecular_family.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 from typing import TYPE_CHECKING
-from nplinker.strain import Strain
-from nplinker.strain_collection import StrainCollection
+from ..strain.strain import Strain
+from ..strain.strain_collection import StrainCollection
 
 
 if TYPE_CHECKING:

src/nplinker/metabolomics/spectrum.py

@@ -3,7 +3,7 @@
 from typing import TYPE_CHECKING
 import numpy as np
 from nplinker.strain import Strain
-from nplinker.strain_collection import StrainCollection
+from nplinker.strain import StrainCollection
 
 
 if TYPE_CHECKING: