add support of mibig v4.0 (#286)

[MIBiG v4.0](https://mibig.secondarymetabolites.org/download) is released recently. This PR adds support for it.

src/nplinker/genomics/mibig/mibig_downloader.py

@@ -21,6 +21,7 @@
     "2.0": "843ce4677db6d11422f0e6d94dd03e81",
     "3.0": "7c38b90f939086c03392d99a913baef9",
     "3.1": "643d1349722a9437d8dcf558dac5f815",
+    "4.0": "70d1e7d573652ba62548b1fcfbdbf844",
 }
 
 
@@ -31,6 +32,8 @@ def download_and_extract_mibig_metadata(
 ):
     """Download and extract MIBiG metadata json files.
 
+    The MIBiG metadata json files are available at https://mibig.secondarymetabolites.org/download.
+
     Note that it does not matter whether the metadata json files are in nested folders or not in the archive,
     all json files will be extracted to the same location, i.e. `extract_path`. The nested
     folders will be removed if they exist. So the `extract_path` will have only json files.
@@ -39,7 +42,7 @@ def download_and_extract_mibig_metadata(
         download_root: Path to the directory in which to place the downloaded archive.
         extract_path: Path to an empty directory where the json files will be extracted.
             The directory must be empty if it exists. If it doesn't exist, the directory will be created.
-        version: _description_. Defaults to "3.1".
+        version: MIBiG version. Defaults to "3.1".
 
     Examples:
         >>> download_and_extract_mibig_metadata("/data/download", "/data/mibig_metadata")
@@ -58,7 +61,7 @@ def download_and_extract_mibig_metadata(
             raise ValueError(f'Nonempty directory: "{extract_path}"')
 
     # download and extract
-    md5 = _MD5_MIBIG_METADATA[version]
+    md5 = _MD5_MIBIG_METADATA.get(version, None)
     download_and_extract_archive(
         url=MIBIG_METADATA_URL.format(version=version),
         download_root=download_root,

src/nplinker/genomics/mibig/mibig_metadata.py

@@ -9,6 +9,8 @@ class MibigMetadata:
     MIBiG is a specification of BGC metadata and use JSON schema to
     represent BGC metadata. More details see:
     https://mibig.secondarymetabolites.org/download.
+
+    This class supports MIBiG version 1.0 to 4.0.
     """
 
     def __init__(self, file: str | PathLike) -> None:
@@ -37,22 +39,37 @@ def mibig_accession(self) -> str:
     def biosyn_class(self) -> tuple[str]:
         """Get the value of metadata item 'biosyn_class'.
 
-        The 'biosyn_class' is biosynthetic class(es), namely the type of
-        natural product or secondary metabolite.
+        The 'biosyn_class' is biosynthetic class(es) defined by MIBiG.
 
-        MIBiG defines 6 major biosynthetic classes for natural products,
+        Before version 4.0 of MIBiG, it defines 6 major biosynthetic classes,
         including `NRP`, `Polyketide`, `RiPP`, `Terpene`, `Saccharide`
-        and `Alkaloid`. Note that natural products created by the other
-        biosynthetic mechanisms fall under the category `Other`. For more details
-        see [the paper](https://doi.org/10.1186/s40793-018-0318-y).
+        and `Alkaloid`.
+
+        Starting from version 4.0, MIBiG defines 5 major biosynthetic classes,
+        including `PKS`, `NRPS`, `Ribosomal`, `Terpene` and `Saccharide`.
+
+        The mapping between the old and new classes is as follows:
+
+        - `NRP` -> `NRPS`
+        - `Polyketide` -> `PKS`
+        - `RiPP` -> `Ribosomal`
+        - `Terpene` -> `Terpene`
+        - `Saccharide` -> `Saccharide`
+        - `Alkaloid` -> `Other`
+
+        Note that natural products that do not fit into any of the above
+        biosynthetic classes fall under the category `Other`.
         """
         return self._biosyn_class
 
     def _parse_metadata(self) -> None:
         """Parse metadata to get 'mibig_accession' and 'biosyn_class' values."""
-        if "general_params" in self.metadata:
+        if "general_params" in self.metadata:  # version ≤1.4
             self._mibig_accession = self.metadata["general_params"]["mibig_accession"]
             self._biosyn_class = tuple(self.metadata["general_params"]["biosyn_class"])
-        else:  # version≥2.0
+        elif "cluster" in self.metadata:  # version ≥2.0 and <4.0
             self._mibig_accession = self.metadata["cluster"]["mibig_accession"]
             self._biosyn_class = tuple(self.metadata["cluster"]["biosyn_class"])
+        elif "version" in self.metadata:  # version≥4.0
+            self._mibig_accession = self.metadata["accession"]
+            self._biosyn_class = tuple(i["class"] for i in self.metadata["biosynthesis"]["classes"])