BREAKING CHANGE: GenomeInfo -> AssemblyInfo migration (#6)

README.md

@@ -1 +1 @@
-# genomeinfo
+# assemblyinfo

genomeinfo/__init__.py → assemblyinfo/__init__.py

@@ -1,20 +1,20 @@
 from __future__ import annotations
 
 from . import core
-from .interface import GenomeInfo
+from .interface import AssemblyInfo
 
 for module in [core]:
     for name, func in module.__dict__.items():
         if callable(func) and not name.startswith("_"):
-            setattr(GenomeInfo, name, func)
+            setattr(AssemblyInfo, name, func)
 
-__all__ = ["GenomeInfo"]
+__all__ = ["AssemblyInfo"]
 
 
-_db: GenomeInfo | None = None
+_db: AssemblyInfo | None = None
 
-def connect() -> GenomeInfo:
+def connect() -> AssemblyInfo:
     global _db
     if _db is None:
-        _db = GenomeInfo()
+        _db = AssemblyInfo()
     return _db

genomeinfo/core/__init__.py → assemblyinfo/core/__init__.py

@@ -5,7 +5,7 @@
     get_refseq_accession,
 )
 from .assembly import (
-    AssemblyInfo,
+    Assembly,
     assembly_info,
 )
 from .chrom import (
@@ -52,6 +52,6 @@
     "get_chromsizes",
     "get_chrom_eq",
     "get_seqinfo",
-    "AssemblyInfo",
+    "Assembly",
     "assembly_info",
 ]

genomeinfo/core/acc.py → assemblyinfo/core/acc.py

@@ -29,7 +29,7 @@ def get_genbank_accession(cls, patch: str) -> str:
 
     Examples
     --------
-    >>> GenomeInfo.get_genbank_accession("GRCh38.p14")
+    >>> AssemblyInfo.get_genbank_accession("GRCh38.p14")
     """
     if not patch:
         raise ValueError("ERROR: you must provide a patch!")
@@ -60,7 +60,7 @@ def get_refseq_accession(cls, patch: str) -> str:
 
     Examples
     --------
-    >>> GenomeInfo.get_refseq_accession("GRCh38.p14")
+    >>> AssemblyInfo.get_refseq_accession("GRCh38.p14")
     """
     if not patch:
         raise ValueError("ERROR: you must provide a patch!")
@@ -91,7 +91,7 @@ def get_patch_from_accession(cls, accession: str) -> List[str]:
 
     Examples
     --------
-    >>> GenomeInfo.get_patch_from_accession("GCA_000001405.29")
+    >>> AssemblyInfo.get_patch_from_accession("GCA_000001405.29")
     """
     if not accession:
         raise ValueError("ERROR: you must provide an accession!")
@@ -130,7 +130,7 @@ def get_assembly_from_accession(cls, accession: str) -> List[str]:
 
     Examples
     --------
-    >>> GenomeInfo.get_assembly_from_accession("GCA_000001405.29")
+    >>> AssemblyInfo.get_assembly_from_accession("GCA_000001405.29")
     """
     if not accession:
         raise ValueError("ERROR: you must provide an accession!")

genomeinfo/core/assembly.py → assemblyinfo/core/assembly.py

@@ -6,11 +6,11 @@
 from .chrom import filter_chromosome_data
 from .info import get_assembly_metadata
 
-__all__ = ["AssemblyInfo", "assembly_info"]
+__all__ = ["Assembly", "assembly_info"]
 
 
 @dataclass
-class AssemblyInfo:
+class Assembly:
     """
     A dataclass to store assembly information.
     """
@@ -35,7 +35,7 @@ def chromeq(self) -> Dict[str, Dict[str, str]]:
         return pd.DataFrame(self.aliases).T
 
     def __repr__(self):
-        return (f"AssemblyInfo(assembly={self.assembly}",
+        return (f"Assembly(assembly={self.assembly}",
                 f"species={self.species}",
                 f"common_name={self.common_name})")
 
@@ -47,7 +47,7 @@ def assembly_info(
     roles: Optional[List[str]] = None,
     units: Optional[List[str]] = None,
     length: Optional[str] = None,
-) -> AssemblyInfo:
+) -> Assembly:
     """
     Get assembly information for a given assembly.
     Parameters
@@ -64,7 +64,7 @@ def assembly_info(
         Chromosome length.
     Returns
     -------
-    AssemblyInfo
+    Assembly
         Assembly information.
     Examples
     --------
@@ -92,7 +92,7 @@ def assembly_info(
 
     metadata = get_assembly_metadata(cls, assembly=assembly)
 
-    return AssemblyInfo(
+    return Assembly(
         assembly=assembly,
         species=metadata["species"],
         common_name=metadata["common_name"],

genomeinfo/core/chrom.py → assemblyinfo/core/chrom.py

@@ -44,7 +44,7 @@ def filter_chromosome_data(
 
     Examples
     --------
-    >>> GenomeInfo.filter_chromosome_data("hg38", roles=["assembled"])
+    >>> AssemblyInfo.filter_chromosome_data("hg38", roles=["assembled"])
     """
     if assembly in cls._data["assembly"].tolist():
         group = "assembly"
@@ -121,7 +121,7 @@ def get_chromnames(
 
     Examples
     --------
-    >>> GenomeInfo.get_chromnames("hg38", provider="ucsc")
+    >>> AssemblyInfo.get_chromnames("hg38", provider="ucsc")
     """
     if not provider or provider == "ucsc":
         colname = "name"
@@ -173,7 +173,7 @@ def get_chromsizes(
 
     Examples
     --------
-    >>> GenomeInfo.get_chromsizes("hg38", provider="ucsc")
+    >>> AssemblyInfo.get_chromsizes("hg38", provider="ucsc")
     """
     if not provider or provider == "ucsc":
         colname = "name"
@@ -226,7 +226,7 @@ def get_chrom_eq(
 
     Examples
     --------
-    >>> GenomeInfo.get_chrom_eq("hg38", providers=["ucsc", "genbank"])
+    >>> AssemblyInfo.get_chrom_eq("hg38", providers=["ucsc", "genbank"])
     """
     if not providers:
         providers = ["name", "ncbi", "genbank", "refseq"]
@@ -257,7 +257,7 @@ def get_seqinfo(cls, assembly: str) -> pd.DataFrame:
 
     Examples
     --------
-    >>> GenomeInfo.get_seqinfo("hg38")
+    >>> AssemblyInfo.get_seqinfo("hg38")
     """
     if assembly in cls._data["assembly"].tolist():
         group = "assembly"

genomeinfo/core/info.py → assemblyinfo/core/info.py

@@ -21,14 +21,14 @@
 
 def get_db(cls) -> pd.DataFrame:
     """
-    Returns the GenomeInfo database.
+    Returns the AssemblyInfo database.
 
     This method returns the database stored in the class attribute `_data`.
 
     Parameters
     ----------
     cls : type
-        The class object containing the GenomeInfo data.
+        The class object containing the AssemblyInfo data.
 
     Returns
     -------
@@ -37,24 +37,24 @@ def get_db(cls) -> pd.DataFrame:
 
     Examples
     --------
-    >>> GenomeInfo.get_db()
+    >>> AssemblyInfo.get_db()
     """
 
     return cls._data
 
 
 def info(cls) -> str:
     """
-    Display information about available entries in GenomeInfo.
+    Display information about available entries in AssemblyInfo.
 
     This method prints a formatted message showing the unique values for
     species, UCSC assemblies, and NCBI assemblies available in the
-    GenomeInfo data.
+    AssemblyInfo data.
 
     Parameters
     ----------
     cls : type
-        The class object containing the GenomeInfo data.
+        The class object containing the AssemblyInfo data.
 
     Returns
     -------
@@ -63,9 +63,9 @@ def info(cls) -> str:
 
     Examples
     --------
-    >>> GenomeInfo.info()
+    >>> AssemblyInfo.info()
     ```
-    GenomeInfo available entries:
+    AssemblyInfo available entries:
         Species:
             human, mouse, rat
         Assemblies (UCSC):
@@ -123,7 +123,7 @@ def get_info(cls, key: str, value: Optional[str]) -> pd.DataFrame:
 
     Examples
     --------
-    >>> GenomeInfo.get_info("species", "homo_sapiens")
+    >>> AssemblyInfo.get_info("species", "homo_sapiens")
     """
     if value is None:
         raise ValueError(f"ERROR! Pick a {key}: {cls._data[key].unique()}")
@@ -163,7 +163,7 @@ def get_species_info(cls, species: Optional[str] = None) -> str:
 
     Examples
     --------
-    >>> GenomeInfo.get_species_info("species", "homo_sapiens")
+    >>> AssemblyInfo.get_species_info("species", "homo_sapiens")
     ```
     Genome Information for homo_sapiens:
     Common Names:
@@ -201,7 +201,7 @@ def get_organism_info(cls, organism: Optional[str] = None) -> str:
 
     Examples
     --------
-    >>> GenomeInfo.get_species_info("species", "homo_sapiens")
+    >>> AssemblyInfo.get_species_info("species", "homo_sapiens")
     ```
     Genome Information for human:
     Species:
@@ -249,7 +249,7 @@ def get_assembly_metadata(cls, assembly: Optional[str] = None) -> Dict[str, Any]
 
     Examples
     --------
-    >>> GenomeInfo.get_assembly_metadata("hg38")
+    >>> AssemblyInfo.get_assembly_metadata("hg38")
         {
             'assembly_level': 'Chromosome',
             'assembly_method': None,
@@ -316,7 +316,7 @@ def build_assembly_info(cls, local_db: pd.DataFrame, assembly: str) -> Dict[str,
 
     Examples
     --------
-    >>> GenomeInfo.build_assembly_info(local_db, "hg38")
+    >>> AssemblyInfo.build_assembly_info(local_db, "hg38")
     """
     if len(local_db.patch) > 1:
         latest = sorted(local_db.patch.tolist(), key=get_version, reverse=True)[0]
@@ -357,7 +357,7 @@ def available_assemblies(cls, provider: Optional[str] = None) -> List[str]:
 
     Examples
     --------
-    >>> GenomeInfo.available_assemblies()
+    >>> AssemblyInfo.available_assemblies()
     ```
         ['WS144',
          'WBcel215',
@@ -397,7 +397,7 @@ def available_patches(cls, assembly: Optional[str] = None) -> List[str]:
 
     Examples
     --------
-    >>> GenomeInfo.available_patches('GRCh38')
+    >>> AssemblyInfo.available_patches('GRCh38')
     ```
         ['GRCh38',
          'GRCh38.p1',
@@ -433,7 +433,7 @@ def available_species(cls) -> List[str]:
 
     Examples
     --------
-    >>> GenomeInfo.available_species()
+    >>> AssemblyInfo.available_species()
     ```
     ['homo_sapiens', 'mus_musculus']
     ```
@@ -462,7 +462,7 @@ def available_accessions(cls, assembly: str) -> List[str]:
 
     Examples
     ---------
-    >>> GenomeInfo.available_accessions('hg38')
+    >>> AssemblyInfo.available_accessions('hg38')
      ```
     ['GCA_000001405.15',
      'GCA_000001405.16',

genomeinfo/interface.py → assemblyinfo/interface.py

@@ -4,10 +4,10 @@
 
 import pyarrow.parquet as pq
 
-__all__ = ["GenomeInfo"]
+__all__ = ["AssemblyInfo"]
 
 
-class GenomeInfo:
+class AssemblyInfo:
     _instance = None
     _db_path = Path(__file__).parent / "data" / "db.parquet"
 
@@ -23,5 +23,5 @@ def _load_db(self) -> None:
 
     @classmethod
     def connect(cls):
-        """Returns the singleton instance of GenomeInfo."""
+        """Returns the singleton instance of AssemblyInfo."""
         return cls()

docs/conf.py

@@ -9,9 +9,9 @@
 # -- Project information -----------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
-info = metadata("genomeinfo")
+info = metadata("assemblyinfo")
 project_name = info["Name"]
-project = "GenomeInfo"
+project = "AssemblyInfo"
 author = "Open2C"
 copyright = f"{datetime.now():%Y}, {author}."
 version = info["Version"]

docs/index.rst

@@ -1,12 +1,12 @@
-.. GenomeInfo documentation master file, created by
+.. assemblyinfo documentation master file, created by
    sphinx-quickstart on Sat Jul  6 23:33:22 2024.
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-genomeinfo
-==========
+assemblyinfo
+============
 
-`Genomeinfo <https://github.com/open2c/genomeinfo>`_ is a library to interact with genome metadata from different providers in python. This package is build on top of NCBI and UCSC data, allowing fast and accurate interconversions between chromosome names, latest assemblies and more!
+`Assemblyinfo <https://github.com/open2c/assemblyinfo>`_ is a library to interact with genome metadata from different providers in python. This package is build on top of NCBI and UCSC data, allowing fast and accurate interconversions between chromosome names, latest assemblies and more!
 
 .. toctree::
    :maxdepth: 2

docs/quickstart.md

@@ -3,18 +3,18 @@
 ## Installation
 
 ```
-$ pip install genomeinfo
+$ pip install assemblyinfo
 ```
 
 To install the latest development version of bioframe from github, first make a local clone of the github repository:
 
 ```
-$ git clone https://github.com/open2c/genomeinfo
+$ git clone https://github.com/open2c/assemblyinfo
 ```
 
 Then, compile and install bioframe in [development mode](https://setuptools.readthedocs.io/en/latest/setuptools.html#development-mode). This installs the package without moving it to a system folder, and thus allows for testing changes to the python code on the fly.
 
 ```
-$ cd bioframe
+$ cd assemblyinfo
 $ pip install -e ./
 ```