aldepyde 0.0.0a32__py3-none-any.whl → 0.0.0a35__py3-none-any.whl

aldepyde/__init__.py

@@ -17,25 +17,6 @@ def get_cache() -> CacheManager:
     global _cache_manager
     return _cache_manager
 
-# def get_cache() -> _cache_handler:
-#     global _cache
-#     # if _cache.null:
-#     #     return create_cache()
-#     return _cache
-
-# def SaveConfig(path: str="config.json", indent: str = "") -> None:
-#     global _config
-#     get_config().Save(path=path, indent=indent)
-#
-#
-# def LoadConfig(s: dict | str, ignore_missing=False) -> None:
-#     global _config
-#     get_config().Load(s, ignore_missing=ignore_missing)
-
-
-# from . import rand
-# from . import biomolecule
-# from . import fetcher
 
 from importlib import import_module
 

aldepyde/biomolecule/__init__.py

@@ -13,3 +13,6 @@ __all__ =  list(set(_amino_acid.__all__.copy()) |
            set(_pdb.__all__.copy()) |
            set(_rna.__all__.copy()))
 
+import sys
+
+sys.stderr.write("Note that the `biomolecule` submodule is not yet fully tested and may be unstable")

aldepyde/databases/SCOPe_Astral.py

@@ -0,0 +1,71 @@
+from aldepyde.databases._database import local_database
+import operator
+from contextlib import nullcontext
+import re
+
+class scop_parser(local_database):
+    op = {
+        "and": lambda a,b,c: a and b and c,
+        "or": lambda a,b,c: a or b or c
+    }
+
+    def fetch(self, url):
+        pass
+
+    def fetch_code(self, codes):
+        pass
+
+    def parse(self, text):
+        pass
+
+    def extract_all_scop(self):
+        pass
+
+    def partition_scope(self):
+        pass
+
+    def extract_all_astral(self):
+        lines = self.fp.readlines()
+        entry = b""
+        for line in lines:
+            if line.startswith(b">") and len(entry) > 0:
+                yield entry
+                entry = b""
+            entry += line
+        yield entry
+
+    # TODO allow a list of search parameters. Big challenge to make efficient, but could be cute
+    def partition_astral(self, destination:None|str=None, append=False, class_name:str=b'',contains_id:str=b'' , contains_desc:str=b'', mode="and") -> dict:
+        mode = mode.lower()
+        # Everything is a byte string in order to play nicely with future parent methods
+        if isinstance(class_name, str):
+            class_name = class_name.encode('utf-8')
+        if isinstance(contains_desc, str):
+            contains_desc = contains_desc.encode('utf-8')
+        if isinstance(contains_id, str):
+            contains_id = contains_id.encode('utf-8')
+        if mode != "and" and mode != "or":
+            raise ValueError("mode must be \"and\" or \"or\".")
+        logic = scop_parser.op[mode]
+        regex = re.compile(b">[a-zA-Z0-9_.]* *[a-l](.[0-9]+)?(.[0-9]+)?(.[0-9]+)?")
+        if append:
+            file_context = open(destination, 'ab') if destination is not None else nullcontext()
+        else:
+            file_context = open(destination, 'wb') if destination is not None else nullcontext()
+        with file_context as fp:
+            ret_dict = dict()
+            for line in self.extract_all_astral():
+                identifiers = regex.search(line).group().split()
+                id = identifiers[0]
+                cls = identifiers[1]
+                unmatched_spl = regex.sub(b'', line).split(b'\n')
+                desc = unmatched_spl[0]
+                sequence = unmatched_spl[1:]
+                if logic(class_name.lower() in cls.lower(), contains_id.lower() in id.lower(), contains_desc.lower() in desc.lower()):
+                    ret_dict[id] = { # Yes, I know '>' isn't part of the FASTA identifier. This keeps things more consistant
+                        "class" : cls,
+                        "description" : desc,
+                        "sequence" : b"".join(sequence)
+                    }
+                    fp.write(line)
+        return ret_dict

aldepyde/databases/UniRef.py

@@ -1,23 +1,22 @@
 import zlib
-
-from aldepyde.databases.RemoteFileHandler import RemoteFileHandler
-from aldepyde.databases._database import _database
+from aldepyde.databases._database import streamable_database
 from aldepyde.utils import ProgressBar
-import os
-import gzip
 
-class uniref_parser(_database):
+class uniref_parser(streamable_database):
     def __init__(self):
-        pass
+        super().__init__()
+
+    # TODO single entry parsing
+    # TODO store metadata upon request
+    # TODO implement abstract methods
 
-    #TODO Fix the total calculation
     @staticmethod
-    def stream_uniref_gz(filepath, chunk_size=8192, use_progress_bar=False):
-        if use_progress_bar is not None:
-            raw_stream, size = _database.open_stream(filepath)
-            pbar = ProgressBar(size//chunk_size) if use_progress_bar else None
-            decompressor = zlib.decompressobj(16 + zlib.MAX_WBITS)
-            try:
+    def stream_uniref_gz(filepath, chunk_size=8192, use_progress_bar=False, stitch=False):
+        raw_stream, size = streamable_database.open_stream(filepath)
+        pbar = ProgressBar(size//chunk_size) if use_progress_bar else None
+        decompressor = zlib.decompressobj(16 + zlib.MAX_WBITS)
+        try:
+            if not stitch:
                 while True:
                     comp_chunk = raw_stream.read(chunk_size)
                     if not comp_chunk:
@@ -30,8 +29,27 @@ class uniref_parser(_database):
                 final = decompressor.flush()
                 if final:
                     yield final
-            finally:
-                raw_stream.close()
+            else:
+                # Really hacky solution for now
+                # TODO Clean this up
+                yield from uniref_parser.stitch_streamed_sequences(
+                    uniref_parser.stream_uniref_gz(filepath=filepath, chunk_size=chunk_size, use_progress_bar=use_progress_bar, stitch=False))
+        finally:
+            raw_stream.close()
+
+    @staticmethod
+    def download_file(url, destination, chunk_size=8192, use_progress_bar=False):
+        raw_stream, size = streamable_database.open_stream(url)
+        pbar = ProgressBar(size // chunk_size) if use_progress_bar else None
+        with open(destination, 'wb') as fp:
+            while True:
+                chunk = raw_stream.read(chunk_size)
+                if not chunk:
+                    break
+                if pbar is not None:
+                    pbar.update()
+                fp.write(chunk)
+
 
     @staticmethod
     def stitch_streamed_sequences(stream, as_str=True):
@@ -52,24 +70,45 @@ class uniref_parser(_database):
         return b"".join(lines[1:])
 
     @staticmethod
-    def stream_uniref50(chunk_size=8192, use_progress_bar=False):
-        yield from uniref_parser.stream_uniref_gz('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz',
+    def stream_uniref50(chunk_size=8192, use_progress_bar=False, stitch=False):
+        if not stitch:
+            yield from uniref_parser.stream_uniref_gz('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz',
                                                   chunk_size=chunk_size, use_progress_bar=use_progress_bar)
-        # yield from RemoteFileHandler.stream_url(
-        #         'https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz', chunk_size=chunk_size)
+        else:
+            yield from uniref_parser.stitch_streamed_sequences(uniref_parser.stream_uniref_gz(
+                'https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz',
+                                                  chunk_size=chunk_size, use_progress_bar=use_progress_bar))
 
     @staticmethod
-    def stream_uniref90(chunk_size=8192, use_progress_bar=False):
-        yield from uniref_parser.stream_uniref_gz('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz',
+    def stream_uniref90(chunk_size=8192, use_progress_bar=False, stitch=False):
+        if not stitch:
+            yield from uniref_parser.stream_uniref_gz('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz',
                                                   chunk_size=chunk_size, use_progress_bar=use_progress_bar)
-
-        # yield from RemoteFileHandler.stream_url(
-        #         'https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz', chunk_size=chunk_size)
+        else:
+            yield from uniref_parser.stitch_streamed_sequences(uniref_parser.stream_uniref_gz(
+                'https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz',
+                chunk_size=chunk_size, use_progress_bar=use_progress_bar))
 
     @staticmethod
-    def stream_uniref100(chunk_size=8192, use_progress_bar=False):
-        yield from uniref_parser.stream_uniref_gz('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz',
+    def stream_uniref100(chunk_size=8192, use_progress_bar=False, stitch=False):
+        if not stitch:
+            yield from uniref_parser.stream_uniref_gz('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.fasta.gz',
                                                   chunk_size=chunk_size, use_progress_bar=use_progress_bar)
+        else:
+            yield from uniref_parser.stitch_streamed_sequences(uniref_parser.stream_uniref_gz(
+                'https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.fasta.gz',
+                chunk_size=chunk_size, use_progress_bar=use_progress_bar))
+
+    @staticmethod
+    def download_uniref50(destination='uniref50.fasta.gz', chunk_size=8192, use_progress_bar=False):
+        uniref_parser.download_file('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50/uniref50.fasta.gz', destination=destination,
+                                    chunk_size=chunk_size, use_progress_bar=use_progress_bar)
 
-        # yield from RemoteFileHandler.stream_url(
-        #         'https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.fasta.gz', chunk_size=chunk_size)
+    @staticmethod
+    def download_uniref90(destination='uniref90.fasta.gz', chunk_size=8192, use_progress_bar=False):
+        uniref_parser.download_file('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz', destination=destination,
+                                    chunk_size=chunk_size, use_progress_bar=use_progress_bar)
+    @staticmethod
+    def download_uniref100(destination='uniref100.fasta.gz', chunk_size=8192, use_progress_bar=False):
+        uniref_parser.download_file('https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref100/uniref100.fasta.gz', destination=destination,
+                                    chunk_size=chunk_size, use_progress_bar=use_progress_bar)

aldepyde/databases/_database.py

@@ -5,7 +5,10 @@ import os
 from typing import Tuple, BinaryIO
 from io import TextIOWrapper
 
-class _database(ABC):
+class streamable_database(ABC):
+
+    def __init__(self):
+        pass
 
     @abstractmethod
     def fetch(self, url):
@@ -35,4 +38,35 @@ class _database(ABC):
     # Yes, I know the first conditionals do the same thing
 
     def __call__(self):
-        pass
+        pass
+
+class local_database(ABC):
+
+    def __init__(self, filepath=None, as_fp=False):
+        self.fp = None
+        self.as_fp = as_fp
+        self.size = None
+        self.load_path(filepath)
+
+    def load_path(self, filepath):
+        self.filepath = filepath
+
+    def get_pointer(self):
+        return self.fp
+
+    def __enter__(self):
+        self.fp, self.size = local_database.open_stream(self.filepath)
+        if self.as_fp:
+            return self.fp
+        else:
+            return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        if self.fp is not None:
+            self.fp.close()
+        self.fp = None
+
+    @staticmethod
+    def open_stream(source:str) -> Tuple[BinaryIO, int] | None:
+        size = os.path.getsize(source)
+        return open(source, 'rb'), size

aldepyde/rand/RandomProtein.py

@@ -11,6 +11,8 @@ class InvalidDistribution(Exception):
 class ImpossibleSetting(Exception):
     pass
 
+
+# TODO This whole thing needs to be cleaned up to better align with more modern python
 class RandomProtein:
     # Hardcode data for now
     def __init__(self, His_Is_Charged=True, Cys_Is_Polar=True, Charged_Is_Polar=True, Distribution="Swiss"):

aldepyde/rand/__init__.py

@@ -1,3 +1,6 @@
 from aldepyde.rand.RandomProtein import *
 
-__all__ = ['RandomProtein']
+__all__ = ['RandomProtein']
+
+import sys
+sys.stderr.write("Note that the `rand` submodule is not yet fully tested and may be unstable")

{aldepyde-0.0.0a32.dist-info → aldepyde-0.0.0a35.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aldepyde
-Version: 0.0.0a32
+Version: 0.0.0a35
 Summary: A package of chemistry and biochemical tools
 Author-email: Nate McMurray <nate.mcmurray13@gmail.com>
 License: MIT License

{aldepyde-0.0.0a32.dist-info → aldepyde-0.0.0a35.dist-info}/RECORD

@@ -1,4 +1,4 @@
-aldepyde/__init__.py,sha256=MY5qU07PyoSEySBCRiQcjiYhME8F4EjjTeTtBOf71zE,1378
+aldepyde/__init__.py,sha256=vAL59PwNON2aqFJWnN62vwuJ2Q-1F0qwbGQb3ek4dnw,862
 aldepyde/_config.py,sha256=Jne1TH8w_brEpUD3b-4XY2T8nXtWi8mTcBV5_YqMlX0,4789
 aldepyde/configurable.py,sha256=OJ7vLA-UIAmsNVw_A_j2nCERUi91kRtFGZS9Brr_7s0,214
 aldepyde/data.py,sha256=4dhArC3yt8u7sArrZ5lvWEtwFC7rhM4B02LofbQVV64,5780
@@ -9,7 +9,7 @@ aldepyde/Parsers/_pdb_parser.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 aldepyde/biomolecule/Residue.py,sha256=CgTEIT7F4ljgxSscxzGU1AuThIRnX7i1mJ1DleUrcN0,172
 aldepyde/biomolecule/_Atom.py,sha256=XkZ-qu7U2EHbRJ7erLKV-qUc6NpizCiWbxqGZw0FHpQ,3314
 aldepyde/biomolecule/_AtomFactory.py,sha256=CA4PCESBe55ttr4riBX0F8nFToqbAAT4VSgP06_WER4,2642
-aldepyde/biomolecule/__init__.py,sha256=FlVxzp2MSgD6hGZUo-1mY6M4AarSxqFdNw2mpLRiu5Y,482
+aldepyde/biomolecule/__init__.py,sha256=mBr_PozzTu70-rgMWXFFJQB5ZINjQBFOo5F7Lt-JdQg,597
 aldepyde/biomolecule/_amino_acid.py,sha256=Ovgx12oygCDQuZjSSRVhdMY7nNPhJWFgcLIB537x-QM,116
 aldepyde/biomolecule/_dna.py,sha256=VWanPQRkD_GHMLjudSsZkDzIHVMWqcPB87b4APpGZC0,102
 aldepyde/biomolecule/_pdb.py,sha256=fh0hZaueFV8EuKfGBTpmCyI40fR7l6HYUFiGAS1kGto,17244
@@ -24,20 +24,21 @@ aldepyde/data/RemoteFileHandler.py,sha256=aPASdoYgt0xnRrSYiwMcefQAizLIbB93SKVrlf
 aldepyde/data/__init__.py,sha256=_yKL38EKhXkRM8PSafeee0A6VXGncAoUXVdUyiJ5n3s,48
 aldepyde/databases/PDB.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aldepyde/databases/RemoteFileHandler.py,sha256=HHx69o6IpI60lf_7hY1ZwI8k0OVyfofG4x1bFeF1uL4,1231
-aldepyde/databases/UniRef.py,sha256=AMRUXe8hy6il7EDWcBeQAM2g51_t3q0y-UoXhIPJpdU,3567
+aldepyde/databases/SCOPe_Astral.py,sha256=zj34CbMSTmTa-KBowND-S9rxNGGFnr84OuxC_fumM6E,2821
+aldepyde/databases/UniRef.py,sha256=lAT5XVO9Rk4_9XDKs5Nr1aGBbkaQ6m-vM0yufym43aY,6004
 aldepyde/databases/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aldepyde/databases/_database.py,sha256=ZRwGWyuhXHe9i0WYzStqRL7-SYevQkR5Jik7J360a2A,949
+aldepyde/databases/_database.py,sha256=fvm4jaP9UKHDeS-0wwWyp7i4uo9PjCGDbwJgdkD8MLo,1822
 aldepyde/fetcher/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aldepyde/fetcher/test.py,sha256=Q0O3TrMnyd_V3QZvMaDtkFGXIvtQLg57RofKjxtG8Y8,23
 aldepyde/json/CHG.json,sha256=igz1QSwoyXieOWMRwPnQjUJX29N5bk5OBVkhpFjyCzo,614
 aldepyde/json/Swiss_Prot.json,sha256=mJiUiYnvDLa_59tlb_hcIsaYGFrwvJAorwhHc2O9H1U,612
 aldepyde/json/chemistry.json,sha256=pCWYNRv5xVEMuhYi1nn1RutgsoFSMo_TRu1dk_TYyds,124436
-aldepyde/rand/RandomProtein.py,sha256=CaFYJh8WiT5hvvWONXNkJAEVLefu7qPfnLi7WR5YL1g,16056
-aldepyde/rand/__init__.py,sha256=1EztGz5e6NRmKuAfp66trQDDa5ov-_ZkxrD9Zp8fScA,72
+aldepyde/rand/RandomProtein.py,sha256=sNXx4jop9Fplz2oz4g6pEArF69j31_PvtiZuRpLz51I,16146
+aldepyde/rand/__init__.py,sha256=Q30wrG_XHrmdgaXaLWSlce_ZGT_ZpOT3CYLDj6OgEy0,182
 aldepyde/stats/ProteinStats.py,sha256=t_gqhld2wKweszPZvtHhrORadFc28glFx5OgJs23TsM,2569
 aldepyde/stats/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aldepyde-0.0.0a32.dist-info/licenses/LICENSE,sha256=VbOVaNlEaWa9cnYi8gOnenCBAVk9s_P3J_z-n_F-638,1091
-aldepyde-0.0.0a32.dist-info/METADATA,sha256=VpqfGzulHQ-omiPapAvVCVMIRGeTxPKUroF8FJkKBe8,2554
-aldepyde-0.0.0a32.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-aldepyde-0.0.0a32.dist-info/top_level.txt,sha256=xv0YJ1izG4AP9ZlielN_0z9QGQQdwtHFM3-TmJivBOM,9
-aldepyde-0.0.0a32.dist-info/RECORD,,
+aldepyde-0.0.0a35.dist-info/licenses/LICENSE,sha256=VbOVaNlEaWa9cnYi8gOnenCBAVk9s_P3J_z-n_F-638,1091
+aldepyde-0.0.0a35.dist-info/METADATA,sha256=NdHCpQYVP7NbBRxOmUXvu5ZlsD94jVS_z6ABY_Ejees,2554
+aldepyde-0.0.0a35.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+aldepyde-0.0.0a35.dist-info/top_level.txt,sha256=xv0YJ1izG4AP9ZlielN_0z9QGQQdwtHFM3-TmJivBOM,9
+aldepyde-0.0.0a35.dist-info/RECORD,,