XspecT 0.1.3__py3-none-any.whl → 0.2.0__py3-none-any.whl

xspect/train_filter/extract_and_concatenate.py

@@ -1,6 +1,4 @@
-"""
-
-"""
+""" Module for extracting and concatenating assemblies. """
 
 __author__ = "Berger, Phillip"
 
@@ -8,121 +6,119 @@ import os
 import shutil
 from pathlib import Path
 from Bio import SeqIO
-from loguru import logger
-import xspect.file_io as file_io
-
-
-class ExtractConcatenate:
-    _fasta_endings = ["fasta", "fna", "fa", "ffn", "frn"]
-
-    def __init__(self, dir_name: str, delete: bool):
-        self._path = Path(os.getcwd()) / "genus_metadata" / dir_name
-        self._dir_name = dir_name
-        self._delete = delete
-        self._all_assemblies: list[str] = list()
-
-    def bf(self):
-        zip_path = self._path / "zip_files"
-        unzipped_path = self._path / "zip_files_extracted"
-        concatenate_path = self._path / "concatenate"
-        logger.info("Extracting assemblies")
-        file_io.extract_zip(zip_path, unzipped_path)
-        logger.info("Concatenating assemblies")
-        self._concatenate_bf(unzipped_path, concatenate_path)
-        self._save_all_assemblies()
-        if self._delete:
-            logger.info("Deleting copies")
-            file_io.delete_zip_files(zip_path)
-            shutil.rmtree(zip_path, ignore_errors=False)
-            shutil.rmtree(unzipped_path, ignore_errors=False)
-
-    def svm(self, species_accessions: dict):
-        zip_path = self._path / "training_data_zipped"
-        unzipped_path = self._path / "training_data_unzipped"
-        assemblies_path = self._path / "training_data"
-        logger.info("Extracting assemblies")
-        file_io.extract_zip(zip_path, unzipped_path)
-        logger.info("Copying assemblies into one folder")
-        self._copy_assemblies(unzipped_path, assemblies_path)
-        logger.info("Changing headers")
-        self._change_header(assemblies_path, species_accessions)
-        if self._delete:
-            logger.info("Deleting copies")
-            file_io.delete_zip_files(zip_path)
-            shutil.rmtree(zip_path, ignore_errors=False)
-            shutil.rmtree(unzipped_path, ignore_errors=False)
-
-    def _copy_assemblies(self, unzipped_path, assemblies_path):
-        os.mkdir(assemblies_path)
-        for folder in os.listdir(unzipped_path):
-            for root, dirs, files in os.walk(unzipped_path / str(folder)):
-                for file in files:
-                    file_ending = file.split(".")[-1]
-                    if file_ending in self._fasta_endings:
-                        file_path = Path(root) / file
-                        shutil.copy(file_path, (assemblies_path / file))
-
-    @staticmethod
-    def _change_header(assemblies_path, species_accessions: dict):
-        files = os.listdir(assemblies_path)
-        # Iterate through all species.
-        for name, accessions in species_accessions.items():
-            # Iterate through all accessions of the current species.
-            for accession in accessions:
-                # Iterate through all file names.
-                for file in files:
-                    if accession in file:
-                        file_path = assemblies_path / str(file)
-                        # Change the header.
-                        with open(file_path, "r") as f:
-                            sequence = ""
-                            for line in f.readlines():
-                                if line[0] != ">":
-                                    sequence += line
-                            new_header = f">{name}\n"
-                        with open(file_path, "w") as f:
-                            f.write(new_header)
-                            f.write(sequence)
-
-    def _concatenate_bf(self, unzipped_path, concatenate_path):
-        # Make new directory
-        os.mkdir(concatenate_path)
-
-        genus = self._dir_name.split("_")[0]
-        meta_path = self._path / (genus + ".fasta")
-
-        # Open the fasta files for each species.
-        for folder in os.listdir(unzipped_path):
-            species_files = list()
-            # Walk through dirs to get all fasta files.
-            for root, dirs, files in os.walk(unzipped_path / folder):
-                for file in files:
-                    file_ending = file.split(".")[-1]
-                    if file_ending in self._fasta_endings:
-                        species_files.append(Path(root) / file)
-                        self._all_assemblies.append(".".join(str(file).split(".")[:-1]))
-
-            # Gather all sequences and headers.
-            sequences = list()
-            headers = list()
-            for file in species_files:
-                records = SeqIO.parse(file, "fasta")
-                for record in records:
-                    headers.append(record.id)
-                    sequences.append(str(record.seq))
-
-            # Concatenate sequences
-            species_sequence = "".join(sequences)
-            species_header = ">" + " § ".join(headers) + "\n"
-
-            # Save concatenated sequences and headers
-            species_path = concatenate_path / (folder + ".fasta")
-            with open(species_path, "w") as species_file:
-                species_file.write(species_header)
-                species_file.write(species_sequence)
-
-    def _save_all_assemblies(self):
-        path = self._path / "all_bf_assemblies.txt"
-        with open(path, "w") as file:
-            for assembly in self._all_assemblies:
-                file.write(f"{assembly}\n")
+from xspect import file_io
+from xspect.definitions import get_xspect_tmp_path, fasta_endings
+
+
+def change_header(assemblies_path, species_accessions: dict):
+    """Change the header of the assemblies to the species name."""
+    files = os.listdir(assemblies_path)
+    # Iterate through all species.
+    for name, accessions in species_accessions.items():
+        # Iterate through all accessions of the current species.
+        for accession in accessions:
+            # Iterate through all file names.
+            for file in files:
+                if accession in file:
+                    file_path = assemblies_path / str(file)
+                    # Change the header.
+                    with open(file_path, "r", encoding="utf-8") as f:
+                        sequence = ""
+                        for line in f.readlines():
+                            if line[0] != ">":
+                                sequence += line
+                        new_header = f">{name}\n"
+                    with open(file_path, "w", encoding="utf-8") as f:
+                        f.write(new_header)
+                        f.write(sequence)
+
+
+def copy_assemblies(unzipped_path, assemblies_path):
+    """Copy all assemblies to a new directory."""
+    os.mkdir(assemblies_path)
+    for folder in os.listdir(unzipped_path):
+        for root, _, files in os.walk(unzipped_path / str(folder)):
+            for file in files:
+                file_ending = file.split(".")[-1]
+                if file_ending in fasta_endings:
+                    file_path = Path(root) / file
+                    shutil.copy(file_path, (assemblies_path / file))
+
+
+def concatenate_bf(unzipped_path, concatenate_path):
+    """Concatenate all assemblies for Bloom filter training."""
+
+    all_assemblies = []
+
+    # Make new directory
+    os.mkdir(concatenate_path)
+
+    # Open the fasta files for each species.
+    for folder in os.listdir(unzipped_path):
+        species_files = []
+        # Walk through dirs to get all fasta files.
+        for root, _, files in os.walk(unzipped_path / folder):
+            for file in files:
+                file_ending = file.split(".")[-1]
+                if file_ending in fasta_endings:
+                    species_files.append(Path(root) / file)
+                    all_assemblies.append(".".join(str(file).split(".")[:-1]))
+
+        # Gather all sequences and headers.
+        sequences = []
+        headers = []
+        for file in species_files:
+            records = SeqIO.parse(file, "fasta")
+            for record in records:
+                headers.append(record.id)
+                sequences.append(str(record.seq))
+
+        # Concatenate sequences
+        species_sequence = "".join(sequences)
+        species_header = ">" + " § ".join(headers) + "\n"
+
+        # Save concatenated sequences and headers
+        species_path = concatenate_path / (folder + ".fasta")
+        with open(species_path, "w", encoding="utf-8") as species_file:
+            species_file.write(species_header)
+            species_file.write(species_sequence)
+
+    return all_assemblies
+
+
+def save_all_assemblies(dir_path: Path, all_assemblies: list[str]):
+    """Save all assemblies to a file."""
+    path = dir_path / "all_bf_assemblies.txt"
+    with open(path, "w", encoding="utf-8") as file:
+        for assembly in all_assemblies:
+            file.write(f"{assembly}\n")
+
+
+def bf(dir_name: str, delete: bool):
+    """Extract and concatenate assemblies for Bloom filter training."""
+    dir_path = get_xspect_tmp_path() / dir_name
+    zip_path = dir_path / "zip_files"
+    unzipped_path = dir_path / "zip_files_extracted"
+    concatenate_path = dir_path / "concatenate"
+    file_io.extract_zip(zip_path, unzipped_path)
+    all_assemblies = concatenate_bf(unzipped_path, concatenate_path)
+    save_all_assemblies(dir_path, all_assemblies)
+    if delete:
+        file_io.delete_zip_files(zip_path)
+        shutil.rmtree(zip_path, ignore_errors=False)
+        shutil.rmtree(unzipped_path, ignore_errors=False)
+
+
+def svm(species_accessions: dict, dir_name: str, delete: bool):
+    """Extract and concatenate assemblies for generating SVM training data."""
+    dir_path = get_xspect_tmp_path() / dir_name
+    zip_path = dir_path / "training_data_zipped"
+    unzipped_path = dir_path / "training_data_unzipped"
+    assemblies_path = dir_path / "training_data"
+    file_io.extract_zip(zip_path, unzipped_path)
+    copy_assemblies(unzipped_path, assemblies_path)
+    change_header(assemblies_path, species_accessions)
+    if delete:
+        file_io.delete_zip_files(zip_path)
+        shutil.rmtree(zip_path, ignore_errors=False)
+        shutil.rmtree(unzipped_path, ignore_errors=False)

xspect/train_filter/html_scrap.py

@@ -1,26 +1,25 @@
-"""
-
-"""
+""" HTML Scraping for the taxonomy check results from NCBI."""
 
 __author__ = "Berger, Phillip"
 
 import datetime
-import requests
 import pickle
+import sys
 import time
-from pathlib import Path
-import os
-
+import requests
 from loguru import logger
+from xspect.definitions import get_xspect_root_path
 
 
 class TaxonomyCheck:
+    """Class to get the GCFs that passed the taxonomy check from NCBI."""
+
     _main_url = "https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/ANI_report_prokaryotes.txt"
     _test_url = "https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/"
-    _main_path = Path(os.getcwd()) / "genus_metadata" / "taxonomy_check.txt"
-    _test_path = Path(os.getcwd()) / "genus_metadata" / "tax_check_date.txt"
+    _main_path = get_xspect_root_path() / "taxonomy_check.txt"
+    _test_path = get_xspect_root_path() / "tax_check_date.txt"
     _new_time: list
-    _tax_check_ok = list()
+    _tax_check_ok = []
 
     def __init__(self):
         old_time = self._get_old_tax_date()
@@ -48,7 +47,7 @@ class TaxonomyCheck:
         else:
             logger.error("Nothing was found")
             logger.error("Aborting")
-            exit()
+            sys.exit()
 
     def _get_old_tax_date(self):
         try:
@@ -59,7 +58,7 @@ class TaxonomyCheck:
             return None
 
     def _get_new_tax_date(self):
-        raw_response = requests.get(self._test_url)
+        raw_response = requests.get(self._test_url, timeout=5)
         data = raw_response.text.split("\n")
         for line in data:
             if "ANI_report_prokaryotes.txt" in line:
@@ -69,22 +68,22 @@ class TaxonomyCheck:
                     int(date_parts[0]), int(date_parts[1]), int(date_parts[2])
                 )
                 time_parts = line_parts[-2].split(":")
-                time = datetime.time(int(time_parts[0]), int(time_parts[1]))
-                new_time = [date, time]
+                combined_time = datetime.time(int(time_parts[0]), int(time_parts[1]))
+                new_time = [date, combined_time]
 
                 return new_time
 
         return None
 
     def _update_tax_check(self):
-        raw_response = requests.get(self._main_url)
+        raw_response = requests.get(self._main_url, timeout=5)
         all_tax_checks = raw_response.text.split("\n")[1:-1]
         self._get_gcf_ok(all_tax_checks)
         self._save_time()
         self._save_file()
 
     def _get_gcf_ok(self, all_tax_checks: list):
-        tax_check_ok = list()
+        tax_check_ok = []
         for line in all_tax_checks:
             line_parts = line.split("\t")
             gcf = line_parts[1]
@@ -111,16 +110,5 @@ class TaxonomyCheck:
         return time.asctime(time.localtime()).split()[3]
 
     def ani_gcf(self):
+        """Returns ANI GCFs that passed the taxonomy check."""
         return self._tax_check_ok
-
-
-def main():
-    start = time.perf_counter()
-    tax_check = TaxonomyCheck()
-    end = time.perf_counter()
-    print(f"{end-start:.2f} s\n")
-    print(tax_check.ani_gcf()[:5])
-
-
-if __name__ == "__main__":
-    main()

xspect/train_filter/ncbi_api/download_assemblies.py

@@ -1,12 +1,12 @@
-"""
-
-"""
+"""This module contains methods to download assemblies from the NCBI database."""
 
 __author__ = "Berger, Phillip"
 
+# pylint: disable=line-too-long
+
 import os
-from pathlib import Path
 import requests
+from xspect.definitions import get_xspect_tmp_path
 
 
 def download_assemblies(accessions, dir_name, target_folder, zip_file_name):
@@ -21,12 +21,11 @@ def download_assemblies(accessions, dir_name, target_folder, zip_file_name):
     :param zip_file_name: Name of the zip file. E.g. Klebsiella aerogenes.zip.
     :type zip_file_name: str
     """
-    path = (
-        Path(os.getcwd()) / "genus_metadata" / dir_name / target_folder / zip_file_name
-    )
+
+    path = get_xspect_tmp_path() / dir_name / target_folder / zip_file_name
     api_url = f"https://api.ncbi.nlm.nih.gov/datasets/v1/genome/accession/{','.join(accessions)}/download"
     parameters = {"include_annotation_type": "GENOME_FASTA", "filename": zip_file_name}
     os.makedirs(os.path.dirname(path), exist_ok=True)
-    genome_download = requests.get(api_url, params=parameters)
+    genome_download = requests.get(api_url, params=parameters, timeout=20)
     with open(path, "wb") as f:
         f.write(genome_download.content)

xspect/train_filter/ncbi_api/ncbi_assembly_metadata.py

@@ -1,10 +1,8 @@
-"""
-
-"""
+""" Collects metadata of assemblies from NCBI API """
 
 __author__ = "Berger, Phillip"
 
-from time import sleep, asctime, localtime
+from time import sleep
 
 import requests
 
@@ -12,6 +10,8 @@ from loguru import logger
 
 
 class NCBIAssemblyMetadata:
+    """Class to collect metadata of assemblies from the NCBI API."""
+
     _all_metadata: dict
     _count: int
     _ani_gcf: list
@@ -28,9 +28,9 @@ class NCBIAssemblyMetadata:
 
         self._set_parameters()
 
-        tmp_metadata = dict()
+        tmp_metadata = {}
         for tax_id, curr_metadata in self._all_metadata.items():
-            sleep(1)
+            sleep(2)
             species_name = curr_metadata["sci_name"]
             logger.info("Collecting metadata of {name}", name=species_name)
             accessions = self._make_request(taxon=tax_id)
@@ -73,10 +73,10 @@ class NCBIAssemblyMetadata:
 
     def _make_request(self, taxon: str):
         api_url = f"https://api.ncbi.nlm.nih.gov/datasets/v1/genome/taxon/{taxon}"
-        accessions = list()
+        accessions = []
         count = 0
         for request_type, parameters in self._parameters.items():
-            raw_response = requests.get(api_url, params=parameters)
+            raw_response = requests.get(api_url, params=parameters, timeout=5)
             response = raw_response.json()
             if response:
                 try:
@@ -95,7 +95,6 @@ class NCBIAssemblyMetadata:
                         else:
                             break
                 except KeyError:
-                    pass
                     logger.debug(
                         "While requesting: {type} an error response was given",
                         type=request_type,
@@ -107,12 +106,5 @@ class NCBIAssemblyMetadata:
         return accessions
 
     def get_all_metadata(self):
+        """Returns all metadata of the assemblies."""
         return self._all_metadata_complete
-
-
-def main():
-    pass
-
-
-if __name__ == "__main__":
-    main()

xspect/train_filter/ncbi_api/ncbi_children_tree.py

@@ -6,6 +6,7 @@ The children are only of the next lower rank of the parent taxon.
 
 __author__ = "Berger, Phillip"
 
+import sys
 import requests
 
 from loguru import logger
@@ -24,7 +25,7 @@ class NCBIChildrenTree:
     def _request_tree(self):
         """Make the request for the children tree at the NCBI Datasets API."""
         api_url = f"https://api.ncbi.nlm.nih.gov/datasets/v1/taxonomy/taxon/{self._taxon}/filtered_subtree"
-        raw_response = requests.get(api_url)
+        raw_response = requests.get(api_url, timeout=5)
         self._response = raw_response.json()["edges"]
         self._parent_taxon_id = str(self._response["1"]["visible_children"][0])
         try:
@@ -33,7 +34,7 @@ class NCBIChildrenTree:
             logger.error("KeyError for key: {key}", key=self._parent_taxon_id)
             logger.error("Response: {response}", response=str(self._response))
             logger.error("Aborting")
-            exit()
+            sys.exit()
         for child_id in tmp_children_ids:
             self._children_taxon_ids.append(str(child_id))
 

xspect/train_filter/ncbi_api/ncbi_taxon_metadata.py

@@ -1,6 +1,4 @@
-"""
-
-"""
+""" This module is used to retrieve metadata from the NCBI taxonomy database. """
 
 __author__ = "Berger, Phillip"
 
@@ -10,19 +8,21 @@ from loguru import logger
 
 
 class NCBITaxonMetadata:
+    """Class to retrieve metadata from the NCBI taxonomy database."""
+
     _taxon: str
     _response: dict
     _all_metadata: dict
 
     def __init__(self, taxon: list[str]):
         self._taxon = ",".join(taxon)
-        self._all_metadata = dict()
+        self._all_metadata = {}
         self._request_metadata()
         self._collect_all_metadata()
 
     def _request_metadata(self):
         api_url = f"https://api.ncbi.nlm.nih.gov/datasets/v1/taxonomy/taxon/{str(self._taxon)}"
-        raw_response = requests.get(api_url)
+        raw_response = requests.get(api_url, timeout=5)
         self._response = raw_response.json()["taxonomy_nodes"]
 
     def _collect_all_metadata(self):
@@ -47,7 +47,9 @@ class NCBITaxonMetadata:
                 logger.debug("{name} was not used for training", name=name)
 
     def get_response(self):
+        """Returns the raw response from the NCBI taxonomy database."""
         return self._response
 
     def get_metadata(self):
+        """Returns the metadata from the NCBI taxonomy database."""
         return self._all_metadata

XspecT-0.1.3.dist-info/RECORD

@@ -1,49 +0,0 @@
-xspect/BF_v2.py,sha256=05sp27VzxFtsjt2oyMyhW4aqNmUxGTori49j6lxo1BU,25392
-xspect/Bootstrap.py,sha256=AYyEBo3MoOnPqhPAHe726mX8L9NuXDa5SATxZKLMv3s,830
-xspect/Classifier.py,sha256=BgqpZiMYi2maaccTzJcgH2tjrtDH-U7COc7E4t4cQt8,3602
-xspect/OXA_Table.py,sha256=1GxsyxMpUEgQirY0nJHtR3jl61DoPZh2Rb9L0VdMxD4,1632
-xspect/WebApp.py,sha256=H4NyfDELrqUSFKOGDLNSJxsNzfLsCX9_BJMln9UXQk0,24941
-xspect/XspecT_mini.py,sha256=OApDXSVIZFK8ZNpNJRPYTlyOLszZbpkJt3jJC51hV8Q,54694
-xspect/XspecT_trainer.py,sha256=6Gj2mltyVyM8Rsh5EU8tSCGMG7niYBLfId664zYaVXI,21703
-xspect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/download_filters.py,sha256=wSyX-IucjuKIEcVx-E0ClsA0XL0DI1FgMlO2UULgaXc,1048
-xspect/file_io.py,sha256=IWae7xxAt-EmyEbxo0nDSe3RJHmLkQT5jNS2Z3qLKdg,4807
-xspect/main.py,sha256=xZxaXOUvA26OurM9DLsbqDzpUEvbtTZOs4916y2Ifdo,2948
-xspect/map_kmers.py,sha256=63iTQS_GZZBK2DxjEs5xoI4KgfpZOntCKul06rrgi5w,6000
-xspect/search_filter.py,sha256=a0n2VHmmfVqXaKwLLb478Lvb46kN2GwNgFOZmee1_xo,17261
-xspect/static/How-To.png,sha256=QO6HydIHcL3oM9feMxmfZcKE8M62fIRl2xs_5S_NL5M,119621
-xspect/static/Logo.png,sha256=bvOWMpqxmBigg9jEvZtIMOsXncbSFwnYu4eYNSf1_Qw,296095
-xspect/static/Logo2.png,sha256=V7hpGb3XYLN5vEQQNJdpNjQX_F2A_f1wKAP8N37NwGs,292730
-xspect/static/Workflow_AspecT.png,sha256=RsFIN_18d71cSdupskRHb9X-P0xCsX2mNSS381bPzfc,80863
-xspect/static/Workflow_ClAssT.png,sha256=92stJJHeLO7RhK1shuKehP-AGWeQLWMEbpX3KneSe4I,1136026
-xspect/static/js.js,sha256=2sVwS3AToSO0IsEYvRxT_8HQRQPPJuzVFAQok16SDhg,21344
-xspect/static/main.css,sha256=9Dkd6EaiF9-mLkXsOV0tQhDoO6Uuw-X2StqzKUGv2lE,4623
-xspect/templates/400.html,sha256=XpJT3nyaCHgCYUpbNJymUziB3SBaccb02PV77d5QHjI,2672
-xspect/templates/401.html,sha256=5LUGd5MEmsFaOBbXHL1nDQJBmEi3KEYTgc4gdM8s2wU,2504
-xspect/templates/404.html,sha256=XjnJXkKHJfVMOhJ75xDS-a7VnbcikAXI7JS5sdxokVo,2487
-xspect/templates/500.html,sha256=y5UIlBffXdg7c95hcT3qwWmxvXHqSlLUE8dUV7gkIFE,2570
-xspect/templates/about.html,sha256=xLI9orZJAAoFnRDmrVczZuFnTkurbC3qmC_ITQdan2Y,26509
-xspect/templates/home.html,sha256=MGQN1dJ2yaz7j8Z2N5pzvTDaZyiWdrlQvYwiTGXpjfA,1667
-xspect/templates/layoutabout.html,sha256=ICC8g0DP8a7MLNrEYnXBgtnkwMjIktsimmqwqjMU2yw,3847
-xspect/templates/layouthome.html,sha256=6EtVD-L6xlTc7XGk77f9CARKW7JLpv2iiyUci1BK00A,2870
-xspect/templates/layoutspecies.html,sha256=MNGSDEvuKFvgsyXoRLCu-rma10gntUI9vP_9a2sNl7M,24008
-xspect/templates/species.html,sha256=rD9fCmSgyI8hRcmy56mNQH7VR5jnmtriv9WlvTIJJjE,2412
-xspect/train_filter/README_XspecT_Erweiterung.md,sha256=Gn64Biz32LiUfQVYb43Hez6ihDTSFTLfEMwUJ_l1MGU,2879
-xspect/train_filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/train_filter/create_svm.py,sha256=sktMp8tmQWjcbWkiEzRizabB4qF9wVr7bds2jAvxx4Y,6830
-xspect/train_filter/extract_and_concatenate.py,sha256=kXGqCrOk3TbOkKLJV8nKC6nL8Zg0TWKDCJu2gq8K_cw,5239
-xspect/train_filter/get_paths.py,sha256=JXPbv_Fx5BKHZQ4bkSIGU7yj5zjkmhsI0Z6U4nU0gug,941
-xspect/train_filter/html_scrap.py,sha256=iQXREhG37SNUx7gHoP8eqayMEIH00QLFMTNmIMogb_M,3799
-xspect/train_filter/interface_XspecT.py,sha256=HVCwVHqtvJ1EA9u6GByeKCve-6sADK5AceB5itPV62k,6735
-xspect/train_filter/k_mer_count.py,sha256=0yHCxzsOH8LhO6tD35O7BjWodfE5lJDKWYzzcCrr0JE,5226
-xspect/train_filter/ncbi_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/train_filter/ncbi_api/download_assemblies.py,sha256=iX1qK8R6p2b3RiHPfqVsLp-dV_7iZZv0AxY1xQ-Ad48,1171
-xspect/train_filter/ncbi_api/ncbi_assembly_metadata.py,sha256=RhHvxKiQ8HJgoSb6njYEgO_vPioBqEMPvT3lE2lHXp0,3766
-xspect/train_filter/ncbi_api/ncbi_children_tree.py,sha256=pmzg6-fDGLinNSXNbBRv0v62lRgHxW4aXZ0uV1TJhOE,1793
-xspect/train_filter/ncbi_api/ncbi_taxon_metadata.py,sha256=uhBBGffgL4mcJpyp9KxVyOGUh8FxUTAI4xKzoLDav_Y,1577
-XspecT-0.1.3.dist-info/LICENSE,sha256=bhBGDKIRUVwYIHGOGO5hshzuVHyqFJajvSOA3XXOLKI,1094
-XspecT-0.1.3.dist-info/METADATA,sha256=ulwNLqzESiHPxspAckJm3RkWXg5qf-T6KoNvfTnsH0g,5475
-XspecT-0.1.3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-XspecT-0.1.3.dist-info/entry_points.txt,sha256=L7qliX3pIuwupQxpuOSsrBJCSHYPOPNEzH8KZKQGGUw,43
-XspecT-0.1.3.dist-info/top_level.txt,sha256=hdoa4cnBv6OVzpyhMmyxpJxEydH5n2lDciy8urc1paE,7
-XspecT-0.1.3.dist-info/RECORD,,