XspecT 0.2.6__py3-none-any.whl → 0.4.0__py3-none-any.whl

xspect/train_filter/ncbi_api/ncbi_assembly_metadata.py

@@ -1,110 +0,0 @@
-""" Collects metadata of assemblies from NCBI API """
-
-__author__ = "Berger, Phillip"
-
-from time import sleep
-
-import requests
-
-from loguru import logger
-
-
-class NCBIAssemblyMetadata:
-    """Class to collect metadata of assemblies from the NCBI API."""
-
-    _all_metadata: dict
-    _count: int
-    _ani_gcf: list
-    _parameters: dict
-    _accessions: list[str]
-    _contig_n50: int
-    _all_metadata_complete: dict
-
-    def __init__(self, all_metadata: dict, ani_gcf: list, count=8, contig_n50=10000):
-        self._all_metadata = all_metadata
-        self._count = count
-        self._ani_gcf = ani_gcf
-        self._contig_n50 = contig_n50
-
-        self._set_parameters()
-
-        tmp_metadata = {}
-        for tax_id, curr_metadata in self._all_metadata.items():
-            sleep(2)
-            species_name = curr_metadata["sci_name"]
-            logger.info("Collecting metadata of {name}", name=species_name)
-            accessions = self._make_request(taxon=tax_id)
-            if len(accessions) != 0:
-                curr_metadata["accessions"] = accessions
-                tmp_metadata[tax_id] = curr_metadata
-
-        self._all_metadata_complete = tmp_metadata
-
-    def _set_parameters(self):
-        params = {
-            "filters.reference_only": "false",
-            "filters.assembly_source": "refseq",
-            "filters.exclude_atypical": "true",
-            "page_size": self._count,
-            "page_token": "",
-        }
-        params_ref = params.copy()
-        params_ref["filters.reference_only"] = "true"
-
-        params_comp_genome = params.copy()
-        params_comp_genome["filters.assembly_level"] = "complete_genome"
-
-        params_chrom = params.copy()
-        params_chrom["filters.assembly_level"] = "chromosome"
-
-        params_scaffold = params.copy()
-        params_scaffold["filters.assembly_level"] = "scaffold"
-
-        params_contig = params.copy()
-        params_contig["filters.assembly_level"] = "contig"
-
-        self._parameters = {
-            "params_ref": params_ref,
-            "params_comp_genome": params_comp_genome,
-            "params_chrom": params_chrom,
-            "params_scaffold": params_scaffold,
-            "params_contig": params_contig,
-        }
-
-    def _make_request(self, taxon: str):
-        api_url = f"https://api.ncbi.nlm.nih.gov/datasets/v1/genome/taxon/{taxon}"
-        accessions = []
-        count = 0
-        for request_type, parameters in self._parameters.items():
-            raw_response = requests.get(api_url, params=parameters, timeout=5)
-            response = raw_response.json()
-            if response:
-                try:
-                    assemblies = response["assemblies"]
-                    for assembly in assemblies:
-                        curr_assembly = assembly["assembly"]
-                        curr_accession = curr_assembly["assembly_accession"]
-                        curr_contig_n50 = curr_assembly["contig_n50"]
-                        if count < self._count:
-                            if (
-                                curr_accession in self._ani_gcf
-                                and curr_contig_n50 > self._contig_n50
-                            ):
-                                accessions.append(curr_accession)
-                                count += 1
-                        else:
-                            break
-                except KeyError:
-                    logger.debug(
-                        "While requesting: {type} an error response was given",
-                        type=request_type,
-                    )
-                    logger.debug(str(response))
-
-            if count >= self._count:
-                break
-        return accessions
-
-    def get_all_metadata(self):
-        """Returns all metadata of the assemblies."""
-        return self._all_metadata_complete

xspect/train_filter/ncbi_api/ncbi_children_tree.py

@@ -1,53 +0,0 @@
-"""This class uses the NCBI Datasets API to get the taxonomy tree of a given Taxon.
-
-The taxonomy tree consists of only the next children to the parent taxon.
-The children are only of the next lower rank of the parent taxon.
-"""
-
-__author__ = "Berger, Phillip"
-
-import sys
-import requests
-
-from loguru import logger
-
-
-class NCBIChildrenTree:
-    _taxon: str
-    _response: dict
-    _parent_taxon_id: str
-    _children_taxon_ids = list()
-
-    def __init__(self, taxon: str):
-        self._taxon = taxon
-        self._request_tree()
-
-    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, timeout=5)
-        self._response = raw_response.json()["edges"]
-        self._parent_taxon_id = str(self._response["1"]["visible_children"][0])
-        try:
-            tmp_children_ids = self._response[self._parent_taxon_id]["visible_children"]
-        except KeyError:
-            logger.error("KeyError for key: {key}", key=self._parent_taxon_id)
-            logger.error("Response: {response}", response=str(self._response))
-            logger.error("Aborting")
-            sys.exit()
-        for child_id in tmp_children_ids:
-            self._children_taxon_ids.append(str(child_id))
-
-    def parent_id(self):
-        """The NCBI taxon ID of the given Taxon at the initialisation.
-
-        :return: The taxon ID.
-        """
-        return self._parent_taxon_id
-
-    def children_ids(self) -> list[str]:
-        """The NCBI taxon IDs of all children of the given Taxon. The children are all of a lower rank than the parent.
-
-        :return: The taxon IDs as a list.
-        """
-        return self._children_taxon_ids

xspect/train_filter/ncbi_api/ncbi_taxon_metadata.py

@@ -1,55 +0,0 @@
-""" This module is used to retrieve metadata from the NCBI taxonomy database. """
-
-__author__ = "Berger, Phillip"
-
-import requests
-
-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 = {}
-        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, timeout=5)
-        self._response = raw_response.json()["taxonomy_nodes"]
-
-    def _collect_all_metadata(self):
-        for child_metadata in self._response:
-            taxonomy = child_metadata["taxonomy"]
-            rank = taxonomy["rank"]
-            name = taxonomy["organism_name"]
-            tax_id = str(taxonomy["tax_id"])
-            lineage = taxonomy["lineage"]
-            if "Candidatus" not in name:
-                if " sp. " not in name:
-                    metadata = {
-                        "sci_name": name,
-                        "tax_id": tax_id,
-                        "rank": rank,
-                        "lineage": lineage,
-                    }
-                    self._all_metadata[tax_id] = metadata
-                else:
-                    logger.debug("{name} was not used for training", name=name)
-            else:
-                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