scdataloader 0.0.4__py3-none-any.whl → 1.0.5__py3-none-any.whl

scdataloader/preprocess.py

@@ -1,4 +1,4 @@
-from typing import Any, Callable, Optional, Union
+from typing import Callable, Optional, Union
 from uuid import uuid4
 
 import anndata as ad
@@ -7,9 +7,7 @@ import numpy as np
 import pandas as pd
 import scanpy as sc
 from anndata import AnnData
-from django.db import IntegrityError
 from scipy.sparse import csr_matrix
-import os
 
 from scdataloader import utils as data_utils
 
@@ -204,7 +202,9 @@ class Preprocessor:
             )
         )
 
-        if self.is_symbol:
+        if self.is_symbol or not adata.var.index.str.contains("ENSG").any():
+            if not adata.var.index.str.contains("ENSG").any():
+                print("No ENSG genes found, assuming gene symbols...")
             genesdf["ensembl_gene_id"] = genesdf.index
             var = (
                 adata.var.merge(
@@ -266,9 +266,6 @@ class Preprocessor:
         # QC
 
         adata.var[genesdf.columns] = genesdf.loc[adata.var.index]
-        for name in ["stable_id", "created_at", "updated_at"]:
-            if name in adata.var.columns:
-                adata.var = adata.var.drop(columns=name)
         print("startin QC")
         sc.pp.calculate_qc_metrics(
             adata, qc_vars=["mt", "ribo", "hb"], inplace=True, percent_top=[20]
@@ -692,209 +689,3 @@ def additional_postprocess(adata):
     # to query N next time points we just get the N elements below and check they are in the group
     # to query the N nearest neighbors we just get the N elements above and N below and check they are in the group
     return adata
-
-
-"""
-sexr = {
-    "Male": "PATO:0000384",
-    "Female": "PATO:0000383",
-}
-tissuer = {
-    "Kidney": "UBERON:0002113",
-    "Lung": "UBERON:0002048",
-    "Heart": "UBERON:0000948",
-    "Liver": "UBERON:0002107",
-    "Brain": "UBERON:0000955",
-    "BAT": "UBERON:0001348",
-    "Jejunum": "UBERON:0002115",
-    "Colon": "UBERON:0001155",
-    "Ileum": "UBERON:0002116",
-    "Stomach": "UBERON:0000945",
-    "gWAT": "UBERON:0001347",
-    "Duodenum": "UBERON:0002114",
-    "iWAT": "UBERON:0001347",
-    "Muscle": "UBERON:0001630",
-}
-ager = {
-    "03_months": "MmusDv:0000063",
-    "16_months": "MmusDv:0000087",
-    "06_months": "MmusDv:0000077",
-    "23_months": "MmusDv:0000127",
-    "12_months": "MmusDv:0000083",
-    "21_months": "MmusDv:0000125",
-}
-
-celltyper = {
-    "Proximal tubule cells": "epithelial cell of proximal tubule",
-    "Vascular endothelial cells": "endothelial cell of vascular tree",
-    "Intestinal epithelial cells": "intestinal epithelial cell",
-    "Hepatocytes": "hepatocyte",
-    "Fibroblasts": "fibroblast",
-    "Lymphoid cells_T cells": "T cell",
-    "Myeloid cells": "myeloid cell",
-    "Brown adipocytes": "brown fat cell",
-    "Lymphoid cells_B cells": "B cell",
-    "Adipocytes": "fat cell",
-    "Type II alveolar epithelial cells": "type II pneumocyte",
-    "Colonic epithelial cells": "colon epithelial cell",
-    "Mural cells": "mural cell",
-    "Cerebellum granule neurons": "cerebellar neuron",
-    "Goblet cells": "goblet cell",
-    "Vascular endothelial cells_General capillary cells": "endothelial cell of vascular tree",
-    "Ventricular cardiomyocytes": "regular ventricular cardiac myocyte",
-    "Type II myonuclei": "type II muscle cell",
-    "Thick ascending limb of LOH cells": "vasa recta ascending limb cell",
-    "Gastric mucous cells": "mucous cell of stomach",
-    "Distal convoluted tubule cells": "kidney distal convoluted tubule epithelial cell",
-    "Adipoce stem and progenitor cells": "hepatic oval stem cell",
-    "Chief cells": "chief cell of parathyroid gland",
-    "Paneth cells": "paneth cell",
-    "Myeloid cells_Alveolar macrophages": "alveolar macrophage",
-    "Lymphoid cells_Plasma cells": "plasma cell",
-    "Secretory cells": "secretory cell",
-    "Lymphoid cells_Resting B cells": "B cell",
-    "Cortical projection neurons 1": "corticothalamic-projecting glutamatergic cortical neuron",
-    "Endocardial endothelial cells": "endocardial cell",
-    "Type I alveolar epithelial cells": "type I pneumocyte",
-    "Interbrain and midbrain neurons 1": "midbrain dopaminergic neuron",
-    "Interbrain and midbrain neurons 2": "midbrain dopaminergic neuron",
-    "Myeloid cells_Monocytes": "monocyte",
-    "Myeloid cells_Dendritic cells": "myeloid dendritic cell",
-    "Oligodendrocytes": "oligodendrocyte",
-    "Lymphatic endothelial cells": "endothelial cell of lymphatic vessel",
-    "Enteroendocrine cells": "enteroendocrine cell",
-    "Vascular endothelial cells_Aerocytes": "endothelial cell of vascular tree",
-    "Gastric epithelial cells": "epithelial cell of stomach",
-    "Fibro–adipogenic progenitors": "fibro/adipogenic progenitor cell",
-    "Parietal cells": "parietal cell",
-    "Astrocytes": "astrocyte",
-    "Connecting tubule cells": "kidney connecting tubule beta-intercalated cell",
-    "Hepatic stellate cells": "hepatic stellate cell",
-    "Striatal neurons 1": "striatum neuron",
-    "Mesothelial cells": "mesothelial cell",
-    "Lymphoid cells_Cycling B cells": "germinal center B cell",
-    "Type B intercalated cells": "renal beta-intercalated cell",
-    "Type A intercalated cells": "renal alpha-intercalated cell",
-    "Myeloid cells_Neutrophils": "neutrophil",
-    "Principal cells": "renal principal cell",
-    "Cortical projection neurons 2": "corticothalamic-projecting glutamatergic cortical neuron",
-    "Muc2-producing goblet cells": "intestine goblet cell",
-    "OB neurons 1": "olfactory bulb interneuron",
-    "Atrial cardiomyocytes": "regular atrial cardiac myocyte",
-    "Lymphoid cells": "leukocyte",
-    "Skeletal muscle cells": "cell of skeletal muscle",
-    "Neural cells": "neural cell",
-    "Cerebellum interneurons": "cerebellar neuron",
-    "Interneurons 1": "interneuron",
-    "Descending thin limb of LOH cells": "vasa recta descending limb cell",
-    "Tuft cells": "intestinal tuft cell",
-    "Oligodendrocyte progenitor cells": "oligodendrocyte precursor cell",
-    "Enteric glia": "enteroglial cell",
-    "Endothelial cells": "endothelial cell",
-    "Dentate gyrus neurons": "dentate gyrus neuron",
-    "Myeloid cells_Interstitial macrophages": "tissue-resident macrophage",
-    "Ciliated cells": "ciliated cell",
-    "Microglia": "microglial cell",
-    "Interneurons 2": "interneuron",
-    "Ncam1 positive cells": "parafollicular cell",
-    "Rdh16 positive cells": "unknown",
-    "Circulating hepatoblasts": "hepatoblast",
-    "Enteric neurons": "enteric neuron",
-    "Ascending thin limb of LOH cells": "vasa recta ascending limb cell",
-    "Mfge8 positive cells": "unknown",
-    "Cholangiocytes": "cholangiocyte",
-    "Podocytes": "podocyte",
-    "Muscle satellite cells": "skeletal muscle satellite cell",
-    "Purkinje neurons": "Purkinje cell",
-    "Juxtaglomerular cells": "juxtaglomerular complex cell",
-    "Ngf positive cells": "neurogliaform cell",
-    "Bergmann glia": "Bergmann glial cell",
-    "Megf11 positive cells": "unknown",
-    "Myotendinous junction myonuclei": "unknown",
-    "Vascular leptomeningeal cells": "vascular leptomeningeal cell",
-    "Urothelial cells": "urothelial cell",
-    "Tenocytes": "tendon cell",
-    "Myelinating Schwann cells": "myelinating Schwann cell",
-    "Epididymal cells": "epididymis glandular cell",
-    "Muc6-producing goblet cells": "lung goblet cell",
-    "Type I myonuclei": "type I muscle cell",
-    "OB neurons 2": "olfactory bulb interneuron",
-    "Sis positive cells": "unknown",
-    "Lgr5 positive cells": "unknown",
-    "Macula densa cells": "macula densa epithelial cell",
-    "Choroid plexus epithelial cells": "choroid plexus epithelial cell",
-    "Cortical projection neurons 3": "corticothalamic-projecting glutamatergic cortical neuron",
-    "Interstitial cells of Cajal": "interstitial cell of Cajal",
-    "Cacna1b positive cells": "unknown",
-    "Hindbrain neurons 2": "neuron",
-    "Myeloid cells_Basophils": "basophil",
-    "Ependymal cells": "ependymal cell",
-    "Muc5ac-producing goblet cells": "lung goblet cell",
-    "Myeloid cells_Mast cells": "mast cell",
-    "Pulmonary neuroendocrine cells": "lung neuroendocrine cell",
-    "Basal cells": "basal cell",
-    "OB neurons 3": "olfactory bulb interneuron",
-    "Non-myelinating Schwann cells": "non-myelinating Schwann cell",
-    "Asic2 positive cells": "unknown",
-    "Striatal neurons 2": "striatum neuron",
-    "Erythroblasts": "erythroblast",
-    "Hindbrain neurons 1": "neuron",
-    "Neuromuscular junction myonuclei": "unknown",
-    "Habenula neurons": "unknown",
-    "Pituitary cells": "pituitary gland cell",
-    "Unipolar brush cells": "unipolar brush cell",
-    "Pde4c positive cells": "unknown",
-    "Pancreatic acinar cells": "pancreatic acinar cell",
-    "Inferior olivary nucleus neurons": "bushy cell",
-    "Colec10 positive cells": "unknown",
-    "Fcgbp positive cells": "unknown",
-    "Fut9 positive cells": "unknown",
-    "Mirg positive cells": "unknown",
-    "Alox15 positive cells": "unknown",
-    "Osteoblasts": "osteoblast",
-}
-genesdf = utils.load_genes("NCBITaxon:10090")
-{k: v if v =="unknown" else bt.CellType.filter(name=v).one().ontology_id for k, v in celltyper.items()}
-
-adata.obs["organism_ontology_term_id"] = "NCBITaxon:10090"
-adata.obs["tissue_ontology_term_id"] = adata.obs["Organ_name"].replace(tissuer)
-adata.obs["cell_type_ontology_term_id"] = adata.obs["Main_cell_type"].replace(
-    celltyper
-)
-adata.obs["disease_ontology_term_id"] = "PATO:0000461"
-adata.obs["assay_ontology_term_id"] = "unknown"
-adata.obs["self_reported_ethnicity_ontology_term_id"] = "unknown"
-adata.obs["development_stage_ontology_term_id"] = adata.obs["Age_group"].replace(
-    ager
-)
-adata.obs["sex_ontology_term_id"] = adata.obs["Gender"].replace(sexr)
-
-for i in range(num_blocks):
-    start_index = i * block_size
-    end_index = min((i + 1) * block_size, len(adata))
-    block = adata[start_index:end_index].to_memory()
-    # process block here
-
-    block = block[(block.obs["Gene_count"] > 400)]
-    
-    intersect_genes = set(block.var.index).intersection(set(genesdf.index))
-    print(f"Removed {len(block.var.index) - len(intersect_genes)} genes.")
-    block = block[:, list(intersect_genes)]
-    # marking unseen genes
-    unseen = set(genesdf.index) - set(block.var.index)
-    # adding them to adata
-    emptyda = ad.AnnData(
-        csr_matrix((block.shape[0], len(unseen)), dtype=np.float32),
-        var=pd.DataFrame(index=list(unseen)),
-        obs=pd.DataFrame(index=block.obs.index),
-    )
-    block = ad.concat([block, emptyda], axis=1, join="outer", merge="only")
-    # do a validation function
-    block.uns["unseen_genes"] = list(unseen)
-    block = block[:, block.var.sort_index().index]
-    block.var[genesdf.columns] = genesdf.loc[block.var.index]
-    for name in ["stable_id", "created_at", "updated_at"]:
-        if name in block.var.columns:
-            block.var = block.var.drop(columns=name)
-    block.write_h5ad('zhang2024_adata_'+str(i)+".h5ad")
-"""

scdataloader/utils.py

@@ -12,12 +12,48 @@ from scipy.sparse import csr_matrix
 from scipy.stats import median_abs_deviation
 from functools import lru_cache
 from collections import Counter
+from torch import Tensor
+import torch
 
 from typing import Union, List, Optional
 
 from anndata import AnnData
 
 
+def downsample_profile(mat: Tensor, dropout: float):
+    """
+    This function downsamples the expression profile of a given single cell RNA matrix.
+
+    The noise is applied based on the renoise parameter,
+    the total counts of the matrix, and the number of genes. The function first calculates the noise
+    threshold (scaler) based on the renoise parameter. It then generates an initial matrix count by
+    applying a Poisson distribution to a random tensor scaled by the total counts and the number of genes.
+    The function then models the sampling zeros by applying a Poisson distribution to a random tensor
+    scaled by the noise threshold, the total counts, and the number of genes. The function also models
+    the technical zeros by generating a random tensor and comparing it to the noise threshold. The final
+    matrix count is calculated by subtracting the sampling zeros from the initial matrix count and
+    multiplying by the technical zeros. The function ensures that the final matrix count is not less
+    than zero by taking the maximum of the final matrix count and a tensor of zeros. The function
+    returns the final matrix count.
+
+    Args:
+        mat (torch.Tensor): The input matrix.
+        dropout (float): The renoise parameter.
+
+    Returns:
+        torch.Tensor: The matrix count after applying noise.
+    """
+    batch = mat.shape[0]
+    ngenes = mat.shape[1]
+    dropout = dropout * 1.1
+    # we model the sampling zeros (dropping 30% of the reads)
+    res = torch.poisson((mat * (dropout / 2))).int()
+    # we model the technical zeros (dropping 50% of the genes)
+    notdrop = (torch.rand((batch, ngenes), device=mat.device) >= (dropout / 2)).int()
+    mat = (mat - res) * notdrop
+    return torch.maximum(mat, torch.zeros((1, 1), device=mat.device, dtype=torch.int))
+
+
 def createFoldersFor(filepath: str):
     """
     will recursively create folders if needed until having all the folders required to save the file in this filepath
@@ -38,6 +74,7 @@ def _fetchFromServer(
     Args:
         ensemble_server (str): The URL of the ensemble server to fetch data from.
         attributes (list): The list of attributes to fetch from the server.
+        database (str): The database to fetch data from.
 
     Returns:
         pd.DataFrame: A pandas DataFrame containing the fetched data.
@@ -68,6 +105,9 @@ def getBiomartTable(
         ensemble_server (str, optional): the biomart server. Defaults to "http://jul2023.archive.ensembl.org/biomart".
         useCache (bool, optional): whether to use the cache or not. Defaults to False.
         cache_folder (str, optional): the cache folder. Defaults to "/tmp/biomart/".
+        attributes (List[str], optional): the attributes to fetch. Defaults to [].
+        bypass_attributes (bool, optional): whether to bypass the attributes or not. Defaults to False.
+        database (str, optional): the database to fetch from. Defaults to "hsapiens_gene_ensembl".
 
     Raises:
         ValueError: should be a dataframe (when the result from the server is something else)
@@ -98,15 +138,15 @@ def getBiomartTable(
 
         res = _fetchFromServer(ensemble_server, attr + attributes, database=database)
         res.to_csv(cachefile, index=False)
-
     res.columns = attr + attributes
     if type(res) is not type(pd.DataFrame()):
         raise ValueError("should be a dataframe")
-    res = res[~(res["ensembl_gene_id"].isna() & res["hgnc_symbol"].isna())]
-    res.loc[res[res.hgnc_symbol.isna()].index, "hgnc_symbol"] = res[
-        res.hgnc_symbol.isna()
-    ]["ensembl_gene_id"]
-
+    res = res[~(res["ensembl_gene_id"].isna())]
+    if "hgnc_symbol" in res.columns:
+        res = res[res["hgnc_symbol"].isna()]
+        res.loc[res[res.hgnc_symbol.isna()].index, "hgnc_symbol"] = res[
+            res.hgnc_symbol.isna()
+        ]["ensembl_gene_id"]
     return res
 
 
@@ -206,6 +246,16 @@ def get_all_ancestors(val: str, df: pd.DataFrame):
         return set.union(set(parents), *[get_all_ancestors(val, df) for val in parents])
 
 
+# setting a cache of 200 elements
+# @lru_cache(maxsize=200)
+def get_descendants(val, df):
+    ontos = set(df[df.parents__ontology_id.str.contains(val)].index.tolist())
+    r_onto = set()
+    for onto in ontos:
+        r_onto |= get_descendants(onto, df)
+    return r_onto | ontos
+
+
 def get_ancestry_mapping(all_elem: list, onto_df: pd.DataFrame):
     """
     This function generates a mapping of all elements to their ancestors in the ontology dataframe.
@@ -304,13 +354,12 @@ def load_dataset_local(
 
 def load_genes(organisms: Union[str, list] = "NCBITaxon:9606"):  # "NCBITaxon:10090",
     organismdf = []
-    if type(organisms) == str:
+    if type(organisms) is str:
         organisms = [organisms]
     for organism in organisms:
         genesdf = bt.Gene.filter(
             organism_id=bt.Organism.filter(ontology_id=organism).first().id
         ).df()
-        genesdf = genesdf[~genesdf["public_source_id"].isna()]
         genesdf = genesdf.drop_duplicates(subset="ensembl_gene_id")
         genesdf = genesdf.set_index("ensembl_gene_id").sort_index()
         # mitochondrial genes
@@ -321,7 +370,12 @@ def load_genes(organisms: Union[str, list] = "NCBITaxon:9606"):  # "NCBITaxon:10
         genesdf["hb"] = genesdf.symbol.astype(str).str.contains(("^HB[^(P)]"))
         genesdf["organism"] = organism
         organismdf.append(genesdf)
-    return pd.concat(organismdf)
+    organismdf = pd.concat(organismdf)
+    organismdf.drop(
+        columns=["source_id", "run_id", "created_by_id", "updated_at", "stable_id"],
+        inplace=True,
+    )
+    return organismdf
 
 
 def populate_my_ontology(
@@ -358,77 +412,79 @@ def populate_my_ontology(
         diseases (list, optional): List of diseases. Defaults to [].
         dev_stages (list, optional): List of developmental stages. Defaults to [].
     """
-
-    names = bt.CellType.public().df().index if not celltypes else celltypes
-    records = bt.CellType.from_values(names, field="ontology_id")
-    ln.save(records, parents=bool(celltypes))
-    bt.CellType(name="unknown", ontology_id="unknown").save()
+    # cell type
+    if celltypes is not None:
+        names = bt.CellType.public().df().index if not celltypes else celltypes
+        records = bt.CellType.from_values(names, field="ontology_id")
+        ln.save(records)
+        bt.CellType(name="unknown", ontology_id="unknown").save()
     # Organism
-    names = bt.Organism.public().df().index if not organisms else organisms
-    records = [
-        i[0] if type(i) is list else i
-        for i in [bt.Organism.from_public(ontology_id=i) for i in names]
-    ]
-    ln.save(records, parents=bool(organisms))
-    bt.Organism(name="unknown", ontology_id="unknown").save()
+    if organisms is not None:
+        names = bt.Organism.public().df().index if not organisms else organisms
+        records = [
+            i[0] if type(i) is list else i
+            for i in [bt.Organism.from_source(ontology_id=i) for i in names]
+        ]
+        ln.save(records)
+        bt.Organism(name="unknown", ontology_id="unknown").save()
+        organism_names = names
     # Phenotype
-    names = bt.Phenotype.public().df().index if not sex else sex
-    records = [
-        bt.Phenotype.from_public(
-            ontology_id=i,
-            public_source=bt.PublicSource.filter(
-                entity="Phenotype", source="pato"
-            ).one(),
-        )
-        for i in names
-    ]
-    ln.save(records, parents=bool(sex))
-    bt.Phenotype(name="unknown", ontology_id="unknown").save()
+    if sex is not None:
+        names = bt.Phenotype.public().df().index if not sex else sex
+        records = [
+            bt.Phenotype.from_source(
+                ontology_id=i,
+            )
+            for i in names
+        ]
+        ln.save(records)
+        bt.Phenotype(name="unknown", ontology_id="unknown").save()
     # ethnicity
-    names = bt.Ethnicity.public().df().index if not ethnicities else ethnicities
-    records = bt.Ethnicity.from_values(names, field="ontology_id")
-    ln.save(records, parents=bool(ethnicities))
-    bt.Ethnicity(
-        name="unknown", ontology_id="unknown"
-    ).save()  # multi ethnic will have to get renamed
+    if ethnicities is not None:
+        names = bt.Ethnicity.public().df().index if not ethnicities else ethnicities
+        records = bt.Ethnicity.from_values(names, field="ontology_id")
+        ln.save(records)
+        bt.Ethnicity(
+            name="unknown", ontology_id="unknown"
+        ).save()  # multi ethnic will have to get renamed
     # ExperimentalFactor
-    names = bt.ExperimentalFactor.public().df().index if not assays else assays
-    records = bt.ExperimentalFactor.from_values(names, field="ontology_id")
-    ln.save(records, parents=bool(assays))
-    bt.ExperimentalFactor(name="unknown", ontology_id="unknown").save()
-    # lookup = bt.ExperimentalFactor.lookup()
-    # lookup.smart_seq_v4.parents.add(lookup.smart_like)
+    if assays is not None:
+        names = bt.ExperimentalFactor.public().df().index if not assays else assays
+        records = bt.ExperimentalFactor.from_values(names, field="ontology_id")
+        ln.save(records)
+        bt.ExperimentalFactor(name="unknown", ontology_id="unknown").save()
+        # lookup = bt.ExperimentalFactor.lookup()
+        # lookup.smart_seq_v4.parents.add(lookup.smart_like)
     # Tissue
-    names = bt.Tissue.public().df().index if not tissues else tissues
-    records = bt.Tissue.from_values(names, field="ontology_id")
-    ln.save(records, parents=bool(tissues))
-    bt.Tissue(name="unknown", ontology_id="unknown").save()
+    if tissues is not None:
+        names = bt.Tissue.public().df().index if not tissues else tissues
+        records = bt.Tissue.from_values(names, field="ontology_id")
+        ln.save(records)
+        bt.Tissue(name="unknown", ontology_id="unknown").save()
     # DevelopmentalStage
-    names = (
-        bt.DevelopmentalStage.public().df().index if not dev_stages else dev_stages
-    )
-    records = bt.DevelopmentalStage.from_values(names, field="ontology_id")
-    ln.save(records, parents=bool(dev_stages))
-    bt.DevelopmentalStage(name="unknown", ontology_id="unknown").save()
-
-    names = bt.DevelopmentalStage.public(organism="mouse").df().name
-    bionty_source = bt.PublicSource.filter(
-        entity="DevelopmentalStage", organism="mouse"
-    ).one()
-    records = [
-        bt.DevelopmentalStage.from_public(name=i, public_source=bionty_source)
-        for i in names.tolist()
-    ]
-    records[-4] = records[-4][0]
-    ln.save(records)
+    if dev_stages is not None:
+        names = (
+            bt.DevelopmentalStage.public().df().index if not dev_stages else dev_stages
+        )
+        records = bt.DevelopmentalStage.from_values(names, field="ontology_id")
+        ln.save(records)
+        bt.DevelopmentalStage(name="unknown", ontology_id="unknown").save()
+
+        names = bt.DevelopmentalStage.public(organism="mouse").df().index
+        records = [
+            bt.DevelopmentalStage.from_source(ontology_id=i) for i in names.tolist()
+        ]
+        records[-4] = records[-4][0]
+        ln.save(records)
     # Disease
-    names = bt.Disease.public().df().index if not diseases else diseases
-    records = bt.Disease.from_values(names, field="ontology_id")
-    ln.save(records, parents=bool(diseases))
-    bt.Disease(name="normal", ontology_id="PATO:0000461").save()
-    bt.Disease(name="unknown", ontology_id="unknown").save()
+    if diseases is not None:
+        names = bt.Disease.public().df().index if not diseases else diseases
+        records = bt.Disease.from_values(names, field="ontology_id")
+        ln.save(records)
+        bt.Disease(name="normal", ontology_id="PATO:0000461").save()
+        bt.Disease(name="unknown", ontology_id="unknown").save()
     # genes
-    for organism in ["NCBITaxon:10090", "NCBITaxon:9606"]:
+    for organism in organism_names:
         # convert onto to name
         organism = bt.Organism.filter(ontology_id=organism).one().name
         names = bt.Gene.public(organism=organism).df()["ensembl_gene_id"]
@@ -474,26 +530,6 @@ def length_normalize(adata: AnnData, gene_lengths: list):
     return adata
 
 
-def pd_load_cached(url: str, loc: str = "/tmp/", cache: bool = True, **kwargs):
-    """
-    pd_load_cached downloads a file from a url and loads it as a pandas dataframe
-
-    Args:
-        url (str): the url to download the file from
-        loc (str, optional): the location to save the file to. Defaults to "/tmp/".
-        cache (bool, optional): whether to use the cached file or not. Defaults to True.
-
-    Returns:
-        pd.DataFrame: the dataframe
-    """
-    # Check if the file exists, if not, download it
-    loc += url.split("/")[-1]
-    if not os.path.isfile(loc) or not cache:
-        urllib.request.urlretrieve(url, loc)
-    # Load the data from the file
-    return pd.read_csv(loc, **kwargs)
-
-
 def translate(
     val: Union[str, list, set, Counter, dict], t: str = "cell_type_ontology_term_id"
 ):