lamindb 0.77.0__tar.gz → 0.77.2__tar.gz

lamindb-0.77.2/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,15 @@
+name: Report a bug
+description: Report a bug.
+labels:
+  - ":bug: bug"
+body:
+  - type: textarea
+    id: report
+    attributes:
+      label: Add a description
+      placeholder: |
+        Describe and consider providing version information. Please ensure you're on the latest version of lamindb.
+        This is a public repository!
+        Do not reveal any internal information.
+    validations:
+      required: true

{lamindb-0.77.0 → lamindb-0.77.2}/.github/ISSUE_TEMPLATE/config.yml

@@ -2,7 +2,7 @@ blank_issues_enabled: true
 contact_links:
     - name: LaminHub issues
       url: https://github.com/laminlabs/laminhub-public
-      about: If you have issues with LaminHub, please report them here.
+      about: If you have issues with the GUI/web app at lamin.ai, please report them here.
     - name: Enterprise support
       url: https://lamin.ai/contact
-      about: If you have non-technical inquiries, please contact us directly.
+      about: If you have other questions, contact us directly.

lamindb-0.77.2/.github/ISSUE_TEMPLATE/enhancement.yml

@@ -0,0 +1,12 @@
+name: Propose an enhancement
+description: Propose an enhancement.
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Add a description
+      placeholder: |
+        This is a public repository!
+        Do not reveal any internal information.
+    validations:
+      required: true

lamindb-0.77.2/.github/ISSUE_TEMPLATE/usage_question.yml

@@ -0,0 +1,14 @@
+name: Ask a usage question
+description: Ask a usage question.
+labels:
+  - "usage question"
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Add a description
+      placeholder: |
+        This is a public repository!
+        Do not reveal any internal information.
+    validations:
+      required: true

{lamindb-0.77.0 → lamindb-0.77.2}/.gitignore

@@ -20,6 +20,7 @@ lamin-tutorial/
 mytest/
 rds/
 mydb/
+docs/test-registries/
 docs/test-annotate-flexible/
 docs/lamindb.*
 lamin_sphinx

{lamindb-0.77.0 → lamindb-0.77.2}/.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
       - id: prettier
         exclude: |
           (?x)(
-            docs/changelog.md|.github/ISSUE_TEMPLATE/config.yml
+            docs/changelog.md|.github/ISSUE_TEMPLATE/config.yml|tests/core/notebooks/basic-r-notebook.Rmd.cleaned.html
           )
   - repo: https://github.com/kynan/nbstripout
     rev: 0.6.1
@@ -42,6 +42,10 @@ repos:
       - id: mixed-line-ending
         args: [--fix=lf]
       - id: trailing-whitespace
+        exclude: |
+          (?x)(
+              tests/core/notebooks/basic-r-notebook.Rmd.cleaned.html
+            )
       - id: check-case-conflict
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.7.1

{lamindb-0.77.0 → lamindb-0.77.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.77.0
+Version: 0.77.2
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.9,<3.13
@@ -9,11 +9,10 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: lnschema_core==0.77.0
-Requires-Dist: lamin_utils==0.13.8
-Requires-Dist: lamin_cli==0.21.3
-Requires-Dist: lamindb_setup
-Requires-Dist: rapidfuzz
+Requires-Dist: lnschema_core==0.77.1
+Requires-Dist: lamin_utils==0.13.9
+Requires-Dist: lamin_cli==0.22.0
+Requires-Dist: lamindb_setup==0.81.2
 Requires-Dist: pyarrow
 Requires-Dist: typing_extensions!=4.6.0
 Requires-Dist: python-dateutil
@@ -22,7 +21,7 @@ Requires-Dist: fsspec
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
 Requires-Dist: lamindb_setup[aws] ; extra == "aws"
-Requires-Dist: bionty==0.53.1 ; extra == "bionty"
+Requires-Dist: bionty==0.53.2 ; extra == "bionty"
 Requires-Dist: cellregistry ; extra == "cellregistry"
 Requires-Dist: clinicore ; extra == "clinicore"
 Requires-Dist: line_profiler ; extra == "dev"
@@ -41,7 +40,7 @@ Requires-Dist: findrefs ; extra == "findrefs"
 Requires-Dist: lamindb_setup[gcp] ; extra == "gcp"
 Requires-Dist: nbproject==0.10.5 ; extra == "jupyter"
 Requires-Dist: jupytext ; extra == "jupyter"
-Requires-Dist: nbconvert ; extra == "jupyter"
+Requires-Dist: nbconvert>=7.2.1 ; extra == "jupyter"
 Requires-Dist: omop ; extra == "omop"
 Requires-Dist: ourprojects ; extra == "ourprojects"
 Requires-Dist: wetlab ; extra == "wetlab"

{lamindb-0.77.0 → lamindb-0.77.2}/docs/arrays.ipynb

@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Query arrays"
+    "# Slice arrays"
    ]
   },
   {

{lamindb-0.77.0 → lamindb-0.77.2}/docs/bio-registries.ipynb

@@ -697,7 +697,7 @@
    "source": [
     "Sometimes, the default source doesn't contain the ontology term you are looking for.\n",
     "\n",
-    "You can then specify to create a record from a non-default source. For instance, instead of using untyped labels for iris organisms as {doc}`/tutorial2`, we can use the `ncbitaxon` ontology:"
+    "You can then specify to create a record from a non-default source. For instance, we can use the `ncbitaxon` ontology:"
    ]
   },
   {

{lamindb-0.77.0 → lamindb-0.77.2}/docs/curate-df.ipynb

@@ -7,19 +7,76 @@
    "source": [
     "# Curate DataFrames and AnnDatas\n",
     "\n",
-    "Curating datasets typically means three things:\n",
+    "Curating a dataset with LaminDB means three things:\n",
     "\n",
-    "1. Validate: ensure a dataset meets predefined _validation criteria_\n",
-    "2. Standardize: transform a dataset so that it meets validation criteria, e.g., by fixing typos or using standardized identifiers\n",
-    "3. Annotate: link a dataset against metadata records\n",
+    "1. **Validate:** ensure the dataset meets predefined _validation criteria_\n",
+    "2. **Standardize:** transform the dataset so that it meets validation criteria, e.g., by fixing typos or using standard instead of ad hoc identifiers\n",
+    "3. **Annotate:** link the dataset against validated metadata so that it becomes queryable\n",
     "\n",
-    "In LaminDB, valid metadata is metadata that's stored in a metadata registry and _validation criteria_ merely defines a mapping onto a field of a registry.\n",
+    "If a dataset passes validation, curating it takes two lines of code:\n",
     "\n",
-    "```{admonition} Example\n",
+    "```python\n",
+    "curator = ln.Curator.from_df(df, ...)  # create a Curator and pass criteria in \"...\"\n",
+    "curator.save_artifact()                # validates the content of the dataset and saves it as annotated artifact\n",
+    "```\n",
     "\n",
-    "`\"Experiment 1\"` is a valid value for `ULabel.name` if a record with this name exists in the {class}`~lamindb.ULabel` registry.\n",
+    "Beyond having valid content, the curated dataset is now queryable via metadata identifiers found in the dataset because they have been validated & linked against LaminDB registries.\n",
     "\n",
-    "```"
+    ":::{admonition} Definition: valid metadata identifier\n",
+    "\n",
+    "An identifier like `\"Experiment 1\"` is a valid value for `ULabel.name` if a record with `name` `\"Experiment 1\"` exists in the {class}`~lamindb.ULabel` registry.\n",
+    "\n",
+    "```python\n",
+    "categoricals = {\"experiment\": ln.ULabel.name}  # the validation constraint\n",
+    "curator = ln.Curator.from_df(df, categoricals=categoricals)\n",
+    "curator.validate()\n",
+    "```\n",
+    "\n",
+    "The DataFrame validates if \n",
+    "\n",
+    "- there is a column with name `\"experiment\"` in the dataframe whose values are all found in the `name` field of the {class}`~lamindb.ULabel` registry\n",
+    "- the column name `\"experiment\"` is found in the `name` field of the {class}`~lamindb.Feature` registry\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "Beyond validating metadata identifiers, LaminDB also validates data types and dataset schema.\n",
+    "\n",
+    ":::{dropdown} How does validation in LaminDB compare to validation in pandera?\n",
+    "\n",
+    "Like LaminDB, [pandera](https://pandera.readthedocs.io/) validates the _dataset schema_ (i.e., column names and `dtype`s).\n",
+    "\n",
+    "`pandera` is only available for `DataFrame`-like datasets and cannot annotate datasets; i.e., can't make datasets queryable.\n",
+    "\n",
+    "However, it offers an API for range-checks, both for numerical and string-like data. If you need such checks, you can combine LaminDB and pandera-based validation.\n",
+    "\n",
+    "```python\n",
+    "import pandas as pd\n",
+    "import pandera as pa\n",
+    "\n",
+    "# data to validate\n",
+    "df = pd.DataFrame({\n",
+    "    \"column1\": [1, 4, 0, 10, 9],\n",
+    "    \"column2\": [-1.3, -1.4, -2.9, -10.1, -20.4],\n",
+    "    \"column3\": [\"value_1\", \"value_2\", \"value_3\", \"value_2\", \"value_1\"],\n",
+    "})\n",
+    "\n",
+    "# define schema\n",
+    "schema = pa.DataFrameSchema({\n",
+    "    \"column1\": pa.Column(int, checks=pa.Check.le(10)),\n",
+    "    \"column2\": pa.Column(float, checks=pa.Check.lt(-1.2)),\n",
+    "    \"column3\": pa.Column(str, checks=[\n",
+    "        pa.Check.str_startswith(\"value_\"),\n",
+    "        # define custom checks as functions that take a series as input and\n",
+    "        # outputs a boolean or boolean Series\n",
+    "        pa.Check(lambda s: s.str.split(\"_\", expand=True).shape[1] == 2)\n",
+    "    ]),\n",
+    "})\n",
+    "\n",
+    "validated_df = schema(df)  # this corresponds to curator.validate() in LaminDB\n",
+    "print(validated_df)\n",
+    "```\n",
+    "\n",
+    ":::"
    ]
   },
   {
@@ -42,7 +99,7 @@
    "id": "946a3371",
    "metadata": {},
    "source": [
-    "## Validate a DataFrame"
+    "## Curate a DataFrame"
    ]
   },
   {
@@ -72,7 +129,7 @@
     "df = pd.DataFrame(\n",
     "    {\n",
     "        \"temperature\": [37.2, 36.3, 38.2],\n",
-    "        \"cell_type\": [\"cerebral pyramidal neuron\", \"astrocyte\", \"oligodendrocyte\"],\n",
+    "        \"cell_type\": [\"cerebral pyramidal neuron\", \"astrocytic glia\", \"oligodendrocyte\"],\n",
     "        \"assay_ontology_id\": [\"EFO:0008913\", \"EFO:0008913\", \"EFO:0008913\"],\n",
     "        \"donor\": [\"D0001\", \"D0002\", \"D0003\"]\n",
     "    },\n",
@@ -134,22 +191,54 @@
     "curate.validate()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7acf0d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check the non-validated terms\n",
+    "curate.non_validated"
+   ]
+  },
   {
    "cell_type": "markdown",
-   "id": "7c157df6",
+   "id": "8c2417c7",
    "metadata": {},
    "source": [
-    "## Register new metadata values\n",
+    "For `cell_type`, we saw that \"cerebral pyramidal neuron\", \"astrocytic glia\" are not validated.\n",
     "\n",
-    "If you see \"non-validated\" values, you'll need to decide whether to add them to your registries or \"fix\" them in your dataset."
+    "First, let's standardize synonym \"astrocytic glia\" as suggested"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35b3ce8e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "curate.standardize(\"cell_type\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "336293ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# now we have only one non-validated term left\n",
+    "curate.non_validated"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "8c2417c7",
+   "id": "c1bfe41c",
    "metadata": {},
    "source": [
-    "For `cell_type`, we saw that 'cerebral pyramidal neuron' is not validated, let's understand which cell type in the public ontology might be the actual match."
+    "For \"cerebral pyramidal neuron\", let's understand which cell type in the public ontology might be the actual match."
    ]
   },
   {
@@ -235,8 +324,35 @@
    "outputs": [],
    "source": [
     "# validate again\n",
-    "validated = curate.validate()\n",
-    "validated"
+    "curate.validate()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ab7cfff0",
+   "metadata": {},
+   "source": [
+    "Save a curated artifact."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e7e6372",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "artifact = curate.save_artifact(description=\"My curated dataframe\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74f91cc8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "artifact.describe(print_types=True)"
    ]
   },
   {
@@ -244,7 +360,7 @@
    "id": "b9d09a10",
    "metadata": {},
    "source": [
-    "## Validate an AnnData\n",
+    "## Curate an AnnData\n",
     "\n",
     "Here we additionally specify which `var_index` to validate against."
    ]
@@ -271,9 +387,8 @@
     "        \"ENSG00000153563\": [13, 14, 15],\n",
     "        \"ENSGcorrupted\": [16, 17, 18]\n",
     "    }, \n",
-    "    index=df.index\n",
+    "    index=df.index  # because we already curated the dataframe above, it will validate \n",
     ")\n",
-    "\n",
     "adata = ad.AnnData(X=X, obs=df)\n",
     "adata"
    ]
@@ -294,20 +409,7 @@
     "    var_index=bt.Gene.ensembl_gene_id,  # validate var.index against Gene.ensembl_gene_id\n",
     "    categoricals=categoricals, \n",
     "    organism=\"human\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e8d8cee5",
-   "metadata": {
-    "tags": [
-     "hide-output"
-    ]
-   },
-   "outputs": [],
-   "source": [
+    ")\n",
     "curate.validate()"
    ]
   },
@@ -376,18 +478,9 @@
     "    categoricals=categoricals, \n",
     "    organism=\"human\",\n",
     ")\n",
-    "\n",
     "curate.validate()"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "38a30170",
-   "metadata": {},
-   "source": [
-    "## Save a curated artifact"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "a814ef37",
@@ -466,7 +559,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.15"
   },
   "nbproject": {
    "id": "WOK3vP0bNGLx",

{lamindb-0.77.0 → lamindb-0.77.2}/docs/curate-subclass.ipynb

@@ -95,8 +95,8 @@
    "source": [
     "# create example DataFrame that has all mandatory columns but one ('patient_age') is wrongly named\n",
     "data = {\n",
-    "    'disease': ['Alzheimer disease', 'Diabetes mellitus', 'Breast cancer', 'Hypertension', 'Asthma'],\n",
-    "    'phenotype': ['Cognitive decline', 'Hyperglycemia', 'Tumor growth', 'Increased blood pressure', 'Airway inflammation'],\n",
+    "    'disease': ['Alzheimer disease', 'diabetes mellitus', 'breast cancer', 'Hypertension', 'asthma'],\n",
+    "    'phenotype': ['Mental deterioration', 'Hyperglycemia', 'Tumor growth', 'Increased blood pressure', 'Airway inflammation'],\n",
     "    'developmental_stage': ['Adult', 'Adult', 'Adult', 'Adult', 'Child'],\n",
     "    'patient_age': [70, 55, 60, 65, 12],\n",
     "}\n",

{lamindb-0.77.0 → lamindb-0.77.2}/docs/ehrcurator.py

@@ -46,7 +46,7 @@ class EHRCurator(DataFrameCurator):
             if col not in self.data.columns:
                 self.data[col] = default
             else:
-                self.data[col].fillna(default, inplace=True)
+                self.data[col] = self.data[col].fillna(default)
 
         super().__init__(
             df=self.data,

{lamindb-0.77.0 → lamindb-0.77.2}/docs/faq/search.ipynb

@@ -8,33 +8,19 @@
     "# How does search work?"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "955b6253",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from laminci.db import setup_local_test_postgres"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7f312433",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pgurl = setup_local_test_postgres()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "286aeebc",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-cell"
+    ]
+   },
    "outputs": [],
    "source": [
+    "from laminci.db import setup_local_test_postgres\n",
+    "pgurl = setup_local_test_postgres()\n",
     "!lamin init --name benchmark_search --db {pgurl} --schema bionty --storage ./benchmark_search"
    ]
   },
@@ -43,7 +29,7 @@
    "id": "40234d47",
    "metadata": {},
    "source": [
-    "Here we show how to perform text search on `Record` and evaluate some search queries."
+    "Here we show how to perform text search on `Record` and evaluate some search queries for the {class}`bionty.CellType` ontology."
    ]
   },
   {
@@ -54,36 +40,32 @@
    "outputs": [],
    "source": [
     "import lamindb as ln\n",
-    "import bionty as bt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "83a46a9a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "import bionty as bt\n",
+    "\n",
+    "SEARCH_QUERIES_EXACT = (\"t cell\", \"stem cell\", \"b cell\", \"regulatory B cell\", \"Be2 cell\", \"adipocyte\")\n",
+    "SEARCH_QUERIES_CONTAINS = (\"t cel\", \"t-cel\", \"neural\", \"kidney\", \"kidne\")\n",
+    "TOP_N = 20\n",
+    "\n",
     "bt.CellType.import_source()"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7991a73f",
+   "cell_type": "markdown",
+   "id": "799b528e",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "SEARCH_QUERIES_EXACT = (\"t cell\", \"stem cell\", \"b cell\", \"regulatory B cell\", \"Be2 cell\", \"adipocyte\")\n",
-    "SEARCH_QUERIES_CONTAINS = (\"t cel\", \"t-cel\", \"neural\", \"kidney\", \"kidne\")\n",
-    "TOP_N = 20"
+    "## Search the registry"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "682fcd2f",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "for query in SEARCH_QUERIES_EXACT:\n",
@@ -98,7 +80,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "ee059b0d",
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "for query in SEARCH_QUERIES_CONTAINS:\n",
@@ -111,6 +97,32 @@
     "    assert query in top_record.name.lower() or query in top_record.synonyms.lower()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f4e41c9b",
+   "metadata": {},
+   "source": [
+    "## Search the public ontology"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d42c3594",
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "ct_public = bt.CellType.public()\n",
+    "\n",
+    "df = ct_public.search(\"b cell\", limit=20)\n",
+    "assert df.iloc[0][\"name\"] == \"B cell\"\n",
+    "df"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

{lamindb-0.77.0 → lamindb-0.77.2}/docs/faq/symbol-mapping.ipynb

@@ -4,14 +4,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Why should I validate against gene symbols?"
+    "# Why should I not index datasets with gene symbols?"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Gene symbols are widely used in count data for readability, particularly for visualization. However, storing and validating gene symbols presents challenges:\n",
+    "Gene symbols are widely used for readability, particularly for visualization. However, indexing datasets with gene symbols presents challenges:\n",
     "\n",
     "- A single gene may have multiple symbols or aliases.\n",
     "- Gene symbols change over time (e.g., *BRCA2* was once *FACD*) without version tracking.\n",
@@ -55,6 +55,8 @@
    },
    "outputs": [],
    "source": [
+    "import lamindb as ln\n",
+    "import bionty as bt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "import anndata as ad\n",
@@ -77,15 +79,14 @@
    },
    "outputs": [],
    "source": [
-    "import lamindb as ln\n",
-    "import bionty as bt\n",
-    "\n",
     "# map Gene symbols to ENSEMBL IDs\n",
-    "gene_mapper = bt.Gene.standardize(adata.var.index,\n",
-    "                                  field=bt.Gene.symbol,\n",
-    "                                  return_field=bt.Gene.ensembl_gene_id,\n",
-    "                                  return_mapper=True,\n",
-    "                                  organism=\"human\")\n",
+    "gene_mapper = bt.Gene.standardize(\n",
+    "    adata.var.index,\n",
+    "    field=bt.Gene.symbol,\n",
+    "    return_field=bt.Gene.ensembl_gene_id,\n",
+    "    return_mapper=True,\n",
+    "    organism=\"human\"\n",
+    ")\n",
     "adata.var[\"ensembl_id\"] = adata.var.index.map(gene_mapper)\n",
     "adata.var\n"
    ]
@@ -100,9 +101,11 @@
    },
    "outputs": [],
    "source": [
-    "standardized_genes = bt.Gene.from_values(['ENSG00000141510', 'ENSG00000133703', 'ENSG00000111640', 'ENSG00000171862', 'ENSG00000204490', 'ENSG00000112715', 'ENSG00000146648', 'ENSG00000136997', 'ENSG00000012048', 'ENSG00000136244'],\n",
-    "                                         field=bt.Gene.ensembl_gene_id,\n",
-    "                                         organism=\"human\")\n",
+    "standardized_genes = bt.Gene.from_values(\n",
+    "    ['ENSG00000141510', 'ENSG00000133703', 'ENSG00000111640', 'ENSG00000171862', 'ENSG00000204490', 'ENSG00000112715', 'ENSG00000146648', 'ENSG00000136997', 'ENSG00000012048', 'ENSG00000136244'],\n",
+    "    field=bt.Gene.ensembl_gene_id,\n",
+    "    organism=\"human\"\n",
+    ")\n",
     "ln.save(standardized_genes)"
    ]
   },