Skip to content

Commit

Permalink
💄 Prettify Vitessce guide (#23)
Browse files Browse the repository at this point in the history
  • Loading branch information
@falexwolf
falexwolf authored Aug 22, 2024
1 parent df93ae1 commit 6c08e4f
Showing 1 changed file with 72 additions and 101 deletions.
173 changes: 72 additions & 101 deletions docs/vitessce.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"[![](https://img.shields.io/badge/Source%20on%20GitHub-orange)](https://github.com/laminlabs/lamin-spatial/blob/main/docs/vitessce.ipynb)"
"[![](https://img.shields.io/badge/Source%20on%20GitHub-orange)](https://github.com/laminlabs/lamin-spatial/blob/main/docs/vitessce.ipynb) [![hub](https://img.shields.io/badge/View%20on%20LaminHub-mediumseagreen)](https://lamin.ai/laminlabs/lamindata/transform/hqtT4OTr5Tiq5zKv/URbaThYhljgXbZEzgj5x)"
]
},
{
Expand All @@ -20,126 +20,109 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"This tutorial has been adopted from the data preparation examples in [the Vitessce documention](https://vitessce.github.io/vitessce-python)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup\n",
"This tutorial has been adopted from the data preparation examples in [the Vitessce documention](https://vitessce.github.io/vitessce-python).\n",
"\n",
"Install dependencies:\n",
"\n",
"```python\n",
"pip install vitessce\n",
"pip install 'lamindb[jupyter,aws,bionty]'\n",
"```"
"It uses a [dataset](https://www.covid19cellatlas.org/index.healthy.html#habib17) from the COVID-19 Cell Atlas."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"metadata": {
"tags": [
"hide-output"
]
},
"outputs": [],
"source": [
"# !pip install vitessce\n",
"# !pip install 'lamindb[jupyter,aws,bionty]'\n",
"!lamin load laminlabs/lamin-dev # <-- replace with your instance"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"metadata": {
"tags": [
"hide-output"
]
},
"outputs": [],
"source": [
"from urllib.request import urlretrieve\n",
"from pathlib import Path\n",
"from anndata import read_h5ad\n",
"from vitessce import (\n",
" VitessceConfig,\n",
" Component as cm,\n",
" AnnDataWrapper,\n",
")\n",
"from vitessce.data_utils import (\n",
" to_uint8,\n",
" sort_var_axis,\n",
" optimize_adata,\n",
")\n",
"import lamindb as ln"
"import vitessce as vit\n",
"from vitessce import data_utils as vitdu\n",
"import lamindb as ln\n",
"\n",
"# [optional] track the current notebook or script\n",
"ln.context.uid = \"BZhZQ6uIbkWv0000\"\n",
"ln.context.track()"
]
},
{
"cell_type": "code",
"execution_count": null,
"cell_type": "markdown",
"metadata": {},
"outputs": [],
"source": [
"# [optional] track the current notebook or script\n",
"ln.context.uid = \"BZhZQ6uIbkWv0000\"\n",
"ln.context.track()"
"## Save your dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Pre-process the dataset\n",
"\n",
"For this example, we use a dataset from the COVID-19 Cell Atlas https://www.covid19cellatlas.org/index.healthy.html#habib17."
"Convert the dataset to `.zarr` format."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": []
"tags": [
"hide-output"
]
},
"outputs": [],
"source": [
"# From https://github.com/vitessce/vitessce-python/blob/main/demos/habib-2017/src/convert_to_zarr.py\n",
"# from https://github.com/vitessce/vitessce-python/blob/main/demos/habib-2017/src/convert_to_zarr.py\n",
"def convert_h5ad_to_zarr(input_path, output_path):\n",
" adata = read_h5ad(input_path)\n",
" adata = adata[:, adata.var[\"highly_variable\"]].copy()\n",
" leaf_list = sort_var_axis(adata.X, adata.var.index.values)\n",
" leaf_list = vitdu.sort_var_axis(adata.X, adata.var.index.values)\n",
" adata = adata[:, leaf_list].copy()\n",
" adata.layers[\"X_uint8\"] = to_uint8(adata.X, norm_along=\"var\")\n",
" adata = optimize_adata(\n",
" adata.layers[\"X_uint8\"] = vitdu.to_uint8(adata.X, norm_along=\"var\")\n",
" adata = vitdu.optimize_adata(\n",
" adata, obs_cols=[\"CellType\"], obsm_keys=[\"X_umap\"], layer_keys=[\"X_uint8\"]\n",
" )\n",
" adata.write_zarr(output_path)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"hide-output"
]
},
"outputs": [],
"source": [
"adata_filepath = \"./habib17.processed.h5ad\"\n",
"if not Path(adata_filepath).exists():\n",
" adata.write_zarr(output_path)\n",
"\n",
"\n",
"h5ad_filepath = \"./habib17.processed.h5ad\"\n",
"if not Path(h5ad_filepath).exists():\n",
" urlretrieve(\n",
" \"https://covid19.cog.sanger.ac.uk/habib17.processed.h5ad\", adata_filepath\n",
" \"https://covid19.cog.sanger.ac.uk/habib17.processed.h5ad\", h5ad_filepath\n",
" )\n",
"zarr_filepath = \"./hhabib_2017_nature_methods.anndata.zarr\"\n",
"\n",
"convert_h5ad_to_zarr(adata_filepath, zarr_filepath)"
"convert_h5ad_to_zarr(h5ad_filepath, zarr_filepath)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Save dataset"
"Save a `.zarr` version of the dataset to lamindb."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"metadata": {
"tags": [
"hide-output"
]
},
"outputs": [],
"source": [
"zarr_artifact = ln.Artifact(\n",
Expand All @@ -153,25 +136,14 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a `VitessceConfig` object"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
":::{note}\n",
"\n",
"Here is [a note](https://lamin.ai/laminlabs/lamindata/transform/WDjio16cQsdW5zKv) on folder upload speed and we why chose to not use the `.export(to=\"s3\")` functionality of Vitessce.\n",
"\n",
":::"
"## Save a `VitessceConfig` object"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Set up the configuration by adding the views and datasets of interest."
"You can create a dashboard for one or several datasets by using Vitessce's component API."
]
},
{
Expand All @@ -184,12 +156,12 @@
},
"outputs": [],
"source": [
"vc = VitessceConfig(\n",
"vc = vit.VitessceConfig(\n",
" schema_version=\"1.0.15\",\n",
" description=zarr_artifact.description,\n",
")\n",
"dataset = vc.add_dataset(name=\"Habib 2017\").add_object(\n",
" AnnDataWrapper(\n",
" vit.AnnDataWrapper(\n",
" adata_url=zarr_artifact.path.to_url(),\n",
" obs_feature_matrix_path=\"layers/X_uint8\",\n",
" obs_embedding_paths=[\"obsm/X_umap\"],\n",
Expand All @@ -198,40 +170,41 @@
" obs_set_names=[\"Cell Type\"],\n",
" )\n",
")\n",
"obs_sets = vc.add_view(cm.OBS_SETS, dataset=dataset)\n",
"obs_sets_sizes = vc.add_view(cm.OBS_SET_SIZES, dataset=dataset)\n",
"scatterplot = vc.add_view(cm.SCATTERPLOT, dataset=dataset, mapping=\"UMAP\")\n",
"heatmap = vc.add_view(cm.HEATMAP, dataset=dataset)\n",
"genes = vc.add_view(cm.FEATURE_LIST, dataset=dataset)\n",
"vc.layout(((scatterplot | obs_sets) / heatmap) | (obs_sets_sizes / genes))\n",
"\n",
"# inspect the config\n",
"vc.to_dict()"
"obs_sets = vc.add_view(vit.Component.OBS_SETS, dataset=dataset)\n",
"obs_sets_sizes = vc.add_view(vit.Component.OBS_SET_SIZES, dataset=dataset)\n",
"scatterplot = vc.add_view(vit.Component.SCATTERPLOT, dataset=dataset, mapping=\"UMAP\")\n",
"heatmap = vc.add_view(vit.Component.HEATMAP, dataset=dataset)\n",
"genes = vc.add_view(vit.Component.FEATURE_LIST, dataset=dataset)\n",
"vc.layout(((scatterplot | obs_sets) / heatmap) | (obs_sets_sizes / genes))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Save `VitessceConfig` object"
"Save the `VitessceConfig` object."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"metadata": {
"tags": [
"hide-output"
]
},
"outputs": [],
"source": [
"from lamindb.integrations import save_vitessce_config"
"vc_artifact = ln.integrations.save_vitessce_config(\n",
" vc, description=\"View Habib17 in Vitessce\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"cell_type": "markdown",
"metadata": {},
"outputs": [],
"source": [
"vc_artifact = save_vitessce_config(vc, description=\"View Habib17 in Vitessce\")"
"You can now see the Vitessce button show up on your dataset as in this [example dataset](https://lamin.ai/laminlabs/lamindata/artifact/HXJ4DDAw8012jVKwoxgd)."
]
},
{
Expand All @@ -249,21 +222,19 @@
"metadata": {},
"outputs": [],
"source": [
"# [optional] save run report to share notebook with collaborators\n",
"# ln.finish()"
"# [optional] finish run context and auto-save the notebook\n",
"# ln.context.finish()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"See how a Vitessce UI button looks like:\n",
"\n",
"[![hub](https://img.shields.io/badge/View%20in%20LaminHub-mediumseagreen)](https://lamin.ai/laminlabs/lamindata/transform/hqtT4OTr5Tiq5zKv/URbaThYhljgXbZEzgj5x)\n",
":::{note}\n",
"\n",
"<img src=\"https://lamin-site-assets.s3.amazonaws.com/.lamindb/Snwsp5hrG9bAb5Uxtb3P.png\" width=\"700px\">\n",
"Here is [a note](https://lamin.ai/laminlabs/lamindata/transform/WDjio16cQsdW5zKv) on folder upload speed and we why chose not to use the `.export(to=\"s3\")` functionality of Vitessce.\n",
"\n",
"Click the Vitessce button to visualize [this config file](https://lamin.ai/laminlabs/lamindata/artifact/HXJ4DDAw8012jVKwoxgd)."
":::"
]
},
{
Expand Down Expand Up @@ -298,7 +269,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.1.-1"
"version": "3.10.13"
}
},
"nbformat": 4,
Expand Down

0 comments on commit 6c08e4f

Please sign in to comment.