Skip to content

Example using 10x Space Ranger outputs #307

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Example using 10x Space Ranger outputs #307

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
334 changes: 334 additions & 0 deletions docs/notebooks/widget_spaceranger.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,334 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"nbsphinx": "hidden"
},
"source": [
"# Vitessce Widget Tutorial"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Visualization of Space Ranger outputs for 10x Visium\n"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {},
"outputs": [],
"source": [
"from vitessce import (\n",
" VitessceConfig,\n",
" Component as cm,\n",
" CoordinationType as ct,\n",
" OmeTiffWrapper,\n",
" MultiImageWrapper,\n",
" AnnDataWrapper,\n",
" CoordinationLevel as CL,\n",
")\n",
"from vitessce.data_utils import (\n",
" rgb_img_to_ome_tiff,\n",
" VAR_CHUNK_SIZE\n",
")\n",
"import os\n",
"from os.path import join\n",
"import requests\n",
"from anndata import AnnData, read_hdf\n",
"import tifffile\n",
"import tarfile\n",
"import scanpy as sc\n",
"import pandas as pd\n",
"import imageio.v3 as iio\n",
"import json"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 0. Download data\n",
"\n",
"https://www.10xgenomics.com/resources/datasets/gene-protein-expression-library-of-human-tonsil-cytassist-ffpe-2-standard"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"DATA_DIR = join(\"data\", \"human_tonsil\")\n",
"PROCESSED_DIR = join(DATA_DIR, \"processed\")\n",
"os.makedirs(PROCESSED_DIR, exist_ok=True)\n",
"spatial_filepath = join(DATA_DIR, \"spatial.tar.gz\")\n",
"matrix_filepath = join(DATA_DIR, \"matrix.h5\")\n",
"analysis_filepath = join(DATA_DIR, \"analysis.tar.gz\")\n",
"\n",
"base_url = 'https://cf.10xgenomics.com/samples/spatial-exp/2.1.0/CytAssist_FFPE_Protein_Expression_Human_Tonsil/CytAssist_FFPE_Protein_Expression_Human_Tonsil'\n",
"\n",
"# Download\n",
"r_spatial = requests.get(f'{base_url}_spatial.tar.gz')\n",
"with open(spatial_filepath, 'wb') as f:\n",
" f.write(r_spatial.content)\n",
"\n",
"r_matrix = requests.get(f'{base_url}_filtered_feature_bc_matrix.h5')\n",
"with open(matrix_filepath, 'wb') as f:\n",
" f.write(r_matrix.content)\n",
"\n",
"r_analysis = requests.get(f'{base_url}_analysis.tar.gz')\n",
"with open(analysis_filepath, 'wb') as f:\n",
" f.write(r_analysis.content)\n",
" \n",
"# Un-tar\n",
"with tarfile.open(spatial_filepath, \"r:gz\") as tar:\n",
" tar.extractall(path = DATA_DIR)\n",
"with tarfile.open(analysis_filepath, \"r:gz\") as tar:\n",
" tar.extractall(path = DATA_DIR)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Convert data to Vitessce-compatible formats\n",
"\n",
"We need to convert the proprietary 10x Genomics formats to open formats that are compatible with Vitessce such as OME-TIFF and AnnData"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/mkeller/software/miniconda3/envs/vitessce-python-notebooks/lib/python3.9/site-packages/anndata/_core/anndata.py:1900: UserWarning: Variable names are not unique. To make them unique, call `.var_names_make_unique`.\n",
" utils.warn_names_duplicates(\"var\")\n",
"/Users/mkeller/software/miniconda3/envs/vitessce-python-notebooks/lib/python3.9/site-packages/anndata/_core/anndata.py:1900: UserWarning: Variable names are not unique. To make them unique, call `.var_names_make_unique`.\n",
" utils.warn_names_duplicates(\"var\")\n"
]
}
],
"source": [
"adata = sc.read_10x_h5(matrix_filepath)"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {},
"outputs": [],
"source": [
"tsne_df = pd.read_csv(join(DATA_DIR, \"analysis\", \"tsne\", \"gene_expression_2_components\", \"projection.csv\"), index_col=0)"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {},
"outputs": [],
"source": [
"adata.obsm['X_tsne'] = tsne_df.loc[adata.obs.index.tolist()].values"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {},
"outputs": [],
"source": [
"with open(join(DATA_DIR, \"spatial\", \"scalefactors_json.json\"), \"r\") as f:\n",
" scale_factors = json.load(f)"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'regist_target_img_scalef': 0.1533272,\n",
" 'tissue_hires_scalef': 0.051109068,\n",
" 'tissue_lowres_scalef': 0.01533272,\n",
" 'fiducial_diameter_fullres': 383.3196076845379,\n",
" 'spot_diameter_fullres': 255.54640512302527}"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"scale_factors"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
"pos_df = pd.read_csv(join(DATA_DIR, \"spatial\", \"tissue_positions.csv\"), index_col=0)[['pxl_row_in_fullres', 'pxl_col_in_fullres']].loc[adata.obs.index.tolist()]"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {},
"outputs": [],
"source": [
"adata.obsm['X_spatial'] = pos_df.values * scale_factors['tissue_hires_scalef']"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"adata.write_zarr(join(PROCESSED_DIR, \"human_tonsil.h5ad.zarr\"), chunks=(adata.shape[0], VAR_CHUNK_SIZE))"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(3, 1634, 2000)"
]
},
"execution_count": 81,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"img_arr = iio.imread(join(DATA_DIR, \"spatial\", \"tissue_hires_image.png\"))\n",
"img_arr = img_arr.transpose((2, 0, 1))\n",
"img_arr.shape"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {},
"outputs": [],
"source": [
"rgb_img_to_ome_tiff(img_arr, join(PROCESSED_DIR, \"human_tonsil.ome.tiff\"), img_name=\"Image\", axes=\"CYX\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"## 1. Configure Vitessce\n"
]
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {},
"outputs": [],
"source": [
"vc = VitessceConfig(schema_version=\"1.0.16\", name='Tonsil')\n",
"dataset = vc.add_dataset(name='Space Ranger outputs').add_object(AnnDataWrapper(\n",
" adata_path=join(PROCESSED_DIR, \"human_tonsil.h5ad.zarr\"),\n",
" obs_feature_matrix_path=\"X\",\n",
" obs_embedding_paths=[\"obsm/X_tsne\"],\n",
" obs_embedding_names=[\"t-SNE\"],\n",
" obs_locations_path=\"obsm/X_spatial\",\n",
" coordination_values={\n",
" \"obsType\": \"spot\"\n",
" }\n",
")).add_object(OmeTiffWrapper(\n",
" img_path=join(PROCESSED_DIR, \"human_tonsil.ome.tiff\")\n",
"))\n",
"\n",
"spatial = vc.add_view(\"spatial\", dataset=dataset)\n",
"lc = vc.add_view(\"layerController\", dataset=dataset)\n",
"heatmap = vc.add_view(\"heatmap\", dataset=dataset)\n",
"scatterplot = vc.add_view(\"scatterplot\", dataset=dataset, mapping=\"t-SNE\")\n",
"\n",
"vc.link_views([spatial, lc, heatmap, scatterplot], [\"obsType\"], [\"spot\"])\n",
"\n",
"vc.layout((spatial | lc) / (heatmap | scatterplot));"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Create the Vitessce widget"
]
},
{
"cell_type": "code",
"execution_count": 93,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4b44074642ab42fa96867c6787c71173",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VitessceWidget(config={'version': '1.0.16', 'name': 'Tonsil', 'description': '', 'datasets': [{'uid': 'A', 'na…"
]
},
"execution_count": 93,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vw = vc.widget()\n",
"vw"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.0"
}
},
"nbformat": 4,
"nbformat_minor": 4
}