Visualize MuData in Vitessce¶
!lamin load laminlabs/lamindata
💡 connected lamindb: laminlabs/lamindata
import lamindb as ln
ln.context.uid = "aCrfeVoAaDr90000"
ln.context.track()
💡 connected lamindb: laminlabs/lamindata
💡 notebook imports: lamindb==0.70.3 mudata==0.2.3 scanpy==1.10.1 vitessce==3.2.5
💡 saved: Transform(uid='aCrfeVoAaDr95zKv', name='Visualize MuData in Vitessce', key='mudata-vitessce', version='1', type='notebook', updated_at=2024-04-30 12:46:10 UTC, created_by_id=2)
💡 saved: Run(uid='VPYyibO30e6mHkw7DC7r', transform_id=82, created_by_id=2)
Prepare dataset¶
Load MuData object from: https://lamin.ai/laminlabs/lamindata/artifact/DDFxKYXoNMmHzQAHqpx0
mdata_artifact = ln.Artifact.get("DDFxKYXo")
mdata = mdata_artifact.load()
mdata
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/anndata/_core/anndata.py:430: FutureWarning: The dtype argument is deprecated and will be removed in late 2024.
warnings.warn(
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/anndata/_core/anndata.py:430: FutureWarning: The dtype argument is deprecated and will be removed in late 2024.
warnings.warn(
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/anndata/_core/anndata.py:430: FutureWarning: The dtype argument is deprecated and will be removed in late 2024.
warnings.warn(
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/anndata/_core/anndata.py:430: FutureWarning: The dtype argument is deprecated and will be removed in late 2024.
warnings.warn(
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/mudata/_core/mudata.py:491: UserWarning: Cannot join columns with the same name because var_names are intersecting.
warnings.warn(
MuData object with n_obs × n_vars = 20729 × 18776
4 modalities
rna: 20729 x 18649
obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_HTO', 'nFeature_HTO', 'nCount_GDO', 'nCount_ADT', 'nFeature_ADT', 'percent.mito', 'MULTI_ID', 'HTO_classification', 'guide_ID', 'gene_target', 'NT', 'perturbation', 'replicate', 'S.Score', 'G2M.Score', 'Phase'
var: 'name', 'highly_variable', 'means', 'dispersions', 'dispersions_norm'
uns: 'Phase_colors', 'hvg', 'log1p', 'neighbors', 'pca', 'perturbation_colors', 'replicate_colors', 'umap'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
obsp: 'connectivities', 'distances'
adt: 20729 x 4
obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_HTO', 'nFeature_HTO', 'nCount_GDO', 'nCount_ADT', 'nFeature_ADT', 'percent.mito', 'MULTI_ID', 'HTO_classification', 'guide_ID', 'gene_target', 'NT', 'perturbation', 'replicate', 'S.Score', 'G2M.Score', 'Phase'
var: 'name'
hto: 20729 x 12
obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_HTO', 'nFeature_HTO', 'nCount_GDO', 'nCount_ADT', 'nFeature_ADT', 'percent.mito', 'MULTI_ID', 'HTO_classification', 'guide_ID', 'gene_target', 'NT', 'perturbation', 'replicate', 'S.Score', 'G2M.Score', 'Phase'
var: 'name'
uns: 'neighbors', 'umap'
obsm: 'X_umap'
obsp: 'connectivities', 'distances'
gdo: 20729 x 111
obs: 'orig.ident', 'nCount_RNA', 'nFeature_RNA', 'nCount_HTO', 'nFeature_HTO', 'nCount_GDO', 'nCount_ADT', 'nFeature_ADT', 'percent.mito', 'MULTI_ID', 'HTO_classification', 'guide_ID', 'gene_target', 'NT', 'perturbation', 'replicate', 'S.Score', 'G2M.Score', 'Phase'
var: 'name'Subset to hvg for visualization:
mdata.mod["rna"] = mdata["rna"][:, mdata["rna"].var["highly_variable"]]
mdata.update()
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/mudata/_core/mudata.py:491: UserWarning: Cannot join columns with the same name because var_names are intersecting.
warnings.warn(
Write to anndata.zarr:
output_path = "mudata_papalexi21.anndata.zarr"
mdata.write_zarr(output_path)
/opt/miniconda3/envs/py310/lib/python3.10/site-packages/mudata/_core/mudata.py:491: UserWarning: Cannot join columns with the same name because var_names are intersecting.
warnings.warn(
Save dataset¶
zarr_artifact = ln.Artifact(
output_path,
description="MuData from Papalexi21",
)
zarr_artifact.save()
... uploading mudata_papalexi21.anndata.zarr: 0.0%
... uploading mudata_papalexi21.anndata.zarr: 100.0%
from vitessce import (
VitessceConfig,
Component as cm,
AnnDataWrapper,
)
vc = VitessceConfig(
schema_version="1.0.15",
description=zarr_artifact.description,
)
dataset = vc.add_dataset(name="Papalexi21").add_object(
AnnDataWrapper(
adata_url=zarr_artifact.path.to_url(),
obs_feature_matrix_path="mod/rna/X",
obs_embedding_paths=["mod/rna/obsm/X_umap", "mod/rna/obsm/X_pca"],
obs_embedding_names=["UMAP", "PCA"],
obs_set_paths=[
"mod/rna/obs/gene_target",
"mod/rna/obs/guide_ID",
"mod/rna/obs/Phase",
"mod/rna/obs/replicate",
],
obs_set_names=["Gene target", "Guide id", "Cell cycle", "Replicate"],
)
)
obs_sets = vc.add_view(cm.OBS_SETS, dataset=dataset)
obs_sets_sizes = vc.add_view(cm.OBS_SET_SIZES, dataset=dataset)
umap = vc.add_view(cm.SCATTERPLOT, dataset=dataset, mapping="UMAP")
pca = vc.add_view(cm.SCATTERPLOT, dataset=dataset, mapping="PCA")
heatmap = vc.add_view(cm.HEATMAP, dataset=dataset)
genes = vc.add_view(cm.FEATURE_LIST, dataset=dataset)
vc.layout(((umap | pca) / heatmap) | ((genes | obs_sets) / obs_sets_sizes))
# inspect the config
vc.to_dict()
{'version': '1.0.15',
'name': '',
'description': 'MuData from Papalexi21',
'datasets': [{'uid': 'A',
'name': 'Papalexi21',
'files': [{'fileType': 'anndata.zarr',
'url': 'https://lamindata.s3.amazonaws.com/.lamindb/tCUkRcaEjTjhtozp.anndata.zarr',
'options': {'obsEmbedding': [{'path': 'mod/rna/obsm/X_umap',
'dims': [0, 1],
'embeddingType': 'UMAP'},
{'path': 'mod/rna/obsm/X_pca', 'dims': [0, 1], 'embeddingType': 'PCA'}],
'obsSets': [{'name': 'Gene target', 'path': 'mod/rna/obs/gene_target'},
{'name': 'Guide id', 'path': 'mod/rna/obs/guide_ID'},
{'name': 'Cell cycle', 'path': 'mod/rna/obs/Phase'},
{'name': 'Replicate', 'path': 'mod/rna/obs/replicate'}],
'obsFeatureMatrix': {'path': 'mod/rna/X'}}}]}],
'coordinationSpace': {'dataset': {'A': 'A'},
'embeddingType': {'A': 'UMAP', 'B': 'PCA'}},
'layout': [{'component': 'obsSets',
'coordinationScopes': {'dataset': 'A'},
'x': 9.0,
'y': 0.0,
'w': 3.0,
'h': 6.0},
{'component': 'obsSetSizes',
'coordinationScopes': {'dataset': 'A'},
'x': 6.0,
'y': 6.0,
'w': 6.0,
'h': 6.0},
{'component': 'scatterplot',
'coordinationScopes': {'dataset': 'A', 'embeddingType': 'A'},
'x': 0.0,
'y': 0.0,
'w': 3.0,
'h': 6.0},
{'component': 'scatterplot',
'coordinationScopes': {'dataset': 'A', 'embeddingType': 'B'},
'x': 3.0,
'y': 0.0,
'w': 3.0,
'h': 6.0},
{'component': 'heatmap',
'coordinationScopes': {'dataset': 'A'},
'x': 0.0,
'y': 6.0,
'w': 6.0,
'h': 6.0},
{'component': 'featureList',
'coordinationScopes': {'dataset': 'A'},
'x': 6.0,
'y': 0.0,
'w': 3.0,
'h': 6.0}],
'initStrategy': 'auto'}
from lamindb.integrations import save_vitessce_config
vc_artifact = save_vitessce_config(vc, description="View Papalexi21 in Vitessce")
💡 go to: https://lamin.ai/laminlabs/lamindata/artifact/sRapK07mMtToihzFeTaf
ln.finish()
✅ cell execution numbers increase consecutively
✅ saved transform.source_code: Artifact(uid='j6zQfam6cVBHlOR1dTde', suffix='.ipynb', description='Source of transform aCrfeVoAaDr95zKv', version='1', size=4511, hash='cmD2CwZCSebUjDXlzngfmQ', hash_type='md5', visibility=0, key_is_virtual=True, updated_at=2024-04-30 12:52:46 UTC, storage_id=2, created_by_id=2)
✅ saved run.environment: Artifact(uid='nYO2R3tM4rhqB7mZHZnl', suffix='.txt', description='requirements.txt', size=10821, hash='Iu7Isnon8g7iS-XUyNFD7w', hash_type='md5', visibility=0, key_is_virtual=True, updated_at=2024-04-30 12:52:47 UTC, storage_id=2, created_by_id=2)
✅ saved transform.latest_report: Artifact(uid='NEuTTW4HAIX9ORtCuDOe', suffix='.html', description='Report of run VPYyibO30e6mHkw7DC7r', size=293911, hash='ADqBuImn9seir0EPXhGOcg', hash_type='md5', visibility=0, key_is_virtual=True, updated_at=2024-04-30 12:52:48 UTC, storage_id=2, created_by_id=2)
✅ go to: https://lamin.ai/laminlabs/lamindata/transform/aCrfeVoAaDr95zKv