Jupyter Notebook Binder

Multi-modal#

Warning

This is, for now, just a stub.

Here, we’ll showcase how to curate and register ECCITE-seq data from Papalexi21 in the form of MuData objects. ECCITE-seq is designed to enable interrogation of single-cell transcriptomes together with surface protein markers in the context of CRISPR screens.

Setup#

!lamin init --storage ./test-multimodal --schema bionty
Hide code cell output
πŸ’‘ connected lamindb: testuser1/test-multimodal
import lamindb as ln
import bionty as bt

bt.settings.organism = "human"
πŸ’‘ connected lamindb: testuser1/test-multimodal
ln.settings.transform.stem_uid = "yMWSFirS6qv2"
ln.settings.transform.version = "0"
ln.track()
πŸ’‘ notebook imports: bionty==0.42.4 lamindb==0.69.4
πŸ’‘ saved: Transform(uid='yMWSFirS6qv26K79', name='Multi-modal', key='multimodal', version='0', type='notebook', updated_at=2024-03-31 21:42:52 UTC, created_by_id=1)
πŸ’‘ saved: Run(uid='j4JTbSjsOZ1NTft3DwPu', transform_id=1, created_by_id=1)

Papalexi21#

Let’s use a MuData object:

Transform #

Hide code cell content
mdata = ln.core.datasets.mudata_papalexi21_subset()
mdata
MuData object with n_obs Γ— n_vars = 200 Γ— 300
  var:	'name'
  4 modalities
    rna:	200 x 173
      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'
    adt:	200 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:	200 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'
    gdo:	200 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'

MuData objects build on top of AnnData objects to store and serialize multimodal data. More information can be found on the MuData documentation.

First we register the artifact:

artifact = ln.Artifact(
    "papalexi21_subset.h5mu", description="Sub-sampled MuData from Papalexi21"
)
artifact.save()

Now let’s validate and register the 3 feature sets this data contains:

  1. RNA (gene expression)

  2. ADT (antibody derived tags reflecting surface proteins)

  3. obs (metadata)

For the two modalities rna and adt, we use bionty tables as the reference:

Validate #

mdata["rna"].var_names[:5]
Index(['RP5-827C21.6', 'XX-CR54.1', 'SH2D6', 'RP11-379B18.5', 'RP11-778D9.12'], dtype='object', name='index')
bt.Gene.validate(mdata["rna"].var_names, bt.Gene.symbol);
❗ 173 terms (100.00%) are not validated for symbol: RP5-827C21.6, XX-CR54.1, SH2D6, RP11-379B18.5, RP11-778D9.12, RP11-703G6.1, AC005150.1, RP11-717H13.1, CTC-498J12.1, CTC-467M3.1, ARHGAP26-AS1, GABRA1, HIST1H4K, HLA-DQB1-AS1, RP11-524H19.2, SPACA1, VNN1, AC006042.7, AC002066.1, AC073934.6, ...
genes = bt.Gene.from_values(mdata["rna"].var_names, bt.Gene.symbol)
ln.save(genes)
❗ ambiguous validation in Bionty for 6 records: 'HLA-DQB1-AS1', 'CTAGE15', 'CTRB2', 'LGALS9C', 'PCDHB11', 'TBC1D3G'
❗ did not create Gene records for 84 non-validated symbols: 'AC002066.1', 'AC004019.13', 'AC005150.1', 'AC006042.7', 'AC011558.5', 'AC026471.6', 'AC073934.6', 'AC091132.1', 'AC092295.4', 'AC092687.5', 'AE000662.93', 'AL132989.1', 'AP000442.4', 'CTA-373H7.7', 'CTB-134F13.1', 'CTB-31O20.9', 'CTC-498J12.1', 'CTD-2562J17.2', 'CTD-3012A18.1', 'CTD-3065B20.2', ...
mdata["rna"].var_names = bt.Gene.standardize(mdata["rna"].var_names, bt.Gene.symbol)
validated = bt.Gene.validate(mdata["rna"].var_names, bt.Gene.symbol)
❗ 84 terms (48.60%) are not validated for symbol: RP5-827C21.6, XX-CR54.1, RP11-379B18.5, RP11-778D9.12, RP11-703G6.1, AC005150.1, RP11-717H13.1, CTC-498J12.1, RP11-524H19.2, AC006042.7, AC002066.1, AC073934.6, RP11-268G12.1, U52111.14, RP11-235C23.5, RP11-12J10.3, RP11-324E6.9, RP11-187A9.3, RP11-365N19.2, RP11-346D14.1, ...
new_genes = [bt.Gene(symbol=symbol) for symbol in mdata["rna"].var_names[~validated]]
ln.save(new_genes)
bt.Gene.validate(mdata["rna"].var_names, bt.Gene.symbol);
feature_set_rna = ln.FeatureSet.from_values(
    mdata["rna"].var_names, field=bt.Gene.symbol
)
mdata["adt"].var_names
Index(['CD86', 'PDL1', 'PDL2', 'CD366'], dtype='object', name='index')
bt.CellMarker.validate(mdata["adt"].var_names);
❗ 4 terms (100.00%) are not validated for name: CD86, PDL1, PDL2, CD366
markers = bt.CellMarker.from_values(mdata["adt"].var_names)
ln.save(markers)
bt.CellMarker.validate(mdata["adt"].var_names);

Register #

feature_set_adt = ln.FeatureSet.from_values(
    mdata["adt"].var_names, field=bt.CellMarker.name
)

Link them to artifact:

artifact.features._add_feature_set(feature_set_rna, slot="rna")
artifact.features._add_feature_set(feature_set_adt, slot="adt")

The 3rd feature set is the obs:

obs = mdata["rna"].obs

We’re only interested in a single metadata column:

ln.Feature(name="gene_target", type="category").save()
features = ln.Feature.from_df(obs)
ln.save(features)
feature_set_obs = ln.FeatureSet.from_df(obs)
artifact.features._add_feature_set(feature_set_obs, slot="obs")
gene_targets = bt.Gene.from_values(obs["gene_target"], bt.Gene.symbol)
ln.save(gene_targets)
features = ln.Feature.lookup()
artifact.labels.add(gene_targets, feature=features.gene_target)
❗ ambiguous validation in Bionty for 4 records: 'MARCHF8', 'IRF7', 'IFNGR2', 'TNFRSF14'
❗ did not create Gene record for 1 non-validated symbol: 'NT'
nt = ln.ULabel(name="NT", description="Non-targeting control of perturbations")
nt.save()
artifact.labels.add(nt, feature=features.gene_target)
for col in ["orig.ident", "perturbation", "replicate", "Phase", "guide_ID"]:
    labels = [ln.ULabel(name=name) for name in obs[col].unique()]
    ln.save(labels)
❗ loaded ULabel record with same name: 'NT' (disable via ln.settings.upon_create_search_names)
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ records with similar names exist! did you mean to load one of them?
uid score
name
G1 HW3CLeDN 90.0
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
NT w3glRg1R 90.0
❗ records with similar names exist! did you mean to load one of them?
uid score
name
G1 HW3CLeDN 90.0
NT w3glRg1R 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ records with similar names exist! did you mean to load one of them?
uid score
name
G1 HW3CLeDN 90.0
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ records with similar names exist! did you mean to load one of them?
uid score
name
G1 HW3CLeDN 90.0
NT w3glRg1R 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ records with similar names exist! did you mean to load one of them?
uid score
name
G1 HW3CLeDN 90.0
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
NT w3glRg1R 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
NT w3glRg1R 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
NT w3glRg1R 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
G1 HW3CLeDN 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0
❗ record with similar name exist! did you mean to load it?
uid score
name
S S6LBbVzm 90.0

Because none of these labels seem like something we’d want to track in the registry or validate, we don’t link them to the artifact.

artifact.features
Features:
  rna: FeatureSet(uid='MpEU9CNGQZZpfeIK8y8D', n=184, type='number', registry='bionty.Gene', hash='MkNEiIXppO5tY6LeG271', updated_at=2024-03-31 21:42:56 UTC, created_by_id=1)
    'SH2D6', 'MEF2C-AS2', 'ARHGAP26-AS1', 'GABRA1', 'H4C12', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'SPACA1', 'VNN1', 'CTAGE15', 'CTAGE15', 'PFKFB1', 'TRPC5', 'RBPMS-AS1', 'CA8', ...
  adt: FeatureSet(uid='SoSeytRQ0tSiill2k6G7', n=4, type='number', registry='bionty.CellMarker', hash='o8EDT805HnP0Fmk4uZ9e', updated_at=2024-03-31 21:42:56 UTC, created_by_id=1)
    'CD86', 'PDL1', 'PDL2', 'CD366'
  obs: FeatureSet(uid='zmyHo39ia0pNLX1wZP9M', n=19, registry='core.Feature', hash='xh6sNrejzX6pfdot7raj', updated_at=2024-03-31 21:42:57 UTC, created_by_id=1)
    πŸ”— gene_target (bionty.Gene|core.ULabel)
        πŸ”— gene_target (28, bionty.Gene): 'MARCHF8', 'MARCHF8', 'IFNGR1', 'CAV1', 'IRF7', 'IRF7', 'ATF2', 'NFKBIA', 'STAT1', 'SPI1', ...
        πŸ”— gene_target (1, core.ULabel): 'NT'
    orig.ident (category)
    nCount_RNA (number)
    nFeature_RNA (number)
    nCount_HTO (number)
    nFeature_HTO (number)
    nCount_GDO (number)
    nCount_ADT (number)
    nFeature_ADT (number)
    percent.mito (number)
    MULTI_ID (category)
    HTO_classification (category)
    guide_ID (category)
    NT (category)
    perturbation (category)
    replicate (category)
    S.Score (number)
    G2M.Score (number)
    Phase (category)
artifact.describe()
Artifact(uid='iW0vo8wQggnAESMlmV0y', suffix='.h5mu', description='Sub-sampled MuData from Papalexi21', size=606320, hash='RaivS3NesDOP-6kNIuaC3g', hash_type='md5', visibility=1, key_is_virtual=True, updated_at=2024-03-31 21:42:53 UTC)

Provenance:
  πŸ—ƒοΈ storage: Storage(uid='rM0HLtaG', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-multimodal', type='local', updated_at=2024-03-31 21:42:49 UTC, created_by_id=1)
  πŸ“” transform: Transform(uid='yMWSFirS6qv26K79', name='Multi-modal', key='multimodal', version='0', type='notebook', updated_at=2024-03-31 21:42:52 UTC, created_by_id=1)
  πŸ‘£ run: Run(uid='j4JTbSjsOZ1NTft3DwPu', started_at=2024-03-31 21:42:52 UTC, is_consecutive=True, transform_id=1, created_by_id=1)
  πŸ‘€ created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2024-03-31 21:42:49 UTC)
Features:
  rna: FeatureSet(uid='MpEU9CNGQZZpfeIK8y8D', n=184, type='number', registry='bionty.Gene', hash='MkNEiIXppO5tY6LeG271', updated_at=2024-03-31 21:42:56 UTC, created_by_id=1)
    'SH2D6', 'MEF2C-AS2', 'ARHGAP26-AS1', 'GABRA1', 'H4C12', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'HLA-DQB1-AS1', 'SPACA1', 'VNN1', 'CTAGE15', 'CTAGE15', 'PFKFB1', 'TRPC5', 'RBPMS-AS1', 'CA8', ...
  adt: FeatureSet(uid='SoSeytRQ0tSiill2k6G7', n=4, type='number', registry='bionty.CellMarker', hash='o8EDT805HnP0Fmk4uZ9e', updated_at=2024-03-31 21:42:56 UTC, created_by_id=1)
    'CD86', 'PDL1', 'PDL2', 'CD366'
  obs: FeatureSet(uid='zmyHo39ia0pNLX1wZP9M', n=19, registry='core.Feature', hash='xh6sNrejzX6pfdot7raj', updated_at=2024-03-31 21:42:57 UTC, created_by_id=1)
    πŸ”— gene_target (bionty.Gene|core.ULabel)
        πŸ”— gene_target (28, bionty.Gene): 'MARCHF8', 'MARCHF8', 'IFNGR1', 'CAV1', 'IRF7', 'IRF7', 'ATF2', 'NFKBIA', 'STAT1', 'SPI1', ...
        πŸ”— gene_target (1, core.ULabel): 'NT'
    orig.ident (category)
    nCount_RNA (number)
    nFeature_RNA (number)
    nCount_HTO (number)
    nFeature_HTO (number)
    nCount_GDO (number)
    nCount_ADT (number)
    nFeature_ADT (number)
    percent.mito (number)
    MULTI_ID (category)
    HTO_classification (category)
    guide_ID (category)
    NT (category)
    perturbation (category)
    replicate (category)
    S.Score (number)
    G2M.Score (number)
    Phase (category)
Labels:
  🏷️ genes (28, bionty.Gene): 'MARCHF8', 'MARCHF8', 'IFNGR1', 'CAV1', 'IRF7', 'IRF7', 'ATF2', 'NFKBIA', 'STAT1', 'SPI1', ...
  🏷️ ulabels (1, core.ULabel): 'NT'
artifact.view_lineage()
_images/9e094622cc186883a37ed99d45fa9d79b2df3e339eaab1c32b09fb9d62cb160d.svg
# clean up test instance
!lamin delete --force test-multimodal
!rm -r test-multimodal
Hide code cell output
πŸ’‘ deleting instance testuser1/test-multimodal
❗ manually delete your stored data: /home/runner/work/lamin-usecases/lamin-usecases/docs/test-multimodal