Analyze a dataset in memory

Here, we’ll analyze the growing dataset by loading it into memory.

This is only possible if it’s not too large.

If your data is large, you’ll likely want to iterate over the dataset to train a model, the topic of the next page ().

import lamindb as ln
import lnschema_bionty as lb
import anndata as ad

💡 loaded instance: testuser1/test-scrna (lamindb 0.59.0)

ln.track()

💡 notebook imports: anndata==0.9.2 lamindb==0.59.0 lnschema_bionty==0.34.0 scanpy==1.9.5

💡 Transform(uid='mfWKm8OtAzp8z8', name='Analyze a dataset in memory', short_name='scrna4', version='0', type=notebook, updated_at=2023-10-27 14:09:51, created_by_id=1)

💡 Run(uid='f1vpEsbuoXJBxwAlf8ac', run_at=2023-10-27 14:09:51, transform_id=4, created_by_id=1)

ln.Dataset.filter().df()

	uid	name	description	version	hash	reference	reference_type	transform_id	run_id	file_id	storage_id	initial_version_id	visibility	updated_at	created_by_id
id
1	OmLkMWSbDuMAxFj7BqyV	My versioned scRNA-seq dataset	None	1	9sXda5E7BYiVoDOQkTC0KB	None	None	1	1	1.0	None	NaN	0	2023-10-27 14:08:58	1
2	RDxHTczEzFNu9i3W9qtN	My versioned scRNA-seq dataset	None	2	Dhr3T5Txeb_oL64H52lS	None	None	2	2	NaN	None	1.0	0	2023-10-27 14:09:37	1

dataset = ln.Dataset.filter(name="My versioned scRNA-seq dataset", version="2").one()

dataset.files.df()

	uid	storage_id	key	suffix	accessor	description	version	size	hash	hash_type	transform_id	run_id	initial_version_id	visibility	key_is_virtual	updated_at	created_by_id
id
1	OmLkMWSbDuMAxFj7BqyV	1	None	.h5ad	AnnData	Conde22	None	57612943	9sXda5E7BYiVoDOQkTC0KB	sha1-fl	1	1	None	0	True	2023-10-27 14:08:58	1
2	viuAb9psg6SVruytRK7P	1	None	.h5ad	AnnData	10x reference adata	None	857752	U4UmKxr_rN8KlwVK4WYKjw	md5	2	2	None	0	True	2023-10-27 14:09:34	1

If the dataset doesn’t consist of too many files, we can now load it into memory.

Under-the-hood, the AnnData objects are concatenated during loading.

The amount of time this takes depends on a variety of factors.

If it occurs often, one might consider storing a concatenated version of the dataset, rather than the individual pieces.

adata = dataset.load()

The default is an outer join during concatenation as in pandas:

adata

AnnData object with n_obs × n_vars = 1718 × 36508
    obs: 'donor', 'tissue', 'cell_type', 'assay', 'n_genes', 'percent_mito', 'louvain', 'file_uid'
    obsm: 'X_umap', 'X_pca'

The AnnData has the reference to the individual files in the .obs annotations:

adata.obs.file_uid.cat.categories

Index(['OmLkMWSbDuMAxFj7BqyV', 'viuAb9psg6SVruytRK7P'], dtype='object')

We can easily obtain ensemble IDs for gene symbols using the look up object:

genes = lb.Gene.lookup(field="symbol")

genes.itm2b.ensembl_gene_id

'ENSG00000136156'

Let us create a plot:

import scanpy as sc

sc.pp.pca(adata, n_comps=2)

2023-10-27 14:09:55,860:INFO - Failed to extract font properties from /usr/share/fonts/truetype/noto/NotoColorEmoji.ttf: In FT2Font: Can not load face (unknown file format; error code 0x2)

2023-10-27 14:09:55,882:INFO - generated new fontManager

sc.pl.pca(
    adata,
    color=genes.itm2b.ensembl_gene_id,
    title=(
        f"{genes.itm2b.symbol} / {genes.itm2b.ensembl_gene_id} /"
        f" {genes.itm2b.description}"
    ),
    save="_itm2b",
)

WARNING: saving figure to file figures/pca_itm2b.pdf

We could save a plot as a pdf and then see it in the flow diagram:

file = ln.File("./figures/pca_itm2b.pdf", description="My result on ITM2B")
file.save()
file.view_flow()

Show code cell output Hide code cell output

But given the image is part of the notebook, we can also rely on the report that we create when saving the notebook via the command line via:

lamin save <notebook_path>

To see the current notebook, visit: lamin.ai/laminlabs/lamindata/record/core/Transform?uid=mfWKm8OtAzp8z8