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 you deal with particularly large data, please read the guide on iterating over datta batches (to come).

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

💡 loaded instance: testuser1/test-scrna (lamindb 0.56a1)

ln.track()

💡 notebook imports: anndata==0.9.2 lamindb==0.56a1 lnschema_bionty==0.32.0 scanpy==1.9.5

💡 Transform(id=4, uid='mfWKm8OtAzp8z8', name='Analyze a dataset in memory', short_name='scrna4', version='0', type=notebook, updated_at=2023-10-16 21:48:04, created_by_id=1)

💡 Run(id=4, uid='A5UvkmfgqO80MkP0uJfp', run_at=2023-10-16 21:48:04, 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	updated_at	created_by_id
id
1	MpmFBPjOegAuuyRzbGAq	My versioned scRNA-seq dataset	None	1	6Hu1BywwK6bfIU2Dpku2xZ	None	None	1	1	1.0	None	NaN	2023-10-16 21:47:05	1
2	PUwAqZ7C9c7EBQ7f0IgN	My versioned scRNA-seq dataset	None	2	JNjc88f22TLVPJHdgo7X	None	None	2	2	NaN	None	1.0	2023-10-16 21:47:46	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	updated_at	created_by_id
id
1	MpmFBPjOegAuuyRzbGAq	1	None	.h5ad	AnnData	Conde22	None	57615999	6Hu1BywwK6bfIU2Dpku2xZ	sha1-fl	1	1	None	2023-10-16 21:47:05	1
2	qscOv2TpO4PaevwVlwRs	1	None	.h5ad	AnnData	10x reference adata	None	857752	j6o6e27xPdqHQyT7Em_7MQ	md5	2	2	None	2023-10-16 21:47:42	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_id'
    obsm: 'X_umap', 'X_pca'

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

adata.obs.file_id.cat.categories

Int64Index([1, 2], dtype='int64')

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)

2023-10-16 21:48:09,219: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)

2023-10-16 21:48:09,302: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

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

file.view_flow()

Given the image is part of the notebook, there isn’t an actual need to save it and you can also rely on the report that you’ll create when saving the notebook via the command line via:

lamin save <notebook_path>