RxRx: cell imaging 
¶
rxrx.ai hosts high-throughput cell imaging datasets generated by Recursion.
High numbers of fluorescent microscopy images characterize cellular phenotypes in vitro based on morphology and protein expression (5-10 stains) across a range of conditions.
In this guide, you’ll see how to query some of these data using LaminDB. If you’d like to transfer data into your own LaminDB instance, see the .
# !pip install 'lamindb[gcp]' duckdb
!lamin init --modules bionty,pertdb --storage ./test-rxrx
Show code cell output
→ initialized lamindb: testuser1/test-rxrx
import lamindb as ln
Show code cell output
→ connected lamindb: testuser1/test-rxrx
Create the central query object for this instance:
db = ln.DB("laminlabs/lamindata")
Search & look up metadata¶
We’ll find all genetic treatments in the GeneticPerturbation registry:
df = db.pertdb.GeneticPerturbation.to_dataframe()
df.shape
Show code cell output
(8, 17)
Let us create a look up object for siRNAs so that we can easily auto-complete queries involving it:
sirnas = db.pertdb.GeneticPerturbation.filter(type="siRNA").lookup(return_field="name")
We’re also interested in cell lines:
cell_lines = db.bionty.CellLine.lookup(return_field="abbr")
Load the collection¶
This is RxRx1: 125k images for 1138 siRNA perturbation across 4 cell lines reading out 5 stains, image dimension is 512x512x6.
Let us get the corresponding object and some information about it:
collection = db.Collection.get("Br2Z1lVSQBAkkbbt7ILu")
collection.view_lineage()
collection.describe()
Show code cell output
Collection: Annotated RxRx1 images (1) └── uid: Br2Z1lVSQBAkkbbt7ILu run: 2024-06-17T12:31:43.923373+00:00 (01-rxrx1-ingest.ipynb) branch: main space: all created_at: 2024-06-17 12:43:02 UTC created_by: sunnyosun
The dataset consists in a metadata file and a folder path pointing to the image files:
collection.meta_artifact.load().head()
Show code cell output
! run input wasn't tracked, call `ln.track()` and re-run
| site_id | well_id | cell_line | split | experiment | plate | well | site | well_type | sirna | sirna_id | path | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | HEPG2-08_1_B02_1 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 1 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s1_w1.png |
| 1 | HEPG2-08_1_B02_1 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 1 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s1_w2.png |
| 2 | HEPG2-08_1_B02_1 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 1 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s1_w3.png |
| 3 | HEPG2-08_1_B02_1 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 1 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s1_w4.png |
| 4 | HEPG2-08_1_B02_1 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 1 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s1_w5.png |
Query image files¶
Because we didn’t choose to register each image as a record in the Artifact registry, we have to query the images through the metadata file of the dataset:
df = collection.meta_artifact.load()
Show code cell output
! run input wasn't tracked, call `ln.track()` and re-run
We can query a subset of images using metadata registries & pandas query syntax:
query = df[(df.cell_line == cell_lines.hep_g2_cell) & (df.plate == 1) & (df.site == 2)]
query
Show code cell output
| site_id | well_id | cell_line | split | experiment | plate | well | site | well_type | sirna | sirna_id | path | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6 | HEPG2-08_1_B02_2 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 2 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s2_w1.png |
| 7 | HEPG2-08_1_B02_2 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 2 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s2_w2.png |
| 8 | HEPG2-08_1_B02_2 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 2 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s2_w3.png |
| 9 | HEPG2-08_1_B02_2 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 2 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s2_w4.png |
| 10 | HEPG2-08_1_B02_2 | HEPG2-08_1_B02 | HEPG2 | test | HEPG2-08 | 1 | B02 | 2 | negative_control | EMPTY | 1138 | images/test/HEPG2-08/Plate1/B02_s2_w5.png |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 358111 | HEPG2-07_1_O23_2 | HEPG2-07_1_O23 | HEPG2 | train | HEPG2-07 | 1 | O23 | 2 | treatment | s27411 | 489 | images/train/HEPG2-07/Plate1/O23_s2_w2.png |
| 358112 | HEPG2-07_1_O23_2 | HEPG2-07_1_O23 | HEPG2 | train | HEPG2-07 | 1 | O23 | 2 | treatment | s27411 | 489 | images/train/HEPG2-07/Plate1/O23_s2_w3.png |
| 358113 | HEPG2-07_1_O23_2 | HEPG2-07_1_O23 | HEPG2 | train | HEPG2-07 | 1 | O23 | 2 | treatment | s27411 | 489 | images/train/HEPG2-07/Plate1/O23_s2_w4.png |
| 358114 | HEPG2-07_1_O23_2 | HEPG2-07_1_O23 | HEPG2 | train | HEPG2-07 | 1 | O23 | 2 | treatment | s27411 | 489 | images/train/HEPG2-07/Plate1/O23_s2_w5.png |
| 358115 | HEPG2-07_1_O23_2 | HEPG2-07_1_O23 | HEPG2 | train | HEPG2-07 | 1 | O23 | 2 | treatment | s27411 | 489 | images/train/HEPG2-07/Plate1/O23_s2_w6.png |
20328 rows × 12 columns
To access the individual images based on this query result:
collection.data_artifact.storage.root
Show code cell output
'gs://rxrx1-europe-west4'
images = [f"{collection.data_artifact.storage.root}/{key}" for key in query.path]
images
Download an image to disk:
from IPython.display import Image
path = ln.UPath(images[1])
path.download_to(".")
Image(f"./{path.name}")
Use DuckDB to query metadata¶
As an alternative to pandas, we could use DuckDB to query image metadata.
import duckdb
features = db.Feature.lookup(return_field="name")
filter = (
f"{features.cell_line} == '{cell_lines.hep_g2_cell}' and "
f"{features.plate} == '1' and {features.site} == '2'"
)
parquet_data = duckdb.from_parquet(
collection.meta_artifact.path.as_posix() + "?s3_region=us-east-1"
)
parquet_data.filter(filter)
Show code cell output
┌──────────────────┬────────────────┬───────────┬─────────┬────────────┬───────┬─────────┬───────┬──────────────────┬─────────┬──────────┬────────────────────────────────────────────┐
│ site_id │ well_id │ cell_line │ split │ experiment │ plate │ well │ site │ well_type │ sirna │ sirna_id │ path │
│ varchar │ varchar │ varchar │ varchar │ varchar │ int64 │ varchar │ int64 │ varchar │ varchar │ int64 │ varchar │
├──────────────────┼────────────────┼───────────┼─────────┼────────────┼───────┼─────────┼───────┼──────────────────┼─────────┼──────────┼────────────────────────────────────────────┤
│ HEPG2-08_1_B02_2 │ HEPG2-08_1_B02 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B02 │ 2 │ negative_control │ EMPTY │ 1138 │ images/test/HEPG2-08/Plate1/B02_s2_w1.png │
│ HEPG2-08_1_B02_2 │ HEPG2-08_1_B02 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B02 │ 2 │ negative_control │ EMPTY │ 1138 │ images/test/HEPG2-08/Plate1/B02_s2_w2.png │
│ HEPG2-08_1_B02_2 │ HEPG2-08_1_B02 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B02 │ 2 │ negative_control │ EMPTY │ 1138 │ images/test/HEPG2-08/Plate1/B02_s2_w3.png │
│ HEPG2-08_1_B02_2 │ HEPG2-08_1_B02 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B02 │ 2 │ negative_control │ EMPTY │ 1138 │ images/test/HEPG2-08/Plate1/B02_s2_w4.png │
│ HEPG2-08_1_B02_2 │ HEPG2-08_1_B02 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B02 │ 2 │ negative_control │ EMPTY │ 1138 │ images/test/HEPG2-08/Plate1/B02_s2_w5.png │
│ HEPG2-08_1_B02_2 │ HEPG2-08_1_B02 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B02 │ 2 │ negative_control │ EMPTY │ 1138 │ images/test/HEPG2-08/Plate1/B02_s2_w6.png │
│ HEPG2-08_1_B03_2 │ HEPG2-08_1_B03 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B03 │ 2 │ treatment │ s21721 │ 855 │ images/test/HEPG2-08/Plate1/B03_s2_w1.png │
│ HEPG2-08_1_B03_2 │ HEPG2-08_1_B03 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B03 │ 2 │ treatment │ s21721 │ 855 │ images/test/HEPG2-08/Plate1/B03_s2_w2.png │
│ HEPG2-08_1_B03_2 │ HEPG2-08_1_B03 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B03 │ 2 │ treatment │ s21721 │ 855 │ images/test/HEPG2-08/Plate1/B03_s2_w3.png │
│ HEPG2-08_1_B03_2 │ HEPG2-08_1_B03 │ HEPG2 │ test │ HEPG2-08 │ 1 │ B03 │ 2 │ treatment │ s21721 │ 855 │ images/test/HEPG2-08/Plate1/B03_s2_w4.png │
│ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │
│ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │
│ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │ · │
│ HEPG2-02_1_G17_2 │ HEPG2-02_1_G17 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G17 │ 2 │ treatment │ s27876 │ 3 │ images/train/HEPG2-02/Plate1/G17_s2_w1.png │
│ HEPG2-02_1_G17_2 │ HEPG2-02_1_G17 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G17 │ 2 │ treatment │ s27876 │ 3 │ images/train/HEPG2-02/Plate1/G17_s2_w2.png │
│ HEPG2-02_1_G17_2 │ HEPG2-02_1_G17 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G17 │ 2 │ treatment │ s27876 │ 3 │ images/train/HEPG2-02/Plate1/G17_s2_w3.png │
│ HEPG2-02_1_G17_2 │ HEPG2-02_1_G17 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G17 │ 2 │ treatment │ s27876 │ 3 │ images/train/HEPG2-02/Plate1/G17_s2_w4.png │
│ HEPG2-02_1_G17_2 │ HEPG2-02_1_G17 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G17 │ 2 │ treatment │ s27876 │ 3 │ images/train/HEPG2-02/Plate1/G17_s2_w5.png │
│ HEPG2-02_1_G17_2 │ HEPG2-02_1_G17 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G17 │ 2 │ treatment │ s27876 │ 3 │ images/train/HEPG2-02/Plate1/G17_s2_w6.png │
│ HEPG2-02_1_G18_2 │ HEPG2-02_1_G18 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G18 │ 2 │ treatment │ s27646 │ 124 │ images/train/HEPG2-02/Plate1/G18_s2_w1.png │
│ HEPG2-02_1_G18_2 │ HEPG2-02_1_G18 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G18 │ 2 │ treatment │ s27646 │ 124 │ images/train/HEPG2-02/Plate1/G18_s2_w2.png │
│ HEPG2-02_1_G18_2 │ HEPG2-02_1_G18 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G18 │ 2 │ treatment │ s27646 │ 124 │ images/train/HEPG2-02/Plate1/G18_s2_w3.png │
│ HEPG2-02_1_G18_2 │ HEPG2-02_1_G18 │ HEPG2 │ train │ HEPG2-02 │ 1 │ G18 │ 2 │ treatment │ s27646 │ 124 │ images/train/HEPG2-02/Plate1/G18_s2_w4.png │
└──────────────────┴────────────────┴───────────┴─────────┴────────────┴───────┴─────────┴───────┴──────────────────┴─────────┴──────────┴────────────────────────────────────────────┘
? rows (>9999 rows, 20 shown) 12 columns