New submission

Submit prediction

ARC VCC 2025 / Final test / H1 hESC

Free dataset

Download inputs

Use these files to generate predictions on your own infrastructure, then upload your prediction below.

Control cells

.h5ad

Unperturbed expression profiles and input metadata. No treated expression profiles.

Treatment labels

.csv

The target conditions your model should predict for this dataset.

Ordered gene list

.csv

Gene identifiers in the order required for your predictions.

Prediction schema

.json

Matrix location, metadata columns, and input conventions for this dataset.

Prepare your prediction

Source documentation
  1. Load the control cells, treatment labels, and ordered genes above.
  2. Generate at least two cells for each requested treatment in its supplied cell context and batch. Keep the supplied feature order.
  3. Include unperturbed control rows from the supplied inputs under the exact control label below. The evaluator uses these as its baseline.
  4. Save your predicted expression and condition metadata in an .h5ad file using the schema below, then select it in the prediction form.

Match the normalization specified in the prepared input bundle.

Expression matrix
.X
Perturbation column
target_gene
Control label
non-targeting
Cell context column
cell_type
Batch column
batch
Gene set
VCC Human / 18,080 genes

Prepare your prediction

Download the inputs above and follow this dataset’s preparation instructions. Evaluation is not connected for this dataset yet; files will not be uploaded.