Single-Cell RNA-seq — Clustering, Trajectory, DE & GRN (Synthetic HB3.1)¶
- Task ID:
biology.scrna_seq_analysis - Domain:
biology - Subdomain:
transcriptomics - Status:
final - Benchmark set:
seed42(60tasks) - Tags:
scrna_seq,clustering,pseudotime,differential_expression,gene_regulatory_network,pipeline_decisions
Runtime and requirements¶
- Estimated time:
45-90minutes - Python:
>=3.11 - Packages:
numpy,scipy - GPU required:
no - Network required:
no
Public input and output contract¶
Inputs¶
system_info.json(data): Dataset shape metadata and TF gene column indices for GRN scoringcounts.npy(data): Simulated cell-by-gene count matrix (Poisson-like)
Outputs¶
analysis.py(code): Runnable notebook-style pipeline implementing the requested analysesclusters.npy(data): Per-cell discrete cluster assignments (any consistent labeling)pseudotime.npy(data): Scalar pseudotime per cell (monotone preferred along inferred trajectory)de_genes.json(data): {"gene_indices": [int,...]} ranked marker candidates across clustersgrn_scores.npy(data): Directed edge scores among TF genes (columns 0..n_tf_genes-1 of counts)method_choices.json(data): Per-step method selection with justification: normalization, batch correction, clustering, pseudotime, DE, GRN
Public repository files¶
Formal benchmark task directories in the public repository are metadata-only. Versioned prompts and inputs are distributed through the pinned benchmark dataset.
Provenance¶
This task is included in the current seed42 benchmark set at dataset revision f11a199f71fb4b854ac43a1bf548d5df519141a9.
This page is generated only from files tracked in the public ASI-Bench repository at commit f18382f03faf.
Submission bundles, run logs, private scoring configuration, and private reference answers are not read by this page generator.