Skip to content
Home / Catalog / Contextual DNA Regime Interval Mapping

Contextual DNA Regime Interval Mapping

  • Task ID: biology.contextual_dna_regime_mapping
  • Domain: biology
  • Subdomain: computational_genomics
  • Status: final
  • Benchmark set: seed42 (60 tasks)
  • Tags: computational_genomics, dna_segmentation, sequence_regimes, adjacent_base_composition, interval_mapping

Runtime and requirements

  • Estimated time: 35-75 minutes
  • Python: >=3.11
  • Packages: numpy>=2.0, matplotlib>=3.7
  • GPU required: no
  • Network required: no

Public input and output contract

Inputs

  • data/sequence_bundle.fasta (data): Chromosome-like DNA segments. Headers are stable sequence IDs.
  • data/analysis_spec.json (data): Sequence metadata, required output schema, adjacent-pair feature order, and analysis window settings. No labels are included.
  • data/example_window_statistics.npy (data): One unlabeled sliding-window summary track for format reference only: row 0 coordinate, row 1 GC fraction, row 2 CpG observed/expected.

Outputs

  • analysis.py (code): Agent-written implementation and analysis script.
  • predicted_regions.csv (data): Predicted enriched intervals with columns seq_id,start,end,score; 0-based half-open coordinates.
  • state_paths.npz (data): Per-sequence binary regime-path arrays. Keys must match seq_id values.
  • posterior_probs.npz (data): Per-sequence probability-like confidence arrays for the reported enriched regime.
  • fit_diagnostics.json (data): Fitted adjacent-pair regime profiles, persistence summaries, and objective trace.
  • summary_metrics.json (data): Agent-computed summary diagnostics: n_regions, state_fraction_by_sequence, path_confidence_agreement, warnings.
  • diagnostic_plots.png (figure): Genome-track style diagnostic plots showing sequence composition, confidence tracks, and predicted intervals.

Public repository files

View this task in ASI-Bench

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.