Skip to main content
Loading navigation

Build a Research Specimen Biopython Quality Control and Terminology Mapper

Evaluate sequencing run quality metrics from FASTA files and align specimen metadata to standard terminology. Structure results into FHIR Specimen and ResearchStudy observation entities.

Data ScienceHosted by Vera

What you are building

Evaluate sequencing run quality metrics from FASTA files and align specimen metadata to standard terminology. Structure results into FHIR Specimen and ResearchStudy observation entities.

Laboratory Operations Specialist

Read raw specimen FASTA sequences using Biopython SeqIO.

Calculate GC percentage and ambiguity counts for each sample record.

Validate sample metadata against FHIR Foundation administration resource models.

Format audit summaries into structured QC reports for human sign-off.

Web dashboard showing specimen batch QC tables with downloadable FHIR JSON manifests.

Generate synthetic FASTA files with varied nucleotide compositions and simulated specimen identifiers. Starter examples below are synthetic. They are not downloaded records.

Biopython Leverages Biopython's core SeqIO module for parsing FASTA files and calculating sequence composition stats.

mastra-ai, biopython, fastapi. Mastra AI provides declarative workflow orchestration to link parsing, terminology matching, and report generation. Fast hosted model or local Ollama instance for contextual anomaly explanations in QC summaries.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Biopython SeqIO correctly calculates GC content and flags degenerate base thresholds.

Generates valid FHIR Specimen JSON representations with accurate status values.

Includes a human review staging queue for rejected specimens.

```json [ { "input": { "specimen_id": "SPEC-001", "sequence_header": ">sample_01 human_control", "sequence": "GCGCGCGCATATATATGCGC" }, "expected_output": { "specimen_id": "SPEC-001", "length": 20, "gc_content_pct": 60, "qc_status": "PASS", "fhir_resource": "Specimen" } }, { "input": { "specimen_id": "SPEC-002", "sequence_header": ">sample_02 degraded_isolate", "sequence": "NNNNNNCGATNNN" }, "expected_output": { "specimen_id": "SPEC-002", "length": 13, "gc_content_pct": 30.77, "qc_status": "FAIL_HIGH_AMBIGUITY", "fhir_resource": "Specimen" } } ] ```

Confined to pre-analytical laboratory assay quality checks using deidentified research identifiers. Use mock external writes. Require human review before any real deployment.

Rules

Confined to pre-analytical laboratory assay quality checks using deidentified research identifiers. Use mock external writes and human review.

How work is evaluated

Evaluation

Biopython SeqIO correctly calculates GC content and flags degenerate base thresholds. Generates valid FHIR Specimen JSON representations with accurate status values. Includes a human review staging queue for rejected specimens.

Submission format

Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
4 scoring checks
Binary
1 pass or fail dimensions
Ordinal
3 scaled dimensions
Dimension 1

Complete workflow

Read raw specimen FASTA sequences using Biopython SeqIO. Calculate GC percentage and ambiguity counts for each sample record. Validate sample metadata against FHIR Foundation administration resource models. Format audit summaries into structured QC reports for human sign-off.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 2

Correctness and evidence

Biopython SeqIO correctly calculates GC content and flags degenerate base thresholds. Generates valid FHIR Specimen JSON representations with accurate status values. Includes a human review staging queue for rejected specimens.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 3

Review interface

Web dashboard showing specimen batch QC tables with downloadable FHIR JSON manifests.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 4

Safe execution

Confined to pre-analytical laboratory assay quality checks using deidentified research identifiers.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Read raw specimen FASTA sequences using Biopython SeqIO.

  • Calculate GC percentage and ambiguity counts for each sample record.

  • Validate sample metadata against FHIR Foundation administration resource models.

  • Format audit summaries into structured QC reports for human sign-off.

Resources

Dataset notes

Generate synthetic FASTA files with varied nucleotide compositions and simulated specimen identifiers. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Challenge input

Input details are not configured.

Mastra AI

TypeScript agent framework.

Evaluated output

No output checks are configured.

Evaluation checks
  • Read raw specimen FASTA sequences using Biopython SeqIO. Calculate GC percentage and ambiguity counts for e...
  • Biopython SeqIO correctly calculates GC content and flags degenerate base thresholds. Generates valid FHIR...
  • Web dashboard showing specimen batch QC tables with downloadable FHIR JSON manifests.
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 2 configured tools

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Mastra AI · Optional
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • Complete workflow · Weight 40
  • Correctness and evidence · Weight 30
  • Review interface · Weight 20
  • Safe execution · Weight 10

Reference cases

  • 2 public reference cases

Workflow tasks

No workflow tasks are configured.

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Research Specimen Biopython Quality Control and Terminology Mapper