Skip to main content
Loading navigation
Back to challenges

Gestational Phenotype Context-Specific GWAS Triage Engine with PLINK and Python

Context-specific genetic effects modulate risk across distinct stages of pregnancy. You will build a quantitative genetics analysis pipeline using Python and PLINK to execute genome-wide association study (GWAS) triage, identifying interaction effects with a false discovery rate (FDR) under 0.05.

Data ScienceHosted by Vera
Sign in free to start

What you are building

Develop a context-specific GWAS interaction testing workflow using Python and PLINK to prioritize gestational phenotype loci.

How work is evaluated

Evaluation

Evaluates interaction SNP discovery precision and FDR control accuracy on gestational GWAS datasets.

Datasets

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

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

fdr_threshold_check

Ensure significant SNPs maintain FDR q-value < 0.05

Binary check

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

Dimension 2

fdr_rate

Empirical false discovery rate on control loci • target: 0.04 • range: 0-0.1

Binary check

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

Learning goals

  • Perform genotype-environment interaction (GxE) statistical tests on gestational cohort data

  • Execute automated PLINK 2.0 command-line workflows from Python wrappers

  • Apply Benjamini-Hochberg FDR correction across millions of SNP association p-values

Resources

Dataset notes

Gestational phenotype GWAS dataset containing 10,000 samples across 500,000 imputed SNPs.

Challenge setup

Evaluates interaction SNP discovery precision and FDR control accuracy on gestational GWAS datasets.

Challenge input

JSON object with snp_id, gestational_week, and beta_val

PLINK

Standard C++ toolkit for whole genome association analysis.

Evaluated output

JSON object with interaction_p_value float and fdr_q_value float

Evaluation checks
  • Ensure significant SNPs maintain FDR q-value < 0.05
  • Empirical false discovery rate on control loci • target: 0.04 • range: 0-0.1
Configured evaluation evidence
  • Benchmark: GWASBench-Genetics
  • Fdr Rate target: 4%
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

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

View technical recipe

Configured tools

Action Space
  • Tempo Labs · Required
  • LatticeFlow AI · Optional
  • Nvidia · Optional

Evaluation contract

  • fdr_threshold_check · Weight 1
  • fdr_rate · Weight 1

Metrics

  • fdr_rate · Target 0.04

Benchmarks

  • GWASBench-Genetics
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with snp_id, gestational_week, and beta_val

    Output: JSON object with interaction_p_value float and fdr_q_value float

    Execution harness: Python

Evaluation tools

  • PLINK · Genomics GWAS Tool

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Gestational Phenotype Context-Specific GWAS Triage Engine with PLINK and Python