Skip to main content
Loading navigation
Back to challenges

Epigenetic Demethylase Targeting Workflow with Mastra AI

Intrinsically disordered regions regulate chromatin target specificity for RNA and histone demethylases in eukaryotic genomes. Build a Mastra AI TypeScript workflow to analyze protein IDR sequences, simulate genomic binding dynamics, and return quantitative target restraint scores.

Data ScienceHosted by Vera
Sign in free to start

What you are building

Build an integrated Mastra AI agent workflow in TypeScript to model intrinsically disordered region (IDR) constraints on genomic targeting.

How work is evaluated

Evaluation

Evaluates Mastra AI workflow step execution, IDR disorder prediction accuracy, and target restraint score outputs.

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

Restraint Index Range Check

Ensures restraint index is between 0.0 and 1.0.

Binary check

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

Dimension 2

Disorder Correlation

Correlation with biological ground-truth IDR binding restraint experimental metrics. • target: 0.88 • range: 0-1

Binary check

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

Learning goals

  • Construct TypeScript agent workflows using Mastra AI framework.

  • Implement protein sequence analysis routines for intrinsically disordered regions (IDRs).

  • Calculate genomic targeting restraint indices for demethylase enzymes.

  • Output structured genomic coordinate restraint predictions.

Resources

Dataset notes

Demethylase sequence dataset containing IUPred disorder scores, IDR boundaries, and experimental genomic targeting specificity measurements.

Challenge setup

Evaluates Mastra AI workflow step execution, IDR disorder prediction accuracy, and target restraint score outputs.

Challenge input

JSON containing protein_id, amino_acid_sequence, and enzyme_family

Mastra AI

Provides robust TypeScript workflow control loops for bioinformatic analysis.

Evaluated output

JSON containing idr_fraction, calculated_restraint_index, is_genomic_targeting_restrained

Evaluation checks
  • Ensures restraint index is between 0.0 and 1.0.
  • Correlation with biological ground-truth IDR binding restraint experimental metrics. • target: 0.88 • range...
Configured evaluation evidence
  • Benchmark: StructuralBio-Bench
  • Disorder Correlation target: 0.88
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • Mastra AI · Required
  • Jimdo · Optional
  • Lingo · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • Restraint Index Range Check · Weight 1
  • Disorder Correlation · Weight 1

Metrics

  • Disorder Correlation · Target 0.88

Benchmarks

  • StructuralBio-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing protein_id, amino_acid_sequence, and enzyme_family

    Output: JSON containing idr_fraction, calculated_restraint_index, is_genomic_targeting_restrained

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent & Workflow Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Epigenetic Demethylase Targeting Workflow with Mastra AI