Skip to main content
Back to challenges
Challenge

Build a Pioneer Factor Cohesin Binding Predictor with Biopython and XGBoost

Cohesin positioning across the genome is directed by pioneer transcription factor binding motifs. Build a sequence-based machine learning pipeline using Biopython and XGBoost to predict cohesin recruitment sites from genomic motif motifs with F1-score exceeding 0.88.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build an XGBoost genomic binding prediction model utilizing Biopython motif feature extraction.

Delivery guide

How work is evaluated

Evaluation

Evaluates cohesin genomic binding prediction performance (F1-score) on test ChIP-seq loci.

Datasets

Challenge datasets

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

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

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

binding_probability_range_check

Verifies probability 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

f1_score

F1 classification score on held-out chromosomal test set. • 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

What you should walk away with

  • Extract transcription factor position weight matrices (PWMs) using Biopython Bio.motifs.

  • Engineered k-mer sequence features and PWM match scores from ChIP-seq peak regions.

  • Train XGBoost classifiers to distinguish cohesin-bound pioneer factor loci from non-bound regions.

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of 2,000 genomic FASTA regions (500bp) labeled with cohesin ChIP-seq binding status.

Challenge setup

Evaluates cohesin genomic binding prediction performance (F1-score) on test ChIP-seq loci.

Challenge input

JSON containing genomic_coordinates and sequence_fasta

Biopython

Provides sequence parsing and motif matching tools.

XGBoost

Gradient boosting framework for tabular/k-mer classification.

Evaluated output

JSON object with is_cohesin_bound boolean and binding_probability

Evaluation checks
  • Verifies probability is between 0.0 and 1.0.
  • F1 classification score on held-out chromosomal test set. • target: 0.88 • range: 0-1
Configured evaluation evidence
  • Benchmark: ChIP-Bench
  • F1 Score target: 0.88
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Noma Security · Required
  • Windsurf · Optional
  • 01.AI · Optional
Observation
  • Windsurf · Optional

Evaluation contract

  • binding_probability_range_check · Weight 1
  • f1_score · Weight 1

Metrics

  • f1_score · Target 0.88

Benchmarks

  • ChIP-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing genomic_coordinates and sequence_fasta

    Output: JSON object with is_cohesin_bound boolean and binding_probability

    Execution harness: Python

Evaluation tools

  • Biopython · bioinformatics_library
  • XGBoost · machine_learning

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Pioneer Factor Cohesin Binding Predictor with Biopython and XGBoost