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.
What you are building
Build an XGBoost genomic binding prediction model utilizing Biopython motif feature extraction.
How work is evaluated
Evaluates cohesin genomic binding prediction performance (F1-score) on test ChIP-seq loci.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
binding_probability_range_check
Verifies probability is between 0.0 and 1.0.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
f1_score
F1 classification score on held-out chromosomal test set. • target: 0.88 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
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
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
- Verifies probability is between 0.0 and 1.0.
- F1 classification score on held-out chromosomal test set. • target: 0.88 • range: 0-1
- Benchmark: ChIP-Bench
- F1 Score target: 0.88
- 1 public reference case
- 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
- Noma Security · Required
- Windsurf · Optional
- 01.AI · Optional
- 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
- 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.