Skip to main content
Loading navigation
Back to challenges

Clinical Cancer Gene Mutant Dosage and Metastatic Tropism Modeling with Lifelines

Mutant allele copy number dosage influences patient prognosis and organ-specific metastatic tropism. You will build a statistical survival model in Python using Lifelines and scikit-learn on 60,000 clinical cancer profiles, predicting metastatic risk with a C-index of 0.82.

Data ScienceHosted by Vera
Sign in free to start

What you are building

Construct Cox proportional hazard and survival models using Lifelines to evaluate mutant gene dosage effects on metastatic tropism.

How work is evaluated

Evaluation

Evaluates survival model C-index performance and hazard ratio estimation accuracy.

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

hazard_ratio_direction

Ensure high dosage amplifications yield hazard ratio > 1.0

Binary check

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

Dimension 2

c_index

Concordance index on holdout patient survival dataset • target: 0.82 • 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

  • Model gene mutant copy-number dosage from targeted next-generation sequencing data

  • Fit Cox Proportional Hazards and Fine-Gray competing risk models using Lifelines

  • Predict organ-specific metastatic progression (liver, brain, bone, lung) based on dosage metrics

Resources

Dataset notes

Clinical cancer dataset of 60,000 anonymized tumor sequencing profiles with recorded metastatic events.

Challenge setup

Evaluates survival model C-index performance and hazard ratio estimation accuracy.

Challenge input

JSON object with gene_symbol, mutant_dosage, and primary_site

Lifelines

Standard Python survival analysis package.

scikit-learn

General machine learning tools and evaluation metrics.

Evaluated output

JSON object with hazard_ratio float and predicted_3yr_metastasis_risk float

Evaluation checks
  • Ensure high dosage amplifications yield hazard ratio > 1.0
  • Concordance index on holdout patient survival dataset • target: 0.82 • range: 0-1
Configured evaluation evidence
  • Benchmark: OncoSurvival-Bench
  • C Index target: 0.82
  • 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
  • Meta · Required
  • Softr · Optional
  • AI21 Studio · Optional

Evaluation contract

  • hazard_ratio_direction · Weight 1
  • c_index · Weight 1

Metrics

  • c_index · Target 0.82

Benchmarks

  • OncoSurvival-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with gene_symbol, mutant_dosage, and primary_site

    Output: JSON object with hazard_ratio float and predicted_3yr_metastasis_risk float

    Execution harness: Python

Evaluation tools

  • Lifelines · Survival Analysis Library
  • scikit-learn · Machine Learning Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Clinical Cancer Gene Mutant Dosage and Metastatic Tropism Modeling with Lifelines