Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bblodfon/tcga-survmob

Benchmarking survival ML models using many multimodal TCGA datasets

https://github.com/bblodfon/tcga-survmob

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 3 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.1%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Benchmarking survival ML models using many multimodal TCGA datasets

Basic Info
  • Host: GitHub
  • Owner: bblodfon
  • License: mit
  • Language: R
  • Default Branch: main
  • Size: 235 MB
Statistics
  • Stars: 3
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created over 3 years ago · Last pushed about 3 years ago
Metadata Files
Readme License

README.md

tcga-survmob

DOI

Intro

This repository is a continuation of paad-survival-bench, which included the initial code and several investigations conducted in TCGA's PAAD cohort. In the present repository, we use the survmob R package along with many mlr3 packages to benchmark several survival ML models across two TCGA multimodal datasets (PAAD, BLCA) and analyze the output results using Bayesian methods.

Benchmarking Workflow

Each step from the above workflow corresponds to a separate script. These scripts can be accessed in the folders whose names match the abbreviated TCGA study names, e.g. PAAD and BLCA.

The order of script execution per cancer study is as follows:

  • download_data.R => Download omics and clinical data download, initial patient and omic filtering
  • preprocess.R => Convert datasets to mlr3 survival tasks, preprocess omics data
  • data_split.R => Split cohort to train and test sets
  • efs.R => Perform ensemble feature selection (per omic dataset)
  • task_subset.R => Subset mlr3 tasks to the most stable/robust features
  • benchmark.R => Perform the benchmark (AI model tuning and testing on all combinations of omics and clinical data)
  • bench_bayes.R => Fit Bayesian Linear Mixed-Effects (LME) models using the benchmarking results
  • bench_bayes_vis.R => Visualize model and omics rankings and other Bayesian posterior distribution differences
  • bench_boot_vis.R => Visualization of bootstrapped results on the test set cohort

Additional analyses

  • efs_analysis.R => Visualize the ensemble feature selection results per omic
  • efs_multimodal.R => Perform ensemble feature selection on a unified multi-modal dataset that combines all omics and the clinical data
  • benchmark_multimodal.R => Perform the benchmark (AI model tuning and testing on the unified multimodal dataset after feature selection)
  • efs_inv/msr_comp.R => Comparison of two metrics (RCLL vs C-index) for optimizing the ensemble feature selection algorithm

Notes

  • Open an issue if you want the full downloaded or processed datasets or any analysis result (R compressed objects) that due to size restrictions are not on this repository.
  • check_packages.R => versions of most important packages used (for some reproducibility).
    • survmob version used: v0.1.1
    • R library used for download and filtering/processing of the TCGA multi-omics was curatedTCGAData.

Owner

  • Name: John Zobolas
  • Login: bblodfon
  • Kind: user

GitHub Events

Total
Last Year

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 143
  • Total Committers: 1
  • Avg Commits per committer: 143.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
john b****n@g****m 143

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels