Reproducible Data Analysis Pipelines for Precision Medicine
Bibliographic record
Abstract
Abstract Precision medicine brings the promise of more precise diagnosis and individualized therapeutic strategies from analyzing a cancer’s genomic signature. Technologies such as high-throughput sequencing enable cheaper data collection at higher speed, but rely on modern data analysis platforms to extract knowledge from these high dimensional datasets. Since this is a rapidly advancing field, new diagnoses and therapies often require tailoring of the analysis. These pipelines are therefore developed iteratively, continuously modifying analysis parameters before arriving at the final results. To enable reproducible results it is important to record all these modifications and decisions made during the analysis process. We built a system, walrus , to support reproducible analyses for iteratively developed analysis pipelines. The approach is based on our experiences developing and using deep analysis pipelines to provide insights and recommendations for treatment in an actual breast cancer case. We designed walrus for the single servers or small compute clusters typically available for novel treatments in the clinical setting. walrus leverages software containers to provide reproducible execution environments, and integrates with modern version control systems to capture provenance of data and pipeline parameters. We have used walrus to analyze a patient’s primary tumor and adjacent normal tissue, including subsequent metastatic lesions. Although we have used walrus for specialized analyses of whole-exome sequencing datasets, it is a general data analysis tool that can be applied in a variety of scientific disciplines. We have open sourced walrus along with example data analysis pipelines at github.com/uit-bdps/walrus.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.054 | 0.113 |
| Meta-epidemiology (narrow) | 0.003 | 0.003 |
| Meta-epidemiology (broad) | 0.002 | 0.005 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.009 | 0.008 |
| Open science | 0.006 | 0.010 |
| Research integrity | 0.002 | 0.007 |
| Insufficient payload (model declined to judge) | 0.010 | 0.010 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".