SuReCAN: a suite of user-friendly Galaxy machine learning workflows to predict survival and treatment response of cancer patients
Bibliographic record
Abstract
Abstract Cancer is one of the leading lethal causes worldwide, with enormous impact on healthcare, economy and society. One of the main challenges of clinical treatment planning is that patients usually have diverse clinical outcomes given the same diagnosis and treatments. To enable personalized cancer therapeutic planning, (bio)medical data analyses using machine learning (ML) models are introduced to efficiently extract informative biological patterns from the massive volume of complex biological data, aiding in cancer patients’ stratifications. For biomedical researchers without computational biology background, the gap between clinical practice and computational approaches is prominent and hinders the usage of machine learning in medical research. To fill this gap, we created a collection of ML workflows on the Galaxy platform named SUrvival and REsponse prediction for CANcer patients (SuReCAN) for clinicians and biologists to build and deploy predictive ML classifiers. Being freely available and accessible, SuReCAN automates the data analysis process and enables the clinicians and researchers to perform a broad range of predictive tasks. It contains a toolkit of three ML modules with various existing and newly implemented methods on Galaxy: A data normalization module, a feature selection module, and an ML classifier module. We exhibited the utility of SuReCAN with a few real-world datasets to identify pancreatic ductal adenocarcinoma (PDAC) patients’ survival-correlated subtypes and to predict drug response outcomes based on various omics data from patient tumor samples. As a result, all workflows achieved a median accuracy of over 0.8 in PDAC survival-correlated subtype classification. In particular, the workflow combining the feature selection method “SVM-based RFECV ” and the Support Vector Machine classifier consistently outperformed the other workflows, while all classifiers have shown their superiority on different omics data. Importantly, SuReCAN is not only applicable for the clinical prediction tasks shown in the test cases but also suitable for new classifier development and deployment with clinical observations provided by the users. Providing a collection of user-friendly ML workflows, SuReCAN stratifies patients based on their biomedical profiling in a data-driven way and assists biomedical researchers with clinical decision-making and scientific discoveries.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.006 |
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".