A Gene-disease-based Machine Learning Approach to Identify Prostate Cancer Biomarkers
Bibliographic record
Abstract
Identifying biomarkers that can be used to classify certain disease stages, or identify when a disease becomes more aggressive is one of the most important applications of machine learning. Traditional biomarker identification approaches, typically, use machine learning techniques to identify a number of genes and macromolecules as biomarkers that can be used to diagnose specific diseases or states of diseases with very high accuracy, using molecular measurements such as mutations, gene expression, copy number variations, and others. However, Experts' opinions and knowledge is required to validate such findings. We propose a new machine learning model that incorporates a knowledge-based system used to integrate the findings of the DisGeNET database which is a framework that provides proven relationships among diseases and genes. The machine learning pipeline starts by reducing the number of features using a filter based feature selection method. The DisGeNET database is used to score each gene relating to the given cancer name. Then a wrapper-based feature-selection method picks the best set of genes with the highest classification accuracy. The method returned key genes from multiple data sets that classify with high accuracy while being biologically relevant, and no human intervention needed. Initial results provide a high area under the curve with a handful of genes that are already proven to be related to the relevant disease and state based on the latest published medical findings.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".