Summary of Positive-unlabelled Learning For Identifying New Candidate Dietary Restriction-related Genes Among Ageing-related Genes, by Jorge Paz-ruza et al.
Positive-Unlabelled Learning for identifying new candidate Dietary Restriction-related genes among Ageing-related genes
by Jorge Paz-Ruza, Alex A. Freitas, Amparo Alonso-Betanzos, Bertha Guijarro-Berdiñas
First submitted to arxiv on: 14 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A machine learning-based approach is proposed to identify dietary restriction (DR)-related genes among ageing-related genes. The existing ML methods naively label genes without known DR relation as negative examples, which hinders the reliability of the results. This work introduces a novel gene prioritisation method using the Positive-Unlabelled (PU) Learning paradigm, which first selects reliable negative examples and then trains a classifier to differentiate DR-related and non-DR-related genes. The proposed method outperforms existing state-of-the-art approaches in three predictive accuracy metrics with up to 40% lower computational cost. Additionally, four new promising DR-related genes (PRKAB1, PRKAB2, IRS2, PRKAG1) are identified, which have evidence supporting their potential DR-related role. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning is used to find genes related to dietary restriction, a popular way to slow down aging. Right now, scientists use machine learning to look at genes and see if they’re related to dietary restriction or not. But there’s a problem – the existing methods don’t work well because they incorrectly assume that genes without known relationships to dietary restriction aren’t actually related. This new approach solves this problem by first finding reliable examples of genes that are definitely not related to dietary restriction, and then using these examples along with genes we already know are related or not related to train a better model. This improved model can help scientists find new genes that might be related to dietary restriction, which could lead to new discoveries and treatments. |
Keywords
» Artificial intelligence » Machine learning
