Identification of Pancreatic Cancer Driver Genes With a Novel Machine Learning Approach
ISEF · 2022 Computational Biology and Bioinformatics Second Award
Overview
With the lowest 5-year survival rate (9%) among all types of cancer, pancreatic cancer is considered one of the most lethal diseases in the world. Current conventional treatments often fail because there are no reliable genes to target in pancreatic cancer therapies and drugs. Hence, there is a crucial need for the discovery of new pancreatic cancer driver genes for the development of better treatments. This study develops a state-of-the-art machine learning workflow for identifying key driver genes for pancreatic cancer. Our workflow identifies several genes, including KRT17, S100A4, and PTGS2, which have high potential as targets for pancreatic cancer therapies and have been validated with over hundreds of publications in literature. Our workflow also identifies novel genes, including SSFA2 and NDUFA6, that have never been studied before while showing great potential as therapy targets. These new genes provide directions for further experimental studies for advancing pancreatic cancer treatments.
Awards (2)
- Second Award of $2,000 $2,000
- Second Award of $2,000 $2,000
Competition history
- ISEF 2022
Resources
Related projects
ISEF · 2026
Toward Precision Oncology: Integrating Clinical and Mutational Data to Predict Pancreatic Cancer Survival Using Machine Learning
ISEF · 2020
PanCan Diagnosed: Developing an Algorithm for the Accurate and Affordable Early Diagnosis of Pancreatic Cancer via Machine Learning and Bioinformatics
ISEF · 2017
A Multi-Omics Predictive Pipeline for the Discovery of Cancer Driver Genes
ISEF · 2020
PANCREAS.AI: Novel Deep Learning-based Screening Towards Precision Applications for Pancreatic Cancer
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair