Related Experiment Video
Updated: Jun 17, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Discovering predisposing genes for hereditary breast cancer using deep learning.
Gal Passi1, Sari Lieberman2,3,4, Fouad Zahdeh2,3
1The Rachel and Selim Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem 9190401, Israel.
Researchers identified 80 candidate genes linked to hereditary breast cancer (BC) in Middle Eastern families. The study highlights the crucial role of peroxisomal and mitochondrial pathways in BC predisposition and survival.
Area of Science:
- Genetics
- Oncology
- Bioinformatics
Background:
- Breast cancer (BC) is a leading malignancy in Western women, with 10% of cases linked to germline variants.
- The genetic underpinnings of most familial BC cases remain elusive, posing challenges in identifying predisposing genes.
- Rare missense variants, low penetrance, and complex mechanisms complicate the discovery of familial BC genes.
Purpose of the Study:
- To analyze rare missense variants in 12 Middle Eastern families with high BC incidence.
- To identify novel genes contributing to familial breast cancer predisposition.
- To investigate the role of protein-level variant analysis in understanding BC genetics.
Main Methods:
- Developed a high-throughput variant analysis pipeline for family studies.
- Utilized machine learning models and 3D protein structural analysis for variant assessment.
- Analyzed 1218 rare missense variants shared among affected family members.
Main Results:
- Classified 80 genes as candidate pathogenic for breast cancer.
- Identified significant functional enrichment in peroxisomal and mitochondrial pathways.
- Observed segregation of these pathways across seven families and diverse ethnic groups.
Conclusions:
- Peroxisomal and mitochondrial pathways are implicated in germline BC predisposition.
- These pathways may also play a significant role in breast cancer survival.
- The study provides evidence for underappreciated roles of these cellular components in BC etiology.
Related Concept Videos
Cancers Originate from Somatic Mutations in a Single Cell
Adaptive Mechanisms in Cancer Cells
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...
Cancers Originate from Somatic Mutations in a Single Cell
Adaptive Mechanisms in Cancer Cells
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...

