ML Model Identifies Cancer Type-Specific Driver Mutations

According to Statistics Korea, cancer is the top cause of death in 2021, accounting for 26.5 percent of all deaths in Korea. Most cancer patients miss the golden window for treatment since symptoms only develop after the cancer progresses. WHO reports that more than 30 percent of patients can be in complete remission if cancer is detected and treated early. For early cancer diagnosis, it is necessary to predict the driver mutations in tissues and identify whether or not they are cancer-causing.

Recently, a POSTECH research team at the Department of Life Sciences led by Sanguk Kim, PhD, professor, Donghyo Kim, PhD, and Doyeon Ha, PhD candidate, developed a machine learning model that can accurately predict whether tissue-specific mutations in patients’ genes could cause cancer. The findings from the study were published in Briefings in Bioinformatics.

Identifying the cancer type-specific mutations (driver mutations) is pivotal to shedding light on the distinct pathological mechanisms across various tumors and providing each patient with opportunities for treatment. The research team devised a novel feature based on sequence coevolution analysis to identify driver mutations and constructed a machine learning (ML) model with state-of-the-art performance. The team's ML framework outperformed current leading methods of detection as it collected data from 28,000 tumor samples across 66 cancer types.

How does the ML model work?

The researchers developed an ML model that predicts the oncogenicity of driver mutations, using protein sequencing. The model has better accuracy and sensitivity compared to preexisting models. Also, the team successfully identified protein residues or mutations that may cause specific cancers by devising a novel feature based on sequence coevolution analysis for machine learning.

The cancer mutations in the study have been confirmed to play a role in shape-specific oncogenesis by mediating networks of tissue-specific protein interactions. These results show promise to lead the early detection diagnostic technologies and the effective prevention and treatment of cancer.

 “This technology can identify novel oncogenic driver mutations—that were previously undetectable—to help design distinct strategies for cancer diagnosis and treatment that are different from conventional methods,” said Sanguk Kim.

This study was conducted with the support from the POSTECH Medical Device Innovation Center, the Graduate School of Artificial Intelligence, and the Mid-career Researcher Program of the National Research Foundation of Korea.

- This press release was originally published on the Pohang University of Science and Technology website