Pharma Focus Asia
Klöckner Pentaplast - Pentapharm® alfoil® films

A New Machine Learning Method for Cancer Mutation Analysis

Mahnaz Habibi, Golnaz Taheri

Abstract
It is complicated to identify cancer-causing mutations. The recurrence of a mutation in patients remains one of the most reliable features of mutation driver status. However, some mutations are more likely to happen than others for various reasons. Different sequencing analysis has revealed that cancer driver genes operate across complex pathways and networks, with mutations often arising in a mutually exclusive pattern.

Introduction
The driving forces behind cancer are gene, nucleotide, and cellular structure changes. Somatic cells can acquire mutations one or two orders of magnitude more quickly than germline cells, making them more susceptible to different types of cancer. The vast majority of these mutations, called passenger, have little effect on cell proliferation compared to a few driver mutations that give cells a selective advantage.

Materials and Methods:
In this section, we present a new two-step method for identifying driver genes and modules in different types of cancer. In the first step, we proposed an unsupervised machine learning method to recognize a set of candidate driver mutated genes associated with different types of cancer. In this step, we used the information of different patients (cases) with various types of cancer and their associated mutated genes to create a weighted network of mutated genes.

Discussion
New sequencing technologies and improving genomics data help us identify cancer-related genes and modules in various cancers. Most previous studies focus on using statistical methods to identify high-frequency mutation genes. Finding these mutation genes is important in determining the cancer progression mechanism. The critical point is that some critical genes do not have high mutation frequencies and can not be identified depending on the number of mutations and statistical techniques.

Citation: Habibi M, Taheri G (2022) A new machine learning method for cancer mutation analysis. PLoS Comput Biol 18(10): e1010332. https://doi.org/10.1371/journal.pcbi.1010332

Editor: Anna R. Panchenko, Queen’s University, CANADA

Received: June 28, 2022; Accepted: October 5, 2022; Published: October 17, 2022.

Copyright: © 2022 Habibi, Taheri. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All of our codes and data available at our github repository: https://github.com/MahnazHabibi/MutationAnalysis.

Funding: The author(s) received no specific funding for this work.

Competing interests: The authors have declared that no competing interests exist.

magazine-slider-imageBIOVIA from Molecule to MedicineMFA + MMA 2024CPHI China || PMEC China 2024Asia Healthcare Week 2024Advance DoE WorkshopCPHI Korea 2024CHEMICAL INDONESIA 2024INALAB 2024 Thermo Scientific - DynaDrive and DynaSpinRehab Expo 2024ISPE Singapore Affiliate Conference & Exhibition 20242024 PDA Cell and Gene Pharmaceutical Products Conference 2024 PDA Aseptic Manufacturing Excellence Conference2024 PDA Aseptic Processing of Biopharmaceuticals Conference3rd World ADC Asia 2024LogiPharma Asia 2024