2023 World Conference on Lung Cancer (Posters)-EP02.02. Machine Learning for Multi-Omics Data Identifies Vulnerabilities in a Subset of Squamous Cell Lung Cancers

EP02.02. Machine Learning for Multi-Omics Data Identifies Vulnerabilities in a Subset of Squamous Cell Lung Cancers - PDF(Slides)

Back to course

Pdf Summary

A study conducted at the University of Cambridge has used machine learning to analyze multi-omics data to identify vulnerabilities in a subset of squamous cell lung cancers (LUSC). The study found that while most targetable alterations are not present in LUSC, many patients exhibit SOX2 gene amplification as a driver of the disease. <br /><br />The researchers generated a SOX2-associated protein network using a computational pipeline and identified potential drug target candidates in SOX2-driven LUSC. These candidates, including the PI3K/AKT/mTOR pathway, KLF5, and FOXM1, were validated through target inhibition and gene knockout studies. <br /><br />Based on these findings, the study suggests that SOX2 is a driver of LUSC and that multi-omics data has the potential to identify new drug target candidates for the disease. The PI3K/AKT/mTOR pathway, KLF5, and FOXM1 are highlighted as potential targetable vulnerabilities in SOX2-driven LUSC. <br /><br />The study also recommends that clinical trials for LUSC should consider the SOX2 status of patients in order to identify subgroups who might benefit from targeted therapies. Overall, this research provides insights into the molecular mechanisms underlying LUSC and identifies potential therapeutic targets for this subset of lung cancers.

Asset Subtitle

Daniel Kottmann

Meta Tag

Speaker Daniel Kottmann

Topic Tumor Biology: Preclinical Biology - Omics Approaches

Keywords

University of Cambridge

machine learning

multi-omics data

squamous cell lung cancers

LUSC

SOX2 gene amplification

SOX2-associated protein network

PI3K/AKT/mTOR pathway

KLF5

FOXM1