ساخت اکانت کاربری رایگان

مقالات پذیرفته شده کنگره

  • صفحه نخست
  • مقالات پذیرفته شده اولین کنگره بین المللی ژنتیک سرطان
بازنشر

  • Artificial Intelligence in Lung Cancer Genomics: A Brief Review

  • Idin Akbari,1 Elnaz Karbaschian,2,* Ghazal Saeedazari,3
    1. Department of Cell and Molecular Biology, Faculty of Biological Sciences, Tehran North Branch, Islamic Azad University, Tehran, Iran.
    2. Department of Animal Science, Faculty of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran
    3. Department of Cell and Molecular Biology, Faculty of Biological Sciences, Tehran North Branch, Islamic Azad University, Tehran, Iran.


  • Introduction: Lung cancer exhibits substantial molecular heterogeneity, leading to pronounced variability in disease progression, prognosis, and therapeutic outcomes. Although high-throughput technologies including next-generation sequencing (NGS), liquid biopsy, and multi-omics profiling generate extensive molecular datasets, extracting clinically actionable insights using conventional analytical pipelines remains challenging. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL) architectures, has emerged as a transformative paradigm for decoding high-dimensional genomic landscapes and uncovering underlying oncogenic patterns.
  • Methods: This brief review synthesizes recent literature and analytical frameworks regarding the application of AI methodologies in lung cancer genomics. Relevant studies focusing on machine learning, deep learning, and multi-modal data integration pipelines applied to genomic variants, longitudinal liquid biopsy data, and multi-omics datasets were reviewed and categorized according to their clinical and translational utility.
  • Results: AI-driven computational models have demonstrated substantial efficacy in variant identification and functional prioritization, driver mutation classification (such as actionable alterations in EGFR, KRAS, TP53, and MET), novel biomarker discovery, treatment response forecasting, and deciphering mechanisms of therapeutic resistance. Moreover, AI algorithms facilitate the longitudinal tracking of circulating tumor DNA (ctDNA) dynamics and enable the synergistic integration of genomic, transcriptomic, and clinical phenotypes, markedly enhancing patient stratification and precision-oncology decision-making.
  • Conclusion: Artificial intelligence represents a powerful tool to bridge complex genomics with personalized lung cancer management. However, widespread clinical translation requires addressing critical bottlenecks, including high data heterogeneity, limited external validation across diverse cohorts, model interpretability (“black-box” nature), algorithmic bias, and cross-platform reproducibility. Addressing these translational challenges will be essential for integrating AI-assisted genomic frameworks into routine clinical oncology.
  • Keywords: Biomarker discovery; Circulating tumor DNA; Deep learning; Liquid biopsy; Machine learning

به خانواده بزرگ کنسر ژنتیکس و ژنومیکس سرطان بپیوندید!

ایجاد حساب کاربری رایگان