Scholarlink

Background <p>Machine learning algorithms identify patterns that would otherwise be difficult to observe in high-dimensional molecular and clinical data. For this reason, machine learning has the potential to have a profound impact on clinical decision-making and drug target discovery. However, there are technical challenges in adapting these tools for clinical use, including clinical feature engineering, model selection, and defining optimal strategies for model training. For cancer care, RNA sequencing of patient tumor biopsies has already proven to be a powerful molecular assay to characterize tumor-intrinsic and -extrinsic phenotypes influencing therapeutic response, but an optimal solution for using gene expression data to predict outcome is yet to be established.</p> Results <p>We developed the tauX machine learning framework to refine gene expression features and improve the predictive performance of RNA-sequencing data. The tauX framework uses aggregated ratios of positively and negatively associated predictive genes to simplify the prediction task. We showed a significant improvement in predictive performance using a large database of synthetic gene expression profiles. We also showed how the tauX framework can be used to elucidate the mechanisms of response and resistance to checkpoint blockade therapy using data from the Stand Up to Cancer (SU2C) Lung Response Cohort and The Cancer Genome Atlas (TCGA). The tauX framework achieved superior predictive performance (~ 30% improvement) compared to models built upon established feature engineering strategies or widely used cancer gene expression signatures. The tauX framework is available as a freely deployable docker container (<a href="https://hub.docker.com/r/pfeiljx/taux">https://hub.docker.com/r/pfeiljx/taux</a>).</p> Conclusion <p>By simultaneously modeling gene expression signatures associated with response and resistance to drug therapy, the tauX approach revealed expression patterns that can be used to improve genomic medicine strategies in several ways. Significantly, tauX allows the paired response and resistance signatures to be used to design new companion diagnostics. Application of the tauX framework can also be used to identify drug targets by indicating genes that consistently associate with resistance. Improved performance in drug response prediction using the tauX approach can support data-driven decision-making in the precision medicine space that can lead to improved clinical outcomes for patients.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Pairwise ratio transformation of gene expression data leads to improved checkpoint response prediction in lung cancer patients

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月12日

查看全文
  • Jacob Pfeil,
  • Liqian Ma,
  • Hin Ching Lo,
  • Tolga Turan,
  • R. Tyler McLaughlin,
  • Xu Shi,
  • Severiano Villarruel,
  • Stephen Wilson,
  • Xi Zhao,
  • Josue Samayoa,
  • Kyle Halliwill

摘要

Background

Machine learning algorithms identify patterns that would otherwise be difficult to observe in high-dimensional molecular and clinical data. For this reason, machine learning has the potential to have a profound impact on clinical decision-making and drug target discovery. However, there are technical challenges in adapting these tools for clinical use, including clinical feature engineering, model selection, and defining optimal strategies for model training. For cancer care, RNA sequencing of patient tumor biopsies has already proven to be a powerful molecular assay to characterize tumor-intrinsic and -extrinsic phenotypes influencing therapeutic response, but an optimal solution for using gene expression data to predict outcome is yet to be established.

Results

We developed the tauX machine learning framework to refine gene expression features and improve the predictive performance of RNA-sequencing data. The tauX framework uses aggregated ratios of positively and negatively associated predictive genes to simplify the prediction task. We showed a significant improvement in predictive performance using a large database of synthetic gene expression profiles. We also showed how the tauX framework can be used to elucidate the mechanisms of response and resistance to checkpoint blockade therapy using data from the Stand Up to Cancer (SU2C) Lung Response Cohort and The Cancer Genome Atlas (TCGA). The tauX framework achieved superior predictive performance (~ 30% improvement) compared to models built upon established feature engineering strategies or widely used cancer gene expression signatures. The tauX framework is available as a freely deployable docker container (https://hub.docker.com/r/pfeiljx/taux).

Conclusion

By simultaneously modeling gene expression signatures associated with response and resistance to drug therapy, the tauX approach revealed expression patterns that can be used to improve genomic medicine strategies in several ways. Significantly, tauX allows the paired response and resistance signatures to be used to design new companion diagnostics. Application of the tauX framework can also be used to identify drug targets by indicating genes that consistently associate with resistance. Improved performance in drug response prediction using the tauX approach can support data-driven decision-making in the precision medicine space that can lead to improved clinical outcomes for patients.