Predicting tumor response to drugs based on gene-expression biomarkers of sensitivity learned from cancer cell lines

Li, Yuanyuan; Umbach, David M.; Krahn, J.M.; Shats, Igor; Li, Xiaoling; Li, Leping

doi:10.1186/s12864-021-07581-7

Cited by 43 publications

(36 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relationship of GLNM regulator expression and drug sensitivity might provide an important theoretical basis for developing novel cancer treatments. Additionally, these findings provide a rationale for combination therapies to reverse resistance to certain drugs [ 49 ].…”

Section: Discussionmentioning

confidence: 99%

Glutamine Metabolism Regulators Associated with Cancer Development and the Tumor Microenvironment: A Pan-Cancer Multi-Omics Analysis

Zou

et al. 2021

Genes

View full text Add to dashboard Cite

Background: In recent years, metabolic reprogramming has been identified as a hallmark of cancer. Accumulating evidence suggests that glutamine metabolism plays a crucial role in oncogenesis and the tumor microenvironment. In this study, we aimed to perform a systematic and comprehensive analysis of six key metabolic node genes involved in the dynamic regulation of glutamine metabolism (referred to as GLNM regulators) across 33 types of cancer. Methods: We analyzed the gene expression, epigenetic regulation, and genomic alterations of six key GLNM regulators, including SLC1A5, SLC7A5, SLC3A2, SLC7A11, GLS, and GLS2, in pan-cancer using several open-source platforms and databases. Additionally, we investigated the impacts of these gene expression changes on clinical outcomes, drug sensitivity, and the tumor microenvironment. We also attempted to investigate the upstream microRNA–mRNA molecular networks and the downstream signaling pathways involved in order to uncover the potential molecular mechanisms behind metabolic reprogramming. Results: We found that the expression levels of GLNM regulators varied across cancer types and were related to several genomic and immunological characteristics. While the immune scores were generally lower in the tumors with higher gene expression, the types of immune cell infiltration showed significantly different correlations among cancer types, dividing them into two clusters. Furthermore, we showed that elevated GLNM regulators expression was associated with poor overall survival in the majority of cancer types. Lastly, the expression of GLNM regulators was significantly associated with PD-L1 expression and drug sensitivity. Conclusions: The elevated expression of GLNM regulators was associated with poorer cancer prognoses and a cold tumor microenvironment, providing novel insights into cancer treatment and possibly offering alternative options for the treatment of clinically refractory cancers.

show abstract

Section: Discussionmentioning

confidence: 99%

Glutamine Metabolism Regulators Associated with Cancer Development and the Tumor Microenvironment: A Pan-Cancer Multi-Omics Analysis

Zou

et al. 2021

Genes

View full text Add to dashboard Cite

show abstract

“…Taxane and anthracycline-based neoadjuvant chemotherapy is widely used in clinical practice in breast cancer [24], the heterogeneity of molecular features of different subtypes have been explored, which leads to distinct survival outcomes [25,26]. How to predict the long-term outcome of patients remains to be a problem.…”

Section: Discussionmentioning

confidence: 99%

The Target E2F Family Gene PTTG1 for Prediction of Distant Relapse-Free Survival in Breast Cancer Patients Receiving Taxane and Anthracycline-Based NACT

Zheng

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: The breast cancer is the most commonly diagnosed cancer in recent years. The use of neoadjuvant chemotherapy (NACT) makes a significant contribution to chemotherapy in breast cancer. We aimed to develop the novel model as a predictor of distant relapse-free survival (DRFS) in breast cancer patients receiving taxane and anthracycline-based NACT.Methods: We collected the mRNA expression datasets of patients from GSE25055 and GSE25065 in Gene Expression Omnibus (GEO). Univariate and Multivariate Cox Regression Analyses were conducted to achieve the prognostic genes that associated with DRFS. Moreover, the E2F target genes were obtained from GSEA. We obtained the intersection genes between the prognostic genes and E2F target genes, then validated in GSE32603 dataset. And we established a nomogram model based on PTTG1 expression level and several clinical characteristics.Results: There were 95 genes confirmed to be associated with DRFS both in GSE25055 and GSE25065. And PTTG1 was validated as a gene related to DRFS and associated with E2F target hallmark using GSEA analysis and chosen as our target gene. The AUC of PTTG1 model was 0.682 indicating a relatively poor prediction performance. Then a novel nomogram was conducted, the receiver operating characteristic (AUC=0.849), C-index (0.805) and calibration plots were applied to assess the effect of this model.Conclusion: Our study found that the E2F target genes, such as the PTTG1 may serve as a potential biomarker in breast cancer, and provided superior estimation of DRFS, which can guide the clinical practice in NACT of breast cancer.

show abstract

“…Li et al. [ 64 ] employed KNN regression for DRP, in which the sensitivity of a new sample is modelled as the average of the observed sensitivity values of its KNNs. Nearest neighbour methods tend to be problematic in the inadvertent, and typically unknown, presence of many irrelevant data features, and they are computationally intensive.…”

Section: Drp Modelsmentioning

confidence: 99%

An overview of machine learning methods for monotherapy drug response prediction

Firoozbakht

Yousefi

Schwikowski

2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

For an increasing number of preclinical samples, both detailed molecular profiles and their responses to various drugs are becoming available. Efforts to understand, and predict, drug responses in a data-driven manner have led to a proliferation of machine learning (ML) methods, with the longer term ambition of predicting clinical drug responses. Here, we provide a uniquely wide and deep systematic review of the rapidly evolving literature on monotherapy drug response prediction, with a systematic characterization and classification that comprises more than 70 ML methods in 13 subclasses, their input and output data types, modes of evaluation, and code and software availability. ML experts are provided with a fundamental understanding of the biological problem, and how ML methods are configured for it. Biologists and biomedical researchers are introduced to the basic principles of applicable ML methods, and their application to the problem of drug response prediction. We also provide systematic overviews of commonly used data sources used for training and evaluation methods.

show abstract

Predicting tumor response to drugs based on gene-expression biomarkers of sensitivity learned from cancer cell lines

Cited by 43 publications

References 66 publications

Glutamine Metabolism Regulators Associated with Cancer Development and the Tumor Microenvironment: A Pan-Cancer Multi-Omics Analysis

Glutamine Metabolism Regulators Associated with Cancer Development and the Tumor Microenvironment: A Pan-Cancer Multi-Omics Analysis

The Target E2F Family Gene PTTG1 for Prediction of Distant Relapse-Free Survival in Breast Cancer Patients Receiving Taxane and Anthracycline-Based NACT

An overview of machine learning methods for monotherapy drug response prediction

Contact Info

Product

Resources

About