Dataset Information

Network-based drug sensitivity prediction.

ABSTRACT:

Background

Drug sensitivity prediction and drug responsive biomarker selection on high-throughput genomic data is a critical step in drug discovery. Many computational methods have been developed to serve this purpose including several deep neural network models. However, the modular relations among genomic features have been largely ignored in these methods. To overcome this limitation, the role of the gene co-expression network on drug sensitivity prediction is investigated in this study.

Methods

In this paper, we first introduce a network-based method to identify representative features for drug response prediction by using the gene co-expression network. Then, two graph-based neural network models are proposed and both models integrate gene network information directly into neural network for outcome prediction. Next, we present a large-scale comparative study among the proposed network-based methods, canonical prediction algorithms (i.e., Elastic Net, Random Forest, Partial Least Squares Regression, and Support Vector Regression), and deep neural network models for drug sensitivity prediction. All the source code and processed datasets in this study are available at https://github.com/compbiolabucf/drug-sensitivity-prediction .

Results

In the comparison of different feature selection methods and prediction methods on a non-small cell lung cancer (NSCLC) cell line RNA-seq gene expression dataset with 50 different drug treatments, we found that (1) the network-based feature selection method improves the prediction performance compared to Pearson correlation coefficients; (2) Random Forest outperforms all the other canonical prediction algorithms and deep neural network models; (3) the proposed graph-based neural network models show better prediction performance compared to deep neural network model; (4) the prediction performance is drug dependent and it may relate to the drug's mechanism of action.

Conclusions

Network-based feature selection method and prediction models improve the performance of the drug response prediction. The relations between the genomic features are more robust and stable compared to the correlation between each individual genomic feature and the drug response in high dimension and low sample size genomic datasets.

SUBMITTER: Ahmed KT

PROVIDER: S-EPMC7771088 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Network-based drug sensitivity prediction.

Ahmed Khandakar Tanvir KT Park Sunho S Jiang Qibing Q Yeu Yunku Y Hwang TaeHyun T Zhang Wei W

BMC medical genomics 20201228 Suppl 11

<h4>Background</h4>Drug sensitivity prediction and drug responsive biomarker selection on high-throughput genomic data is a critical step in drug discovery. Many computational methods have been developed to serve this purpose including several deep neural network models. However, the modular relations among genomic features have been largely ignored in these methods. To overcome this limitation, the role of the gene co-expression network on drug sensitivity prediction is investigated in this stu ...[more]

PMID: 33371891

Similar Datasets

Project description:Tumorigenesis is a multi-step process, involving the acquisition of multiple oncogenic mutations that transform cells, resulting in systemic dysregulation that enables proliferation, invasion, and other cancer hallmarks. The goal of precision medicine is to identify therapeutically-actionable mutations from large-scale omic datasets. However, the multiplicity of oncogenes required for transformation, known as oncogenic collaboration, makes assigning effective treatments difficult. Motivated by this observation, we propose a new type of oncogenic collaboration where mutations in genes that interact with an oncogene may contribute to the oncogene's deleterious potential, a new genomic feature that we term "surrogate oncogenes." Surrogate oncogenes are representatives of these mutated subnetworks that interact with oncogenes. By mapping mutations to a protein-protein interaction network, we determine the significance of the observed distribution using permutation-based methods. For a panel of 38 breast cancer cell lines, we identified a significant number of surrogate oncogenes in known oncogenes such as BRCA1 and ESR1, lending credence to this approach. In addition, using Random Forest Classifiers, we show that these significant surrogate oncogenes predict drug sensitivity for 74 drugs in the breast cancer cell lines with a mean error rate of 30.9%. Additionally, we show that surrogate oncogenes are predictive of survival in patients. The surrogate oncogene framework incorporates unique or rare mutations from a single sample, and therefore has the potential to integrate patient-unique mutations into drug sensitivity predictions, suggesting a new direction in precision medicine and drug development. Additionally, we show the prevalence of significant surrogate oncogenes in multiple cancers from The Cancer Genome Atlas, suggesting that surrogate oncogenes may be a useful genomic feature for guiding pancancer analyses and assigning therapies across many tissue types.

Project description:As a common malignant tumor disease, thyroid cancer lacks effective preventive and therapeutic drugs. Thus, it is crucial to provide an effective drug selection method for thyroid cancer patients. The connectivity map (CMAP) project provides an experimental validated strategy to repurpose and optimize cancer drugs, the rationale behind which is to select drugs to reverse the gene expression variations induced by cancer. However, it has a few limitations. Firstly, CMAP was performed on cell lines, which are usually different from human tissues. Secondly, only gene expression information was considered, while the information about gene regulations and modules/pathways was more or less ignored. In this study, we first measured comprehensively the perturbations of thyroid cancer on a patient including variations at gene expression level, gene co-expression level and gene module level. After that, we provided a drug selection pipeline to reverse the perturbations based on drug signatures derived from tissue studies. We applied the analyses pipeline to the cancer genome atlas (TCGA) thyroid cancer data consisting of 56 normal and 500 cancer samples. As a result, we obtained 812 up-regulated and 213 down-regulated genes, whose functions are significantly enriched in extracellular matrix and receptor localization to synapses. In addition, a total of 33,778 significant differentiated co-expressed gene pairs were found, which form a larger module associated with impaired immune function and low immunity. Finally, we predicted drugs and gene perturbations that could reverse the gene expression and co-expression changes incurred by the development of thyroid cancer through the Fisher's exact test. Top predicted drugs included validated drugs like baclofen, nevirapine, glucocorticoid, formaldehyde and so on. Combining our analyses with literature mining, we inferred that the regulation of thyroid hormone secretion might be closely related to the inhibition of the proliferation of thyroid cancer cells.

Dataset Information

Network-based drug sensitivity prediction.

Background

Methods

Results

Conclusions

Publications

Network-based drug sensitivity prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets