Graph Convolutional Network for Drug Response Prediction Using Gene Expression Data

Genomic profiles of cancer patients such as gene expression have become a major source to predict responses to drugs in the era of personalized medicine. As large-scale drug screening data with cancer cell lines are available, a number of computational methods have been developed for drug response prediction. However, few methods incorporate both gene expression data and the biological network, which can harbor essential information about the underlying process of the drug response. We proposed an analysis framework called DrugGCN for prediction of Drug response using a Graph Convolutional Network (GCN). DrugGCN first generates a gene graph by combining a Protein-Protein Interaction (PPI) network and gene expression data with feature selection of drug-related genes, and the GCN model detects the local features such as subnetworks of genes that contribute to the drug response by localized filtering. We demonstrated the effectiveness of DrugGCN using biological data showing its high prediction accuracy among the competing methods.

Download Full-text

Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction

Nature Machine Intelligence ◽

10.1038/s42256-021-00408-w ◽

2021 ◽

Author(s):

Hossein Sharifi-Noghabi ◽

Parsa Alamzadeh Harjandi ◽

Olga Zolotareva ◽

Colin C. Collins ◽

Martin Ester

Keyword(s):

Gene Expression ◽

Gene Expression Data ◽

Drug Response ◽

Response Prediction ◽

Expression Data

Download Full-text

Velodrome: Out-of-Distribution Generalization from Labeled and Unlabeled Gene Expression Data for Drug Response Prediction

10.1101/2021.05.25.445658 ◽

2021 ◽

Author(s):

Hossein Sharifi-Noghabi ◽

Parsa Alamzadeh Harjandi ◽

Olga Zolotareva ◽

Colin C Collins ◽

Martin Ester

Keyword(s):

Gene Expression ◽

Transfer Learning ◽

Cell Lines ◽

Gene Expression Data ◽

Drug Response ◽

Response Prediction ◽

Fine Tuning ◽

Expression Data ◽

Target Domain ◽

Data Discrepancy

Data discrepancy between preclinical and clinical datasets poses a major challenge for accurate drug response prediction based on gene expression data. Different methods of transfer learning have been proposed to address this data discrepancy. These methods generally use cell lines as source domains and patients, patient-derived xenografts, or other cell lines as target domains. However, they assume that they have access to the target domain during training or fine-tuning and they can only take labeled source domains as input. The former is a strong assumption that is not satisfied during deployment of these models in the clinic. The latter means these methods rely on labeled source domains which are of limited size. To avoid this assumption, we formulate drug response prediction as an out-of-distribution generalization problem which does not assume that the target domain is accessible during training. Moreover, to exploit unlabeled source domain data, which tends to be much more plentiful than labeled data, we adopt a semi-supervised approach. We propose Velodrome, a semi-supervised method of out-of-distribution generalization that takes labeled and unlabeled data from different resources as input and makes generalizable predictions. Velodrome achieves this goal by introducing an objective function that combines a supervised loss for accurate prediction, an alignment loss for generalization, and a consistency loss to incorporate unlabeled samples. Our experimental results demonstrate that Velodrome outperforms state-of-the-art pharmacogenomics and transfer learning baselines on cell lines, patient-derived xenografts, and patients and therefore, may guide precision oncology more accurately.

Download Full-text

Clinical Drug Response Prediction by Using a Lq Penalized Network-Constrained Logistic Regression Method

Cellular Physiology and Biochemistry ◽

10.1159/000495826 ◽

2018 ◽

Vol 51 (5) ◽

pp. 2073-2084 ◽

Cited By ~ 5

Author(s):

Hai-Hui Huang ◽

Jing-Guo Dai ◽

Yong Liang

Keyword(s):

Gene Expression ◽

Logistic Regression ◽

Personalized Medicine ◽

Gene Expression Data ◽

Drug Response ◽

Prediction Models ◽

Response Prediction ◽

Expression Data

Background/Aims: One of the most important impacts of personalized medicine is the connection between patients’ genotypes and their drug responses. Despite a series of studies exploring this relationship, the predictive ability of such analyses still needs to be strengthened. Methods: Here we present the Lq penalized network-constrained logistic regression (Lq-NLR) method to meet this need, in which the predictors are integrated into the gene expression data and biological network knowledge and are combined with a more aggressive penalty function. Response prediction models for two cancer targeting drugs (erlotinib and sorafenib) were developed from gene expression data and IC50 values from a large panel of cancer cell lines by utilizing the proposed approach. Then the drug responders were tested with the baseline tumor gene expression data, yielding an in vivo drug sensitivity prediction. Results: These results demonstrated the high effectiveness of this approach. One of the best results achieved by our method was a correlation of 0.841 between the cell line in vitro drug response and patient’s in vivo drug response. We then applied these two drug prediction models to develop a personalized medicine approach in which the subsequent treatment depends on each patient’s gene-expression profile. Conclusion: The proposed method is much better than the existing approach and can capture a more accurate reflection of the relationship between genotypes and phenotypes.

Download Full-text

ModuleDiscoverer: Identification of regulatory modules in protein-protein interaction networks

10.1101/119099 ◽

2017 ◽

Author(s):

Sebastian Vlaic ◽

Christian Tokarski-Schnelle ◽

Mika Gustafsson ◽

Uta Dahmen ◽

Reinhard Guthke ◽

...

Keyword(s):

Gene Expression ◽

Gene Expression Data ◽

Large Scale ◽

Protein Interaction Networks ◽

Interaction Networks ◽

Whole Genome ◽

Expression Data ◽

Regulatory Modules ◽

Protein Protein Interaction ◽

Protein Protein Interaction Networks

AbstractThe identification of disease associated modules based on protein-protein interaction networks (PPINs) and gene expression data has provided new insights into the mechanistic nature of diverse diseases. A major problem hampering their identification is the detection of protein communities within large-scale, whole-genome PPINs. Current strategies solve the maximal clique enumeration (MCE) problem, i.e., the enumeration of all non-extendable groups of proteins, where each pair of proteins is connected by an edge. The MCE problem however is non-deterministic polynomial time hard and can thus be computationally overwhelming for large-scale, whole-genome PPINs.We present ModuleDiscoverer, a novel approach for the identification of regulatory modules from PPINs in conjunction with gene-expression data. ModuleDiscoverer is a heuristic that approximates the community structure underlying PPINs. Based on a high-confidence PPIN of Rattus norvegicus and publicly available gene expression data we apply our algorithm to identify the regulatory module of a rat-model of diet induced non-alcoholic steatohepatitis (NASH). We validate the module using single-nucleotide polymorphism data from independent genome-wide association studies. Structural analysis of the module reveals 10 sub-modules. These sub-modules are associated with distinct biological functions and pathways that are relevant to the pathological and clinical situation in NASH.ModuleDiscoverer is freely available upon request from the corresponding author.

Download Full-text

GENE DISCOVERY METHODS FROM LARGE-SCALE GENE EXPRESSION DATA

Quantum Bio-Informatics III ◽

10.1142/9789814304061_0040 ◽

2010 ◽

Author(s):

AKIFUMI SHIMIZU ◽

KENTARO YANO

Keyword(s):

Gene Expression ◽

Gene Expression Data ◽

Large Scale ◽

Gene Discovery ◽

Expression Data

Download Full-text

LSTrAP-Crowd: Prediction of novel components of bacterial ribosomes with crowd-sourced analysis of RNA sequencing data

10.1101/2020.04.20.005249 ◽

2020 ◽

Author(s):

Benedict Hew ◽

Qiao Wen Tan ◽

William Goh ◽

Jonathan Wei Xiong Ng ◽

Kenny Koh ◽

...

Keyword(s):

Gene Expression ◽

Protein Synthesis ◽

Rna Sequencing ◽

Gene Expression Data ◽

Large Scale ◽

Bacterial Resistance ◽

Expression Data ◽

Sequencing Data ◽

Novel Proteins ◽

Novel Antibiotics

AbstractBacterial resistance to antibiotics is a growing problem that is projected to cause more deaths than cancer in 2050. Consequently, novel antibiotics are urgently needed. Since more than half of the available antibiotics target the bacterial ribosomes, proteins that are involved in protein synthesis are thus prime targets for the development of novel antibiotics. However, experimental identification of these potential antibiotic target proteins can be labor-intensive and challenging, as these proteins are likely to be poorly characterized and specific to few bacteria. In order to identify these novel proteins, we established a Large-Scale Transcriptomic Analysis Pipeline in Crowd (LSTrAP-Crowd), where 285 individuals processed 26 terabytes of RNA-sequencing data of the 17 most notorious bacterial pathogens. In total, the crowd processed 26,269 RNA-seq experiments and used the data to construct gene co-expression networks, which were used to identify more than a hundred uncharacterized genes that were transcriptionally associated with protein synthesis. We provide the identity of these genes together with the processed gene expression data. The data can be used to identify other vulnerabilities or bacteria, while our approach demonstrates how the processing of gene expression data can be easily crowdsourced.

Download Full-text