Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models

Zhu, Yitan; Brettin, Thomas; Evrard, Yvonne A.; Xia, Fangfang; Partin, Alexander; Shukla, Maulik; Yoo, Hyunseung; Doroshow, James H.; Stevens, Rick L.

doi:10.3390/genes11091070

Title: Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models

Abstract

The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted p-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response.

Authors:

Zhu, Yitan ^[1]; Brettin, Thomas ^[1]; Evrard, Yvonne A. ^[2]; Xia, Fangfang ^[1];

^[1]; Shukla, Maulik ^[1]; Yoo, Hyunseung ^[1]; Doroshow, James H. ^[3]; Stevens, Rick L. ^[4]

Argonne National Lab. (ANL), Argonne, IL (United States)
National Lab. for Cancer Research, Frederick, MD (United States)
National Cancer Inst., Bethesda, MD (United States)
Argonne National Lab. (ANL), Argonne, IL (United States); Univ. of Chicago, IL (United States)

Publication Date:: Fri Sep 11 00:00:00 EDT 2020

Research Org.:: Argonne National Lab. (ANL), Argonne, IL (United States); Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE; National Institutes of Health (NIH)

OSTI Identifier:: 1757985

Grant/Contract Number:: AC02-06CH11357; AC52-07NA27344; AC52-06NA25396; AC05-00OR22725; JDACS4C; HHSN261200800001E

Resource Type:: Accepted Manuscript

Journal Name:: Genes

Additional Journal Information:: Journal Volume: 11; Journal Issue: 9; Journal ID: ISSN 2073-4425

Publisher:: MDPI

Country of Publication:: United States

Language:: English

Subject:: 60 APPLIED LIFE SCIENCES; general drug response prediction model; gene selection; co-expression extrapolation (COXEN); precision oncology

Citation Formats


                    Zhu, Yitan, Brettin, Thomas, Evrard, Yvonne A., Xia, Fangfang, Partin, Alexander, Shukla, Maulik, Yoo, Hyunseung, Doroshow, James H., and Stevens, Rick L. Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models.  United States: N. p., 2020. 
Web.  doi:10.3390/genes11091070.

Copy to clipboard


                    Zhu, Yitan, Brettin, Thomas, Evrard, Yvonne A., Xia, Fangfang, Partin, Alexander, Shukla, Maulik, Yoo, Hyunseung, Doroshow, James H., & Stevens, Rick L. Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models.  United States.  https://doi.org/10.3390/genes11091070

Copy to clipboard


                    Zhu, Yitan, Brettin, Thomas, Evrard, Yvonne A., Xia, Fangfang, Partin, Alexander, Shukla, Maulik, Yoo, Hyunseung, Doroshow, James H., and Stevens, Rick L. Fri .  
"Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models".  United States.  https://doi.org/10.3390/genes11091070.  https://www.osti.gov/servlets/purl/1757985.

Copy to clipboard


                    
@article{osti_1757985,

  title        = {Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models},

  author       = {Zhu, Yitan and Brettin, Thomas and Evrard, Yvonne A. and Xia, Fangfang and Partin, Alexander and Shukla, Maulik and Yoo, Hyunseung and Doroshow, James H. and Stevens, Rick L.},

  abstractNote = {The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted p-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response.},

  doi          = {10.3390/genes11091070},

  journal      = {Genes},

  number       = 9,

  volume       = 11,

  place        = {United States},

  year         = {Fri Sep 11 00:00:00 EDT 2020},

  month        = {Fri Sep 11 00:00:00 EDT 2020}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.3390/genes11091070

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Hub genes in a pan-cancer co-expression network show potential for predicting drug responses
journal, January 2018

Azuaje, Francisco; Kaoma, Tony; Jeanty, Céline
F1000Research, Vol. 7
DOI: 10.12688/f1000research.17149.1

Intra- and interspecies gene expression models for predicting drug response in canine osteosarcoma
journal, February 2016

Fowles, Jared S.; Brown, Kristen C.; Hess, Ann M.
BMC Bioinformatics, Vol. 17, Issue 1
DOI: 10.1186/s12859-016-0942-8

Dr.VAE: improving drug response prediction via modeling of drug perturbation effects
journal, March 2019

Rampášek, Ladislav; Hidru, Daniel; Smirnov, Petr
Bioinformatics, Vol. 35, Issue 19
DOI: 10.1093/bioinformatics/btz158

Predicting tumor cell line response to drug pairs with deep learning
journal, December 2018

Xia, Fangfang; Shukla, Maulik; Brettin, Thomas
BMC Bioinformatics, Vol. 19, Issue S18
DOI: 10.1186/s12859-018-2509-3

Prospective Comparison of Clinical and Genomic Multivariate Predictors of Response to Neoadjuvant Chemotherapy in Breast Cancer
journal, January 2010

Lee, Jae K.; Coutant, Charles; Kim, Young-Chul
Clinical Cancer Research, Vol. 16, Issue 2
DOI: 10.1158/1078-0432.CCR-09-2247

A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 Profiles
journal, November 2017

Subramanian, Aravind; Narayan, Rajiv; Corsello, Steven M.
Cell, Vol. 171, Issue 6
DOI: 10.1016/j.cell.2017.10.049

Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen
journal, June 2019

Menden, Michael P.; Wang, Dennis; Mason, Mike J.
Nature Communications, Vol. 10, Issue 1
DOI: 10.1038/s41467-019-09799-2

Multigene Expression–Based Predictors for Sensitivity to Vorinostat and Velcade in Non–Small Cell Lung Cancer
journal, August 2010

Nagji, Alykhan S.; Cho, Sang-Hoon; Liu, Yuan
Molecular Cancer Therapeutics, Vol. 9, Issue 10
DOI: 10.1158/1535-7163.MCT-10-0327

Multi-Gene Expression Predictors of Single Drug Responses to Adjuvant Chemotherapy in Ovarian Carcinoma: Predicting Platinum Resistance
journal, February 2012

Ferriss, J. Stuart; Kim, Youngchul; Duska, Linda
PLoS ONE, Vol. 7, Issue 2
DOI: 10.1371/journal.pone.0030550

The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity
journal, March 2012

Barretina, Jordi; Caponigro, Giordano; Stransky, Nicolas
Nature, Vol. 483, Issue 7391
DOI: 10.1038/nature11003

A strategy for predicting the chemosensitivity of human cancers and its application to drug discovery
journal, July 2007

Lee, J. K.; Havaleshko, D. M.; Cho, H.
Proceedings of the National Academy of Sciences, Vol. 104, Issue 32
DOI: 10.1073/pnas.0610292104

A community effort to assess and improve drug sensitivity prediction algorithms
journal, June 2014

Costello, James C.; Heiser, Laura M.; Georgii, Elisabeth
Nature Biotechnology, Vol. 32, Issue 12
DOI: 10.1038/nbt.2877

Reproducible pharmacogenomic profiling of cancer cell line panels
journal, May 2016

Haverty, Peter M.; Lin, Eva; Tan, Jenille
Nature, Vol. 533, Issue 7603
DOI: 10.1038/nature17987

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies
journal, October 2017

Huang, Cai; Mezencev, Roman; McDonald, John F.
PLOS ONE, Vol. 12, Issue 10
DOI: 10.1371/journal.pone.0186906

PDXGEM: patient-derived tumor xenograft-based gene expression model for predicting clinical response to anticancer therapy in cancer patients
journal, July 2020

Kim, Youngchul; Kim, Daewon; Cao, Biwei
BMC Bioinformatics, Vol. 21, Issue 1
DOI: 10.1186/s12859-020-03633-z

The COXEN Principle: Translating Signatures of In vitro Chemosensitivity into Tools for Clinical Outcome Prediction and Drug Discovery in Cancer
journal, February 2010

Smith, Steven C.; Baras, Alexander S.; Lee, Jae K.
Cancer Research, Vol. 70, Issue 5
DOI: 10.1158/0008-5472.CAN-09-3562

Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties
journal, April 2013

Menden, Michael P.; Iorio, Francesco; Garnett, Mathew
PLoS ONE, Vol. 8, Issue 4
DOI: 10.1371/journal.pone.0061318

Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
journal, January 1995

Benjamini, Yoav; Hochberg, Yosef
Journal of the Royal Statistical Society: Series B (Methodological), Vol. 57, Issue 1
DOI: 10.1111/j.2517-6161.1995.tb02031.x

A Concordance Correlation Coefficient to Evaluate Reproducibility
journal, March 1989

Lin, Lawrence I-Kuei
Biometrics, Vol. 45, Issue 1
DOI: 10.2307/2532051

Genomics of Drug Sensitivity in Cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells
journal, November 2012

Yang, Wanjuan; Soares, Jorge; Greninger, Patricia
Nucleic Acids Research, Vol. 41, Issue D1
DOI: 10.1093/nar/gks1111

Cancer Drug Response Profile scan (CDRscan): A Deep Learning Model That Predicts Drug Effectiveness from Cancer Genomic Signature
journal, June 2018

Chang, Yoosup; Park, Hyejin; Yang, Hyun-Jin
Scientific Reports, Vol. 8, Issue 1
DOI: 10.1038/s41598-018-27214-6

Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders
journal, October 2019

Manica, Matteo; Oskooei, Ali; Born, Jannis
Molecular Pharmaceutics, Vol. 16, Issue 12
DOI: 10.1021/acs.molpharmaceut.9b00520

Similar Records in DOE PAGES and OSTI.GOV collections:

Ensemble transfer learning for the prediction of anti-cancer drug response

Journal Article Zhu, Yitan ; Brettin, Thomas ; Evrard, Yvonne A. ; ... - Scientific Reports

Abstract Transfer learning, which transfers patterns learned on a source dataset to a related target dataset for constructing prediction models, has been shown effective in many applications. In this paper, we investigate whether transfer learning can be used to improve the performance of anti-cancer drug response prediction models. Previous transfer learning studies for drug response prediction focused on building models to predict the response of tumor cells to a specific drug treatment. We target the more challenging task of building general prediction models that can make predictions for both new tumor cells and new drugs. Uniquely, we investigate the powermore »« less
https://doi.org/10.1038/s41598-020-74921-0
Systematic drug safety evaluation based on public genomic expression (Connectivity Map) data: Myocardial and infectious adverse reactions as application cases

Journal Article Wang, Kejian ; Weng, Zuquan ; Sun, Liya ; ... - Biochemical and Biophysical Research Communications

Adverse drug reaction (ADR) is of great importance to both regulatory agencies and the pharmaceutical industry. Various techniques, such as quantitative structure–activity relationship (QSAR) and animal toxicology, are widely used to identify potential risks during the preclinical stage of drug development. Despite these efforts, drugs with safety liabilities can still pass through safety checkpoints and enter the market. This situation raises the concern that conventional chemical structure analysis and phenotypic screening are not sufficient to avoid all clinical adverse events. Genomic expression data following in vitro drug treatments characterize drug actions and thus have become widely used in drug repositioning. Inmore »« less
https://doi.org/10.1016/J.BBRC.2014.12.096
Predicting tumor cell line response to drug pairs with deep learning

Journal Article Xia, Fangfang ; Shukla, Maulik ; Brettin, Thomas ; ... - BMC Bioinformatics

The National Cancer Institute drug pair screening effort against 60 well-characterized human tumor cell lines (NCI-60) presents an unprecedented resource for modeling combinational drug activity. We present a computational model for predicting cell line response to a subset of drug pairs in the NCI-ALMANAC database. Based on residual neural networks for encoding features as well as predicting tumor growth, our model explains 94% of the response variance. While our best result is achieved with a combination of molecular feature types (gene expression, microRNA and proteome), we show that most of the predictive power comes from drug descriptors. To further demonstratemore »« less
https://doi.org/10.1186/s12859-018-2509-3

Full Text Available
Learning curves for drug response prediction in cancer cell lines

Journal Article Partin, Alexander ; Brettin, Thomas ; Evrard, Yvonne A. ; ... - BMC Bioinformatics

Motivated by the size and availability of cell line drug sensitivity data, researchers have been developing machine learning (ML) models for predicting drug response to advance cancer treatment. As drug sensitivity studies continue generating drug response data, a common question is whether the generalization performance of existing prediction models can be further improved with more training data. We utilize empirical learning curves for evaluating and comparing the data scaling properties of two neural networks (NNs) and two gradient boosting decision tree (GBDT) models trained on four cell line drug screening datasets. The learning curves are accurately fitted to a powermore »« less
https://doi.org/10.1186/s12859-021-04163-y

Full Text Available
A cross-study analysis of drug response prediction in cancer cell lines

Journal Article Xia, Fangfang ; Allen, Jonathan ; Balaprakash, Prasanna ; ... - Briefings in Bioinformatics

To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross-validation within a single study to assess model accuracy. While an essential first step, cross-validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: National Cancer Institute 60, ancer Therapeutics Response Portal (CTRP), Genomicsmore »« less
https://doi.org/10.1093/bib/bbab356

Similar Records

Title: Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models

Abstract

Citation Formats

Hub genes in a pan-cancer co-expression network show potential for predicting drug responses journal, January 2018

Intra- and interspecies gene expression models for predicting drug response in canine osteosarcoma journal, February 2016

Dr.VAE: improving drug response prediction via modeling of drug perturbation effects journal, March 2019

Predicting tumor cell line response to drug pairs with deep learning journal, December 2018

Prospective Comparison of Clinical and Genomic Multivariate Predictors of Response to Neoadjuvant Chemotherapy in Breast Cancer journal, January 2010

A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 Profiles journal, November 2017

Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen journal, June 2019

Multigene Expression–Based Predictors for Sensitivity to Vorinostat and Velcade in Non–Small Cell Lung Cancer journal, August 2010

Multi-Gene Expression Predictors of Single Drug Responses to Adjuvant Chemotherapy in Ovarian Carcinoma: Predicting Platinum Resistance journal, February 2012

The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity journal, March 2012

A strategy for predicting the chemosensitivity of human cancers and its application to drug discovery journal, July 2007

A community effort to assess and improve drug sensitivity prediction algorithms journal, June 2014

Reproducible pharmacogenomic profiling of cancer cell line panels journal, May 2016

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies journal, October 2017

PDXGEM: patient-derived tumor xenograft-based gene expression model for predicting clinical response to anticancer therapy in cancer patients journal, July 2020

The COXEN Principle: Translating Signatures of In vitro Chemosensitivity into Tools for Clinical Outcome Prediction and Drug Discovery in Cancer journal, February 2010

Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties journal, April 2013

Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing journal, January 1995

A Concordance Correlation Coefficient to Evaluate Reproducibility journal, March 1989

Genomics of Drug Sensitivity in Cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells journal, November 2012

Cancer Drug Response Profile scan (CDRscan): A Deep Learning Model That Predicts Drug Effectiveness from Cancer Genomic Signature journal, June 2018

Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders journal, October 2019

Hub genes in a pan-cancer co-expression network show potential for predicting drug responses
journal, January 2018

Intra- and interspecies gene expression models for predicting drug response in canine osteosarcoma
journal, February 2016

Dr.VAE: improving drug response prediction via modeling of drug perturbation effects
journal, March 2019

Predicting tumor cell line response to drug pairs with deep learning
journal, December 2018

Prospective Comparison of Clinical and Genomic Multivariate Predictors of Response to Neoadjuvant Chemotherapy in Breast Cancer
journal, January 2010

A Next Generation Connectivity Map: L1000 Platform and the First 1,000,000 Profiles
journal, November 2017

Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen
journal, June 2019

Multigene Expression–Based Predictors for Sensitivity to Vorinostat and Velcade in Non–Small Cell Lung Cancer
journal, August 2010

Multi-Gene Expression Predictors of Single Drug Responses to Adjuvant Chemotherapy in Ovarian Carcinoma: Predicting Platinum Resistance
journal, February 2012

The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity
journal, March 2012

A strategy for predicting the chemosensitivity of human cancers and its application to drug discovery
journal, July 2007

A community effort to assess and improve drug sensitivity prediction algorithms
journal, June 2014

Reproducible pharmacogenomic profiling of cancer cell line panels
journal, May 2016

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies
journal, October 2017

PDXGEM: patient-derived tumor xenograft-based gene expression model for predicting clinical response to anticancer therapy in cancer patients
journal, July 2020

The COXEN Principle: Translating Signatures of In vitro Chemosensitivity into Tools for Clinical Outcome Prediction and Drug Discovery in Cancer
journal, February 2010

Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties
journal, April 2013

Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
journal, January 1995

A Concordance Correlation Coefficient to Evaluate Reproducibility
journal, March 1989

Genomics of Drug Sensitivity in Cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells
journal, November 2012

Cancer Drug Response Profile scan (CDRscan): A Deep Learning Model That Predicts Drug Effectiveness from Cancer Genomic Signature
journal, June 2018

Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders
journal, October 2019