Unearthing New Genomic Markers of Drug Response by Improved Measurement of Discriminative Power

Overview

Journal BMC Med Genomics

Publisher Biomed Central

Specialty Genetics

Date 2018 Feb 8

PMID 29409485

Citations 6

Authors

Cuong C Dang

Antonio Peon

Pedro J Ballester

Affiliations

Soon will be listed here.

Abstract

Background: Oncology drugs are only effective in a small proportion of cancer patients. Our current ability to identify these responsive patients before treatment is still poor in most cases. Thus, there is a pressing need to discover response markers for marketed and research oncology drugs. Screening these drugs against a large panel of cancer cell lines has led to the discovery of new genomic markers of in vitro drug response. However, while the identification of such markers among thousands of candidate drug-gene associations in the data is error-prone, an appraisal of the effectiveness of such detection task is currently lacking.

Methods: Here we present a new non-parametric method to measuring the discriminative power of a drug-gene association. Unlike parametric statistical tests, the adopted non-parametric test has the advantage of not making strong assumptions about the data distorting the identification of genomic markers. Furthermore, we introduce a new benchmark to further validate these markers in vitro using more recent data not used to identify the markers.

Results: The application of this new methodology has led to the identification of 128 new genomic markers distributed across 61% of the analysed drugs, including 5 drugs without previously known markers, which were missed by the MANOVA test initially applied to analyse data from the Genomics of Drug Sensitivity in Cancer consortium.

Conclusions: Discovering markers using more than one statistical test and testing them on independent data is unusual. We found this helpful to discard statistically significant drug-gene associations that were actually spurious correlations. This approach also revealed new, independently validated, in vitro markers of drug response such as Temsirolimus-CDKN2A (resistance) and Gemcitabine-EWS_FLI1 (sensitivity).

Citing Articles

2023 Beijing Health Data Science Summit.

Health Data Sci. 2024; 4:0112.

PMID: 38854991 PMC: 11157085. DOI: 10.34133/hds.0112.

Large-Scale Machine Learning Analysis Reveals DNA Methylation and Gene Expression Response Signatures for Gemcitabine-Treated Pancreatic Cancer.

Ogunleye A, Piyawajanusorn C, Ghislat G, Ballester P Health Data Sci. 2024; 4:0108.

PMID: 38486621 PMC: 10904073. DOI: 10.34133/hds.0108.

Interpretable Machine Learning Models to Predict the Resistance of Breast Cancer Patients to Doxorubicin from Their microRNA Profiles.

Ogunleye A, Piyawajanusorn C, Goncalves A, Ghislat G, Ballester P Adv Sci (Weinh). 2022; 9(24):e2201501.

PMID: 35785523 PMC: 9403644. DOI: 10.1002/advs.202201501.

Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles.

Nguyen L, Naulaerts S, Bruna A, Ghislat G, Ballester P Biomedicines. 2021; 9(10).

PMID: 34680436 PMC: 8533095. DOI: 10.3390/biomedicines9101319.

A Methodological Framework to Discover Pharmacogenomic Interactions Based on Random Forests.

Fasola S, Cilluffo G, Montalbano L, Malizia V, Ferrante G, La Grutta S Genes (Basel). 2021; 12(6).

PMID: 34207374 PMC: 8235396. DOI: 10.3390/genes12060933.

References

Smusz S, Kurczab R, Bojarski A . The influence of the inactives subset generation on the performance of machine learning methods. J Cheminform. 2013; 5(1):17. PMC: 3626618. DOI: 10.1186/1758-2946-5-17. View

Riddick G, Song H, Ahn S, Walling J, Borges-Rivera D, Zhang W . Predicting in vitro drug sensitivity using Random Forests. Bioinformatics. 2010; 27(2):220-4. PMC: 3018816. DOI: 10.1093/bioinformatics/btq628. View

Menden M, Iorio F, Garnett M, McDermott U, Benes C, Ballester P . Machine learning prediction of cancer cell sensitivity to drugs based on genomic and chemical properties. PLoS One. 2013; 8(4):e61318. PMC: 3640019. DOI: 10.1371/journal.pone.0061318. View

Klepsch F, Vasanthanathan P, Ecker G . Ligand and structure-based classification models for prediction of P-glycoprotein inhibitors. J Chem Inf Model. 2013; 54(1):218-29. PMC: 3904775. DOI: 10.1021/ci400289j. View

Williams S, Anderson W, Santaguida M, Dylla S . Patient-derived xenografts, the cancer stem cell paradigm, and cancer pathobiology in the 21st century. Lab Invest. 2013; 93(9):970-82. DOI: 10.1038/labinvest.2013.92. View

Papadatos G, van Westen G, Croset S, Santos R, Trubian S, Overington J . A document classifier for medicinal chemistry publications trained on the ChEMBL corpus. J Cheminform. 2014; 6(1):40. PMC: 4158272. DOI: 10.1186/s13321-014-0040-8. View

Simon R, Roychowdhury S . Implementing personalized cancer genomics in clinical trials. Nat Rev Drug Discov. 2013; 12(5):358-69. DOI: 10.1038/nrd3979. View

Deyati A, Younesi E, Hofmann-Apitius M, Novac N . Challenges and opportunities for oncology biomarker discovery. Drug Discov Today. 2013; 18(13-14):614-24. DOI: 10.1016/j.drudis.2012.12.011. View

Cortes-Ciriano I, van Westen G, Bouvier G, Nilges M, Overington J, Bender A . Improved large-scale prediction of growth inhibition patterns using the NCI60 cancer cell line panel. Bioinformatics. 2015; 32(1):85-95. PMC: 4681992. DOI: 10.1093/bioinformatics/btv529. View

10.

Artez A, Bernabe R, Eerola I, Hemsley F, Jennings J, Kerr D . International network of cancer genome projects. Nature. 2010; 464(7291):993-8. PMC: 2902243. DOI: 10.1038/nature08987. View

11.

Ahmed J, Meinel T, Dunkel M, Murgueitio M, Adams R, Blasse C . CancerResource: a comprehensive database of cancer-relevant proteins and compound interactions supported by experimental knowledge. Nucleic Acids Res. 2010; 39(Database issue):D960-7. PMC: 3013779. DOI: 10.1093/nar/gkq910. View

12.

Al-Lazikani B, Banerji U, Workman P . Combinatorial drug therapy for cancer in the post-genomic era. Nat Biotechnol. 2012; 30(7):679-92. DOI: 10.1038/nbt.2284. View

13.

Kolchinsky A, Abi-Haidar A, Kaur J, Hamed A, Rocha L . Classification of protein-protein interaction full-text documents using text and citation network features. IEEE/ACM Trans Comput Biol Bioinform. 2010; 7(3):400-11. DOI: 10.1109/TCBB.2010.55. View

14.

Pemovska T, Kontro M, Yadav B, Edgren H, Eldfors S, Szwajda A . Individualized systems medicine strategy to tailor treatments for patients with chemorefractory acute myeloid leukemia. Cancer Discov. 2013; 3(12):1416-29. DOI: 10.1158/2159-8290.CD-13-0350. View

15.

Weinstein J . Drug discovery: Cell lines battle cancer. Nature. 2012; 483(7391):544-5. DOI: 10.1038/483544a. View

16.

Majumder B, Baraneedharan U, Thiyagarajan S, Radhakrishnan P, Narasimhan H, Dhandapani M . Predicting clinical response to anticancer drugs using an ex vivo platform that captures tumour heterogeneity. Nat Commun. 2015; 6:6169. PMC: 4351621. DOI: 10.1038/ncomms7169. View

17.

Makridakis M, Vlahou A . Secretome proteomics for discovery of cancer biomarkers. J Proteomics. 2010; 73(12):2291-305. DOI: 10.1016/j.jprot.2010.07.001. View

18.

Luengo-Fernandez R, Leal J, Gray A, Sullivan R . Economic burden of cancer across the European Union: a population-based cost analysis. Lancet Oncol. 2013; 14(12):1165-74. DOI: 10.1016/S1470-2045(13)70442-X. View

19.

Kumar R, Chaudhary K, Singla D, Gautam A, Raghava G . Designing of promiscuous inhibitors against pancreatic cancer cell lines. Sci Rep. 2014; 4:4668. PMC: 3985076. DOI: 10.1038/srep04668. View

20.

Malley J, Dasgupta A, Moore J . The limits of p-values for biological data mining. BioData Min. 2013; 6(1):10. PMC: 3668262. DOI: 10.1186/1756-0381-6-10. View