×

Prediction in cancer genomics using topological signatures and machine learning. (English) Zbl 1448.62165

Baas, Nils (ed.) et al., Topological data analysis. Proceedings of the Abel symposium 2018, Geiranger, Norway, June 4–8, 2018. Cham: Springer. Abel Symp. 15, 247-276 (2020).
Summary: Copy Number Aberrations, gains and losses of genomic regions, are a hallmark of cancer and can be experimentally detected using microarray comparative genomic hybridization (aCGH). In previous works, we developed a topology based method to analyze aCGH data whose output are regions of the genome where copy number is altered in patients with a predetermined cancer phenotype. We call this method Topological Analysis of array CGH (TAaCGH). Here we combine TAaCGH with machine learning techniques to build classifiers using copy number aberrations. We chose logistic regression on two different binary phenotypes related to breast cancer to illustrate this approach. The first case consists of patients with over-expression of the ERBB2 gene. Over-expression of ERBB2 is commonly regulated by a copy number gain in chromosome arm 17q. TAaCGH found the region 17q11-q22 associated with the phenotype and using logistic regression we reduced this region to 17q12-q21.31 correctly classifying 78% of the ERBB2 positive individuals (sensitivity) in a validation data set. We also analyzed over-expression in Estrogen Receptor (ER), a second phenotype commonly observed in breast cancer patients and found that the region 5p14.3-12 together with six full arms were associated with the phenotype. Our method identified 4p, 6p and 16q as the strongest predictors correctly classifying 76% of ER positives in our validation data set. However, for this set there was a significant increase in the false positive rate (specificity). We suggest that topological and machine learning methods can be combined for prediction of phenotypes using genetic data.
For the entire collection see [Zbl 1448.62008].

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
92D20 Protein sequences, DNA sequences
62M20 Inference from stochastic processes and prediction
62R40 Topological data analysis
55N31 Persistent homology and applications, topological data analysis
68T05 Learning and adaptive systems in artificial intelligence
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Al-Kuraya, K., Schraml, P., Torhorst, J., Tapia, C., Zaharieva, B., Novotny, H., Spichtin, H., Maurer, R., Mirlacher, M., Köchli, O. and Zuber, M. Prognostic relevance of gene amplifications and coamplifications in breast cancer. Cancer research, 64(23), 8534-8540 (2004) · doi:10.1158/0008-5472.CAN-04-1945
[2] Ardanza-Trevijano, S., Gonzalez G., Borrman T., Garcia J.L., Arsuaga J. Topological analysis of amplicon structure in Comparative Genomic Hybridization (CGH) data: an application to ERBB2/HER2/NEU amplified tumors. In: Bac A., Mari J.L. (eds.) International Workshop on Computational Topology in Image Context. 6th International Workshop, CTIC 2016, Marseille, France, June 15-17. Lecture Notes in Computer Science vol. 9667, pp. 113-129. Springer, Cham. (2016)
[3] Arsuaga, J., Borrman, T., Cavalcante, R., Gonzalez, G., Park, C. Identification of copy number aberrations in breast cancer subtypes using persistence topology. Microarrays 4 (3), 339-69 (2015) · doi:10.3390/microarrays4030339
[4] Bauer, K.R., Brown, M., Cress, R.D., Parise, C. A., & Caggiano, V.: Descriptive analysis of estrogen receptor (ER)-negative, progesterone receptor (PR)-negative, and HER2-negative invasive breast cancer, the so-called triple-negative phenotype: a population-based study from the California cancer Registry. Cancer 109 (9), 1721-1728 (2007) · doi:10.1002/cncr.22618
[5] Bauer U: Ripser: a lean c+ + code for the computation of vietoris-rips persistence barcodes. https://github.com/Ripser/ripser (2017).
[6] Beroukhim, R., Mermel, C.H., Porter, D., Wei, G., Raychaudhuri, S., Donovan, J., Barretina, J., Boehm, J.S., Dobson, J., Urashima, M. and Mc Henry, K.T.: The landscape of somatic copy-number alteration across human cancers. Nature 463, 899-905, (2010) · doi:10.1038/nature08822
[7] Bubenik, P.: Statistical topological data analysis using persistence landscapes. The Journal of Machine Learning Research 16 (1), 77-102 (2015) · Zbl 1337.68221
[8] Burnham, K. P., & Anderson, D. R.: Multimodel inference: understanding AIC and BIC in model selection. Sociological methods & research 33, 261-304 (2004) · doi:10.1177/0049124104268644
[9] Carlson, R. W., Moench, S. J., Hammond, M. E., Perez, E. A., Burstein, H. J., Allred, D. C., … & Hudis, C. A.: HER2 testing in breast cancer: NCCN Task Force report and recommendations. Journal of the National Comprehensive Cancer Network: JNCCN 4, S1-22 (2006) · doi:10.6004/jnccn.2006.0082
[10] Climent, J., Dimitrow, P., Fridlyand, J., Palacios, J., Siebert, R., Albertson, D. G., … & Martinez-Climent, J. A.: Deletion of chromosome 11q predicts response to anthracycline-based chemotherapy in early breast cancer. Cancer research 67, 818-826 (2007) · doi:10.1158/0008-5472.CAN-06-3307
[11] Cuny, M., Kramar, A., Courjal, F., Johannsdottir, V., Iacopetta, B., Fontaine, H., … & Theillet, C.: Relating genotype and phenotype in breast cancer: an analysis of the prognostic significance of amplification at eight different genes or loci and of p53 mutations. Cancer research 60, 1077-1083 (2000)
[12] de Ronde, J. J., Klijn, C., Velds, A., Holstege, H., Reinders, M. J., Jonkers, J., & Wessels, L. F.: KC-SMARTR: An R package for detection of statistically significant aberrations in multi-experiment aCGH data. BMC research notes 3 (298) (2010)
[13] Deming, S. L., Nass, S. J., Dickson, R. B., & Trock, B. J.: C-myc amplification in breast cancer: a meta-analysis of its occurrence and prognostic relevance. British journal of cancer 83 (12), 1688-1695 (2000) · doi:10.1054/bjoc.2000.1522
[14] DeWoskin, D.: Applications of computational homology to analysis of primary breast tumor cgh profiles. Master’s thesis, San Francisco State University (2009)
[15] DeWoskin, D., Climent, J., Cruz-White, I., Vazquez, M., Park, C., & Arsuaga, J.: Applications of computational homology to the analysis of treatment response in breast cancer patients. Topology and its Applications 157 (1), 157-164 (2010) · Zbl 1176.92026 · doi:10.1016/j.topol.2009.04.036
[16] Edelsbrunner, H., & Harer, J.: Persistent homology-a survey. Contemporary mathematics 453, 257-282, (2008) · Zbl 1145.55007 · doi:10.1090/conm/453/08802
[17] Efron, B., & Gong, G.: A leisurely look at the bootstrap, the jackknife, and cross-validation. The American Statistician 37 (1), 36-48 (1983)
[18] Fridlyand, J., Snijders, A. M., Pinkel, D., Albertson, D. G., & Jain, A. N.: Hidden Markov models approach to the analysis of array CGH data. Journal of multivariate analysis 90 (1), 132-153, (2004) · Zbl 1047.92026 · doi:10.1016/j.jmva.2004.02.008
[19] Henselman, G., & Ghrist, R. Matroid filtrations and computational persistent homology. arXiv preprint arXiv:1606.00199 (2016)
[20] Hira, Z. M., & Gillies, D. F.: A review of feature selection and feature extraction methods applied on microarray data. Advances in bioinformatics https://doi.org/10.1155/2015/198363 (2015). · doi:10.1155/2015/198363
[21] Horlings, H.M., Lai, C., Nuyten, D.S., Halfwerk, H., Kristel, P., van Beers, E., Joosse, S.A., Klijn, C., Nederlof, P.M., Reinders, M.J. and Wessels, L.F.: Integration of DNA copy number alterations and prognostic gene expression signatures in breast cancer patients. Clinical Cancer Research, 16 (2):651-663 (2010). · doi:10.1158/1078-0432.CCR-09-0709
[22] Horlings, H.M., Lai, C., Nuyten, D.S., Halfwerk, H., Kristel, P., van Beers, E., Joosse, S.A., Klijn, C., Nederlof, P.M., Reinders, M.J. and Wessels, L.F.: Integration of DNA copy number alterations and prognostic gene expression signatures in breast cancer patients. supplementary material. Clinical Cancer Research http://clincancerres.aacrjournals.org/content/16/2/651/suppl/DC1/. (2010).
[23] Hupé, P., Stransky, N., Thiery, J.P., Radvanyi, F. and Barillot, E.,: Analysis of array CGH data: from signal ratio to gain and loss of DNA regions. Bioinformatics, 20 (18), 3413-3422 (2004). · doi:10.1093/bioinformatics/bth418
[24] Kashyap, H., Ahmed, H.A., Hoque, N., Roy, S. and Bhattacharyya, D.K.. Big data analytics in bioinformatics: A machine learning perspective. arXiv:1506.05101 (2015)
[25] Kelley, D.R., Snoek, J. and Rinn, J.L.: Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome research, 26 (7), 990-999 (2016). · doi:10.1101/gr.200535.115
[26] Khaled, W.T., Lee, S.C., Stingl, J., Chen, X., Ali, H.R., Rueda, O.M., Hadi, F., Wang, J., Yu, Y., Chin, S.F. and Stratton, M.: Bcl11a is a triple-negative breast cancer gene with critical functions in stem and progenitor cells. Nature communications, 6, 6987 (2015). · doi:10.1038/ncomms6987
[27] Kim, H.C., Lee, J.Y., Sung, H., Choi, J.Y., Park, S.K., Lee, K.M., Kim, Y.J., Go, M.J., Li, L., Cho, Y.S. and Park, M. A genome-wide association study identifies a breast cancer risk variant in ERBB4 at 2q34: results from the seoul breast cancer study. Breast Cancer Research, 14 (2):R56 (2012). · doi:10.1186/bcr3158
[28] Klijn, C., Holstege, H., de Ridder, J., Liu, X., Reinders, M., Jonkers, J. and Wessels, L.: Identification of cancer genes using a statistical framework for multiexperiment analysis of nondiscretized array CGH data. Nucleic acids research, 36 (2), e13-e13, (2008). · doi:10.1093/nar/gkm1143
[29] Lai, C., Horlings, H.M., van de Vijver, M.J., van Beers, E.H., Nederlof, P.M., Wessels, L.F. and Reinders, M.J.: SIRAC: Supervised identification of regions of aberration in aCGH datasets. BMC bioinformatics, 8 (1), 422 (2007) · doi:10.1186/1471-2105-8-422
[30] Lerebours, F., Bieche, I. and Lidereau, R.: Update on inflammatory breast cancer. Breast Cancer Research, 7 (2), 52-XX (2005)
[31] Long, J., Cai, Q., Shu, X.O., Qu, S., Li, C., Zheng, Y., Gu, K., Wang, W., Xiang, Y.B., Cheng, J. and Chen, K.: Identification of a functional genetic variant at 16q12. 1 for breast cancer risk: results from the asia breast cancer consortium. PLoS genetics, 6 (6), e1001002 (2010)
[32] Meier, L., Van De Geer, S. and Bühlmann, P.: The group lasso for logistic regression. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 70(1), 53-71 (2008) · Zbl 1400.62276
[33] Mendelsohn, J., Howley, P.M., Israel, M.A., Gray, J. and Thompson, C.B: The Molecular Basis of Cancer E-Book. Elsevier Health Sciences (2014)
[34] Meyerson, M., Gabriel, S., Getz, G.: Advances in understanding cancer genomes through second-generation sequencing. Nat Rev Genet. 11, 685-696 (2010) · doi:10.1038/nrg2841
[35] Mischaikow, K. and Nanda, V: Morse theory for filtrations and efficient computation of persistent homology. Discrete & Computational Geometry, 50 (2), 330-353 (2013) · Zbl 1278.57030 · doi:10.1007/s00454-013-9529-6
[36] Mizukami, Y., Nonomura, A., Takizawa, T., Noguchi, M., Michigishi, T., Nakamura, S. and Ishizaki, T.: N-myc protein expression in human breast carcinoma: prognostic implications. Anticancer research, 15 (6B), 2899-2905 (1995)
[37] National Cancer Institute, https://www.cancer.gov/types/breast/patient/breasttreatment-pdq. Accessed Sept. 2018.
[38] Nanda, V.: Perseus, the persistent homology software. http://www.sas.upenn.edu/vnanda/perseus, Accessed 04 Aug. 2019
[39] Nanda, V. and Sazdanovic, R.. Simplicial models and topological inference in biological systems. In: Jonoska N and Saito M (eds) Discrete and topological models in molecular biology, pp 109-141. Springer Science and Business Media, (2014) · Zbl 1290.92005
[40] Peduzzi, P., Concato, J., Kemper, E., Holford, T.R. and Feinstein, A.R. A simulation study of the number of events per variable in logistic regression analysis. Journal of clinical epidemiology, 49 (12), 1373-1379 (1996) · doi:10.1016/S0895-4356(96)00236-3
[41] Pinkel, D. and Albertson, D.G.: Array comparative genomic hybridization and its applications in cancer. Nature genetics, 37 (6s):S11-S17 (2005) · doi:10.1038/ng1569
[42] R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria, http://www.R-project.org/ (2017). Accessed 2017.
[43] Reis-Filho, J.S., Savage, K., Lambros, M.B., James, M., Steele, D., Jones, R.L. and Dowsett, M.: Cyclin d1 protein overexpression and CCND1 amplification in breast carcinomas: an immunohistochemical and chromogenic in situ hybridisation analysis. Modern pathology, 19 (7), 999-1009 (2006). · doi:10.1038/modpathol.3800621
[44] Sexton H. and Vejdemo-Johansson M: jplex, http://comptop.stanford.edu/programs/jplex/ (2008). Accessed December 2008.
[45] Shivapurkar, N., Sood, S., Wistuba, I.I., Virmani, A.K., Maitra, A., Milchgrub, S., Minna, J.D. and Gazdar, A.F.: Multiple regions of chromosome 4 demonstrating allelic losses in breast carcinomas. Cancer research, 59 (15), 3576-3580 (1999)
[46] Stacey, S.N., Manolescu, A., Sulem, P., Thorlacius, S., Gudjonsson, S.A., Jonsson, G.F., Jakobsdottir, M., Bergthorsson, J.T., Gudmundsson, J., Aben, K.K. and Strobbe, L.J.: Common variants on chromosome 5p12 confer susceptibility to estrogen receptor-positive breast cancer. Nature genetics, 40 (6), 703-706 (2008) · doi:10.1038/ng.131
[47] The GUDHI Project. Gudhi: User and reference manual. http://gudhi.gforge.inria.fr/ (2015)
[48] Toloşi, L. and Lengauer, T. Classification with correlated features: unreliability of feature ranking and solutions. Bioinformatics, 27 (14):1986-1994 (2011) · doi:10.1093/bioinformatics/btr300
[49] Vittinghoff, E. and McCulloch, C.E.: Relaxing the rule of ten events per variable in logistic and cox regression. American journal of epidemiology, 165 (6):710-718 (2007). · doi:10.1093/aje/kwk052
[50] Whitaker, J.W., Chen, Z. and Wang, W.: Predicting the human epigenome from DNA motifs. Nature methods, 12 (3), 265-272 (2015) · doi:10.1038/nmeth.3065
[51] Wolff, A.C., Hammond, M.E.H., Hicks, D.G., Dowsett, M., McShane, L.M., Allison, K.H., Allred, D.C., Bartlett, J.M., Bilous, M., Fitzgibbons, P. and Hanna, W. Recommendations for human epidermal growth factor receptor 2 testing in breast cancer: American society of clinical oncology/college of american pathologists clinical practice guideline update. Archives of Pathology and Laboratory Medicine, 138 (2), 241-256 (2013). · doi:10.5858/arpa.2013-0953-SA
[52] Zomorodian A. · doi:10.1016/j.cag.2010.03.007
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.