Abstract
Machine learning models can use information from gene expressions in patients to efficiently predict the severity of symptoms for several diseases. Medical experts, however, still need to understand the reasoning behind the predictions before trusting them. In their day-to-day practice, physicians prefer using gene expression profiles, consisting of a discretized subset of all data from gene expressions: in these profiles, genes are typically reported as either over-expressed or under-expressed, using discretization thresholds computed on data from a healthy control group. A discretized profile allows medical experts to quickly categorize patients at a glance. Building on previous works related to the automatic discretization of patient profiles, we present a novel approach that frames the problem as a multi-objective optimization task: on the one hand, after discretization, the medical expert would prefer to have as few different profiles as possible, to be able to classify patients in an intuitive way; on the other hand, the loss of information has to be minimized. Loss of information can be estimated using the performance of a classifier trained on the discretized gene expression levels. We apply one common state-of-the-art evolutionary multi-objective algorithm, NSGA-II, to the discretization of a dataset of COVID-19 patients that developed either mild or severe symptoms. The results show not only that the solutions found by the approach dominate traditional discretization based on statistical analysis and are more generally valid than those obtained through single-objective optimization, but that the candidate Pareto-optimal solutions preserve the sense-making that practitioners find necessary to trust the results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alghamdi, H.S., Amoudi, G., Elhag, S., Saeedi, K., Nasser, J.: Deep learning approaches for detecting Covid-19 from chest x-ray images: a survey. IEEE Access 9, 20235–20254 (2021)
Bernal, E., et al.: Activating killer-cell immunoglobulin-like receptors are associated with the severity of Covid-19. J. Infect. Diseases (2021)
Brazma, A., Vilo, J.: Gene expression data analysis. FEBS Lett. 480(1), 17–24 (2000)
Breiman, L.: Pasting small votes for classification in large databases and on-line. Mach. Learn. 36(1–2), 85–103 (1999)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Cantu, N., et al.: Synergistic effects of multiple factors involved in Covid-19-dependent muscle loss. Aging Disease, 9 (2021)
Cavallo, J.J., Donoho, D.A., Forman, H.P.: Hospital capacity and operations in the coronavirus disease 2019 (COVID-19) pandemic—planning for the nth patient. JAMA Health Forum 1(3), e200345 (2020). https://doi.org/10.1001/jamahealthforum.2020.0345
de Chassey, B., et al.: The interactomes of influenza virus ns1 and ns2 proteins identify new host factors and provide insights for adar1 playing a supportive role in virus replication. PLoS Pathog. 9(7), e1003440 (2013)
Chen, S., Duan, H., Xie, Y., Li, X., Zhao, Y.: Expression and prognostic analysis of rho gtpase-activating protein 11a in lung adenocarcinoma. Ann. Transl. Med. 9(10) (2021)
Chien, Y., Fu, K.S.: On the generalized karhunen-loève expansion (corresp.). IEEE Trans. Inf. Theory 13(3), 518–520 (1967)
Chin, L., Gray, J.W.: Translating insights from the cancer genome into clinical practice. Nature 452(7187), 553–563 (2008)
Cox, D.R.: The regression analysis of binary sequences. J. Roy. Stat. Soc. Ser. B (Methodol.), 215–242 (1958)
Crammer, K., Dekel, O., Keshet, J., Shalev-Shwartz, S., Singer, Y.: Online passive-aggressive algorithms. J. Mach. Learn. Res. 7(Mar), 551–585 (2006)
Cruz-Rodriguez, N., Quijano, S.M., Enciso, L.J., Combita, A.L., Zabaleta, J.: Gene expression signature predicts induction treatment response and clinical outcome in adult Colombian patients with acute lymphoblastic leukemia (2016)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Delorey, T.M., et al.: Covid-19 tissue atlases reveal SARS-COV-2 pathology and cellular targets. Nature, 1–8 (2021)
Fang, K.Y., et al.: Screening the hub genes and analyzing the mechanisms in discharged Covid-19 patients retesting positive through bioinformatics analysis. J. Clin. Lab. Anal. 36(7), e24495 (2022)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. stat., 1189–1232 (2001)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Mach. Learn. 46(1–3), 389–422 (2002)
Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1), 55–67 (1970). https://doi.org/10.1080/00401706.1970.10488634
Klaric, L., et al.: Mendelian randomisation identifies alternative splicing of the FAS death receptor as a mediator of severe Covid-19. medRxiv (2021)
Klopfenstein, T., et al.: Features of anosmia in Covid-19. Medecine et maladies infectieuses 50(5), 436–439 (2020)
Konigsberg, I.R., et al.: Host methylation predicts SARS-COV-2 infection and clinical outcome. Commun. Med. 1(1), 1–10 (2021)
Lewis, P.: The characteristic selection problem in recognition systems. IRE Trans. Inf. Theory 8(2), 171–178 (1962)
Lopez-Rincon, A., Martinez-Archundia, M., Martinez-Ruiz, G.U., Schoenhuth, A., Tonda, A.: Automatic discovery of 100-mirna signature for cancer classification using ensemble feature selection. BMC Bioinform. 20(1), 480 (2019)
Lopez-Rincon, A., et al.: Machine learning-based ensemble recursive feature selection of circulating mirnas for cancer tumor classification. Cancers 12(7), 1785 (2020)
Lu, Y., et al.: Dynamic edge-based biomarker non-invasively predicts hepatocellular carcinoma with hepatitis b virus infection for individual patients based on blood testing. J. Mol. Cell Biol. 11(8), 665–677 (2019)
Ma, Y., Chen, S.S., Feng, Y.Y., Wang, H.L.: Identification of novel biomarkers involved in pulmonary arterial hypertension based on multiple-microarray analysis. Biosci. Rep. 40(9) (2020)
Mouhrim, N., Tonda, A., Rodríguez-Guerra, I., Kraneveld, A.D., Rincon, A.L.: An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion. ACM, July 2022. https://doi.org/10.1145/3520304.3529001
de Moura, M.C., et al.: Epigenome-wide association study of Covid-19 severity with respiratory failure. EBioMedicine 66, 103339 (2021)
Ng, D.L., et al.: A diagnostic host response biosignature for Covid-19 from RNA profiling of nasal swabs and blood. Sci. Adv. 7(6), eabe5984 (2021)
Paiva, B., et al.: Phenotypic and genomic analysis of multiple myeloma minimal residual disease tumor cells: a new model to understand chemoresistance. Blood J. Am. Soc. Hematol. 127(15), 1896–1906 (2016)
Pedregosa, F.,et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Platt, J.: Others: probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 10(3), 61–74 (1999)
Rincon, A.L., Kraneveld, A.D., Tonda, A.: Batch correction of genomic data in chronic fatigue syndrome using CMA-ES. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, pp. 277–278. ACM, Cancun, July 2020. https://doi.org/10.1145/3377929.3389947
Roser, M.: Covid-19 data explorer (2022). https://ourworldindata.org/explorers/coronavirus-data-explorer
Safran, M., et al.: Genecards version 3: the human gene integrator. Database 2010 (2010)
Sussman, N.: Time for bed(s): hospital capacity and mortality from Covid-19. COVIDEconomics, pp. 116–129 (2020)
Torabi, A., et al.: Proinflammatory cytokines in the olfactory mucosa result in Covid-19 induced anosmia. ACS Chem. Neurosci. 11(13), 1909–1913 (2020)
Turjya, R.R., Khan, M.A.A.K., Mir Md. Khademul Islam, A.B.: Perversely expressed long noncoding RNAs can alter host response and viral proliferation in SARS-COV-2 infection. Future Virol. 15(9), 577–593 (2020)
Vabalas, A., Gowen, E., Poliakoff, E., Casson, A.J.: Machine learning algorithm validation with a limited sample size. PLoS ONE 14(11), e0224365 (2019)
Vignolo, L.D., Milone, D.H., Scharcanski, J.: Feature selection for face recognition based on multi-objective evolutionary wrappers. Expert Syst. Appl. 40(13), 5077–5084 (2013)
Wilson, J.C., et al.: Integrated mirna/cytokine/chemokine profiling reveals severity-associated step changes and principal correlates of fatality in Covid-19. Iscience, 103672 (2021)
Xu, J., et al.: RhoGAPs attenuate cell proliferation by direct interaction with p53 tetramerization domain. Cell Rep. 3(5), 1526–1538 (2013)
Yan, J., Li, P., Gao, R., Li, Y., Chen, L.: Identifying critical states of complex diseases by single-sample jensen-shannon divergence. Front. Oncol. 11, 1824 (2021)
Zhang, L., et al.: Long noncoding RNA expression profile from cryptococcal meningitis patients identifies dpy19l1p1 as a new disease marker. CNS Neurosci. Therapeutics 25(6), 772–782 (2019)
Zhang, T.: Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Twenty-First International Conference on Machine Learning - ICML 2004. ACM Press (2004). https://doi.org/10.1145/1015330.1015332
Zhou, Z., Li, S., Qin, G., Folkert, M., Jiang, S., Wang, J.: Multi-objective-based radiomic feature selection for lesion malignancy classification. IEEE J. Biomed. Health Inform. 24(1), 194–204 (2020). https://doi.org/10.1109/jbhi.2019.2902298
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rojas-Velazquez, D., Tonda, A., Rodriguez-Guerra, I., Kraneveld, A.D., Lopez-Rincon, A. (2023). Multi-objective Evolutionary Discretization of Gene Expression Profiles: Application to COVID-19 Severity Prediction. In: Correia, J., Smith, S., Qaddoura, R. (eds) Applications of Evolutionary Computation. EvoApplications 2023. Lecture Notes in Computer Science, vol 13989. Springer, Cham. https://doi.org/10.1007/978-3-031-30229-9_45
Download citation
DOI: https://doi.org/10.1007/978-3-031-30229-9_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30228-2
Online ISBN: 978-3-031-30229-9
eBook Packages: Computer ScienceComputer Science (R0)