Kanser Sınıflandırma için Logaritmik Sıra Birleştirme Yöntemini Kullanan Yeni Topluluk Öznitelik Seçim Tekniği

Yıl 2024, Cilt: 12 Sayı: 2, 1000 - 1035, 29.04.2024

Hüseyin Güney , Hüseyin Öztoprak

https://doi.org/10.29130/dubited.1225446

Öz

Son araştırmalar, topluluk öznitelik seçiminin (TÖS) mikrodizi veri sınıflandırmasında olağanüstü bir başarı elde ettiğini göstermiştir. Bununla birlikte, yetersiz birleştirme yöntemleri ve optimize edilmemiş ÖS teknikleri gibi konuların kısmen çözülmüş olarak kaldığı görülmektedir. Bu çalışma, TÖS yöntemlerinde özellik birleştirmeyi geliştirmek için logaritmik sıralama birleştirme (LRA) yöntemini önerdi. Ek olarak, önerilen yöntemin performansını geliştirmek için birkaç yöntemle birlikte kullanan hibrit yöntemler sunulmuştur. Ayrıca, öznitelik seçiminin optimizasyonunun etkisini ölçmek için optimize edilmiş öznitelik seçim tekniğinden elde edilen öznitelik sıralamalarına da önerilen yöntem uygulanmıştır. Hazırlanan deney, beş ikili mikrodizi veri seti üzerinde gerçekleştirilmiş olup, deney sonuçları, LRA'nın ortalama sıra birleştirme yöntemine (MRA) kıyaslanabilir bir sınıflandırma performansı sağladığını ve gen seçim istikrarı açısından MRA'dan daha iyi performans elde ettiğini göstermiştir. Ek olarak, hibrit teknikler, MRA ile aynı veya daha iyi sınıflandırma doğruluğu sağladı ve gen seçim istikrarını önemli ölçüde artırdı. Ayrıca önerilen bazı konfigürasyonlar, MRA'dan daha iyi doğruluk, hassasiyet ve özgüllük performansına ulaştı. Ayrıca, optimize edilmiş LRA, optimize edilmemiş LRA ve MRA'ya kıyasla gen seçim istikrarını önemli ölçüde iyileştirmiştir. Son olarak, sonuçlar diğer çalışmalarla karşılaştırıldığında, optimize edilmiş LRA'nın dikkate değer bir gen se.im istikrarı sağladığı görülmüştür ve bu çalışmanın bu alanda çalışan uzmanların kanser teşhisinde nispeten daha küçük bir gen kümesi kullanarak daha isabetli teşhis koymalarına yardımcı olabileceği vurgulanmıştır.

Anahtar Kelimeler

Mikrodizi Veri Kümesi, Topluluk Öğrenme, Birleştirme Yöntemleri, Destek Vektör Makineleri, Tekrarlayan Öznitelik Seçimi (SVM-RFE), Microarray Data, Ensemble Learning, Aggregation Methods, Support Vector Machine Recursive Feature Elimination (SVM-RFE)

A Novel Ensemble Feature Selection Technique for Cancer Classification Using Logarithmic Rank Aggregation Method

Öz

Recent studies have shown that ensemble feature selection (EFS) has achieved outstanding performance in microarray data classification. However, some issues remain partially resolved, such as suboptimal aggregation methods and non-optimised underlying FS techniques. This study proposed the logarithmic rank aggregate (LRA) method to improve feature aggregation in EFS. Additionally, a hybrid aggregation framework was presented to improve the performance of the proposed method by combining it with several methods. Furthermore, the proposed method was applied to the feature rank lists obtained from the optimised FS technique to investigate the impact of FS technique optimisation. The experimental setup was performed on five binary microarray datasets. The experimental results showed that LRA provides a comparable classification performance to mean rank aggregation (MRA) and outperforms MRA in terms of gene selection stability. In addition, hybrid techniques provided the same or better classification accuracy as MRA and significantly improved stability. Moreover, some proposed configurations had better accuracy, sensitivity, and specificity performance than MRA. Furthermore, the optimised LRA drastically improved the FS stability compared to the unoptimised LRA and MRA. Finally, When the results were compared with other studies, it was shown that optimised LRA provided a remarkable stability performance, which can help domain experts diagnose cancer diseases with a relatively smaller subset of genes.

Anahtar Kelimeler

Microarray Data, Ensemble Learning, Aggregation Methods, Support Vector Machine Recursive Feature Elimination (SVM-RFE)

Kaynakça

• [1] N. Mahendran, P. M. Durai Raj Vincent, K. Srinivasan, and C.-Y. Chang, “Machine learning based Computational Gene Selection Models: A survey, performance evaluation, open issues, and future research directions,” Frontiers in Genetics, vol. 11, 2020. doi:10.3389/fgene.2020.603808.
• [2] V. K. Chauhan, K. Dahiya, and A. Sharma, “Problem formulations and solvers in Linear SVM: A Review,” Artificial Intelligence Review, vol. 52, no. 2, pp. 803–855, 2018. doi:10.1007/s10462-018-9614-6.
• [3] V. Bolón-Canedo, N. Sánchez-Maroño, A. Alonso-Betanzos, J. M. Benítez, and F. Herrera, “A review of microarray datasets and Applied Feature Selection Methods,” Information Sciences, vol. 282, pp. 111–135, 2014. doi:10.1016/j.ins.2014.05.042.
• [4] T. Abeel, T. Helleputte, Y. Van de Peer, P. Dupont, and Y. Saeys, “Robust biomarker identification for cancer diagnosis with Ensemble Feature Selection Methods,” Bioinformatics, vol. 26, no. 3, pp. 392–398, 2009. doi:10.1093/bioinformatics/btp630.
• [5] H. Güney and H. Öztoprak, “Microarray‐based cancer diagnosis: Repeated cross‐validation‐based ensemble feature selection,” Electronics Letters, vol. 54, no. 5, pp. 272–274, 2018. doi:10.1049/el.2017.4550.
• [6] D. Guan, W. Yuan, Y.-K. Lee, K. Najeebullah, and M. K. Rasel, “A review of Ensemble Learning Based Feature Selection,” IETE Technical Review, vol. 31, no. 3, pp. 190–198, 2014. doi:10.1080/02564602.2014.906859.
• [7] B. Pes, “Ensemble feature selection for high-dimensional data: A stability analysis across multiple domains,” Neural Computing and Applications, vol. 32, no. 10, pp. 5951–5973, 2019. doi:10.1007/s00521-019-04082-3.
• [8] A. Ben Brahim and M. Limam, “Ensemble feature selection for High Dimensional Data: A new method and a comparative study,” Advances in Data Analysis and Classification, vol. 12, no. 4, pp. 937–952, 2017. doi:10.1007/s11634-017-0285-y.
• [9] V. Bolón-Canedo, N. Sánchez-Maroño, and A. Alonso-Betanzos, “An ensemble of filters and classifiers for Microarray Data Classification,” Pattern Recognition, vol. 45, no. 1, pp. 531–539, 2012. doi:10.1016/j.patcog.2011.06.006.
• [10] A. Anaissi, M. Goyal, D. R. Catchpoole, A. Braytee, and P. J. Kennedy, “Ensemble feature learning of genomic data using support Vector Machine,” PLOS ONE, vol. 11, no. 6, 2016. doi:10.1371/journal.pone.0157330.
• [11] P. Yang, B. B. Zhou, Z. Zhang, and A. Y. Zomaya, “A multi-filter enhanced genetic ensemble system for gene selection and sample classification of Microarray Data,” BMC Bioinformatics, vol. 11, no. S1, 2010. doi:10.1186/1471-2105-11-s1-s5.
• [12] B. Seijo-Pardo, I. Porto-Díaz, V. Bolón-Canedo, and A. Alonso-Betanzos, “Ensemble feature selection: Homogeneous and heterogeneous approaches,” Knowledge-Based Systems, vol. 118, pp. 124–139, 2017. doi:10.1016/j.knosys.2016.11.017.
• [13] L. Cleofas-Sánchez, J. S. Sánchez, and V. García, “Gene selection and disease prediction from gene expression data using a two-stage hetero-associative memory,” Progress in Artificial Intelligence, vol. 8, no. 1, pp. 63–71, 2018. doi:10.1007/s13748-018-0148-6.
• [14] S. Hengpraprohm and S. Jungjit, “Ensemble feature selection for breast cancer classification using Microarray Data,” Inteligencia Artificial, vol. 23, no. 65, pp. 100–114, 2020. doi:10.4114/intartif.vol23iss65pp100-114.
• [15] B. Venkatesh and J. Anuradha, “A fuzzy gaussian rank aggregation ensemble feature selection method for Microarray Data,” International Journal of Knowledge-based and Intelligent Engineering Systems, vol. 24, no. 4, pp. 289–301, 2021. doi:10.3233/kes-190134.
• [16] A. Wang et al., “Stable and accurate feature selection from microarray data with ensembled fast correlation based filter,” 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020. doi:10.1109/bibm49941.2020.9313533.
• [17] M. Momenzadeh, M. Sehhati, and H. Rabbani, “A novel feature selection method for microarray data classification based on Hidden Markov Model,” Journal of Biomedical Informatics, vol. 95, p. 103213, 2019. doi:10.1016/j.jbi.2019.103213.
• [18] G. Zhang, J. Hou, J. Wang, C. Yan, and J. Luo, “Feature selection for microarray data classification using hybrid information gain and a modified binary krill herd algorithm,” Interdisciplinary Sciences: Computational Life Sciences, vol. 12, no. 3, pp. 288–301, 2020. doi:10.1007/s12539-020-00372-w.
• [19] O. A. Alomari et al., “Gene selection for microarray data classification based on Gray Wolf optimiser enhanced with TRIZ-inspired operators,” Knowledge-Based Systems, vol. 223, p. 107034, 2021. doi:10.1016/j.knosys.2021.107034.
• [20] X. Zheng, W. Zhu, C. Tang, and M. Wang, “Gene selection for microarray data classification via Adaptive Hypergraph Embedded Dictionary Learning,” Gene, vol. 706, pp. 188–200, 2019. doi:10.1016/j.gene.2019.04.060.
• [21] S. Raghavendra. N and P. C. Deka, “Support Vector Machine applications in the field of Hydrology: A Review,” Applied Soft Computing, vol. 19, pp. 372–386, 2014. doi:10.1016/j.asoc.2014.02.002.
• [22] X. Zhang, D. Qiu, and F. Chen, “Support vector machine with parameter optimisation by a novel hybrid method and its application to fault diagnosis,” Neurocomputing, vol. 149, pp. 641–651, 2015. doi:10.1016/j.neucom.2014.08.010.
• [23] I. Guyon, J. Weston, S. Barnhill, and V. Vapnik, “Gene Selection for Cancer Classification using Support Vector Machines,” Machine Learning, vol. 46(1), pp. 389–442, 2002.
• [24] R. Wald, T. M. Khoshgoftaar, and D. Dittman, “Mean aggregation versus robust rank aggregation for ensemble Gene Selection,” 2012 11th International Conference on Machine Learning and Applications, 2012. doi:10.1109/icmla.2012.20.
• [25] A.-C. Haury, P. Gestraud, and J.-P. Vert, “The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures,” PLoS ONE, vol. 6, no. 12, 2011. doi:10.1371/journal.pone.0028210.
• [26] U. Alon et al., “Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays,” Proceedings of the National Academy of Sciences, vol. 96, no. 12, pp. 6745–6750, 1999. doi:10.1073/pnas.96.12.6745.
• [27] D. Singh et al., “Gene expression correlates of clinical prostate cancer behaviour,” Cancer cell, vol. 1, pp. 203–209, 2002.
• [28] T. R. Golub et al., “Molecular classification of cancer: Class Discovery and class prediction by Gene Expression Monitoring,” Science, vol. 286, no. 5439, pp. 531–537, 1999. doi:10.1126/science.286.5439.531.
• [29] G. J. Gordon et al., “Translation of microarray data into clinically relevant cancer diagnostic tests using gene expression ratios in lung cancer and mesothelioma,” Cancer Res, vol. 62, pp. 4963–4967, 2002. doi:10.1126/science.286.5439.531.
• [30] A. Alizadeh et al., “Distinct types of diffuse large B-cell lymphoma identified by gene expression profiling,” Nature, vol. 403, pp. 503–511, 2000.
• [31] T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006. doi:10.1016/j.patrec.2005.10.010
• [32] L. I. Kuncheva, “A stability index for feature selection,” In Artificial intelligence and applications, pp. 421–427, 2007.
• [33] Z. Li, W. Xie, and T. Liu, “Efficient feature selection and classification for Microarray Data,” PLOS ONE, vol. 13, no. 8, 2018. doi:10.1371/journal.pone.0202167.
• [34] Q. Chen, Z. Meng, and R. Su, “Werfe: A gene selection algorithm based on recursive feature elimination and ensemble strategy,” Frontiers in Bioengineering and Biotechnology, vol. 8, 2020. doi:10.3389/fbioe.2020.00496.
• [35] M. K. Ebrahimpour and M. Eftekhari, “Ensemble of Feature Selection Methods: A hesitant fuzzy sets approach,” Applied Soft Computing, vol. 50, pp. 300–312, 2017. doi:10.1016/j.asoc.2016.11.021.
• [36] M. Qaraad, S. Amjad, P. El-Kafrawy, H. Fathi, and I. I. M. Manhrawy, “Parameters optimisation of elastic net for high dimensional data using PSO algorithm,” 2020 International Conference on Intelligent Systems and Computer Vision (ISCV), 2020. doi:10.1109/iscv49265.2020.9204218.
• [37] M. S. Othman, S. R. Kumaran, and L. M. Yusuf, “Gene selection using hybrid multi-objective cuckoo search algorithm with evolutionary operators for cancer microarray data,” IEEE Access, vol. 8, pp. 186348–186361, 2020. doi:10.1109/access.2020.3029890.
• [38] D. Santhakumar and S. Logeswari, “Efficient attribute selection technique for leukaemia prediction using microarray gene data,” Soft Computing, vol. 24, no. 18, pp. 14265–14274, 2020. doi:10.1007/s00500-020-04793-z.
• [39] [1] K. Cahyaningrum, Adiwijaya, and W. Astuti, “Microarray gene expression classification for cancer detection using artificial neural networks and genetic algorithm hybrid intelligence,” 2020 International Conference on Data Science and Its Applications (ICoDSA), 2020. doi:10.1109/icodsa50139.2020.9213051.
• [40] T. Nguyen, A. Khosravi, D. Creighton, and S. Nahavandi, “A novel aggregate gene selection method for microarray data classification,” Pattern Recognition Letters, vol. 60, pp. 16–23, 2015. doi: 10.1016/j.patrec.2015.03.018.