Improving Long Non-Coding RNA Prediction through Recursive Feature Elimination and XGBoost

Year 2025, EARLY VIEW, 1 - 1

Freshta Alizada , Volkan Altuntaş

https://doi.org/10.2339/politeknik.1627668

Abstract

In recent years, advancements in high-throughput technologies have uncovered numerous concealed layers known as non-coding Ribonucleic Acids (ncRNAs), shifting the protein-centric view of genomes. NcRNAs, previously considered insignificant segments of the genome, are now recognized as essential functional components in prokaryotic and eukaryotic organisms. Long non-coding RNAs (lncRNAs) are a unique category of ncRNAs with 200 nucleotides length, which are instrumental in key biological functions, including cellular differentiation, regulatory mechanisms, and epigenetic modifications. Despite the similarities between lncRNAs and messenger RNAs (mRNAs), there is a fundamental difference: mRNAs encode proteins, whereas lncRNAs do not. This study aims to distinguish these two RNA classes from each other by designing a robust machine learning (ML) pipeline employing Recursive Feature Elimination (RFE) for dimensionality reduction of dataset and XGBoost (XGB) classification model. Whereas previous studies trained and tested machine learning models using the complete set of dataset features, we employ the RFE technique to reduce the number of features, thereby we achieve a more optimal dataset with relevant features. To evaluate the predictive performance of our pipeline, we used error rate, accuracy, precision, recall, and F1-score. Compared to three existing lncRNA identification tools in the literature, our pipeline demonstrated superior prediction accuracy and precision at 93.42% and 94.19% respectively.

Keywords

Recursive Feature Elimination, XGBoost, lncRNAs, Bioinformatics, Machine Learning.

Ethical Statement

No ethics committee approval was required for this study because only publicly available data was used in the research.

Supporting Institution

in this research we did not access help from any organization

Thanks

I thank Doç. Dr. Volkan ALTUNTAŞ, my instructor for helping me in writing this research article

Tekrarlayan Özellik Eliminasyonu ve XGBoost ile Uzun Kodlamayan RNA Tahmininin İyileştirilmesi

Abstract

Son yıllarda, yüksek verimli teknolojilerdeki ilerlemeler, kodlamayan Ribonükleik Asitler (ncRNA'lar) olarak bilinen çok sayıda gizli katmanı ortaya çıkararak genomların protein merkezli görüşünü değiştirdi. Daha önce genomun önemsiz bölümleri olarak kabul edilen NcRNA'lar, artık prokaryotik ve ökaryotik organizmalarda temel işlevsel bileşenler olarak kabul ediliyor. Uzun kodlamayan RNA'lar (lncRNA'lar), hücresel farklılaşma, düzenleyici mekanizmalar ve epigenetik modifikasyonlar dahil olmak üzere temel biyolojik işlevlerde etkili olan 200 nükleotid uzunluğundaki benzersiz bir ncRNA kategorisidir. LncRNA'lar ve haberci RNA'lar (mRNA'lar) arasındaki benzerliklere rağmen, temel bir fark vardır: mRNA'lar protein kodlar, oysa lncRNA'lar kodlamaz. Bu çalışma, veri kümesinin boyutsallığını azaltmak için Tekrarlayan Özellik Eliminasyonu (RFE) ve XGBoost (XGB) sınıflandırma modelini kullanan sağlam bir makine öğrenimi (ML) boru hattı tasarlayarak bu iki RNA sınıfını birbirinden ayırmayı amaçlamaktadır. Önceki çalışmalar, veri kümesi özelliklerinin tamamını kullanarak makine öğrenimi modellerini eğitmiş ve test etmişken, biz özellik sayısını azaltmak için RFE tekniğini kullanıyoruz, böylece ilgili özelliklere sahip daha optimum bir veri kümesi elde ediyoruz. Boru hattımızın tahmin performansını değerlendirmek için hata oranı, doğruluk, kesinlik, geri çağırma ve F1 puanını kullandık. Literatürdeki üç mevcut lncRNA tanımlama aracıyla karşılaştırıldığında, boru hattımız sırasıyla %93,42 ve %94,19'da üstün tahmin doğruluğu ve kesinlik gösterdi.

Keywords

Özyinelemeli Özellik Giderme, XGBoost, lncRNA, Biyoinformatik, Makine Öğrenm

References

• [1] Bonidia R. P.,Machida J.S.,Negri T.C.,Alves W.A.L.,Kashiwabara A.Y.,Domingues D.S., Charvalho A.D., Paschoal A.R. and Shanches D.S., “A Novel Decomposing Model with Evolutionary Algorithms for Feature Selection in Long Non-Coding RNAs”, IEEE Access, 8: 181683–181697, (2020).
• [2] Nuray, B. and Altuntaş, V., “RNA m6A Modifikasyon Bölgelerinin Sınıflandırılması için Öznitelik Çıkarma ve Boyut Azaltma Yöntemlerinin Karşılaştırılması”. Politeknik Dergisi, pp.1-1. (2024).
• [3] Sreeshma C. M., Manu M. and Gopakumar G., “Identification of Long Non-Coding RNA From Inherent Features Using Machine Learning Techniques”, International Conference on Bioinformatics and Systems Biology", BSB 2018: 97–102, (2018).
• [4] Chen M., Peng Y., Li A., Deng Y., Deng Y. and Li Z., “A Novel lncRNA-Disease Association Prediction Model Using Laplacian Regularized Least Squares and Space Projection-Federated Method”, IEEE Access, 8: 111614–111625, (2020).
• [5] Zampetaki A., Albrecht A. and Steinhofel K., “Long Non-Coding RNA Structure and Function: Is There A Link?”, Frontiers in Physiology, 9(AUG): 1–8, (2018).
• [6] Lima D. D. S., Amichi L. J. A., Fernandez M. A., Constantino A. A. and Seixas F. A. V., “NCYPred: A Bidirectional LSTM Network with Attention for Y RNA and Short Non-Coding RNA Classification”, IEEE/ACM Transactions on Computational Biology and Bioinformatics,20(1): 557–565,(2023).
• [7] Alessio E., Bonadio R. S., Buson L., Chemello F. and Cagnin S., "A Single Cell But Many Different Transcripts: A journey into the world of long non-coding RNAs", International Journal of Molecular Sciences,21(1), (2020).
• [8] Wang W., Min L.,Qiu X., Wu X., Liu C., Ma J., Zhang D. and Zhu L., “Biological Function of Long Non-Coding RNA (LncRNA) Xist”, Frontiers in Cell and Developmental Biology, 9(Jue): 1–27, (2021).
• [9] Xuan P., Zhao Y., Cui H., Zhan L., Jin Q., Zhang T. and Nakaguchi T., “Semantic Meta-Path Enhanced Global and Local Topology Learning for lncRNA-Disease Association Prediction”, IEEE-ACM Transactions on Computational Biology and Bioinformatics, 20(2): 1480–1491, (2023).
• [10] Wang B. and Zhang J., “Logistic Regression Analysis for LncRNA-Disease Association Prediction Based on Random Forest and Clinical Stage Data”, IEEE Access, 8: 35004–35017, (2020).
• [11] Xie G., Jiang J. and Sun Y., “LDA-LNSUBRW: LncRNA-Disease Association Prediction Based on Linear Neighborhood Similarity and Unbalanced Bi-Random Walk”, IEEE/ACM Transactions on Computational Biology and Bioinformatics,19(2): 989–997, (2022).
• [12] Hu J. and Andrews B., “Distinguishing Long Non-Coding RNAs From mRNAs Using A Two-layer Structured Classifier”, IEEE International Conference on Computational Advances in Bio and Medical Sciences, ICCABS,2017-Octob: 1–5, (2017).
• [13] Shen C., Mao D., Tang J., Liao Z. and Chen S., “Prediction of LncRNA-Protein Interactions Based on Kernel Combinations and Graph Convolutional Networks”, IEEE Journal of Biomedical and Health Informatics, 28(4): 1937–1948, (2024).
• [14] Shen C., Ding Y., Tang J., Jiang L. and Guo F., “LPI-KTASLP: Prediction of LncRNA-Protein Interaction by Semi-Supervised Link Learning with Multivariate Information”, IEEE Access, 7: 13486–13496, (2019).
• [15] Liu X. Q., Li B. X., Zeng G. R., Liu Q. Y. and Ai D. M., “Prediction of Long Non-Coding RNAs Based on Deep Learning”, Genes, 10(4): (2019).
• [16] Wang L., Zheng S.,Zhang H.,Qiu Z.,Zhong X.,Liu H.and Liu Y., “NcRFP: A Novel end-To-end Method for Non-Coding RNAs Family Prediction Based on Deep Learning”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18(2): 784–789, (2021).
• [17] Zhang T., Wang M., Xi J. and Li A., “LPGNMF: Predicting Long Non-Coding RNA and Protein Interaction Using Graph Regularized Nonnegative Matrix Factorization”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 17(1): 189–197, (2020).
• [18] Zhang T., Tang Q., Nie F., Zhao Q. and Chen W., “DeepLncPro: an Interpretable Convolutional Neural Network Model for Identifying Long Non-Coding RNA Promoters”, Briefings in Bioinformatics, 23(6): 1–9, (2022).
• [19] Schneider H. W., Raiol T., Brigido M. M., Walter M. E. M. T. and Stadler P. F., “A Support Vector Machine based method to distinguish long non-coding RNAs from protein coding transcripts”, BMC Genomics, vol. 18(1): 1–14, (2017).
• [20] Budak H., Kaya S. B. and Cagirici H. B., “Long Non-Coding RNA in Plants in the Era of Reference Sequences”, Frontiers in Plant Science.,11(March): 1–10, (2020).
• [21] Musleh S., Islam M. T. and Alam T., “LNCRI: Long Non-Coding RNA Identifier in Multiple Species”, IEEE Access, 9: 167219–167228, (2021).
• [22] Ping P., Wang L., Kuang L., Ye S., Iqbal M. F. B. and Pei T., “A Novel Method for LncRNA-Disease Association Prediction Based on an lncRNA-Disease Association Network”, IEEE-ACM Transactions on Computational Biology and Bioinformatics, 16(2): 688–693, (2019).
• [23] Ganapaneni M. D., Paruchuru K. H., Ambati J. H., Valavala M. and Sobin C. C., “Detecting Long Non-Coding RNAs Responsible for Cancer Development”, Proceedings - 2022 OITS International Conference on Information Technology, OCIT 2022, 164–169,(2022).
• [24] Wang Y., Zhao P., Du H., Cao Y., Peng Q. and Fu L., “LncDLSM: Identification of Long Non-Coding RNAs with Deep Learning-Based Sequence Model”, IEEE Journal of Biomedical and Health Informatics,27(4): 2117–2127,(2023).
• [25] Amin N., McGrath A., and Chen Y. P. P., “FexRNA: Exploratory Data Analysis and Feature Selection of Non-Coding RNA”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18(6): 2795–2801,(2021).
• [26] Zhu R., Wang Y., Liu J. X. and Dai L. Y., “IPCARF: Improving Lncrna-Disease Association Prediction Using Incremental Principal Component Analysis Feature Selection and A Random Rorest Classifier”, BMC Bioinformatics, 22(1): 1–17,(2021).
• [27] Yao D., Zhan X., Zhan X., Kwoh C. K., Li P. and Wang J., “A Random Forest Based Computational Model for Predicting Novel LncRNA-Disease Associations”, BMC Bioinformatics, 21(1): 1–18,(2020).
• [28] Fan X.-N. and Zhang S.-W., “lncRNA-MFDL: Identification of Human Long Non-Coding RNAs by Fusing Multiple Features and Using Deep Learning”, Molecular BioSystems., 11(3): 892–897,(2015).
• [29] Ventola G. M. M., Noviello T. M. R., D’Aniello S., Spagnuolo A., Ceccarelli M. and Cerulo L., “Identification of Long Non-Coding Transcripts with Feature Selection: A Comparative Study”, BMC Bioinformatics,18(1): 187, (2017).
• [30] Hatipoğlu, A. and Altuntaş, V.,” DeepTFBS: Transkripsiyon Faktörü Bağlanma Bölgeleri Tahmini İçin Derin Öğrenme Yöntemleri Kullanan Hibrit Bir Model”. Politeknik Dergisi, pp.1-1. (2024).
• [31] Zhang B., Zhang Y. and Jiang X., “Feature selection for global tropospheric ozone prediction based on the BO-XGBoost-RFE algorithm”, Scientific Reports, 12(1): 1–10, (2022).
• [32] Granitto P. M., Furlanello C., Biasioli F. and Gasperi F., “Recursive Feature Elimination with Random Forest for PTR-MS Analysis of Agro-industrial Products”, Chemometrics and Intelligent Laboratory Systems, 83(2): 83–90, (2006).
• [33] Tripathi R., Patel S., Kumari V., Chakraborty P. and Varadwaj P. K., “DeepLNC, a Long Non-Coding RNA Prediction Tool Using Deep Neural Network”, Network Modeling Analysis in Health Informatics and Bioinformatics, 5(1): 21: (2016).
• [34] Gamgam H. and Altunkaynak B., “Test Statistic for Ordered Alternatives based on Wilcoxon Signed Rank.” [Online]. Available: http://dergipark.gov.tr/gujs
• [35] Atilkan. Y. et al., “Advancing Crayfish Disease Detection: A Comparative Study of Deep Learning and Canonical Machine Learning Techniques,” Applied Sciences (Switzerland), 14(14): (2024).
• [36] Zhang C., Liu C., Zhang X., and Almpanidis G., “An Up-to-Date Comparison of State-of-the-Art Classification Algorithms”, Expert Systems with Applications,82: 128–150, (2017).
• [37] Ahmad I., Basheri M., Iqbal M. J., and Rahim A., “Performance Comparison of Support Vector Machine, Random Forest, and Extreme Learning Machine for Intrusion Detection”, IEEE Access, 6,33789–33795:(2018).
• [38] Nacar E. N. and Erdebilli B., “Makine Öğrenmesi Algoritmaları ile Satış Tahmini,” Journal of Industrial Engineering", 2(2): 307–320,(2021).
• [39] Camalan. M. and Çavur. M., “Using Random Forest Tree Classification for Evaluating Vertical Cross-Sections in Epoxy Blocks to Get Unbiased Estimates for 3D Mineral Map,” Politeknik Dergisi, 24(1), 113–120, (2021).
• [40] Jakkula V., “Tutorial on Support Vector Machine (SVM)”, School of EECS, Washington State University,1–13:(2011).
• [41] Bekçioğulları M. F, Dikici B., Açıkgöz H., and Keçecioğlu Ö. F., “Güneş Enerjisinin Kısa-Dönem Tahmininde Farklı Makine Öğrenme Yöntemlerinin Karşılaştırılması Comparison of Different Machine Learning Methods in Short-Term Forecasting of Solar Energy”, EMO Bilimsel Dergi, 11(22):37–45, (2021).
• [42] Long W. J., Griffith J. L., Selker H. P., and D’Agostino R. B., “A Comparison of Logistic Regression to Decision-Tree Induction in A Medical Domain”, Computers and Biomedical Research, 26(1): 74–97, (1993).
• [43] Mitrea C. A., Lee C. K. M., and Wu Z., “A Comparison Between Neural Networks and Traditional Forecasting Methods: A Case Study”, International Journal of Engineering Business Management, 1(2):19–24, (2009).
• [44] Çalışan. M. and Talu M. F., “Comparison of Methods for Determining Activity from Physical Movements,” Politeknik Dergisi, 24(1),17–23,(2021).
• [45] Ekincioğlu. G., Akbay. D., and Keser. S., “Estimating Uniaxial Compressive Strength of Sedimentary Rocks with Leeb hardness Using SVM Regression Analysis and Artificial Neural Networks,” Journal of Polytechnic, 1–1, (2024).