Hybrid Machine Learning And Deep Learning Models For Multi-Omics Data Fusion In Bioinformatics
DOI:
https://doi.org/10.29284/3vxd0351Keywords:
Deep learning; Machine Learning; Multi-Omics; Bioinformatics; LSTM; Regression.Abstract
Since multi-omics data (high-dimensional data, including many variables, like genomics, transcriptomics and proteomics) are high-dimensional (have many variables), heterogeneous (are data of different types), and interdependent (variables can affect each other), there is a significant challenge in integrating various data types in a synergistic manner (without, it may not be feasible). This paper is an attempt to tackle the problem of predicting drug sensitivity by offering a hybrid machine learning (ML, algorithms that learn patterns by analyzing data) and deep learning (DL, a type of ML based on neural network architectures to learn patterns of data) model of not only predicting drug sensitivity, but also using Genomics of Drug Sensitivity in Cancer (GDSC) data. The method involves applying sophisticated preprocessing, strict feature selection techniques (Random Forest, tree-based algorithm; LASSO regression, feature selection that chooses features by pruning irrelevant ones; Mutual Information which is a dependency measure between variables) as well as a hybrid model design favoring classical ML models (Random Forest, SVM--Support Vector Machine) over the deep learning style (LSTM-Long short-term memory networks, a sequence-based version of recurrent neural network). The metrics of the evaluation give a very high R 2 (coefficient of determination, a measure of model fit) of 0.991, and the evaluations are very small MAE ( Mean absolute error: square root of average squared error), RMSE (Root mean squared error: square root of average squared error), and MSE ( Mean squared error: square root of average squared error), resulting in approximately 12 percent higher accuracy than conventional approximations: Ridge Regression, XGBoost (Extreme gradient boosting), and Random Forest alone. This also shows the strength (capacity to work with diverse circumstances), generalizability (capacity to be used in new information), and enhanced predictive capabilities of the hybrid method of modeling nonlinear associations in multi-omics information, thus enhancing precision medicine (health care customized to patients in terms of genetic, environmental, and lifestyle determinants) uses.
References
[1]M. A. Mohammed, A. Lakhan, K. H. Abdulkareem, and B. Garcia-Zapirain, “A hybrid cancer prediction based on multi-omics data and reinforcement learning, state action reward state action (SARSA),” Comput. Biol. Med., vol. 154, p. 106617, Mar. 2023, doi: 10.1016/j.compbiomed.2023.106617.
[2]A. Mohammed Yousif, Noor M Jassam, Ahmad Salim, Hussein Ali Bardan, Ahmed Farhan Mutlak and A. F. A. D. Sallibi, “Melanoma Skin Cancer Detection Using Deep Learning Methods and Binary Melanoma Skin Cancer Detection Using Deep Learning Methods and Binary GWO Algorithm,” no. January, 2025, doi: 10.54216/FPA.180211.
[3]M. H. M. Khan et al., “Multi- class classification of breast cancer abnormalities using Deep Convolutional Neural Network (CNN),” PLoS One, vol. 16, no. 8 August 2021, pp. 1–15, 2021, doi: 10.1371/journal.pone.0256500.
[4]K. Chaudhary, O. B., Poirion, L., Lu, and L. X. Garmire, “Deep learning–based multi-omics integration robustly predicts survival in liver cancer,” Clin. Cancer Res., vol. 24, no. 6, pp. 1248–1259, 2019, doi: 10.1158/1078-0432.CCR-17-0853.
[5]J. Wandy and R. Daly, “GraphOmics: an interactive platform to explore and integrate multi-omics data,” BMC Bioinformatics, vol. 22, no. 1, pp. 1–19, 2021, doi: 10.1186/s12859-021-04500-1.
[6]M. Tounsi, E. Aram, A. T. Azar, A. Al-Khayyat, and I. K. Ibraheem, “A Comprehensive Review on Biomedical Image Classification using Deep Learning Models,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 1, pp. 19538 – 19545, 2025, doi: 10.48084/etasr. 8728.
[7]M. Yousif and B. Al-Khateeb, “Quantum Deep Learning: A Review,” Iraqi J. Sci., vol. 65, no. 8, pp. 4588–4605, 2024, doi: 10.24996/ijs.2024.65.8.37.
[8]M. Yousif, I. A. Ahmad, A. R. Hmeed, and A. A. Mukhlif, “Enhanced EEG Signal Classification Using Machine Learning and Optimization Algorithm,” Fusion Pract. Appl., vol. 17, no. 2, pp. 211–218, 2025, doi: 10.54216/FPA.170216.
[9]Ayyadevara and V. Kishore, “Gradient Boosting Machine,” Springer, pp. 117–134, 2018, doi: 10.1007/978-1-4842-3564-5.
[10]M. Y. Hasan, D. J. Kadhim, and A. J. Humaidi, “Prediction of electricity consumption and residential bills based on an artificial neural network,” Int. Rev. Appl. Sci. Eng., vol. 16, no. 1, pp. 142 – 152, 2025, doi: 10.1556/1848.2024.00856.
[11]S. M. Al-Barzinji, “Diagnosis of lung cancer disease using machine learning techniques,” Iraqi J. Inf. Technol. V, vol. 8, pp. 110–130, 2018.
[12]A. A. Aldujaili, M. Rosa-Zurera, and M. Utrilla-Manso, “Review of Parkinson’s disease detection with deep learning machines,” Multimed. Tools Appl., vol. 84, no. 6, pp. 3015 – 3051, 2025, doi: 10.1007/s11042-024-20466-7.
[13]K. K. Mujeeb Rahman, M. Nasor, and A. Imran, “Automatic Screening of Diabetic Retinopathy Using Fundus Images and Machine Learning Algorithms,” Diagnostics, vol. 12, no. 9, 2022, doi: 10.3390/diagnostics12092262.
[14]M. S. Al-Ani, Q. Al-Shayea, S. M. Al-Barzinji, D. M. S. Al-Ani, and Z. M. S. Al-Ani, “COVID-19 Diagnosis Applied DWT and CNN on X-ray Chest Images,” UHD J. Sci. Technol., vol. 7, no. 2, pp. 69–76, 2023, doi: 10.21928/uhdjst.v7n2y2023.pp69-76.
[15]A. A. Abdalhameed and A. I. Kadhim, “Molecular Swarm Optimization Analysis of Data Transmission and Recurrent Neural Networks (RNNs) for Attack Prevention in Mobile Ad Hoc Networks (MANETs),” KSII Trans. Internet Inf. Syst., vol. 19, no. 3, pp. 973 – 986, 2025, doi: 10.3837/tiis. 2025.03.014.
[16]S. Pang and X. Yang, “Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification,” Comput. Intell. Neurosci., vol. 2016, 2016, doi: 10.1155/2016/3049632.
[17]A. Ullah, J. Ahmad, K. Muhammad, M. Sajjad, and S. W. Baik, “Action Recognition in Video Sequences using Deep Bi-Directional LSTM with CNN Features,” IEEE Access, vol. 6, pp. 1155–1166, 2017, doi: 10.1109/ACCESS.2017.2778011.
[18]M. Yousif, B. Al-khateeb, and B. Garcia-zapirain, “A New Quantum Circuit of Quantum Convolutional Neural Network for X-Ray Images Classification,” IEEE Access, vol. 12, no. March, 2024.
[19]S. KILICARSLAN, M. CELIK, and Ş. SAHIN, “Hybrid models based on genetic algorithm and deep learning algorithms for nutritional Anemia disease classification,” Biomed. Signal Process. Control, vol. 63, no. November 2019, 2021, doi: 10.1016/j.bspc.2020.102231.
[20]U. Kumar Lilhore et al., “A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameter optimization,” Sci. Rep., vol. 14, no. 1, p. 4299, 2024, doi: 10.1038/s41598-024-54212-8.
[21]A. Mosslah, A. A. Mosslah, R. H. Mahdi, and S. M. Al-barzinji, “Performance Evaluation Of The Deep Learning System For Weed Performance Evaluation Of The Deep Learning System For Weed,” 2023.
[22]R. S. Patil and N. Biradar, “Automated mammogram breast cancer detection using the optimized combination of convolutional and recurrent neural network,” Evol. Intell., vol. 14, no. 4, pp. 1459–1474, 2021, doi: 10.1007/s12065-020-00403-x.
[23]M. A. Mohammed, B. Al-khateeb, M. Yousif, S. A. Mostafa, S. Kadry, and K. H. Abdulkareem, “Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model,” vol. 2022, 2022.
[24]S. Yang, Z. Wang, C. Wang, C. Li, and B. Wang, “Comparative Evaluation of Machine Learning Models for Subtyping Triple-Negative Breast Cancer: A Deep Learning-Based Multi-Omics Data Integration Approach,” J Cancer, vol. 15, pp. 3943–3957, 2024, doi: 10.7150/jca. 93215.
[25]M. Briscik, G. Tazza, M.-A. Dillies, L. Vidács, and S. Dejean, “Supervised Multiple Kernel Learning approaches for multi-omics data integration,” BioData Min., pp. 0–25, 2024, doi: 10.1186/s13040-024-00406-9.
[26]Y. Zhou et al., “Multimodal functional deep learning for multiomics data,” Brief. Bioinform., vol. 25, no. 5, p. bbae448, 2024, doi: 10.1093/bib/bbae448.
[27]L. M. Sanches, P. H. G., de Melo, N. C., Porcari, A. M., & de Carvalho, “Integrating Molecular Perspectives: Strategies for Comprehensive Multi-Omics Integrative Data Analysis and Machine Learning Applications in Transcriptomics, Proteomics, and Metabolomics,” Biology (Basel), vol. 13, no. 11, 2024.
[28]M. Tsagiopoulou and I. G. Gut, “Machine learning and multi-omics data in chronic lymphocytic leukemia: the future of precision medicine?” Front. Genet., vol. 14, no. January, pp. 1–7, 2023, doi: 10.3389/fgene. 2023.1304661.
[29]W. Lan, H. Liao, Q. Chen, L. Zhu, Y. Pan, and Y. P. P. Chen, “DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery,” Brief. Bioinform., vol. 25, no. 3, 2024, doi: 10.1093/bib/bbae185.
[30]E. Hasan, “CANCER DRUG SENSITIVITY THROUGH GENOMIC DATA : INTEGRATING INSIGHTS FOR PERSONALIZED MEDICINE IN THE USA HEALTHCARE SYSTEM,” vol. 06, pp. 36–53, 2024.
[31]A. Mehmood, S. Nawab, Y. Jin, H. Hassan, A. C. Kaushik, and D.-Q. Wei, “Ranking Breast Cancer Drugs and Biomarkers Identification Using Machine Learning and Pharmacogenomics,” ACS Pharmacol. Transl. Sci., vol. 6, no. 3, pp. 399–409, Mar. 2023, doi: 10.1021/acsptsci. 2c00212.
[32]X. Y. Liu and X. Y. Mei, “Prediction of drug sensitivity based on multi-omics data using deep learning and similarity network fusion approaches,” Front. Bioeng. Biotechnol., vol. 11, no. April, pp. 1–12, 2023, doi: 10.3389/fbioe. 2023.1156372.
[33]Y. L. Huang et al., “Organotypic Models for Functional Drug Testing of Human Cancers,” BME Front., vol. 4, p. 22, 2023, doi: 10.34133/bmef. 0022.
[34]L. Pant, A. Al Mukaddim, K. Rahman, and A. A. L. Sayeed, “Genomic predictors of drug sensitivity in cancer : Integrating genomic data for personalized medicine in the USA,” vol. 5, no. 12, pp. 2682–2702, 2024, doi: 10.51594/csitrj.v5i12.1760.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
