International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Transformer Based Gene Expression Signature Prediction for Early Cancer Detection and Classification |
|---|---|
| ABSTRACT | The process of identifying cancer at an early stage followed by its proper identification method leads to enhanced patient survival rates and enables doctors to create suitable treatment strategies. Next-generation sequencing technologies have developed through their technological advancements to produce extensive gene expression data which scientists use to study the molecular patterns associated with different cancer types and cancer progress stages. The combination of high-dimensional gene expression data and limited sample sizes proves to be a major obstacle for both traditional machine learning techniques and deep learning systems. The traditional models need human experts to choose their features but they fail to detect sophisticated gene interactions that scientists require to discover dependable cancer detection biomarkers which work in early stages. We developed a Transformer-Based Gene Expression Signature Prediction model which enables early detection and classification of cancer cases in this research. The framework employs a transformer architecture which contains a multi-head self-attention mechanism to learn gene relationships while it extracts essential gene expression patterns without needing prior feature selection. The system uses genomic data analysis techniques to connect distant genomic information which enables better biomarker detection and more accurate early stage cancer type identification. Our research demonstrates that the transformer-based approach outperforms traditional machine learning and deep learning methods in all evaluation metrics which include accuracy and precision and recall and F1-score. The model decreases misclassification rates while it shows the gene expression patterns that relate to cancer. The research results demonstrate that transformer-based models present a strong method for analyzing gene expression data which enables better early cancer detection results and better support for decision-making purposes |
| AUTHOR | S.T.P.L. VARAPRASAD, B. NAVYA, J. RISHITHA, V. GOWTHAM, G. LOKESH, M. KHAGAPATHI Assistance Professor, Department of CSE(AI&ML), Nadimpalli Satyanarayana Raju Institute of Technology (NSRIT), Vishakhapatnam, India Students, Department of CSE(AL&ML), Nadimpalli Satyanarayana Raju Institute of Technology (NSRIT), Vishakhapatnam, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE. 2026.1403107 |
| pdf/107_Transformer Based Gene Expression Signature Prediction for Early Cancer Detection and Classification.pdf | |
| KEYWORDS | |
| References | [1] World Health Organization, WHO report on cancer: Setting priorities, investing wisely and providing care for all, 2020. [2] Kwang-Hyun Yu and Michael Snyder, “Omics profiling in precision oncology,” Molecular & Cellular Proteomics, vol. 15, no. 8, pp. 2525–2536, 2016. [3] Michael Snyder, Genomics and Personalized Medicine: What Everyone Needs to Know. Oxford University Press, 2016. [4] William D. Travis, Elisabetta Brambilla, and Gregory J. Riely, “New pathologic classification of lung cancer: relevance for clinical practice and clinical trials,” Journal of Clinical Oncology, vol. 31, no. 8, pp. 992–1001, 2013. [5] Stephan C. Schuster, “Next-generation sequencing transforms today's biology,” Nature Methods, vol. 5, no. 1, pp. 16–18, 2008. [6] Douglas Hanahan and Robert A. Weinberg, “Hallmarks of cancer: the next generation,” Cell, vol. 144, no. 5, pp. 646–674, 2011. [7] Andrea Sboner et al., “Molecular sampling of prostate cancer: a dilemma for predicting disease progression,” BMC Medical Genomics, vol. 3, no. 1, 2010. [8] Rafael M. Luque-Baena et al., “Application of genetic algorithms and constructive neural networks for the analysis of microarray cancer data,” Theoretical Biology and Medical Modelling, vol. 11, no. 1, 2014. [9] Arun Natarajan and T. Ravi, “A survey on gene feature selection using microarray data for cancer classification,” International Journal of Computer Science & Communication, vol. 5, no. 1, pp. 126–129, 2014. [10] Nguyen T. Duc et al., “3D deep learning based automatic diagnosis of Alzheimer’s disease with joint MMSE prediction using resting-state fMRI,” Neuroinformatics, vol. 18, no. 1, pp. 71– 86, 2020. [11] Sandeep Dubey et al., “Anomalous event recognition in videos based on joint learning of motion and appearance,” Applied Sciences, vol. 11, no. 3, 2021. [12] Martin Popel et al., “Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals,” Nature Communications, vol. 11, no. 1, 2020. [13] Andre Esteva et al., “Deep learning-enabled medical computer vision,” npj Digital Medicine, vol. 4, no. 1, 2021. [14] Guangyu Liu, Beyond predictive modeling: new computational aspects for deep learningbased biological applications, Massachusetts Institute of Technology, 2020. [15] J. Wu and C. Hicks, “Breast cancer type classification using machine learning,” Journal of Personalized Medicine, vol. 11, no. 2, 2021. [16] Fang Hu et al., “Gene expression classification of lung adenocarcinoma into molecular subtypes,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 17, no. 4, pp. 1187–1197, 2019. [17] S. Tarek et al., “Gene expression based cancer classification,” Egyptian Informatics Journal, vol. 18, no. 3, pp. 151–159, 2017. [18] M. Mostavi et al., “Convolutional neural network models for cancer type prediction based on gene expression,” BMC Medical Genomics, vol. 13, 2020. [19] Keras-vis contributors, “Keras-vis visualization toolkit,” GitHub repository, 2017. [20] G. López-García et al., “Transfer learning with convolutional neural networks for cancer survival prediction using gene-expression data,” PLOS ONE, vol. 15, no. 3, 2020. [21] F. Gao et al., “DeepCC: a novel deep learning-based framework for cancer molecular subtype classification,” Oncogenesis, vol. 8, no. 9, 2019. [22] Amir Beykikhoshk et al., “DeepTRIAGE: interpretable biomarker scores using attention mechanisms for classification of breast cancer subtypes,” BMC Medical Genomics, vol. 13, 2020. [23] M. Bicakci et al., “Metabolic imaging based sub-classification of lung cancer,” IEEE Access, vol. 8, pp. 218470–218476, 2020. [24] J.-H. Chiang and S.-H. Ho, “A combination of rough-based feature selection and RBF neural network for classification using gene expression data,” IEEE Transactions on Nanobioscience, vol. 7, no. 1, pp. 91–99, 2008. [25] Shangqian Liu et al., “Feature selection of gene expression data for cancer classification using double RBF-kernels,” BMC Bioinformatics, vol. 19, 2018. |
