This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Garima Mathur,
Nikhlesh Pathik,
Priyanshu Pathekar*,
- Associate Professor, Department of Computer Science and Engineering, Sagar Institute of Science and Technology (SISTec), Bhopal, Madhya Pradesh, India
- Associate Professor, Department of Computer Science and Engineering (CSE), Sagar Institute of Science and Technology (SISTec), Bhopal, Madhya Pradesh, India
- Junior Research Fellow, Department of Computer Science and Engineering (CSE), Sagar Institute of Science and Technology (SISTec), Bhopal, Madhya Pradesh, India
Abstract
The identification of genetic variants, tracing of disease-associated mutations, and the reconstruction of evolutionary relationships from raw sequence data are all achieved by the analysis of DNA sequence. The FASTA format is plain text and is an easy-to-read format, which is why it has endured four decades of the field’s growth into bioinformatics. Classical alignment programs like BLAST and Smith-Waterman work well with small data sets, but are limited by O(nm) efficiency when using gigabases or petabases. In many classification problems, machine learning avoids the need for pairwise alignment. This paper proposes Weighted Positional Frequency Matrix (WPFM), an entropy-driven feature representation system along with a transformer encoder to classify a sequence based on a FASTA database. The model is tested on 47 benchmark datasets covering 2.3 × 10⁹ base pairs and achieves MCC = 0.847 and 94.7% accuracy, which are 8.3 percentage points better than the standard PWM for the promoter prediction task. The improvement is not a statistical artefact as confirmed by a paired McNemar test (p < 0.01). An ablation study is conducted to isolate the contribution of the WPFM entropy weighting, positional encoding and attention mechanism to this gain, by using a component-wise ablation design.
Keywords: DNA Sequence Analysis, FASTA Format, Machine Learning, Transformer, WPFM, Bioinformatics.
References
[1] Asim MN, Ibrahim MA, Zaib A, Dengel A. DNA sequence analysis landscape: a comprehensive review of DNA sequence analysis task types, databases, datasets, word embedding methods, and language models. Frontiers in Medicine. 2025 Apr 8;12:1503229.
[2] Nerkar V, Kimbahune V. Deep learning approaches in genomic analysis: A review of DNA sequence classification techniques. International Journal of Scientific Research & Engineering Trends. 2024;10(2):439-45.
[3] Nasir MU, Gollapalli M, Zubair M, Saleem MA, Mehmood S, Khan MA, Mosavi A. Advance genome disorder prediction model empowered with deep learning. IEEE Access. 2022 Jun 29;10:70317-28.
[4] Dip SA, Shuvo UA, Chau T, Song H, Choi P, Wang X, Zhang L. PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model. bioRxiv. 2024 Jun 22:2024-06.
[5] Sadad T, Aurangzeb RA, Safran M, Imran, Alfarhood S, Kim J. Classification of highly divergent viruses from DNA/RNA sequence using transformer-based models. Biomedicines. 2023 Apr 28;11(5):1323.
[6] Kanna SR, Murthy MY, Gawali MB, Rubai SM, Reddy NS, Brammya G, Preetha NN. A deep learning-based disease diagnosis with intrusion detection for a secured healthcare system. Knowledge and Information Systems. 2024 Sep;66(9):5669-707.
[7] Wekesa JS, Kimwele M. A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment. Frontiers in genetics. 2023 Jul 20;14:1199087.
[8] Salloum SA, Alomari KM, Salloum A. DNA sequence classification for diabetes mellitus using NuSVC and XGBoost: A comparative. Plos one. 2025 Jul 18;20(7):e0328253.
[9] Abhadionmhen AO, Asogwa CN, Ezema ME, Nzeh RC, Ezeora NJ, Abhadiomhen SE, Echezona SC, Udanor CN. Machine learning approaches for microorganism identification, virulence assessment, and antimicrobial susceptibility evaluation using DNA sequencing methods: a systematic review. Molecular Biotechnology. 2025 Nov;67(11):4038-66.
[10] Roman-Naranjo P, Parra-Perez AM, Lopez-Escamez JA. A systematic review on machine learning approaches in the diagnosis and prognosis of rare genetic diseases. Journal of biomedical informatics. 2023 Jul 1;143:104429.
[11] Gunasekaran H, Ramalakshmi K, Rex Macedo Arokiaraj A, Deepa Kanmani S, Venkatesan C, Suresh Gnana Dhas C. Analysis of DNA sequence classification using CNN and hybrid models. Computational and Mathematical Methods in Medicine. 2021;2021(1):1835056.
[12] Bhumika C, Nayak P, Janapati R, Srijampana VG, Trivedi V. Interpretable Multi-Task Learning Framework for DNA Intelligence. In2025 OITS International Conference on Information Technology (OCIT) 2025 Dec 18 (pp. 425-431). IEEE.
[13] Mathur G, Pandey A, Goyal S. A review on blockchain for DNA sequence: security issues, application in DNA classification, challenges and future trends. Multimedia Tools and Applications. 2024 Jan;83(2):5813-35.
[14] Cruz D, Almeida JR, Silva JM, Oliveira JL. SecureFASTA: Ensuring privacy and trust when sharing genomic data. In2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS) 2023 Jun 22 (pp. 173-178). IEEE.
[15] Dedeturk BA, Soran A, Bakir-Gungor B. Blockchain for genomics and healthcare: a literature review, current status, classification and open issues. PeerJ. 2021 Sep 30;9:e12130.
[16] Bathula A, Gupta SK, Merugu S, Saba L, Khanna NN, Laird JR, Sanagala SS, Singh R, Garg D, Fouda MM, Suri JS. Blockchain, artificial intelligence, and healthcare: the tripod of future—a narrative review. Artificial Intelligence Review. 2024 Aug 8;57(9):238.
[17] Abbas SR, Abbas Z, Zahir A, Lee SW. Advancing genome-based precision medicine: A review on machine learning applications for rare genetic disorders. Briefings in Bioinformatics. 2025 Jul;26(4):bbaf329.
[18] Bhosale YH, Patnaik KS. Bio-medical imaging (X-ray, CT, ultrasound, ECG), genome sequences applications of deep neural network and machine learning in diagnosis, detection, classification, and segmentation of COVID-19: a Meta-analysis & systematic review. Multimedia Tools and Applications. 2023 Oct;82(25):39157-210.
[19] Lee SJ, Rho M. Multimodal deep learning applied to classify healthy and disease states of human microbiome. Scientific reports. 2022 Jan 17;12(1):824.
[20] Logeshwaran J, Adhikari N, Joshi SS, Saxena P, Sharma A. The deep DNA machine learning model to classify the tumor genome of patients with tumor sequencing. International Journal of Health Sciences. 2022 Jul;6(S5):9364-75.
[21] Ramji B, Bhukya R. Extended Early Disease Predicting Futures with Advanced Mutation Detection Analysis and Modeling by Using DNA Sequencing Techniques. In2025 12th International Conference on Emerging Trends in Engineering & Technology-Signal and Information Processing (ICETET-SIP) 2025 Aug 1 (pp. 1-6). IEEE.
[22] Sravanthi J, Bhukya R. Predicting Disease Futures with Advanced mutation detection Analysis and Predictive Modeling by using DNA sequences. In2025 6th International Conference on Recent Advances in Information Technology (RAIT) 2025 Mar 6 (pp. 1-6). IEEE.
[23] Mathur G, Pandey A, Goyal S. A comprehensive tool for rapid and accurate prediction of disease using DNA sequence classifier: G. Mathur et al. Journal of Ambient Intelligence and Humanized Computing. 2023 Oct;14(10):13869-85.
[24] Famuji TS, Grancho B, Fanani GP, Talirongan H, Sumantri RB. A Thirdweb-Based smart contract framework for secure sharing of human genetic data on the ethereum blockchain. Scientific Journal of Engineering Research. 2025 Jun 24;1(3):109-19.
[25] Guo X, Khalid MA, Domingos I, Michala AL, Adriko M, Rowel C, Ajambo D, Garrett A, Kar S, Yan X, Reboud J. Smartphone-based DNA diagnostics for malaria detection using deep learning for local decision support and blockchain technology for security. Nature Electronics. 2021 Aug;4(8):615-24.
[26] Jin XL, Zhang M, Zhou Z, Yu X. Application of a blockchain platform to manage and secure personal genomic data: a case study of LifeCODE. ai in China. Journal of medical Internet research. 2019 Sep 10;21(9):e13587.
[27] Mohamed HG, Alrowais F, Al-Wesabi FN, Duhayyim MA, Hilal AM, Motwakel A. Blockchain enabled deep learning model with modified coati optimization for sustainable healthcare disease detection and classification. Scientific Reports. 2025 Jul 1;15(1):21058.
[28] Bhardwaj T, Sumangali K. An explainable federated blockchain framework with privacy- preserving AI optimization for securing healthcare data. Scientific reports. 2025 Jul 1;15(1):21799.
[29] Hai T, Sarkar A, Aksoy M, Karmakar R, Manna S, Prasad A. Elevating security and disease forecasting in smart healthcare through artificial neural synchronized federated learning. Cluster Computing. 2024 Sep;27(6):7889-914.
[30] Shammi SA, Ghosh P, Sutradhar A, Shamrat FJ, Moni MA, De Oliveira TE. Advances in artificial intelligence and blockchain technologies for early detection of human diseases. IEEE Transactions on Computational Social Systems. 2024 Sep 24;12(1):210-37.
| Volume | 04 | |
| 02 | ||
| Received | 22/07/2026 | |
| Accepted | 06/10/2026 | |
| Published | 16/10/2026 | |
| Publication Time | 86 Days |