Yeni Bir DNA Sınıflandırma Deneyi: Kolmogorov-Arnold Ağları ile İnsan Maymun Çiçeği DNA-Motifleri için Mekânsal Transkriptomik Analizi

Abstract

Mekânsal Transkriptomik (ST), bir doku veya organizmanın farklı bölgelerindeki gen ifade modellerini anlamak için güçlü bir araç olarak ortaya çıkmıştır. Hastalık araştırmaları ve yeni tedavilerin geliştirilmesi için çok önemlidir. Bir doku lamının belirli, lokalize alanlarında gen ifadesinin ölçülmesine izin verir, ancak bunu sınırlı verimle yapar. Bununla birlikte, ST teknolojileri tarafından üretilen veriler karakteristik olarak gürültülü, yüksek boyutlu, seyrek ve çok modludur; histolojik görüntüler ve sayım matrisleri gibi unsurları kapsar. ST verilerini analiz etmek için genellikle geleneksel istatistiksel veya makine öğrenimi tekniklerine dayanan mevcut yöntemlerin, ölçek, çok modluluk ve uzamsal çözünürlük, hassasiyet ve gen kapsamı dahil olmak üzere uzamsal olarak çözülmüş verilerin doğal sınırlamaları gibi zorluklar nedeniyle birçok durumda yetersiz olduğu kanıtlanmıştır. Bu özel zorlukların üstesinden gelmek için araştırmacılar derin öğrenme tabanlı modellere yönelmiştir. Bu çalışmada, maymun çiçeği transkriptomik örneğinin bölgesel kökenini tahmin etmek için son teknoloji ürünü bir derin öğrenme modeli olan Kolmogorov-Arnold Ağlarını (KAN'lar) kullanarak transkriptomik analizine yeni bir yaklaşım sunuyoruz. KAN'ların karmaşık, doğrusal olmayan işlevleri öğrenme ve temsil etme yeteneğinden yararlanarak, gen ifadesinin karmaşık uzamsal modellerini ortaya çıkarmayı ve altta yatan biyolojik süreçler hakkında içgörü kazanmayı amaçlıyoruz. Çalışmanın analizi Amerika ve Asya olmak üzere iki farklı bölgeye odaklanmakta ve KAN tabanlı bir sınıflandırıcı kullanmaktadır. Sonuçlar, Amerika bölgesi için 0,45 hassasiyet ve 0,93 geri çağırma ile KAN'ların bu bağlamda umut verici performansını göstermektedir, bu da bu bölgeden örnekleri doğru bir şekilde tanımlama konusunda güçlü bir yeteneğe işaret etmektedir. Bulgular, DNA motiflerinden maymun çiçeğinin bölgesel transkriptomunun tahmin edilmesinin filogenetik analizler için görüntü tabanlı taramayı kolaylaştırabileceğini göstermektedir.

Keywords

• Mekânsal Transkriptomik
• Kolmogorov-Arnold Ağları
• Derin Öğrenme
• Gen Örüntüleri
• Bölgesel Sınıflandırma

A Novel DNA Classification Experiment: Spatial Transcriptomics analysis for human Monkeypox DNA-Motifs with Kolmogorov–Arnold Networks

Abstract

Spatial Transcriptomics(ST) has emerged as a powerful tool for understanding gene expression patterns across different regions of a tissue or organism. It is crucial for disease research and developing new therapies. It allows for the measurement of gene expression across specific, localized areas of a tissue slide, though it does so with limited throughput. Yet, the data produced by ST technologies are characteristically noisy, high-dimensional, sparse, and multi-modal, encompassing elements like histological images and count matrices. Existing methods for analyzing ST data, which often rely on traditional statistical or machine learning techniques, have proven inadequate in many cases due to challenges like scale, multi-modality, and the inherent limitations of spatially-resolved data, including spatial resolution, sensitivity, and gene coverage. To address these specific challenges, researchers have turned to deep learning-based models. In this study, we present a novel approach to transcriptomics analysis using Kolmogorov-Arnold Networks (KANs), a state-of-the-art deep learning model to predict regional origin of monkeypox transcriptomic sample. By leveraging the ability of KANs to learn and represent complex, non-linear functions, we aim to uncover intricate spatial patterns of gene expression and gain insights into the underlying biological processes. Study’s analysis focuses on two distinct regions, America and Asia, and employs a KAN-based classifier. The results demonstrate the promising performance of KANs in this context, with a precision of 0.45 and a recall of 0.93 for the America region, indicating a strong ability to correctly identify samples from this region. Findings indicate that predicting the regional transcriptome of monkeypox from DNA motifs could facilitate image-based screening for phylogenetic analyses.

Keywords

• Deep Learning
• Gene Expression Patterns
• Regional Classification
• Spatial Transcriptomics
• Kolmogorov-Arnold Networks

References

1. [1] H. Park et al., “Spatial Transcriptomics: Technical Aspects of Recent Developments and Their Applications in Neuroscience and Cancer Research,” Adv. Sci., vol. 10, no. 16, p. 2206939, Jun. 2023, doi: 10.1002/advs.202206939.
2. [2] A. A. Heydari and S. S. Sindi, “Deep learning in spatial transcriptomics: Learning from the next next-generation sequencing,” Biophys. Rev., vol. 4, no. 1, p. 011306, Mar. 2023, doi: 10.1063/5.0091135.
3. [3] D. F. Miyagishima et al., “157 Identifying Spatial Transcriptomics Signaling Networks in Human Glioblastoma Using Graph-Based Machine Learning,” Neurosurgery, vol. 69, no. Supplement_1, pp. 42–42, Apr. 2023, doi: 10.1227/neu.0000000000002375_157.
4. [4] I. Covert, R. Gala, T. Wang, K. Svoboda, U. Sümbül, and S.-I. Lee, “Predictive and robust gene selection for spatial transcriptomics,” Nat. Commun., vol. 14, no. 1, p. 2091, Apr. 2023, doi: 10.1038/s41467-023-37392-1.
5. [5] A. J. Lee, R. Cahill, and R. Abbasi-Asl, “Machine Learning for Uncovering Biological Insights in Spatial Transcriptomics Data,” 2023, doi: 10.48550/ARXIV.2303.16725.
6. [6] Z. Qiu, S. Li, M. Luo, S. Zhu, Z. Wang, and Y. Jiang, “Detection of differentially expressed genes in spatial transcriptomics data by spatial analysis of spatial transcriptomics: A novel method based on spatial statistics,” Front. Neurosci., vol. 16, p. 1086168, Nov. 2022, doi: 10.3389/fnins.2022.1086168.
7. [7] F. Qin, X. Luo, B. Cai, F. Xiao, and G. Cai, “Spatial pattern and differential expression analysis with spatial transcriptomic data,” Jul. 09, 2023. doi: 10.1101/2023.07.06.547967.
8. [8] A. Robles-Remacho*, R. M. Sanchez-Martin, and J. J. Diaz-Mochon*, “Spatial Transcriptomics: Emerging Technologies in Tissue Gene Expression Profiling,” Apr. 28, 2023. doi: 10.26434/chemrxiv-2023-n20f0.

9. [9] M. Zahmatyar et al., “Human monkeypox: history, presentations, transmission, epidemiology, diagnosis, treatment, and prevention,” Front. Med., vol. 10, p. 1157670, Jul. 2023, doi: 10.3389/fmed.2023.1157670.
10. [10] Y. Li, S. Stanojevic, and L. X. Garmire, “Emerging artificial intelligence applications in Spatial Transcriptomics analysis,” Comput. Struct. Biotechnol. J., vol. 20, pp. 2895–2908, 2022, doi: 10.1016/j.csbj.2022.05.056.
11. [11] M. M. Ahsan et al., “Deep transfer learning approaches for Monkeypox disease diagnosis,” Expert Syst. Appl., vol. 216, p. 119483, Apr. 2023, doi: 10.1016/j.eswa.2022.119483.
12. [12] O. Attallah, “MonDiaL-CAD: Monkeypox diagnosis via selected hybrid CNNs unified with feature selection and ensemble learning,” Digit. Health, vol. 9, p. 205520762311800, Jan. 2023, doi: 10.1177/20552076231180054.
13. [13] F. Yasmin et al., “PoxNet22: A Fine-Tuned Model for the Classification of Monkeypox Disease Using Transfer Learning,” IEEE Access, vol. 11, pp. 24053–24076, 2023, doi: 10.1109/ACCESS.2023.3253868.
14. [14] R. Olusegun, T. Oladunni, H. Audu, Y. Houkpati, and S. Bengesi, “Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach,” IEEE Access, vol. 11, pp. 49882–49894, 2023, doi: 10.1109/ACCESS.2023.3277868.
15. [15] M. Altun, H. Gürüler, O. Özkaraca, F. Khan, J. Khan, and Y. Lee, “Monkeypox Detection Using CNN with Transfer Learning,” Sensors, vol. 23, no. 4, p. 1783, Feb. 2023, doi: 10.3390/s23041783.
16. [16] A. H. Thieme et al., “A deep-learning algorithm to classify skin lesions from mpox virus infection,” Nat. Med., vol. 29, no. 3, pp. 738–747, Mar. 2023, doi: 10.1038/s41591-023-02225-7.
17. [17] R. Pramanik, B. Banerjee, G. Efimenko, D. Kaplun, and R. Sarkar, “Monkeypox detection from skin lesion images using an amalgamation of CNN models aided with Beta function-based normalization scheme,” PLOS ONE, vol. 18, no. 4, p. e0281815, Apr. 2023, doi: 10.1371/journal.pone.0281815.
18. [18] V. H. Sahin, I. Oztel, and G. Yolcu Oztel, “Human Monkeypox Classification from Skin Lesion Images with Deep Pre-trained Network using Mobile Application,” J. Med. Syst., vol. 46, no. 11, p. 79, Oct. 2022, doi: 10.1007/s10916-022-01863-7.
19. [19] J. Gao et al., “Monkeypox outbreaks in the context of the COVID-19 pandemic: Network and clustering analyses of global risks and modified SEIR prediction of epidemic trends,” Front. Public Health, vol. 11, p. 1052946, Jan. 2023, doi: 10.3389/fpubh.2023.1052946.
20. [20] Y. Shu and J. McCauley, “GISAID: Global initiative on sharing all influenza data – from vision to reality,” Eurosurveillance, vol. 22, no. 13, Mar. 2017, doi: 10.2807/1560-7917.ES.2017.22.13.30494.
21. [21] E. L. Hatcher et al., “Virus Variation Resource – improved response to emergent viral outbreaks,” Nucleic Acids Res., vol. 45, no. D1, pp. D482–D490, Jan. 2017, doi: 10.1093/nar/gkw1065.
22. [22] W. R. Pearson and D. J. Lipman, “Improved tools for biological sequence comparison.,” Proc. Natl. Acad. Sci., vol. 85, no. 8, pp. 2444–2448, Apr. 1988, doi: 10.1073/pnas.85.8.2444.
23. [23] W. S. Klug, M. R. Cummings, C. A. Spencer, M. A. Palladino, and D. J. Killian, Essentials of genetics, Tenth edition. Hoboken, NJ: Pearson, 2020.
24. [24] A. N. Kolmogorov, “On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition,” presented at the Doklady Akademii Nauk, Russian Academy of Sciences, 1957, pp. 953–956.
25. [25] Z. Liu et al., “KAN: Kolmogorov-Arnold Networks,” ArXiv Prepr. ArXiv240419756, 2024.
26. [26] E. Waisberg et al., “Transfer learning as an AI-based solution to address limited datasets in space medicine,” Life Sci. Space Res., vol. 36, pp. 36–38, Feb. 2023, doi: 10.1016/j.lssr.2022.12.002.
27. [27] L. Jin, C. Qu, Y. Zhang, C. Fan, Z. Zhu, and S. Liu, “Transfer Learning on Trial: A Case Study to Apply Existing Models to Heterogeneous Datasets,” in 2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA), Beihai, China: IEEE, Mar. 2023, pp. 292–296. doi: 10.1109/PRMVIA58252.2023.00054.
28. [28] K. Combs, H. Lu, and T. J. Bihl, “Transfer Learning and Analogical Inference: A Critical Comparison of Algorithms, Methods, and Applications,” Algorithms, vol. 16, no. 3, p. 146, Mar. 2023, doi: 10.3390/a16030146.
29. [29] J. Wang and Y. Chen, “From Machine Learning to Transfer Learning,” in Introduction to Transfer Learning, in Machine Learning: Foundations, Methodologies, and Applications. , Singapore: Springer Nature Singapore, 2023, pp. 39–52. doi: 10.1007/978-981-19-7584-4_2.
30. [30] A. H. Ali, M. G. Yaseen, M. Aljanabi, S. A. Abed, and C. Gpt, “Transfer Learning: A New Promising Techniques,” Mesopotamian J. Big Data, pp. 29–30, Feb. 2023, doi: 10.58496/MJBD/2023/004.
31. [31] Z. Wu and I. Savidis, “Transfer Learning for Reuse of Analog Circuit Sizing Models Across Technology Nodes,” in 2022 IEEE International Symposium on Circuits and Systems (ISCAS), Austin, TX, USA: IEEE, May 2022, pp. 1033–1037. doi: 10.1109/ISCAS48785.2022.9937457.