Varyant Etki Tahmininde Makine Öğrenmesi Yöntemlerinin Kullanımına Yönelik Bibliyometrik Bir Analiz

Öz

İnsan genomunda oluşan varyantların fenotip üzerindeki etkisinin tahmin edilmesinde yapay zeka, makine öğrenmesi ve derin öğrenme gibi hesaplamalı yöntemlerin kullanıldığı çalışmalar son zamanlarda giderek artmıştır. Bu çalışmanın amacı bibliyometrik yöntem kullanılarak varyant etki tahmininde makine öğrenmesi yöntemlerinin kullanıldığı bilimsel araştırmalara genel bir bakış sunmaktır. Bu amaç doğrultusunda çalışmada ilgili literatüre ulaşmak için Web of Science Core Collection (WoSCC) veritabanı kullanılmıştır. Ülkeler, kurumlar, yazarlar, dergiler, alıntılar ve anahtar kelimeler R-Studio programında “bibliometrix” kütüphanesi kullanılarak analiz edilmiştir. Yapılan analiz sonucunda göre varyant etki tahmininde makine öğrenmesi yöntemlerinin kullanımına ilişkin yapılan bilimsel yayınların son yıllarda popülerliğinin giderek arttığı ve bu artıştaki en büyük payın United States’te yer alan kurumların China, Germany, England ve Australia ile ortak araştırmalara bağlı olduğu görülmüştür. Bu alanda yayın üretimindeki araştırmacılara bakıldığında Majid Masso ve Yuedong Yang tarafından yapılan yayınların uzun bir zamana yayıldığı, son birkaç yıldır yapılan yayınlardaki araştırmacılara bakıldığında ise Yongguo Liu, Yun Zhang, Haicang Zhang ve Jiajing Zhu’nun ön plana çıktığı görülmektedir. En çok atıf alan yazarın ise Jian Zhou (1.116) olduğu görülmüştür. Son yıllarda bu alandaki yayınlarda artan bir eğilim olmasına rağmen yine de eski yayınlara daha çok atıf yapıldığı belirlenmiştir. Dolayısıyla bu alanda halen daha araştırma yapılmasına, uluslararası işbirliğinin ve iletişimin güçlendirilmesine ve deneyim kazanılarak literatür kalitesinin arttırılmasına ihtiyaç duyulduğu ortaya çıkmıştır.

Anahtar Kelimeler

• Bibliyometrik analiz
• Bibliometrix
• Varyant etki tahmini
• Makine öğrenmesi

A Bibliometric Analysis of the Use of Machine Learning Methods in Variant Effect Prediction

Öz

Studies using computational methods such as artificial intelligence, machine learning and deep learning to predict the effect of variants occurring in the human genome on the phenotype have increased recently. The aim of this study is to provide an overview of scientific research using machine learning methods in variant effect prediction using the bibliometric method. For this purpose, the Web of Science Core Collection (WoSCC) database was used to access the relevant literature in the study. Countries, institutions, authors, journals, quotations and keywords were analyzed using the "bibliometrix" library in the R-Studio program. As a result of the analysis, it has been seen that the popularity of scientific publications on the use of machine learning methods in variant effect prediction has increased in recent years, and the largest share of this increase is due to joint research by institutions in the United States with China, Germany, England and Australia. In the publication production in this field, it can be seen that the publications made by researchers Majid Masso and Yuedong Yang have spread over a long period of time, and when looking at the publications made in the last few years, researchers Yongguo Liu, Yun Zhang, Haicang Zhang and Jiajing Zhu come to the fore. It was observed that the most cited author was researcher Jian Zhou (1.116). Although there has been an increasing trend in publications in this field in recent years, it has been determined that older publications are still cited more. Therefore, it has become clear that there is still a need to conduct further research in this field, to strengthen international cooperation and communication, and to increase the quality of the literature by gaining experience.

Anahtar Kelimeler

• Bibliometric Analysis
• Bibliometrix
• Variant Effect Prediction
• Machine Learning

Kaynakça

1. Almagro Armenteros JJ., Sønderby CK., Sønderby SK., Nielsen H., Winther O. DeepLoc: prediction of protein subcellular localization using deep learning. Bioinformatics 2017; 33(21): 3387-3395.
2. Angermueller C., Pärnamaa T., Parts L., Stegle O. Deep learning for computational biology. Molecular Systems Biology 2016; 12(7): 878-894.
3. Aria M., Cuccurullo C. bibliometrix: An R-tool for comprehensive science mapping analysis. Journal of Informetrics 2017; 11(4): 959-975.
4. Bromberg Y., Prabakaran R., Kabir A., Shehu A. Variant effect prediction in the age of machine learning. Cold Spring Harbor Perspectives in Biology 2024; 16(7): a041467.
5. Donthu N., Kumar S., Mukherjee D., Pandey N., Lim WM. How to conduct a bibliometric analysis: An overview and guidelines. J. Bus. Res. 2021; 133: 285-296.
6. Fidanoğlu P., Belder N., Erdoğan B., İlk Ö., Rajabli F., Özdağ H. Genom projeleri 5N1H: Ne, nerede, ne zaman, nasıl, neden ve hangi popülasyonda? Türk Hijyen ve Deneysel Biyoloji Dergisi 2013; 71(1): 45-60.
7. Frazer J., Notin P., Dias M., Gomez A., Min JK., Brock K., Gal Y., Marks DS. Disease variant prediction with deep generative models of evolutionary data. Nature 2021; 599(7883): 91-95.
8. Horne J., Shukla D. Recent advances in machine learning variant effect prediction tools for protein engineering. Industrial and Engineering Chemistry Research 2022; 61(19): 6235-6245.

9. Ionita-Laza I., Mccallum K., Xu B., Buxbaum JD. A spectral approach integrating functional genomic annotations for coding and noncoding variants. Nature Genetics 2016; 48(2): 214–220.
10. Jiang T., Fang L., Wang K. Deciphering the language of nature: A transformer-based language model for deleterious mutations in proteins. The Innovation 2021; 4(5).
11. Li MX., Gui HS., Kwan JSH., Bao S.Y, Sham PC. A comprehensive framework for prioritizing variants in exome sequencing studies of Mendelian diseases. Nucleic Acids Research 2012; 40(7): e53.
12. Livesey BJ., Marsh JA. Advancing variant effect prediction using protein language models. Nature Genetics 2023; 55(9): 1426-1427.
13. Mahmood K, Jung CH., Philip G., Georgeson P., Chung J., Pope BJ., Park DJ. Variant effect prediction tools assessed using independent, functional assay-based datasets: Implications for discovery and diagnostics. Human Genomics 2017; 11: 1–8.
14. Niroula A., Vihinen M. Variation interpretation predictors: Principles, types, performance, and choice. Human Mutation 2016; 37(6): 579–597.
15. Niroula A., Vihinen M. How good are pathogenicity predictors in detecting benign variants? PLoS Computational Biology 2019; 15: 1–17.
16. Qi H., Zhang H., Zhao Y., Chen C., Long JJ., Chung WK., Guan Y., Shen Y. MVP predicts the pathogenicity of missense variants by deep learning. Nature Communications 2021; 12(1): 510.
17. Qiu J., Nechaev D., Rost B. Protein-protein and protein-nucleic acid binding residues are important for common and rare sequence variants in human. BMC Bioinformatics 2020; 21: 452.
18. Qu H., Fang X. A brief review on the human encyclopedia of DNA elements (ENCODE) project. Genomics Proteomics Bioinformatics 2013; 11(3): 135–141.
19. Rentzsch P., Schubach M., Shendure J., Kircher M. CADD-Splice-improving genome-wide variant effect prediction using deep learning-derived splice scores. Genome Medicine 2021; 13: 1-12.
20. Riesselman AJ., Ingraham JB., Marks DS. Deep generative models of genetic variation capture the effects of mutations. Nature Methods 2018; 15(10): 816-822.
21. Tang H., Thomas PD. Tools for predicting the functional impact of nonsynonymous genetic variation. Genetics 2016; 203(2): 635–647.
22. The ENCODE Project Consortium. Identification and analysis of functional elements in 1% of the human genome by the ENCODE pilot project. Nature 2007; 447: 799-816.
23. The International HapMap Consortium. The international HapMap project. Nature 2003; 426: 789-796.
24. The 1000 Genomes Project Consortium. A map of human genome variation from population scale sequencing. Nature 2010; 467: 1061-1073.
25. Xu F., Guo G., Zhu F., Tan X., Fan L. Protein deep profile and model predictions for identifying the causal genes of male infertility based on deep learning. Information Fusion 2021; 75: 70-89.
26. Zhou J., Troyanskaya OG. Predicting effects of noncoding variants with deep learning–based sequence model. Nature Methods 2015; 12(10): 931-934.