SavedAdd your journal

Journals / Türk Biyokimya Dergisi / 2017 / Cilt: 42 - Sayı: 2

Comparison of two inference approaches in Gaussian graphical models

Gaussian grafiksel modelinde iki tahmin yaklaşımının karşılaştırılması

Vilda PURUTÇUOĞLU
Ernst WİT
Ezgi AYYILDIZ
Pages
203–211
Publication Date
2022-11-05
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The analyses are conducted by Monte Carlo runs under different dimensional systems.Results: The results indicate that the TGD algorithm is more accurate than the glasso method in all selected criteria, whereas, it is more computationally demanding than this method too.Discussion and conclusion: Therefore, in high dimensional systems, we recommend glasso for its computational efficiency in spite of its loss in accuracy and we believe than the computational cost of the TGD algorithm can be improved by suggesting alternative steps in inference of the network

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Introduction: The Gaussian Graphical Model (GGM) is one of the well-known probabilistic models which is based on the conditional independency of nodes in the biological system.
📊
Key Findings & Data:Here, we compare the estimates of the GGM parameters by the graphical lasso (glasso) method and the threshold gradient descent (TGD) algorithm.Methods: We evaluate the performance of both techniques via certain measures such as specificity, F-measure and AUC (area under the curve).
💡
Conclusion & Impact:The analyses are conducted by Monte Carlo runs under different dimensional systems.Results: The results indicate that the TGD algorithm is more accurate than the glasso method in all selected criteria, whereas, it is more computationally demanding than this method too.Discussion and conclusion: Therefore, in high dimensional systems, we recommend glasso for its computational efficiency in spite of its loss in accuracy and we believe than the computational cost of the TGD algorithm can be improved by suggesting alternative steps in inference of the network
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Introduction: The Gaussian Graphical Model (GGM) is one of the well-known probabilistic models which is based on the conditional independency of nodes in the biological system. Here, we compare the estimates of the GGM parameters by the graphical lasso (glasso) method and the threshold gradient descent (TGD) algorithm.Methods: We evaluate the performance of both techniques via certain measures such as specificity, F-measure and AUC (area under the curve). The analyses are conducted by Monte Carlo runs under different dimensional systems.Results: The results indicate that the TGD algorithm is more accurate than the glasso method in all selected criteria, whereas, it is more computationally demanding than this method too.Discussion and conclusion: Therefore, in high dimensional systems, we recommend glasso for its computational efficiency in spite of its loss in accuracy and we believe than the computational cost of the TGD algorithm can be improved by suggesting alternative steps in inference of the network

Özet

Giriş ve amaç: Gaussian grafiksel modeli (GGM), biyolojik sistemde düğümlerin koşullu bağımsızlığına dayanan, en çok bilinen olasılık modellerinden biridir. Bu çalışmada, GGM'in parametre tahminlerini grafiksel lasso metodu ve eşik meyil iniş algoritması kullanarak karşılaştırmaktayız.Yöntem ve gereçler: Her iki tekniğin performanslarını belirginlik, F-ölçüsü ve AUC (eğri altında kalan alan) ölçüleri kullanarak değerlendirmekteyiz. Analizler, Monte Carlo simulasyonları ile farklı boyutlardaki sistemler kullanılarak yapılmıştır.Bulgular: Sonuçlar TGD algoritmasının, seçilen bütün kriterler için glasso yöntemine göre daha doğru sonuçlar verdiğini, buna karşın, hesaplama süresi açısından da glasso'ya göre daha uzun zaman gerektirdiğini göstermektedir.Tartişma ve sonuç: Bu nedenle, büyük boyutlu sistemlerde, doğruluktan kaybetmesine rağmen, glasso'yu hesaplamadaki hızından dolayı tavsiye etmekteyiz ve inanıyoruz ki TGD algoritmasının hesaplama maliyeti, sistemin tahmininde, alternatif basamaklar önerilerek iyileştirilebilir

🔖

Cite This Article

PURUTÇUOĞLU, V., WİT, E., AYYILDIZ, E. (2022). Comparison of two inference approaches in Gaussian graphical models. Türk Biyokimya Dergisi, Cilt: 42 - Sayı: 2, 203–211. https://ajindex.com/articles/611345

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (20)

  1. Bower JM, Bolouri H. Computational modeling genetic and biochemical networks. Cambridge, Massachusetts: Institute of Technology Press, 2001
  2. Strimmer K, Schafer J. A shrinkage approach to large-scale covariance matrix estimation and implication for functional genomics. Stat Appl Genet Mol Biol 2005;4:Article 32
  3. Meinshausen N, Bühlmann P. High dimensional graphs and variable selection with the lasso. Ann Stat 2006;34:1436–62
  4. Friedman JH, Hastie T, Tibshirani R. Sparse inverse covariance estimation with the graphical lasso. Biostatistics 2008;9:432–41
  5. Whittaker J. Graphical models in applied multivariate statistics. New York: John Wiley and Sons, 1990
  6. Witten D, Friedman J, Simon N. New insights and faster computations for the graphical lasso. J Comput Graph Stat 2011;20:892–900
  7. Tibshirani R. Regression shrinkage and selection via the lasso. J Royal Stat Soc 1996;58:267–88
  8. Goeman JJ. L1 - Penalized estimation in the cox proportional hazards model. Biometrical J 2010;52:70–84
  9. Banerjee O, Ghaoui L, D’Aspremont A. Model selection through sparse maximum likelihood estimation. J Mach Learn Res 2008;9:485–516
  10. Fan J, Li R. Variable selection via nonconcave penalized likelihood and its oracle properties. J Am Stat Assoc 2001;96:1348–60
  11. Zou H. The adaptive lasso and its oracle properties. J Am Stat Assoc 2006;101:1418–29
  12. Tibshirani R, Saunders M, Rosset S, Zhu J, Knight K. Sparsity and smoothness via the fused lasso. J Royal Stat Soc 2005;67:91–108
  13. Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc 2005;67(Part 2):301–20
  14. Efron B, Hastie T, Johnstone I, Tibshirani R. Least angle regression. Ann Stat 2004;32:407–99
  15. Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning: prediction, inference and data mining, 2nd ed. New York: Springer-Verlag, 2009
  16. Wit E, Vinciotti V, Purutçuoğlu V. Statistics for biological networks. 25th International Biometric Conference Short Course Notes, Florianopolis, Brazil. 2010
  17. Friedman JH, Popescu BE. Gradient directed regularization. Technical Report, Stanford University, 2004
  18. Barabasi AL, Oltvai, ZN. Network biology: understanding the cell’s functional organization. Nat Rev Genet 2004;5:101–13
  19. Ayyıldız, E. Gaussian graphical approaches in estimation of biological systems. Master Thesis, Graduate School of Natural and Applied Sciences, Department of Statistics, METU, Ankara, Turkey, 2013
  20. Shuai K, Li