بهبود تخصیص‌اعتبار قوانین در سیستم دسته‌‌بندیادگیر با یادگیری تقویتی مارکوف برای پیش‌‌بینی ساختار دوم پروتئین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری مهندسی کامپیوتر، واحد میبد، دانشگاه آزاد اسلامی، میبد، ایران.

2 استادیار گروه مهندسی کامپیوتر، واحد میبد، دانشگاه آزاد اسلامی، میبد، ایران

3 استادیار گروه مهندسی کامپیوتر، واحد مرودشت، دانشگاه آزاد اسلامی، مرودشت، ایران.

چکیده

این پژوهش برای افزایش دقت تخصیص‌ اعتبار قوانین در سیستم دسته‌ بند یادگیر با استفاده از یادگیری تقویتی مارکوف جهت پیش‌ بینی ساختار دوم پروتئین ‌است که یادگیری تقویتی مارکوف در سیستم دسته‌ بند یادگیر، جایگزین الگوریتم Bucket Brigade ‌شده‌ است. برای آموزش سیستم از مجموعه دادگان Protein Data Bank استفاده‌‌ می‌شود که شامل پروتئین 4L1W با تعداد نمونه 5741 است که 70 درصد برای آموزش و 30 درصد جهت آزمایش استفاده‌ شده‌ است. پس از آموزش سیستم، تعدادی دسته‌ بند(قوانین) باارزش، تولید‌ می‌شود که در مرحله آزمایش از این قوانین برای پیش‌ بینی ساختار دوم پروتئین استفاده‌ خواهد شد. نتایج آزمایش‌ها نشان‌ می‌دهد دقت سیستم دسته‌‌ بند یادگیر با یادگیری تقویتی مارکوف در نوع ساده و توسعه‌ یافته آن، افزایش‌ یافته‌ است. با استفاده از یادگیری تقویتی مارکوف، ارزش‌گذاری به هر قانون بهبود داده‌ می‌شود، به گونه‌ای که دقت سیستم دسته‌بند ساده %82.5 و سیستم دسته‌بند توسعه یافته %85 بهبود یافته‌ است.

کلیدواژه‌ها

عنوان مقاله [English]

Improving Credit Assignment in a learning classier system with Markov reinforcement learning for protein secondary structure prediction

نویسندگان [English]

  • mohammadreza dehghanimahmoudabadi 1
  • Kamal Mirzaie 2
  • farzad peyravi 3
1 Ph.D. Student of Computer Engineering, Maybod Branch, Islamic Azad University, Maybod, Iran.
2 Department of Computer Engineering, Maybod Branch Islamic Azad University, Maybod, Iran
3 Department of Computer Engineering, Marvdasht Branch, Islamic Azad University, Marvdasht, Iran
چکیده [English]

This research aims to enhance the accuracy of credit assignment for rules in a learning classifier system using Markov Reinforcement Learning for predicting the secondary structure of proteins. Markov Reinforcement Learning has replaced the Bucket Brigade algorithm in the learning classifier system. The Protein Data Bank dataset is utilized to train the system, specifically the protein 4L1W with 5741 samples, where 70% is used for training and 30% for testing purposes. Following the system's training, a set of valuable classifiers (rules) is generated, which will be employed in the testing phase to predict the protein's secondary structure. The experimental results demonstrate an improvement in the accuracy of the Markov Reinforcement Learning classifier system, both in the Learning classifier system and the eXtended classifier system. Through Markov Reinforcement Learning, the credit assignment to each rule is enhanced, resulting in an accuracy improvement of 82.5% for the Learning classifier system and 85% for the eXtended classifier system.

کلیدواژه‌ها [English]

  • Bioinformatics
  • Protein Secondary Structure
  • Learning Classifier System
  • Markov Reinforcement Learning

مراجع

J. Petrie, P. E. Czabotar, and J. M. Murphy, “The Structural Basis of Necroptotic Cell Death Signaling.,” trends Biochem. Sci., vol. 44, no. 1, pp. 53–63, 2019.
G. Krebs, V. Alexandrov, C. A. Wilson, N. Echols, H. Yu, and M. Gerstein, “Normal Mode Analysis of Macromolecular Motions in a Database Framework: Developing Mode Concentration as a Useful Classifying Statistic.,” Proteins, vol. 48, no. 4, pp. 682–695, 2002.
T. Chen and R. Weiss, “Artificial Cell-Cell Communication in Yeast Saccharomyces Cerevisiae Using Signaling Elements from Arabidopsis Thaliana,” Nat. Biotechnol., vol. 23, no. 12, pp. 1551–1555, 2005.
P. Ferreira, T. T. Dorini, F. B. Santos, A. J. S. Machado, and L. T. F. Eleno, “Elastic Anisotropy and Thermal Properties of Extended Linear Chain Compounds MV2Ga4 From ab-initio Calculations,” materialia, vol. 4, pp. 529–539, 2018.
N. Allen, S. Entova, L. C. Ray, and B. Imperiali, “Monotopic Membrane Proteins Join the Fold,” Trends Biochem. Sci., vol. 44, no. 1, pp. 7–20, Jan. 2019.
Sharma et al., “The Health of Things for Classification of Protein Structure Using Improved Grey Wolf Optimization,” J. Supercomput., vol. 76, no. 2, pp. 1226–1241, 2020.
Lan, M. Ye, R. Shao, B. Zhong, P. C. Yuen, and H. Zhou, “Learning Modality-Consistency Feature Templates: A Robust RGB-Infrared Tracking System,” IEEE Trans. Ind. Electron., vol. 66, no. 12, pp. 9887–9897, 2019.
Basith, B. Manavalan, T. H. Shin, and G. Lee, “SDM6A: A Web-Based Integrative Machine-Learning Framework for Predicting 6mA Sites in the Rice Genome,” Mol. Ther. - Nucleic Acids, vol. 18, pp. 131–141, 2019.
A. Toussi and J. Haddadnia, “Improving Protein Secondary Structure Prediction: the Evolutionary Optimized Classification Algorithms,” Struct. Chem., vol. 30, no. 4, pp. 1257–1266, 2019.
W. Wilson, “Classifier ّFitness Based on Accuracy,” Evol. Comput., vol. 3, no. 2, pp. 149–175, 1995.
Drugowitsch, “Design and Analysis of Learning Classifier Systems: A Probabilistic Approach,” Stud. Comput. Intell., p. 268, 2008.
Shankar and S. Louis, “Learning Classifier Systems for User Context Learning,” Congress on Evolutionary Computation, vol. 3. pp. 2069–2075, 2005.
Maiti, A. Hassan, and P. Mitra, “Boosting Phosphorylation Site Prediction with Sequence Feature-Based Machine Learning.,” Proteins, vol. 88, no. 2, pp. 284–291, 2020.
R. Pakraei and K. Mirzaie, “The Introduction of a Heuristic Mutation Operator to Strengthen the Discovery Component of XCS,” J. Adv. Comput. Res., vol. 9, no. 1, pp. 51–70, 2018.
Hua and Z. Sun, “A Novel Method of Protein Secondary Structure Prediction with High Segment Overlap Measure: Support Vector Machine Approach1 1Edited by B. Holland,” J. Mol. Biol., vol. 308, no. 2, pp. 397–407, 2001.
L. Lanzi, “Using Raw Accuracy to Estimate Classifier Fitness in XCS,” Genetic and Evolutionary Computation Conference. pp. 1922–1923, 2003.
Compiani, D. Montanari, and R. Serra, “Learning and Bucket Brigade Dynamics in Classifier Systems,” Phys. d nonlinear Phenom., vol. 42, pp. 202–212, 1990.
L. Young and C. Eccles, “Automatic Construction of Markov Decision Process Models for Multi-Agent Reinforcement Learning,” 2020.
J. Urbanowicz and J. H. Moore, “Learning Classifier Systems: A Complete Introduction, Review, and Roadmap,” J. Artif. Evol. Appl., vol. 2009, pp. 1–25, 2009.
Nakata, T. Kovacs, and K. Takadama, “A Modified XCS Classifier System for Sequence Labeling,” Genetic and Evolutionary Computation Conference. pp. 565–572, 2014.
Wang, M. La Russa, and L. S. Qi, “CRISPR/Cas9 in Genome Editing and Beyond,” Annu. Rev. Biochem., vol. 85, no. 1, pp. 227–264, 2016.
Casillas, B. Carse, and L. Bull, “Fuzzy-XCS: A Michigan Genetic Fuzzy System,” IEEE Trans. Fuzzy Syst., vol. 15, no. 4, pp. 536–550, 2007.
M. Badrabadi and M. Mirzaie, "Relationship between B-factor and average shortest path in the protein structure," Archives of Advances in Biosciences, vol. 5, no.3 2014.
Wardah, M. G. M. Khan, A. Sharma, and M. A. Rashid, “Protein secondary structure prediction using neural networks and deep learning: A review,” Comput. Biol. Chem., vol. 81, pp. 1–8, 2019.
Smolarczyk, I. Roterman, I. Konieczna, and K. Stapor, “Protein Secondary Structure Prediction: A Review of Progress and Directions,” Curr. Bioinform., vol. 15, pp. 90–107, Mar. 2020.
Lyu, Z. Wang, F. Luo, J. Shuai, and Y. Huang, “Protein Secondary Structure Prediction With a Reductive Deep Learning Method.,” Front. Bioeng. Biotechnol., vol. 9, p. 687426, 2021.
L. Young and C. Eccles, "Automatic Construction of Markov Decision Process Models for Multi-Agent Reinforcement Learning," 2020.
Zhang, X.-J. Hu, and S.-X. Lin, “https://www.rcsb.org/structure/4L1W,” visited on 2022, Apr. 16, 2014.
 
پژوهش های نظری و کاربردی هوش ماشینی
دوره 1، شماره 2
آذر 1402
صفحه 92-104

فایل ها

هم رسانی

ارجاع به این مقاله

آمار