Abstract
We have studied the ability of three types of neural networks to predict the closeness of a given protein model to the native structure associated with its sequence. We show that a partial combination of the Levenberg–Marquardt algorithm and the back-propagation algorithm produced the best results, giving the lowest error and largest Pearson correlation coefficient. We also find, as previous studies, that adding associative memory to a neural network improves its performance. Additionally, we find that the hybrid method we propose was the most robust in the sense that other configurations of it experienced less decline in comparison to the other methods. We find that the hybrid networks also undergo more fluctuations on the path to convergence. We propose that these fluctuations allow for better sampling. Overall we find it may be beneficial to treat different parts of a neural network with varied computational approaches during optimization.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cheng J, Tegge AN, Baldi P (2008) Machine learning methods for protein structure prediction. IEEE Rev Biomed Eng 1:41–49
Jain P, Garibaldi JM, Hirst JD (2009) Supervised machine learning algorithms for protein structure classification. Comput Biol Chem 33(3):216–223
Faraggi E, Kloczkowski, A (2014) A global machine learning based scoring function for protein structure prediction. Proteins Struct Funct Bioinf 82(5):752–759
Lima AN, Philot EA, Trossini GHG, Scott LPB, Maltarollo VG, Honorio KM (2016) Use of machine learning approaches for novel drug discovery. Expert Opin Drug Discov 11(3):225–239
Baldi P (2018). Deep learning in biomedical data science. Annu Rev Biomed Data Sci 1:181–205
Zhang Y, Skolnick J (2004) Scoring function for automated assessment of protein structure template quality. Proteins Struct Funct Bioinf 57(4):702–710
Zhang Y, Skolnick J (2005) Tm-align: a protein structure alignment algorithm based on the tm-score. Nucleic Acids Res 33(7):2302–2309
Xu J, Zhang Y (2010) How significant is a protein structure similarity with tm-score= 0.5? Bioinformatics 26(7):889–895
Faraggi E, Zhou Y, Kloczkowski A (2014) Accurate single-sequence prediction of solvent accessible surface area using local and global features. Proteins Struct Funct Bioinf 82(11):3170–3176
Chakravarty S, Varadarajan R (1999) Residue depth: a novel parameter for the analysis of protein structure and stability. Structure 7(7):723–732
Tan KP, Varadarajan R, Madhusudhan MS (2011) Depth: a web server to compute depth and predict small-molecule binding cavities in proteins. Nucleic Acids Res 39(suppl_2):W242–W248
Berman HM, Westbrook J, Feng Z, Gilliland G, Bhat TN, Weissig H, Shindyalov IN, Bourne PE (2000) The protein data bank. Nucleic Acids Res 28(1):235–242
Berman H, Henrick K, Nakamura H (2003) Announcing the worldwide protein data bank. Nat Struct Mol Biol 10(12):980
Faraggi E, Kloczkowski, A (2015) Genn: a general neural network for learning tabulated data with examples from protein structure prediction. In: Artificial neural networks. Springer, Berlin, pp 165–178
Elman JL (1990) Finding structure in time. Cogn Sci 14(2):179–211
Baldi P, Pollastri G, Andersen CAF, Brunak S (2000) Matching protein beta-sheet partners by feedforward and recurrent neural networks. In: Proceedings of the 2000 conference on intelligent systems for molecular biology (ISMB00), La Jolla. AAAI Press, Palo Alto, pp 25–36
Pollastri G, Baldi P, Fariselli P, Casadio R (2001) Improved prediction of the number of residue contacts in proteins by recurrent neural networks. Bioinformatics 17(suppl_1):S234–S242
Guler NF, Ubeyli ED, Guler I (2005) Recurrent neural networks employing Lyapunov exponents for EEG signals classification. Expert Syst Appl 29(3):506–514
Hagan MT, Menhaj MB (1994) Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993
Wilamowski BM, Iplikci S, Kaynak O, Efe MO (2001). An algorithm for fast convergence in training neural networks. In: IJCNN’01. International joint conference on neural networks, proceedings (Cat. No. 01CH37222), vol 3. IEEE, Piscataway, pp 1778–1782
Moré JJ (1978) The Levenberg-Marquardt algorithm: implementation and theory. In: Numerical analysis. Springer, Berlin, pp 105–116
Battiti R (1992) First-and second-order methods for learning: between steepest descent and newton’s method. Neural Comput 4(2):141–166
Lourakis MLA, Argyros AA (2005) Is Levenberg-Marquardt the most efficient optimization algorithm for implementing bundle adjustment? In: Tenth IEEE international conference on computer vision (ICCV’05) volume 1, vol 2. IEEE, Piscataway, pp 1526–1531
Suratgar AA, Tavakoli MB, Hoseinabadi A (2007) Modified Levenberg-Marquardt method for neural networks training. Int J Comput Inf Eng 1(6):1745–1747
Moult J, Fidelis K, Kryshtafovych A, Schwede T, Tramontano A (2016) Critical assessment of methods of protein structure prediction: progress and new directions in round xi. Proteins Struct Funct Bioinf 84:4–14
Samudrala R, Levitt M (2000) Decoys 2̆018r2̆019us: a database of incorrect conformations to improve protein structure prediction. Protein Sci 9(7):1399–1401
Faraggi E, Xue B, Zhou Y (2009) Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network. Proteins Struct Funct Bioinf 74(4):847–856
Faraggi E, Yang Y, Zhang S, Zhou Y (2009) Predicting continuous local structure and the effect of its substitution for secondary structure in fragment-free protein structure prediction. Structure 17(11):1515–1527
Faraggi E, Zhang T, Yang Y, Kurgan L, Zhou Y (2012) Spine x: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles. J Comput Chem 33(3):259–267
Acknowledgements
This work was funded in part by a National Science Foundation grant DBI 1661391, and National Institutes of Health grants R01 GM127701 and R01 GM127701-01S1. Additional support provided by the Lilly Endowment, Inc., through its support for the Indiana University Pervasive Technology Institute, and through the National Science Foundation under Grant No. CNS-0521433.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Science+Business Media, LLC, part of Springer Nature
About this protocol
Cite this protocol
Faraggi, E., Jernigan, R.L., Kloczkowski, A. (2021). A Hybrid Levenberg–Marquardt Algorithm on a Recursive Neural Network for Scoring Protein Models. In: Cartwright, H. (eds) Artificial Neural Networks. Methods in Molecular Biology, vol 2190. Humana, New York, NY. https://doi.org/10.1007/978-1-0716-0826-5_15
Download citation
DOI: https://doi.org/10.1007/978-1-0716-0826-5_15
Published:
Publisher Name: Humana, New York, NY
Print ISBN: 978-1-0716-0825-8
Online ISBN: 978-1-0716-0826-5
eBook Packages: Springer Protocols