Prediction of solubility of lysozyme in lysozyme-NaCl-H2O system with artificial neural network

Xiangping Zhang; Suojiang Zhang; Xuezhong He

doi:10.1016/j.jcrysgro.2003.12.038

Prediction of solubility of lysozyme in lysozyme-NaCl-H₂O system with artificial neural network

Xiangping Zhang, Suojiang Zhang^*, Xuezhong He

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

27 Scopus citations

Abstract

Modeling and prediction of protein solubility is a key to developing the protein crystal growth and crystallization process. In this paper a back propagation network was used for predicting the solubility of protein in lysozyme-NaCl-H₂O system. It was found that properly selected and trained neural network could fairly represent the dependence of protein solubility on the pH, salt concentration, and temperature. The RMSD (root mean square deviation) for prediction of the solubility of lysozyme in lysozyme-NaCl-H₂O system was 0.07% by the artificial neural network (ANN) method, which is better than that of with thermodynamic models. The ANNs have been proven to be an effective tool for correlation and prediction of protein solubility in protein-salt-water system.

Original language	English
Pages (from-to)	409-416
Number of pages	8
Journal	Journal of Crystal Growth
Volume	264
Issue number	1-3
DOIs	https://doi.org/10.1016/j.jcrysgro.2003.12.038
State	Published - 15 Mar 2004
Externally published	Yes

Keywords

A1. Prediction
A1. Solubility
B1. Artificial neural network
B1. Lysozyme B1. Protein

Access to Document

10.1016/j.jcrysgro.2003.12.038

Cite this

@article{b46728a806ab4d2db60886d769143a82,

title = "Prediction of solubility of lysozyme in lysozyme-NaCl-H2O system with artificial neural network",

abstract = "Modeling and prediction of protein solubility is a key to developing the protein crystal growth and crystallization process. In this paper a back propagation network was used for predicting the solubility of protein in lysozyme-NaCl-H2O system. It was found that properly selected and trained neural network could fairly represent the dependence of protein solubility on the pH, salt concentration, and temperature. The RMSD (root mean square deviation) for prediction of the solubility of lysozyme in lysozyme-NaCl-H2O system was 0.07% by the artificial neural network (ANN) method, which is better than that of with thermodynamic models. The ANNs have been proven to be an effective tool for correlation and prediction of protein solubility in protein-salt-water system.",

keywords = "A1. Prediction, A1. Solubility, B1. Artificial neural network, B1. Lysozyme B1. Protein",

author = "Xiangping Zhang and Suojiang Zhang and Xuezhong He",

note = "Funding Information: This work was supported by National Scientific Funding of China (NSFC) (No. 20276073), and Postdoctoral Funding of Wangkuancheng, Chinese Academy of Sciences. ",

year = "2004",

month = mar,

day = "15",

doi = "10.1016/j.jcrysgro.2003.12.038",

language = "英语",

volume = "264",

pages = "409--416",

journal = "Journal of Crystal Growth",

issn = "0022-0248",

publisher = "Elsevier",

number = "1-3",

}

TY - JOUR

T1 - Prediction of solubility of lysozyme in lysozyme-NaCl-H2O system with artificial neural network

AU - Zhang, Xiangping

AU - Zhang, Suojiang

AU - He, Xuezhong

N1 - Funding Information: This work was supported by National Scientific Funding of China (NSFC) (No. 20276073), and Postdoctoral Funding of Wangkuancheng, Chinese Academy of Sciences.

PY - 2004/3/15

Y1 - 2004/3/15

N2 - Modeling and prediction of protein solubility is a key to developing the protein crystal growth and crystallization process. In this paper a back propagation network was used for predicting the solubility of protein in lysozyme-NaCl-H2O system. It was found that properly selected and trained neural network could fairly represent the dependence of protein solubility on the pH, salt concentration, and temperature. The RMSD (root mean square deviation) for prediction of the solubility of lysozyme in lysozyme-NaCl-H2O system was 0.07% by the artificial neural network (ANN) method, which is better than that of with thermodynamic models. The ANNs have been proven to be an effective tool for correlation and prediction of protein solubility in protein-salt-water system.

AB - Modeling and prediction of protein solubility is a key to developing the protein crystal growth and crystallization process. In this paper a back propagation network was used for predicting the solubility of protein in lysozyme-NaCl-H2O system. It was found that properly selected and trained neural network could fairly represent the dependence of protein solubility on the pH, salt concentration, and temperature. The RMSD (root mean square deviation) for prediction of the solubility of lysozyme in lysozyme-NaCl-H2O system was 0.07% by the artificial neural network (ANN) method, which is better than that of with thermodynamic models. The ANNs have been proven to be an effective tool for correlation and prediction of protein solubility in protein-salt-water system.

KW - A1. Prediction

KW - A1. Solubility

KW - B1. Artificial neural network

KW - B1. Lysozyme B1. Protein

UR - http://www.scopus.com/inward/record.url?scp=1342306639&partnerID=8YFLogxK

U2 - 10.1016/j.jcrysgro.2003.12.038

DO - 10.1016/j.jcrysgro.2003.12.038

M3 - 文章

AN - SCOPUS:1342306639

SN - 0022-0248

VL - 264

SP - 409

EP - 416

JO - Journal of Crystal Growth

JF - Journal of Crystal Growth

IS - 1-3

ER -

Prediction of solubility of lysozyme in lysozyme-NaCl-H₂O system with artificial neural network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this