Develop machine learning-based regression predictive models for engineering protein solubility
Tóm tắt
Protein activity is a significant characteristic for recombinant proteins which can be used as biocatalysts. High activity of proteins reduces the cost of biocatalysts. A model that can predict protein activity from amino acid sequence is highly desired, as it aids experimental improvement of proteins. However, only limited data for protein activity are currently available, which prevents the development of such models. Since protein activity and solubility are correlated for some proteins, the publicly available solubility dataset may be adopted to develop models that can predict protein solubility from sequence. The models could serve as a tool to indirectly predict protein activity from sequence. In literature, predicting protein solubility from sequence has been intensively explored, but the predicted solubility represented in binary values from all the developed models was not suitable for guiding experimental designs to improve protein solubility. Here we propose new machine learning (ML) models for improving protein solubility in vivo.
We first implemented a novel approach that predicted protein solubility in continuous numerical values instead of binary ones. After combining it with various ML algorithms, we achieved a R2 of 0.4115 when support vector machine algorithm was used. Continuous values of solubility are more meaningful in protein engineering, as they enable researchers to choose proteins with higher predicted solubility for experimental validation, while binary values fail to distinguish proteins with the same value—there are only two possible values so many proteins have the same one.
We present the ML workflow as a series of IPython notebooks hosted on GitHub (https://github.com/xiaomizhou616/protein_solubility). The workflow can be used as a template for analysis of other expression and solubility datasets.
Supplementary data are available at Bioinformatics online.
Từ khóa
Tài liệu tham khảo
Agostini, 2012, Sequence-based prediction of protein solubility, J. Mol. Biol, 421, 237, 10.1016/j.jmb.2011.12.005
Arjovsky, 2017, Wasserstein GAN, arXiv Preprint arXiv, 1701, 07875
Chan, 2010, Learning to predict expression efficacy of vectors in recombinant protein production, BMC Bioinform, 11, S21., 10.1186/1471-2105-11-S1-S21
Christendat, 2000, Structural proteomics of an archaeon, Nat. Struct. Mol. Biol, 7, 903, 10.1038/82823
Diaz, 2010, Prediction of protein solubility in Escherichia coli using logistic regression, Biotechnol. Bioeng, 105, 374, 10.1002/bit.22537
Fang, 2013, Discrimination of soluble and aggregation-prone proteins based on sequence information, Mol. Biosyst, 9, 806, 10.1039/c3mb70033j
Goh, 2004, Mining the structural genomics pipeline: identification of protein properties that affect high-throughput experimental analysis, J. Mol. Biol, 336, 115, 10.1016/j.jmb.2003.11.053
Goodfellow, 2014, Generative adversarial nets, Advances in Neural Information Processing Systems, Montreal, Canada, 2672
Gulrajani, 2017, Improved training of Wasserstein GANs, arXiv Preprint arXiv, 00028
Gupta, 2018, Feedback GAN (FBGAN) for DNA: a novel feedback-loop architecture for optimizing protein functions, arXiv Preprint arXiv, 01694
Hirose, 2011, Statistical analysis of features associated with protein expression/solubility in an in vivo Escherichia coli expression system and a wheat germ cell-free expression system, J. Biochem, 150, 73, 10.1093/jb/mvr042
Hirose, 2013, ESPRESSO: a system for estimating protein expression and solubility in protein expression systems, Proteomics, 13, 1444, 10.1002/pmic.201200175
Huang, 2012
Idicula-Thomas, 2006, A support vector machine-based method for predicting the propensity of a protein to be soluble or to form inclusion body on overexpression in Escherichia coli, Bioinformatics, 22, 278, 10.1093/bioinformatics/bti810
Idicula-Thomas, 2005, Understanding the relationship between the primary structure of proteins and its propensity to be soluble on overexpression in Escherichia coli, Protein Sci, 14, 582, 10.1110/ps.041009005
Kitagawa, 2005, Complete set of ORF clones of Escherichia coli ASKA library (a complete set of E. coli K-12 ORF archive): unique resources for biological research, DNA Res, 12, 291, 10.1093/dnares/dsi012
Magnan, 2009, SOLpro: accurate sequence-based prediction of protein solubility, Bioinformatics, 25, 2200, 10.1093/bioinformatics/btp386
Mirza, 2014, Conditional generative adversarial nets, arXiv Preprint arXiv, 1784
Niwa, 2009, Bimodal protein solubility distribution revealed by an aggregation analysis of the entire ensemble of Escherichia coli proteins, Proc. Natl. Acad. Sci. USA, 106, 4201, 10.1073/pnas.0811922106
Qi, 2018
Rawi, 2017, PaRSnIP: sequence-based protein solubility prediction using gradient boosting machine, Bioinformatics, 34, 1092, 10.1093/bioinformatics/btx662
Rumelhart, 1985
Samak, 2012
Smialowski, 2012, PROSO II–a new method for protein solubility prediction, FEBS J, 279, 2192, 10.1111/j.1742-4658.2012.08603.x
Smialowski, 2007, Protein solubility: sequence based prediction and experimental verification, Bioinformatics, 23, 2536, 10.1093/bioinformatics/btl623
Stiglic, 2012, Comprehensive decision tree models in bioinformatics, PLoS One, 7, e33812., 10.1371/journal.pone.0033812
Wilkinson, 1991, Predicting the solubility of recombinant proteins in Escherichia coli, Nat. Biotechnol, 9, 443., 10.1038/nbt0591-443
Xiao, 2014, Protr: protein sequence descriptor calculation and similarity computation with R, R Package Version, 0.2
Xiaohui, 2014, Predicting the protein solubility by integrating chaos games representation and entropy in information theory, Expert Syst. Appl, 41, 1672, 10.1016/j.eswa.2013.08.064