Guangya Zhang

Predicting the cofactors of oxidoreductases based on amino acid composition distribution and Chou's amphiphilic pseudo-amino acid composition

Predicting the cofactors of oxidoreductases plays an important role in inferring their catalytic mechanism. Feature extraction is a critical part in the prediction systems, requiring raw sequence data to be transformed into appropriate numerical feature vectors while minimizing information loss. In this paper, we present an amino acid composition distribution method for extracting useful features from primary sequence, and the k-nearest neighbor was used as the classifier. The overall prediction accuracy evaluated by the 10-fold cross-validation reached 90.74%. Comparing our method with other eight feature extraction methods, the improvement of the overall prediction accuracy ranged from 3.49% to 15.74%. Our experimental results confirm that the method we proposed is very useful and may be used for other bioinformatical predictions. Interestingly, when features extracted by our method and Chous amphiphilic pseudo-amino acid composition were combined, the overall accuracy could reach 92.53%.

Predicting Lipase Types by Improved Chous Pseudo-Amino Acid Composition

By proposing a improved Chous pseudo amino acid composition approach to extract the features of the sequences, a powerful predictor based on k-nearest neighbor was introduced to identify the types of lipases according to their sequences. To avoid redundancy and bias, demonstrations were performed on a dataset where none of the proteins has > or =25% sequence identity to any other. The overall success rate thus obtained by the 10-fold cross-validation test was over 90%, indicating that the improved Chous pseudo amino acid composition might be a useful tool for extracting the features of protein sequences, or at lease can play a complementary role to many of the other existing approaches.

Support vector machine for discrimination of thermophilic and mesophilic proteins based on amino acid composition.

The identification of the thermostability from the amino acid sequence information would be helpful in computational screening for thermostable proteins. We have developed a method to discriminate thermophilic and mesophilic proteins based on support vector machines. Using self-consistency validation, 5-fold cross-validation and independent testing procedure with other datasets, this module achieved overall accuracy of 94.2%, 90.5% and 92.4%, respectively. The performance of this SVM-based module was better than the classifiers built using alternative machine learning and statistical algorithms including artificial neural networks, Bayesian statistics, and decision trees, when evaluated using these three validation methods. The influence of protein size on prediction accuracy was also addressed.

RETRACTED: Identifying halophilic proteins based on random forests with preprocessing of the pseudo-amino acid composition

This article has been retracted: please see Elsevier Policy on Article Withdrawal (http://www.elsevier.com/locate/withdrawalpolicy). This article has been retracted at the request of the authors. When using the resampling method to preprocess the raw data of the paper used, some of the types of the proteins (i.e., the HI, HO and NP) were changed; thus, the predicting accuracy cannot reflect the real results. This means the effectiveness of resampling methods in this article gives false results. The Publisher apologizes for any inconvenience this may cause.

A novel method for simultaneous purification and immobilization of a xylanase-lichenase chimera via SpyTag/SpyCatcher spontaneous reaction

We generated a bifunctional enzyme chimera containing the xylanase and lichenase coupled with SpyTag between them. Meanwhile, we generated another chimera containing SpyCatcher and elastin-like polypeptides (ELPs). As ELPs could bond to the xylanase-lichenase chimera through SpyTag/SpyCatcher spontaneous reaction in mild condition, which would lead to the formation of a 3-arm star multifunctional chimera. We purified the xylanase-lichenase by the non-chromatographic purification tag of ELPs. Interestingly, 57.5% of the xylanase and 47.2% of the lichenase in chimera self-assembled into insoluble active particles during the process of purification, which could serve as immobilized bifunctional enzymes. Notably, the immobilized chimera xylanase-lichenase showed a remarkable stability even after 10 reaction cycles, which retained around 56% (lichenase) and 44% (xylanase) of their initial activities, respectively. Moreover, the enhanced thermostability of the immobilized enzymes was also achieved. After incubating at 60u202f°C for 60u202fmin, the residual activity of the immobilized lichenase was 35%, while the free one was only 24%. Unexpectedly, the free xylanase almost lost its activity when incubated at 55u202f°C for 60u202fmin, whereas the immobilized xylanase retained 10% of its activity. However, the catalytic efficiency (kcat/Km) of the free xylanase was 1.7-fold higher than the immobilized one, while the free lichenase was 1.1-fold higher than the immobilized one. This is among the first known reports that two enzymes are purified and immobilized in one-step. This novel strategy is easy to scale up and may meet the demands of biofuel industry. It would have great potentials in other biotechnological fields, such as the multifunctional biomaterials systems.