Prediction of xylanase optimal temperature by support vector regression

Background: Support vector machine (SVM), a novel powerful machine learning technology, was used to develop the non-linear quantitative structure-property relationship (QSPR) model of the G/11 xylanase based on the amino acid composition. The uniform design (UD) method was applied to optimize the running parameters of SVM for the first time. Results: Results showed that the predicted optimum temperature of leave-one-out (LOO) cross-validation fitted the experimental optimum temperature very well, when the running parameter C, ξ, and γ was 50, 0.001 and 1.5, respectively. The average root-mean-square errors (RMSE) of the LOO cross-validation were 9.53ºC, while the RMSE of the back propagation neural network (BPNN), was 11.55ºC. The predictive ability of SVM is a minor improvement over BPNN, but it is superior to the reported method based on stepwise regression. Two experimental examples proved the validation of the model for predicting the optimal temperature of xylanase. Conclusion: The results indicated that UD might be an effective method to optimize the parameters of SVM, which could be used as an alternative powerful modeling tool for QSPR studies of xylanase.

Codon optimization of 1, 3-propanediol oxidoreductase expression in escherichia coli and enzymatic properties

The gene dhaT from Klebsiella pneumoniae encoding 1,3-propanediol oxidoreductase (PDOR) was de novo synthesized by splicing overlap extension polymerase chain reaction (SOE-PCR) primarily according to Escherichia coli’s codon usage, as well as mRNA secondary structure. After optimization, Codon Adaptation Index (CAI) value was improved from 0.75 to 0.83, meanwhile energy of mRNA secondary structure was increased from -400.1 to -86.8 kcal/mol. This synthetic DNA was under control by phage T7 promoter in the expression vector pET-15b and transformed into the E. coli BL21 (DE3) strain. Inducers such as isopropyl beta-D-thiogalactoside (IPTG) and lactose were compared by activity at different inducing time. The activity of PDOR after codon optimized was 385.4 +/- 3.6 U/mL, which was almost 5-fold higher than wild type (82.3 +/- 1.5 U/ml) under the flask culture at 25ºC for 10 hrs. Then his-tagged enzyme was separated by using Ni-IDA column. The favorite environment for enzyme activity was at 5°C and pH 10.0, PDOR showed a certainly stability in potassium carbonate buffer for 2 hrs at diverse temperatures, enzyme activity was significantly improved by Mn2+.