Follow-up of N400 in the Rehabilitation of First-episode Schizophrenia / 中华医学杂志(英文版)

<p><b>BACKGROUND</b>The N400 component of event-related potentials (ERP) has recently drawn widespread attention at home and abroad. This study was to explore the relationship between N400 changes and risperidone treatment and rehabilitation infirst-episode schizophrenia (FES).</p><p><b>METHODS</b>ERP component N400 was recorded by Guangzhou Runjie WJ-1 ERP instruments, in 58 FES before and 6 months, 15 months after risperidone treatment, and in 62 normal controls. The patients' syndromes were assessed by Positive and Negative Syndrome Scale (PANSS). And the stimuli are Chinese sentences with matching (congruent) or mismatching (incongruent) ending words.</p><p><b>RESULTS</b>N400 latencies were prolonged, and amplitudes were decreased in Cz, Pz, Fz, C3, C4, in FES compared with in NC, before treatment. The prolonged N400 latencies and decreased amplitudes were negatively correlated with the patients' positive scale and total scale of PANSS. There are significant differences of N400 amplitudes and latencies in 6 months and 15 months follow-up after treatment. Before treatment, 6 months and 15 months after treatment, N400 latencies are 446 ± 35 ms, 440 ± 37 ms, 414 ± 31 ms (F = 9.72, P < 0.01) in incongruent situation; N400 amplitudes are 5.2 ± 4.6 μV, 5.7 ± 4.8 μV, 7.3 ± 5.0 μV (F = 2.06, P > 0.05) in congruent situation, and 8.5 ± 5.9 μV, 10.1 ± 5.0 μV, 11.9 ± 7.0 μV (F = 3.697, P < 0.05) in incongruent situation.</p><p><b>CONCLUSIONS</b>N400 could be used to predict the effects of treatment of schizophrenia to some degree. The linguistic and cognitive impairment in schizophrenia can be improved by antipsychotic drugs.</p>

A uniform design based PCA-SVM model for predicting optimum pH in chitinase / 生物工程学报

The principal component analysis (PCA) was applied to the data processing in training sets, the new principal components were then used as input data for support vector machine model. A prediction model for optimum pH of chitinase was established based on uniform design. When The regularized constant C, epsilon and Gamma were 10, 0.7 and 0.5 respectively, the calculated pHs fitted the reported optimum pHs of chitinase very well and the MAPEs (Mean Absolute Percent Error) was 3.76%. At the same time, the predicted pHs fitted the reported optimum pHs well and the MAE (Mean Absolute Error) was 0.42 pH unit. It was superior in fittings and predictions compared to the model based on back propagation (BP) neural network.

Molecular docking of Bacillus pumilus xylanase and xylan substrate using computer modeling / 生物工程学报

Bacillus pumilus xylanase was cloned and sequenced. Based on the tertiary structure that originated from homology modeling, the potential active pocket was searched and ligand-protein docking was performed using relative softwares. The information extracted from the molecular docking is analyzed; several amino acid residues might play a vital role in the xylanase catalytic reaction are obtained to instruct the further modification of xylanase directed-evolution.

A prediction model for the activity of insecticidal crystal proteins from Bacillus thuringiensis based on support vector machine / 生物工程学报

A quantitative structure-property relationship (QSPR) model in terms of amino acid composition and the activity of Bacillus thuringiensis insecticidal crystal proteins was established. Support vector machine (SVM) is a novel general machine-learning tool based on the structural risk minimization principle that exhibits good generalization when fault samples are few; it is especially suitable for classification, forecasting, and estimation in cases where small amounts of samples are involved such as fault diagnosis; however, some parameters of SVM are selected based on the experience of the operator, which has led to decreased efficiency of SVM in practical application. The uniform design (UD) method was applied to optimize the running parameters of SVM. It was found that the average accuracy rate approached 73% when the penalty factor was 0.01, the epsilon 0.2, the gamma 0.05, and the range 0.5. The results indicated that UD might be used an effective method to optimize the parameters of SVM and SVM and could be used as an alternative powerful modeling tool for QSPR studies of the activity of Bacillus thuringiensis (Bt) insecticidal crystal proteins. Therefore, a novel method for predicting the insecticidal activity of Bt insecticidal crystal proteins was proposed by the authors of this study.

Application of boosting-based decision tree ensemble classifiers for discrimination of thermophilic and mesophilic proteins / 生物工程学报

In this paper, the Boosting-based decision tree ensemble classifiers were applied to discriminate thermophilic and mesophilic proteins. Three methods, namely, self-consistency test, 5-fold cross-validation and independent testing with other dataset, were used to evaluate the performance and robust of the models. Logitboost, as a novel classifier in Boosting algorithm, performed better than Adaboost. The overall accuracy of the three methods was 100%, 88.4% and 89.5%, respectively. It was demonstrated that LogitBoost performed comparably or even better than that of neural network, a very powerful classifier widely used in biological literatures. The influence of protein size on discrimination was addressed. It is anticipated that the power in predicting many bio-macromolecular attributes will be further strengthened if the Boosting and some other existing algorithms can be effectively complemented with each other.

A study on the discrimination of thermophilic and mesophilic proteins based on dipeptide composition / 生物工程学报

In this work, the dipeptide composition of 3216 thermophilic and 4007 mesophilic protein sequences was systematically analyzed. We found that the thermophilic proteins contained more dipeptides such as EE, EK, KE, VE, EI, KI, EV, KK, VK and IE, whereas less dipeptides such as AA, LL, LA, AL, QA, QL, AQ, LT, TL and EQ. Based on this information, a statistical method for discriminating thermophilic and mesophilic proteins was developed. Our approach correctly picked up the thermophilic proteins with the accuracy of 94.0% and 89%, respectively, for the testing sets of 382 and 73 thermophilic proteins. And for the testing 325 and 73 mesophilic proteins, the accuracy was 85.2% and 89%, respectively. The influence of specific dipeptides on discrimination was also discussed.

A model for amino acid composition and optimum pH in G/11 xylanase based on neural networks / 生物工程学报

In this paper, a prediction model for amino acid composition and optimum pH of xylanase in G/11 family was established in terms of an artificial neural networks based on uniform design. Results showed that the calculated and predicted pHs fitted the optimum pHs of xylanase very well and the MAPEs (Mean mean Absolute Percent Error) were 3.02% and 4.06%, the MSEs (Mean Square Error) were 0.19 and 0.19 pH unit, the MAE (Mean Absolute Error) were 0.11 and 0.19 pH unit, respectively. It was better in fittings and predictions compared with the reported model based on stepwise regression.

A study on the pattern recognition of thermophilic and mesophilic proteins / 生物工程学报

Pattern recognition of thermophilic and mesophilic proteins were studied through principle component analysis, partial least-square regression and BP neural network. The results showed that the fitting accuracy of the three methods was 92%, 95% and 98%, respectively. And the forecasting accuracy was 60%, 72.5% and 72.5%, respectively. The best forecasting accuracy for thermophilic proteins was 75%, and for mesophilic proteins was 85%. A mathematical model was established and the biological meaning of it was expatiated on, a new method to discriminate the thermophilic and mesophilic proteins based on their sequences was established here.