CAJ | 학술논문

【目的】利用α-淀粉酶Amy7c及其突变体的氨基酸信息，预测该酶的催化常数（Kcat），并筛选出能预测α-淀粉酶Kcat最具效果的氨基酸属性。【方法】先以20-1前馈反向传播的神经网络为模型，完成535种氨基酸属性对α-淀粉酶 Amy7C及其突变体催化常数的拟合。再将α-淀粉酶 Amy7C及其54个突变体的数据分为2组，用35个酶作为训练组进行拟合，20个酶作为验证组进行检验。最后，对8种不同层次及神经元个数的模型进行比较。【结果】110个氨基酸属性可实现20-1神经网络模型收敛，表明这些氨基酸属性可用于预测α-淀粉酶的催化常数，不同指标的预测效果不同。多模型的分析结果显示，不同模型对训练组R值的结果具有显著性差异，而对训练组P值、验证组R值和验证组P 值结果无显著性差异。【结论】氨基酸分布概率等属性可以用于预测α-淀粉酶催化常数。四层神经网络模型是预测α-淀粉酶催化常数的相对理想的模型。
【목적】이용α-정분매Amy7c급기돌변체적안기산신식，예측해매적최화상수（Kcat），병사선출능예측α-정분매Kcat최구효과적안기산속성。【방법】선이20-1전궤반향전파적신경망락위모형，완성535충안기산속성대α-정분매 Amy7C급기돌변체최화상수적의합。재장α-정분매 Amy7C급기54개돌변체적수거분위2조，용35개매작위훈련조진행의합，20개매작위험증조진행검험。최후，대8충불동층차급신경원개수적모형진행비교。【결과】110개안기산속성가실현20-1신경망락모형수렴，표명저사안기산속성가용우예측α-정분매적최화상수，불동지표적예측효과불동。다모형적분석결과현시，불동모형대훈련조R치적결과구유현저성차이，이대훈련조P치、험증조R치화험증조P 치결과무현저성차이。【결론】안기산분포개솔등속성가이용우예측α-정분매최화상수。사층신경망락모형시예측α-정분매최화상수적상대이상적모형。
Objective]The Kcat ofα-amylase Amy7C and its mutants was predicted using ami-no acid information,and the most suitable amino acid property for predicting Kcat ofα-amyl-ase was selected.[Methods]20-1 feedforward backpropagation neural network was used to screen 535 amino acid properties as predictors to predict the Kcat ofα-amylase Amy7C and its 54 mutants,which were divided into two group,35 of them served as training group for fitting,and the other 20 were treated as validation.Eight models for different layers and numbers of neurons were also compared.[Results]110 amino acid properties,which con-verged during fitting in the 20-1 neural network model,could be used to predict the Kcat. Different amino acid properties presented different predicting effect.The multi-model results showed that there was significant difference between R values in training groups,but there was no significant difference between P values in training groups,as well as R and P values in vali-dation groups.[Conclusion]Some amino acid properties such as distribution probability could be used to predict the Kcat of α-amylase,to which four-layer neural network reveals the rela-tive ideal model.