iRSC-PseAAC:Predicting Redox-sensitive Cysteine Sites in Proteins Based on Effective Dimension Reduction Algorithm LDA
10.13865/j.cnki.cjbmb.2024.06.1122
- VernacularTitle:iRSC-PseAAC:基于有效降维算法LDA预测蛋白质中的氧化还原敏感半胱氨酸位点
- Author:
Xin WEI
1
;
Chun-Sheng LIU
;
Zhe LV
;
Gang LIN
;
Si-Qin HU
;
Jian-Hua JIA
Author Information
1. 江西服装学院商学院数理统计教研室,南昌 330201
- Keywords:
redox-sensitive cysteine(RSC);
feature extraction;
word embedding;
linear discriminant analysis;
machine learning
- From:
Chinese Journal of Biochemistry and Molecular Biology
2024;40(7):1009-1016
- CountryChina
- Language:Chinese
-
Abstract:
Redox-sensitive cysteine(RSC)thiol plays an important role in many biological processes such as photosynthesis,cellular metabolism,and transcription.Therefore,it is necessary to identify red-ox-sensitive cysteine accurately.However,traditional redox-sensitive cysteine identification is very ex-pensive and time-consuming.At present,there is an urgent need for a mathematical calculation method to identify sequence information and redox-sensitive cysteines quickly and accurately.Here,we devel-oped an effective predictor called iRSC-PseAAC,which used the dimension reduction algorithm LDA combined with the support vector machine to predict redox-sensitive cysteine sites.In the cross-validation results,the specificity(Sp),sensitivity(Sn),accuracy(Acc)and Matthews correlation coefficient(MCC)were 0.841,0.868,0.859 and 0.692 respectively.In the independent dataset results,the Sp,Sn,Acc and MCC were 0.906,0.882,0.890 and 0.767 respectively.compared with existing prediction methods,iRSC-PseAAC had obvious improvement effect.The method proposed for this study can also be used for many problems in computational proteomics.
