换一批PERISCOPE-Opt: Machine learning-based prediction of optimal fermentation conditions and yields of recombinant periplasmic protein expressed in <i>Escherichia coli</i>.
第一单位：
Chemical Engineering Discipline, School of Engineering, Monash University Malaysia, Jalan Lagoon Selatan, 47500 Bandar Sunway, Malaysia.
作者：
关键词
AUC, area under the curveCV, cross-validationCfsSubsetEval, Correlation-based Forward Selection Subset EvaluatorClassifierSubsetEval, Classifier Subset EvaluatorE. coli, Escherichia coliEscherichia coliFC1, Feature Category 1FC2, Feature Category 2FC3, Feature Category 3FC4, Feature Category 4IPTG, isopropyl β-D-1-thiogalactopyranosideLOOCV, Leave-one-out cross-validationMAE, mean absolute errorMCC, Mathew correlation coefficientML, machine learningMLR, machine learning in RMachine learningOD, optical density at 600 nmOptimizationPCC, Pearson correlation coefficientPeriplasmic expressionPrediction modelRF, random forestRFR, RF regressionRFR-High, RFR for highRFR-Medium, RFR for mediumRMSE, root mean squared errorRPP, Recombinant protein productionRSM, response surface methodologyRecombinant protein productionSMOTE, Synthetic Minority Over-sampling TechniqueSP, signal peptidesSVM, support vector machinesSVR, SVM regressionSVR-Low, SVR for class: "low"XGB, XGBoostpI, isoelectric point
DOI
10.1016/j.csbj.2022.06.006
PMID
35765650
发布时间
2022-07-16
- 浏览2
相似文献
- 中文期刊
- 外文期刊
- 学位论文
- 会议论文
