Identification of thermophilic proteins by incorporating evolutionary and acid dissociation information into Chou's general pseudo amino acid composition

A Method for Prediction of Thermophilic Protein Based on Reduced Amino Acids and Mixed Features

“…Notably, our method got the highest accuracy values based on the results of the MRMD methods, which denotes our proposed method outperformed the method described by Lin (Lin and Chen, 2011). Additionally, the performance of the proposed method was better than the effects described by Fan et al (2016) too, suggesting that the proposed method could be a state-of-the-art model in current research.…”

“…Our method was also compared with the results of Lin (Lin and Chen, 2011) and the method of using the same dataset (Fan et al, 2016). The results are shown in Figure 2D.…”

“…Proteins denature when the environmental temperature increases dramatically (Tang et al, 2017). However, thermophiles can survive in temperatures ranging from 41 • C to 122 • C (Takai et al, 2008;Fan et al, 2016) and produce enzymes that react well at higher environmental temperatures, such as 120 • C (Fan et al, 2016). In enzyme engineering, identifying the functional mechanisms of these proteins will provide insights into the design and optimization of enzymes (Tang et al, 2017).…”

“…Lin et al constructed a dataset containing 915 thermophilic proteins and 793 non-thermophilic proteins, and predicted 93.8% thermophilic proteins and 92.7% nonthermophilic proteins using SVM. The same conclusion was also reached by Nakariyakul et al (2012), who obtained 93.3% identification accuracy in the same database used by Lin. In another study, Fan et al (2016) integrated information on the amino acid composition, evolution information, and acid dissociation constant to identify thermophiles by SVM, yielding an overall accuracy of 93.53%. Modarres et al (2018) proposed a new thermophilic protein database, which contained 14 million protein sequences.…”

Improving enzyme optimum temperature prediction with resampling strategies and ensemble learning

“…Accordingly, many tools have been developed over the past two decades to predict the enzyme melting temperature (Tm), 1-3 the change in thermodynamic stability (∆∆G) upon point mutations, [4][5][6][7][8][9][10][11][12] or the optimal growth temperature (OGT) of the source organism. [13][14][15][16][17][18][19][20][21] Unfortunately, for prediction purposes, higher OGT or thermal stability do not necessarily indicate substantial catalytic activity at high temperatures. 22,23 Hence, a tool that directly predicts the optimal catalytic temperature (Topt) of enzymes is desirable.…”