The structures and activities of enzymes are influenced by pH of the environment. Understanding and distinguishing the adaptation mechanisms of enzymes to extreme pH values is of great significance for elucidating the molecular mechanisms and promoting the industrial applications of enzymes. In this study, the ESM-2 protein language model was used to encode the secreted microbial proteins with the optimal performance above pH 9 and below pH 5, which yielded 47 725 high-pH protein sequences and 66 079 low-pH protein sequences, respectively. A deep learning model was constructed to identify protein acid-base tolerance based on amino acid sequences. The model showcased significantly higher accuracy than other methods, with the overall accuracy of 94.8%, precision of 91.8%, and a recall rate of 93.4% on the test set. Furthermore, we built a website (https://enzymepred.biodesign.ac.cn), which enabled users to predict the acid-base tolerance by submitting the protein sequences of enzymes. This study has accelerated the application of enzymes in various fields, including biotechnology, pharmaceuticals, and chemicals. It provides a powerful tool for the rapid screening and optimization of industrial enzymes.
Deep Learning ; Hydrogen-Ion Concentration ; Amino Acid Sequence ; Enzymes/metabolism* ; Sequence Analysis, Protein ; Proteins/metabolism* ; Bacterial Proteins/metabolism*

OBJECTIVE:To investigate the distribution and drug resistance of Acinetobacter baumannii in our hospital,and provide reference for rational use of antibiotics. METHODS:Clinical specimen of inpatients in our hospital from Jan. 2012 to Dec. 2015 was collected,the identification of strains and drug sensitivity test were performed by the VITEK-2 microorganism analyzer;use rate of antibiotics and detection of multidrug-resistant and pandrug-resistant A. baumannii for inpatients in our hospital were an-alyzed,and their correlation was detected by Pearson correlation analysis. RESULTS:Totally 2 468 strains of A. baumannii were isolated in our hospital during 2012-2015,mainly derived from sputum samples (88.2%),distributed in respiratory medicine de-partment(47.0%)and ICU(13.1%);A. baumannii showed totally high drug resistance to common antibiotics,and only sensitive to tigecycline. Totally 386(79.3%),434(61.6%),358(53.4%)and 291(48.0%)strains multidrug-resistant A. baumannii were detected every year in our hospital;and pandrug-resistant A. baumannii were 336(69.0%),385(54.7%),331(49.3%)and 256 (42.2%) strains,respectively. There was a positive correlation between the percentage of multidrug-resistant and pandrug-resistant A. baumannii in total strains and use rate of antibiotics (r=0.987、0.981,P<0.05). CONCLUSIONS:A. baumannii has emerged as an important pathogen in hospital acquired infections,which mainly caused respiratory system infection;the drug resistance situ-ation is not optimistic,tigecycline can be used as one of the best choice for treatment of A. baumannii infections;our hospital should continue to control the use of antibiotics to decrease the emerging of drug resistance strains.