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*

ObjectiveTo conduct on-site epidemiological investigation， emergency response， tracing of infection source and analysis of a confirmed COVID-19 case of a foreign airline cargo service staff member in Shanghai’s international airport， aiming to provide reference for prevention of imported COVID-19 cases under regular prevention and control of COVID-19. MethodsA retrospective field epidemiological investigation was conducted to collect information of basic characteristics， illness onset， diagnosis， treatment， clinical manifestations， exposure history and risk factors within 14 days before onset， close contacts， close contacts of close contacts， and key places related to activity trajectories. Respiratory tract specimens of cases and contacts were collected for detection of SARS-CoV-2 by real time RT-PCR （rRT-PCR）. Emergency response， including infection source analysis and contact management， was conducted. ResultsThe case developed pharyngeal itch on July 28， 2021， and fever on the 30th， and went to the hospital for treatment twice on the 31st. Because his specimen was positive for SARS-CoV-2 by rRT-PCR on August 1， he was isolated and treated on August 2 and diagnosed as a confirmed case of COVID-19. The case was a foreign airline cargo service member at an international airport. The two regular nucleic acid screenings of him as a high-risk occupation on July 21 and 28 were negative. He did not leave Shanghai within 14 days before the onset of illness. During July 22nd and 23rd， he was repeatedly exposed during work to the high-risk environment that may have been contaminated by SARS-CoV-2 and had contact with the crew of foreign airlines， and the personal protection was not standardized. None of the 67 close contacts and 567 close contacts of close contacts in Shanghai showed symptoms during the 14-day medical quarantine， and the specimens of them were all negative for SARS-CoV-2 by rRT-PCR. The results of genome sequencing analysis showed that the genomic homology between the virus of the case and the one of recent domestic local epidemic and the recent imported cases was low， and the homology with the overseas Delta mutant strain was higher than that of the domestic Delta mutant strain. ConclusionThe situation of prevention of COVID-19 import is still serious. It is necessary to conduct regular nucleic acid screening for high-risk occupational groups， strengthen the diagnosis and reporting awareness of medical institutions， effectively implement the prevention and control measures for people， objects， and environment at international airports， and further enhance the public's awareness of personal protection.