Human-virus protein-protein interactions(PPIs)play critical roles in viral infection.For example,the spike protein of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)binds primarily to human angiotensinconv...Human-virus protein-protein interactions(PPIs)play critical roles in viral infection.For example,the spike protein of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)binds primarily to human angiotensinconverting enzyme 2(ACE2)protein to infect human cells.Thus,identifying and blocking these PPIs contribute to controlling and preventing viruses.However,wet-lab experiment-based identification of human-virus PPIs is usually expensive,labor-intensive,and time-consuming,which presents the need for computational methods.Many machine-learning methods have been proposed recently and achieved good results in predicting humanvirus PPIs.However,most methods are based on protein sequence features and apply manually extracted features,such as statistical characteristics,phylogenetic profiles,and physicochemical properties.In this work,we present an embedding-based neural framework with convolutional neural network(CNN)and bi-directional long short-term memory unit(Bi-LSTM)architecture,named Emvirus,to predict human-virus PPIs(including human-SARS-CoV-2 PPIs).In addition,we conduct cross-viral experiments to explore the generalization ability of Emvirus.Compared to other feature extraction methods,Emvirus achieves better prediction accuracy.展开更多
To investigate HIV genotypes isolated from blood donors in Beijing, the samples positive for anti-HIV antibody with ELISAwere confirmed by HIV blot. All 26 samples were confirmed positive for anti-HIV antibody. RNA fr...To investigate HIV genotypes isolated from blood donors in Beijing, the samples positive for anti-HIV antibody with ELISAwere confirmed by HIV blot. All 26 samples were confirmed positive for anti-HIV antibody. RNA from those samples were detected with RT-PCR. 20 of them were positive for HIV RNA. The purified PCR products were cloned. The sequences were determined and analyzed. The results showed that 10 of 20 isolates were CRF BC, 9 of them were genotype B, 1 of them were CRF AE. 6 of 9 genotype B belong to B’(Thailand B), the remaining 3 isolates may belong to western genotype B. The results indicated that several different genotypes of HIV which are predominant in China may exist in Beijing. This result may be helpful for the development of HIV vaccine in Beijing.展开更多
文摘Human-virus protein-protein interactions(PPIs)play critical roles in viral infection.For example,the spike protein of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)binds primarily to human angiotensinconverting enzyme 2(ACE2)protein to infect human cells.Thus,identifying and blocking these PPIs contribute to controlling and preventing viruses.However,wet-lab experiment-based identification of human-virus PPIs is usually expensive,labor-intensive,and time-consuming,which presents the need for computational methods.Many machine-learning methods have been proposed recently and achieved good results in predicting humanvirus PPIs.However,most methods are based on protein sequence features and apply manually extracted features,such as statistical characteristics,phylogenetic profiles,and physicochemical properties.In this work,we present an embedding-based neural framework with convolutional neural network(CNN)and bi-directional long short-term memory unit(Bi-LSTM)architecture,named Emvirus,to predict human-virus PPIs(including human-SARS-CoV-2 PPIs).In addition,we conduct cross-viral experiments to explore the generalization ability of Emvirus.Compared to other feature extraction methods,Emvirus achieves better prediction accuracy.
文摘To investigate HIV genotypes isolated from blood donors in Beijing, the samples positive for anti-HIV antibody with ELISAwere confirmed by HIV blot. All 26 samples were confirmed positive for anti-HIV antibody. RNA from those samples were detected with RT-PCR. 20 of them were positive for HIV RNA. The purified PCR products were cloned. The sequences were determined and analyzed. The results showed that 10 of 20 isolates were CRF BC, 9 of them were genotype B, 1 of them were CRF AE. 6 of 9 genotype B belong to B’(Thailand B), the remaining 3 isolates may belong to western genotype B. The results indicated that several different genotypes of HIV which are predominant in China may exist in Beijing. This result may be helpful for the development of HIV vaccine in Beijing.