Prediction of drug-protein binding is critical for virtual drug screening.Many deep learning methods have been proposed to predict the drug-protein binding based on protein sequences and drug representation sequences....Prediction of drug-protein binding is critical for virtual drug screening.Many deep learning methods have been proposed to predict the drug-protein binding based on protein sequences and drug representation sequences.However,most existing methods extract features from protein and drug sequences separately.As a result,they can not learn the features characterizing the drug-protein interactions.In addition,the existing methods encode the protein(drug)sequence usually based on the assumption that each amino acid(atom)has the same contribution to the binding,ignoring different impacts of different amino acids(atoms)on the binding.However,the event of drug-protein binding usually occurs between conserved residue fragments in the protein sequence and atom fragments of the drug molecule.Therefore,a more comprehensive encoding strategy is required to extract information from the conserved fragments.In this paper,we propose a novel model,named FragDPI,to predict the drug-protein binding affinity.Unlike other methods,we encode the sequences based on the conserved fragments and encode the protein and drug into a unified vector.Moreover,we adopt a novel two-step training strategy to train FragDPI.The pre-training step is to learn the interactions between different fragments using unsupervised learning.The fine-tuning step is for predicting the binding affinities using supervised learning.The experiment results have illustrated the superiority of FragDPI.展开更多
Potassium dehydroandrographolide succinate （DAS-K） has antibacterial and antiviral effects. It has been used widely for the treatment of virus pneumonia, malaria and respiratory infections. In this work, a novel flo...Potassium dehydroandrographolide succinate （DAS-K） has antibacterial and antiviral effects. It has been used widely for the treatment of virus pneumonia, malaria and respiratory infections. In this work, a novel flow-injection chemiluminescence （CL） method for the determination of DAS-K was proposed. The method is based on the reaction between DAS-K and hexacyanoferrate（III） in alkaline solution to give weak CL signal, which is enhanced by rhodamine B. The experimental conditions for the CL reaction were optimized and the possible reaction mechanism was discussed. Under the optimum conditions, the concentration of DAS-K is proportional to the CL intensity in the range of 0.1-80 μmol·L^-1 with a detection limit of 0.05 μmol·L^-1. The interaction of the DAS-K with bovine serum albumin by on-line ultrafiltration and flow-injection chemiluminescence was studied. The concentrations of unbound DAS-K from ultra filter tube were determined by the flow-injection CL method. The binding parameters were estimated by the Scatchard plot and Klotz plot. The proposed system proved that FIA-CL coupled with on-line ultrafiltration sampling was a fast and simple technique for the study of drug-protein interaction.展开更多
A new method to determine the interaction between drug and protein has been developed by utilizing the technique of microdialysis sampling with the ketoprofen and the human serum albumin (HSA) as the model of drug and...A new method to determine the interaction between drug and protein has been developed by utilizing the technique of microdialysis sampling with the ketoprofen and the human serum albumin (HSA) as the model of drug and protein.Two kinds of binding sites of HSA to ketoprofen have been observed.The binding constants and number of binding sites obtained by the Scatchard equation are 0.799,3.18×106 mol-1 L and 2.15,2.01×105 mol-1 L,respectively The displacement binding of drugs to HSA has also been studied.The strong displacement of competitive binding of ibuprofen with ketoprofen to HSA was observed,which means that the primary binding site of HSA to ketoprofen and that to ibuprofen are the same.However,only a weaker displacement of warfarin for the association of ketoprofen with HSA was observed,which may suggest that the primary binding site of HSA to ketoprofen is different from that to warfarin.Such a displacement effect for competitive binding of drugs to HSA was explained by the displacement model in the liquid-solid adsorption chromatography.展开更多
基金supported by the National Key R&D Program of China(2019YFA0904303).
文摘Prediction of drug-protein binding is critical for virtual drug screening.Many deep learning methods have been proposed to predict the drug-protein binding based on protein sequences and drug representation sequences.However,most existing methods extract features from protein and drug sequences separately.As a result,they can not learn the features characterizing the drug-protein interactions.In addition,the existing methods encode the protein(drug)sequence usually based on the assumption that each amino acid(atom)has the same contribution to the binding,ignoring different impacts of different amino acids(atoms)on the binding.However,the event of drug-protein binding usually occurs between conserved residue fragments in the protein sequence and atom fragments of the drug molecule.Therefore,a more comprehensive encoding strategy is required to extract information from the conserved fragments.In this paper,we propose a novel model,named FragDPI,to predict the drug-protein binding affinity.Unlike other methods,we encode the sequences based on the conserved fragments and encode the protein and drug into a unified vector.Moreover,we adopt a novel two-step training strategy to train FragDPI.The pre-training step is to learn the interactions between different fragments using unsupervised learning.The fine-tuning step is for predicting the binding affinities using supervised learning.The experiment results have illustrated the superiority of FragDPI.
基金Project supported by the National Natural Science Foundation of China （No 30470886）.
文摘Potassium dehydroandrographolide succinate （DAS-K） has antibacterial and antiviral effects. It has been used widely for the treatment of virus pneumonia, malaria and respiratory infections. In this work, a novel flow-injection chemiluminescence （CL） method for the determination of DAS-K was proposed. The method is based on the reaction between DAS-K and hexacyanoferrate（III） in alkaline solution to give weak CL signal, which is enhanced by rhodamine B. The experimental conditions for the CL reaction were optimized and the possible reaction mechanism was discussed. Under the optimum conditions, the concentration of DAS-K is proportional to the CL intensity in the range of 0.1-80 μmol·L^-1 with a detection limit of 0.05 μmol·L^-1. The interaction of the DAS-K with bovine serum albumin by on-line ultrafiltration and flow-injection chemiluminescence was studied. The concentrations of unbound DAS-K from ultra filter tube were determined by the flow-injection CL method. The binding parameters were estimated by the Scatchard plot and Klotz plot. The proposed system proved that FIA-CL coupled with on-line ultrafiltration sampling was a fast and simple technique for the study of drug-protein interaction.
基金Project supported by the Chinese Academy of Sciencesthe National Natural Science Foundation of China
文摘A new method to determine the interaction between drug and protein has been developed by utilizing the technique of microdialysis sampling with the ketoprofen and the human serum albumin (HSA) as the model of drug and protein.Two kinds of binding sites of HSA to ketoprofen have been observed.The binding constants and number of binding sites obtained by the Scatchard equation are 0.799,3.18×106 mol-1 L and 2.15,2.01×105 mol-1 L,respectively The displacement binding of drugs to HSA has also been studied.The strong displacement of competitive binding of ibuprofen with ketoprofen to HSA was observed,which means that the primary binding site of HSA to ketoprofen and that to ibuprofen are the same.However,only a weaker displacement of warfarin for the association of ketoprofen with HSA was observed,which may suggest that the primary binding site of HSA to ketoprofen is different from that to warfarin.Such a displacement effect for competitive binding of drugs to HSA was explained by the displacement model in the liquid-solid adsorption chromatography.
