Drug-target interactions prediction(DTIP)remains an important requirement in thefield of drug discovery and human medicine.The identification of interaction among the drug compound and target protein plays an essential ...Drug-target interactions prediction(DTIP)remains an important requirement in thefield of drug discovery and human medicine.The identification of interaction among the drug compound and target protein plays an essential pro-cess in the drug discovery process.It is a lengthier and complex process for pre-dicting the drug target interaction(DTI)utilizing experimental approaches.To resolve these issues,computational intelligence based DTIP techniques were developed to offer an efficient predictive model with low cost.The recently devel-oped deep learning(DL)models can be employed for the design of effective pre-dictive approaches for DTIP.With this motivation,this paper presents a new drug target interaction prediction using optimal recurrent neural network(DTIP-ORNN)technique.The goal of the DTIP-ORNN technique is to predict the DTIs in a semi-supervised way,i.e.,inclusion of both labelled and unlabelled instances.Initially,the DTIP-ORNN technique performs data preparation process and also includes class labelling process,where the target interactions from the database are used to determine thefinal label of the unlabelled instances.Besides,drug-to-drug(D-D)and target-to-target(T-T)interactions are used for the weight initia-tion of the RNN based bidirectional long short term memory(BiLSTM)model which is then utilized to the prediction of DTIs.Since hyperparameters signifi-cantly affect the prediction performance of the BiLSTM technique,the Adam optimizer is used which mainly helps to improve the DTI prediction outcomes.In order to ensure the enhanced predictive outcomes of the DTIP-ORNN techni-que,a series of simulations are implemented on four benchmark datasets.The comparative result analysis shows the promising performance of the DTIP-ORNN method on the recent approaches.展开更多
As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication ...As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.展开更多
The prediction of the interaction between a drug and a target is the most critical issue in the fields of drug development and repurposing.However,there are still two challenges in current deep learning research:(i)th...The prediction of the interaction between a drug and a target is the most critical issue in the fields of drug development and repurposing.However,there are still two challenges in current deep learning research:(i)the structural information of drug molecules is not fully explored in most drug target studies,and the previous drug SMILES does not correspond well to effective drug molecules and(ii)exploration of the potential relationship between drugs and targets is in need of improvement.In this work,we use a new and better representation of the effective molecular graph structure,SELFIES.We propose a hybrid mechanism framework based on convolutional neural network and graph attention network to capture multi-view feature information of drug and target molecular structures,and we aim to enhance the ability to capture interaction sites between a drug and a target.In this study,our experiments using two different datasets show that the GCARDTI model outperforms a variety of different model algorithms on different metrics.We also demonstrate the accuracy of our model through two case studies.展开更多
In order to produce millimeter-scale plasmas for the research of laser-plasma interactions （LPIs）, gasbag target is designed and tested on Shenguang-III prototype laser facility. The x-ray pinhole images show that m...In order to produce millimeter-scale plasmas for the research of laser-plasma interactions （LPIs）, gasbag target is designed and tested on Shenguang-III prototype laser facility. The x-ray pinhole images show that millimeter-scale plasmas are produced with the gasbag. The electron temperature inferred from the stimulated Raman scattering （SRS） spectrum is about 1.6 keV. The SRS spectrum also indicates that the electron density has a fiat region within the duration of 200 ps. The obvious differences between the results of the gasbag and that of the void half hohlraum show the feasibility of the gasbag target in creating millimeter-scale plasmas. The LPIs in these millimeter-scale plasmas may partially mimic those in the ignition condition because the duration of the existence of a flat plasma density is much larger than the growth time of the two main instabilities, i.e., SRS and stimulated Brillouin scattering （SBS）. So we make the conclusion that the gasbag target can be used to research the large-scale LPIs.展开更多
Genetic interactions are functional crosstalk among different genetic loci that lead to phenotypic changes,such as health or viability alterations.A disease or lethal phenotype that results from the combined effects o...Genetic interactions are functional crosstalk among different genetic loci that lead to phenotypic changes,such as health or viability alterations.A disease or lethal phenotype that results from the combined effects of gene mutations at different loci is termed a synthetic sickness or synthetic lethality,respectively.Studies of genetic interaction have provided insight on the relationships among biochemical processes or pathways.Cancer results from genetic interactions and is a major focus of current studies in genetic interactions.Various basic and translational cancer studies have explored the concept of genetic interactions,including studies of the mechanistic characterization of genes,drug discovery,biomarker identification and the rational design of combination therapies.This review discusses the implications of genetic interactions in the development of personalized cancer therapies,the identification of treatment-responsive genes,the delineation of mechanisms of chemoresistance and the rational design of combined therapeutic strategies to overcome drug resistance.展开更多
Micro RNAs(mi RNAs) are small noncoding RNAs. More than 2500 mature mi RNAs are detected in plants, animals and several types of viruses. Hepatitis C virus(HCV), which is a positive-sense, singlestranded RNA virus, do...Micro RNAs(mi RNAs) are small noncoding RNAs. More than 2500 mature mi RNAs are detected in plants, animals and several types of viruses. Hepatitis C virus(HCV), which is a positive-sense, singlestranded RNA virus, does not encode viral mi RNA. However, HCV infection alters the expression of host mi RNAs, either in cell culture or in patients with liver disease progression, such as liver fibrosis, cirrhosis, and hepatocellular carcinoma. In turn, host mi RNAs regulate HCV life cycle through directly binding to HCV RNAs or indirectly targeting cellular m RNAs. Increasing evidence demonstrates that mi RNAs are one of the centered factors in the interaction network between virus and host. The competitive viral and host RNA hypothesis proposes a latent cross-regulation pattern between host m RNAs and HCV RNAs. High loads of HCV RNA sequester and de-repress host mi RNAs from their normal host targets and thus disturb host gene expression, indicating a means of adaptation for HCV to establish a persistent infection. Some special mi RNAs are closely correlated with liver-specific disease progression and the changed levels of mi RNAs are even higher sensitivity and specificity than those of traditional proteins. Therefore, some of them can serve as novel diagnostic/prognostic biomarkers in HCVinfected patients with liver diseases. They are also attractive therapeutic targets for development of new anti-HCV agents.展开更多
Cdc42 is a member of the Rho subfamily of Ras-related proteins, which were among the first oncogenic proteins to be identified as playing a sig-nificant role in a variety of cellular events [Barbacaid, 1987, Ann. Rev....Cdc42 is a member of the Rho subfamily of Ras-related proteins, which were among the first oncogenic proteins to be identified as playing a sig-nificant role in a variety of cellular events [Barbacaid, 1987, Ann. Rev. Biochem]. Equally important, Protein-Protein Interactions [PPIs] involving Cdc42 continue to highlight the role of Ras-related proteins’ relevance to cancer. As these proteins have been considered incapable of being “druggable”, due to a perceived lack of binding surface[s] that are amenable to small molecule targeting, there remains limited development of therapies to tackle diseased states caused by Cdc42-stimulated hyperactivity. Thusly, it has become important to characterize molecular details, including dynamics, of PPIs involving Cdc42 that may lend themselves as potential targets for therapeutic approaches. Recently, two small molecules, ZCL278 and AZA197, have shown promise in directly targeting Cdc42 to influence PPIs that are capable of causing Cdc42-stimulated abnormal signaling. In this editorial, we highlight recent studies that show case how these two small molecules may influence Cdc42-protein interactions.展开更多
Prostate cancer is a major public health concern worldwide, being one of the most prevalent cancers in men. Great improvements have been made both in terms of early diagnosis and therapeutics. However, there is still ...Prostate cancer is a major public health concern worldwide, being one of the most prevalent cancers in men. Great improvements have been made both in terms of early diagnosis and therapeutics. However, there is still an urgent need for reliable biomarkers that could overcome the lack of cancer-specificity of prostate-specific antigen, as well as alternative therapeutic targets for advanced metastatic cases. Reversible phosphorylation of proteins is a post-translational modification critical to the regulation of numerous cellular processes. Phosphoprotein phosphatase 1(PPP1) is a major serine/threonine phosphatase, whose specificity is determined by its interacting proteins. These interactors can be PPP1 substrates, regulators, or even both. Deregulation of this protein-protein interaction network alters cell dynamics and underlies the development of several cancer hallmarks. Therefore, the identification of PPP1 interactome in specific cellular context is of crucial importance. The knowledge on PPP1 complexes in prostate cancer remains scarce, withonly 4 holoenzymes characterized in human prostate cancer models. However, an increasing number of PPP1 interactors have been identified as expressed in human prostate tissue, including the tumor suppressors TP53 and RB1. Efforts should be made in order to identify the role of such proteins in prostate carcinogenesis, since only 26 have yet well-recognized roles. Here, we revise literature and human protein databases to provide an indepth knowledge on the biological significance of PPP1 complexes in human prostate carcinogenesis and their potential use as therapeutic targets for the development of new therapies for prostate cancer.展开更多
受体相互作用蛋白激酶1(receptor-interacting protein kinase 1,RIPK1)是一种多结构域丝氨酸/苏氨酸蛋白激酶。它通过磷酸化特定的蛋白质,引起下游的信号转导和生物效应。近年来,随着对RIPK1的深入研究,学者发现其在自身免疫性疾病、...受体相互作用蛋白激酶1(receptor-interacting protein kinase 1,RIPK1)是一种多结构域丝氨酸/苏氨酸蛋白激酶。它通过磷酸化特定的蛋白质,引起下游的信号转导和生物效应。近年来,随着对RIPK1的深入研究,学者发现其在自身免疫性疾病、神经退行性疾病,以及多种实体瘤和血液肿瘤中具有重要意义。一方面,RIPK1通过激活特定通路如核因子-κB(nuclear factor-κB,NF-κB)和丝裂原活化蛋白激酶(mitogen-activated protein kinase,MAPK)等促进细胞存活及炎症反应。另一方面,RIPK1通过与胱天蛋白酶-8(cysteinyl aspartate specific proteinase-8,caspase-8)作用促进凋亡,或与RIPK3和混合谱系激酶结构域样假激酶(mixed lineage kinase domain-like protein,MLKL)作用促进坏死性凋亡的发生。RIPK1作为上游信号在不同肿瘤患者中表达水平不同。其支架功能和激酶活性可以调节癌症进展,也可以启动机体适应性免疫,抑制肿瘤进展;此外,还能产生免疫抑制性肿瘤微环境而促进肿瘤的发展。其双重作用在调节癌症的发生、发展及机体免疫反应方面都有所展现,可以作为新的治疗靶点控制癌症进展。该文从RIPK1的结构入手,深入探讨其功能,特别是其在调节癌症进展和免疫反应方面的功能,为癌症靶向药物的开发提供新的思路。展开更多
文摘Drug-target interactions prediction(DTIP)remains an important requirement in thefield of drug discovery and human medicine.The identification of interaction among the drug compound and target protein plays an essential pro-cess in the drug discovery process.It is a lengthier and complex process for pre-dicting the drug target interaction(DTI)utilizing experimental approaches.To resolve these issues,computational intelligence based DTIP techniques were developed to offer an efficient predictive model with low cost.The recently devel-oped deep learning(DL)models can be employed for the design of effective pre-dictive approaches for DTIP.With this motivation,this paper presents a new drug target interaction prediction using optimal recurrent neural network(DTIP-ORNN)technique.The goal of the DTIP-ORNN technique is to predict the DTIs in a semi-supervised way,i.e.,inclusion of both labelled and unlabelled instances.Initially,the DTIP-ORNN technique performs data preparation process and also includes class labelling process,where the target interactions from the database are used to determine thefinal label of the unlabelled instances.Besides,drug-to-drug(D-D)and target-to-target(T-T)interactions are used for the weight initia-tion of the RNN based bidirectional long short term memory(BiLSTM)model which is then utilized to the prediction of DTIs.Since hyperparameters signifi-cantly affect the prediction performance of the BiLSTM technique,the Adam optimizer is used which mainly helps to improve the DTI prediction outcomes.In order to ensure the enhanced predictive outcomes of the DTIP-ORNN techni-que,a series of simulations are implemented on four benchmark datasets.The comparative result analysis shows the promising performance of the DTIP-ORNN method on the recent approaches.
文摘As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.
基金Natural Science Foundation of Shandong Province,Grant/Award Number:ZR2023MF053National Natural Science Foundation of China,Grant/Award Numbers:61902430,61873281。
文摘The prediction of the interaction between a drug and a target is the most critical issue in the fields of drug development and repurposing.However,there are still two challenges in current deep learning research:(i)the structural information of drug molecules is not fully explored in most drug target studies,and the previous drug SMILES does not correspond well to effective drug molecules and(ii)exploration of the potential relationship between drugs and targets is in need of improvement.In this work,we use a new and better representation of the effective molecular graph structure,SELFIES.We propose a hybrid mechanism framework based on convolutional neural network and graph attention network to capture multi-view feature information of drug and target molecular structures,and we aim to enhance the ability to capture interaction sites between a drug and a target.In this study,our experiments using two different datasets show that the GCARDTI model outperforms a variety of different model algorithms on different metrics.We also demonstrate the accuracy of our model through two case studies.
基金Project supported by the National Natural Science Foundation of China (Grant No. 10625523)the Innovation Project of the Chinese Academy of Sciences (Grant No. KJCX2-YW-N36)National High-Tech Program of China
文摘In order to produce millimeter-scale plasmas for the research of laser-plasma interactions （LPIs）, gasbag target is designed and tested on Shenguang-III prototype laser facility. The x-ray pinhole images show that millimeter-scale plasmas are produced with the gasbag. The electron temperature inferred from the stimulated Raman scattering （SRS） spectrum is about 1.6 keV. The SRS spectrum also indicates that the electron density has a fiat region within the duration of 200 ps. The obvious differences between the results of the gasbag and that of the void half hohlraum show the feasibility of the gasbag target in creating millimeter-scale plasmas. The LPIs in these millimeter-scale plasmas may partially mimic those in the ignition condition because the duration of the existence of a flat plasma density is much larger than the growth time of the two main instabilities, i.e., SRS and stimulated Brillouin scattering （SBS）. So we make the conclusion that the gasbag target can be used to research the large-scale LPIs.
基金Supported by the National Natural Science Foundation of China （No.40067116）, the Research Development Foundation of Dalian Naval Academy （No.K200821）.
文摘根据在目标追踪以及澄清的在水下的调遣的即时性能和可靠性的要求，运动展示在水下目标，交往多重模型算法基于模糊逻辑，推理(FIMM ) 被建议。调遣目标的模式被模型集合代表，包括经常的速度模型(CA ) ，歌手模型，和将近经常的速度在 FIMM 技术的水平拐弯的模型(HT ) 。模拟结果与常规 IMM，可靠性和即时性能相比显示出那在水下目标追踪能被 FIMM 改进算法。
文摘Genetic interactions are functional crosstalk among different genetic loci that lead to phenotypic changes,such as health or viability alterations.A disease or lethal phenotype that results from the combined effects of gene mutations at different loci is termed a synthetic sickness or synthetic lethality,respectively.Studies of genetic interaction have provided insight on the relationships among biochemical processes or pathways.Cancer results from genetic interactions and is a major focus of current studies in genetic interactions.Various basic and translational cancer studies have explored the concept of genetic interactions,including studies of the mechanistic characterization of genes,drug discovery,biomarker identification and the rational design of combination therapies.This review discusses the implications of genetic interactions in the development of personalized cancer therapies,the identification of treatment-responsive genes,the delineation of mechanisms of chemoresistance and the rational design of combined therapeutic strategies to overcome drug resistance.
基金Supported by National Natural Science Foundation of China No.81321004 and No.81322050National Mega-Project for“R&D for Innovative Drugs”+3 种基金Ministry of Science and TechnologyChina No.2012ZX09301-002-001Ministry of EducationChina No.NCET-12-0072
文摘Micro RNAs(mi RNAs) are small noncoding RNAs. More than 2500 mature mi RNAs are detected in plants, animals and several types of viruses. Hepatitis C virus(HCV), which is a positive-sense, singlestranded RNA virus, does not encode viral mi RNA. However, HCV infection alters the expression of host mi RNAs, either in cell culture or in patients with liver disease progression, such as liver fibrosis, cirrhosis, and hepatocellular carcinoma. In turn, host mi RNAs regulate HCV life cycle through directly binding to HCV RNAs or indirectly targeting cellular m RNAs. Increasing evidence demonstrates that mi RNAs are one of the centered factors in the interaction network between virus and host. The competitive viral and host RNA hypothesis proposes a latent cross-regulation pattern between host m RNAs and HCV RNAs. High loads of HCV RNA sequester and de-repress host mi RNAs from their normal host targets and thus disturb host gene expression, indicating a means of adaptation for HCV to establish a persistent infection. Some special mi RNAs are closely correlated with liver-specific disease progression and the changed levels of mi RNAs are even higher sensitivity and specificity than those of traditional proteins. Therefore, some of them can serve as novel diagnostic/prognostic biomarkers in HCVinfected patients with liver diseases. They are also attractive therapeutic targets for development of new anti-HCV agents.
文摘Cdc42 is a member of the Rho subfamily of Ras-related proteins, which were among the first oncogenic proteins to be identified as playing a sig-nificant role in a variety of cellular events [Barbacaid, 1987, Ann. Rev. Biochem]. Equally important, Protein-Protein Interactions [PPIs] involving Cdc42 continue to highlight the role of Ras-related proteins’ relevance to cancer. As these proteins have been considered incapable of being “druggable”, due to a perceived lack of binding surface[s] that are amenable to small molecule targeting, there remains limited development of therapies to tackle diseased states caused by Cdc42-stimulated hyperactivity. Thusly, it has become important to characterize molecular details, including dynamics, of PPIs involving Cdc42 that may lend themselves as potential targets for therapeutic approaches. Recently, two small molecules, ZCL278 and AZA197, have shown promise in directly targeting Cdc42 to influence PPIs that are capable of causing Cdc42-stimulated abnormal signaling. In this editorial, we highlight recent studies that show case how these two small molecules may influence Cdc42-protein interactions.
基金Supported by Fundao para a Ciência e Tecnologia(FCT)(PTDC/QUI-BIQ/118492/2010)Fundo Europeu de Desenvolvimento Regional(FEDER)(FCOMP-01-0124-FEDER-020895),Portugal
文摘Prostate cancer is a major public health concern worldwide, being one of the most prevalent cancers in men. Great improvements have been made both in terms of early diagnosis and therapeutics. However, there is still an urgent need for reliable biomarkers that could overcome the lack of cancer-specificity of prostate-specific antigen, as well as alternative therapeutic targets for advanced metastatic cases. Reversible phosphorylation of proteins is a post-translational modification critical to the regulation of numerous cellular processes. Phosphoprotein phosphatase 1(PPP1) is a major serine/threonine phosphatase, whose specificity is determined by its interacting proteins. These interactors can be PPP1 substrates, regulators, or even both. Deregulation of this protein-protein interaction network alters cell dynamics and underlies the development of several cancer hallmarks. Therefore, the identification of PPP1 interactome in specific cellular context is of crucial importance. The knowledge on PPP1 complexes in prostate cancer remains scarce, withonly 4 holoenzymes characterized in human prostate cancer models. However, an increasing number of PPP1 interactors have been identified as expressed in human prostate tissue, including the tumor suppressors TP53 and RB1. Efforts should be made in order to identify the role of such proteins in prostate carcinogenesis, since only 26 have yet well-recognized roles. Here, we revise literature and human protein databases to provide an indepth knowledge on the biological significance of PPP1 complexes in human prostate carcinogenesis and their potential use as therapeutic targets for the development of new therapies for prostate cancer.
文摘受体相互作用蛋白激酶1(receptor-interacting protein kinase 1,RIPK1)是一种多结构域丝氨酸/苏氨酸蛋白激酶。它通过磷酸化特定的蛋白质,引起下游的信号转导和生物效应。近年来,随着对RIPK1的深入研究,学者发现其在自身免疫性疾病、神经退行性疾病,以及多种实体瘤和血液肿瘤中具有重要意义。一方面,RIPK1通过激活特定通路如核因子-κB(nuclear factor-κB,NF-κB)和丝裂原活化蛋白激酶(mitogen-activated protein kinase,MAPK)等促进细胞存活及炎症反应。另一方面,RIPK1通过与胱天蛋白酶-8(cysteinyl aspartate specific proteinase-8,caspase-8)作用促进凋亡,或与RIPK3和混合谱系激酶结构域样假激酶(mixed lineage kinase domain-like protein,MLKL)作用促进坏死性凋亡的发生。RIPK1作为上游信号在不同肿瘤患者中表达水平不同。其支架功能和激酶活性可以调节癌症进展,也可以启动机体适应性免疫,抑制肿瘤进展;此外,还能产生免疫抑制性肿瘤微环境而促进肿瘤的发展。其双重作用在调节癌症的发生、发展及机体免疫反应方面都有所展现,可以作为新的治疗靶点控制癌症进展。该文从RIPK1的结构入手,深入探讨其功能,特别是其在调节癌症进展和免疫反应方面的功能,为癌症靶向药物的开发提供新的思路。
