Binding kinetic properties of protein–ligand complexes are crucial factors affecting the drug potency.Nevertheless,the current in silico techniques are insufficient in providing accurate and robust predictions for bi...Binding kinetic properties of protein–ligand complexes are crucial factors affecting the drug potency.Nevertheless,the current in silico techniques are insufficient in providing accurate and robust predictions for binding kinetic properties.To this end,this work develops a variety of binding kinetic models for predicting a critical binding kinetic property,dissociation rate constant,using eight machine learning(ML)methods(Bayesian Neural Network(BNN),partial least squares regression,Bayesian ridge,Gaussian process regression,principal component regression,random forest,support vector machine,extreme gradient boosting)and the descriptors of the van der Waals/electrostatic interaction energies.These eight models are applied to two case studies involving the HSP90 and RIP1 kinase inhibitors.Both regression results of two case studies indicate that the BNN model has the state-of-the-art prediction accuracy(HSP90:R^(2)_(test)=0:947,MAE_(test)=0.184,rtest=0.976,RMSE_(test)=0.220;RIP1 kinase:R^(2)_(test)=0:745,MAE_(test)=0.188,rtest=0.961,RMSE_(test)=0.290)in comparison with other seven ML models.展开更多
Since its establishment in 2013,BioLiP has become one of the widely used resources for protein-ligand interactions.Nevertheless,several known issues occurred with it over the past decade.For example,the protein-ligand...Since its establishment in 2013,BioLiP has become one of the widely used resources for protein-ligand interactions.Nevertheless,several known issues occurred with it over the past decade.For example,the protein-ligand interactions are represented in the form of single chain-based tertiary structures,which may be inappropriate as many interactions involve multiple protein chains(known as quaternary structures).We sought to address these issues,resulting in Q-BioLiP,a comprehensive resource for quaternary structure-based protein-ligand interactions.The major features of Q-BioLiP include:(1)representing protein structures in the form of quaternary structures rather than single chain-based tertiary structures;(2)pairing DNA/RNA chains properly rather than separation;(3)providing both experimental and predicted binding affinities;(4)retaining both biologically relevant and irrelevant interactions to alleviate the wrong justification of ligands’biological relevance;and(5)developing a new quaternary structure-based algorithm for the modelling of protein-ligand complex structure.With these new features,Q-BioLiP is expected to be a valuable resource for studying biomolecule interactions,including protein-small molecule interaction,protein-metal ion interaction,protein-peptide interaction,protein-protein interaction,protein-DNA/RNA interaction,and RNA-small molecule interaction.Q-BioLiP is freely available at https://yanglab.qd.sdu.edu.cn/Q-BioLiP/.展开更多
目的探究血清分泌型卷曲相关蛋白5(secreted frizzled related protein 5,SFRP-5)、C-X-C基序趋化因子配体16(C-X-C motif chemokine ligand 16,CXCL16)对心肌梗死患者经皮冠状动脉介入(percutaneous coronary intervention,PCI)治疗后...目的探究血清分泌型卷曲相关蛋白5(secreted frizzled related protein 5,SFRP-5)、C-X-C基序趋化因子配体16(C-X-C motif chemokine ligand 16,CXCL16)对心肌梗死患者经皮冠状动脉介入(percutaneous coronary intervention,PCI)治疗后心力衰竭(heart failure,HF)发生的预测价值。方法选取2022年6月至2024年1月于保定市第二中心医院实施PCI治疗的心肌梗死患者152例为研究对象。术后随访1年,根据患者是否发生HF分为HF组和(n=47)非HF组(n=105)。采用酶联免疫吸附试验(enzyme-linked immunosorbent assay,ELISA)法检测PCI治疗前患者血清SFRP-5、CXCL16的浓度;采用多因素Logistic回归法分析影响心肌梗死患者PCI治疗后HF发生的因素;绘制受试者工作特征(receiver operating characteristic,ROC)曲线分析血清SFRP-5、CXCL16浓度对心肌梗死患者PCI治疗后HF发生的预测价值。结果与非HF组患者比较,HF组患者性别、体质量指数(body mass index,BMI)、吸烟史、原发性高血压(高血压)史、糖尿病史、收缩压、舒张压及血肌酐(serum creatinine,Scr)、空腹血糖、总胆固醇浓度比较,差异无统计学意义(P>0.05);血清SFRP-5浓度显著降低,年龄及纤维蛋白原、CXCL16浓度浓度显著升高,差异有统计学意义(P<0.05)。年龄(OR=1.712)、纤维蛋白原(OR=2.240)、CXCL16浓度升高(OR=3.948),SFRP-5浓度降低(OR=0.284)均是影响心肌梗死患者PCI治疗后HF发生的危险因素(P<0.05)。血清SFRP-5、CXCL16浓度单独预测心肌梗死患者PCI治疗后HF发生的曲线下面积(area under the curve,AUC)分别为0.698(95%CI:0.619~0.770)、0.801(95%CI:0.729~0.861),二者联合预测的AUC为0.952(95%CI:0.905~0.980),灵敏度为91.49%,特异度为91.43%。联合预测价值显著高于单一指标预测(Z_(三者联合-SFRP-5)=5.839、Z_(三者联合-CXCL16)=3.564,P<0.05)。结论血清SFRP-5、CXCL16浓度对心肌梗死患者PCI治疗后HF发生具有一定的预测价值,且二者联合的预测价值更高。展开更多
In recent time, data analysis using machine learning accelerates optimized solutions on clinical healthcare systems. The machine learning methods greatly offer an efficient prediction ability in diagnosis system alter...In recent time, data analysis using machine learning accelerates optimized solutions on clinical healthcare systems. The machine learning methods greatly offer an efficient prediction ability in diagnosis system alternative with the clinicians. Most of the systems operate on the extracted features from the patients and most of the predicted cases are accurate. However, in recent time, the prevalence of COVID-19 has emerged the global healthcare industry to find a new drug that suppresses the pandemic outbreak. In this paper, we design a Deep Neural Network(DNN)model that accurately finds the protein-ligand interactions with the drug used. The DNN senses the response of protein-ligand interactions for a specific drug and identifies which drug makes the interaction that combats effectively the virus. With limited genome sequence of Indian patients submitted to the GISAID database, we find that the DNN system is effective in identifying the protein-ligand interactions for a specific drug.展开更多
Because of their important roles in cellular functions, life activities, drug screening, and disease treatment, the development of efficient methods for monitoring protein-ligand interaction is essential. In this stud...Because of their important roles in cellular functions, life activities, drug screening, and disease treatment, the development of efficient methods for monitoring protein-ligand interaction is essential. In this study, inspired by our previous studies on DNA conformation-selective fluorescent indicators, we developed a new sensing platform for monitoring protein-ligand interaction and detecting protein activity based on binding-mediated DNA protection and the dsDNA-lighted fluorophore, ethyl-4-[3,6-bis(1-methyl-4-vinylpyridium iodine)-9 H-carbazol-9-yl)] butanoate(EBCB). The ligand was purposefully linked to the 3?-terminal of a hairpin DNA probe to selectively bind with the target protein and protect the DNA from cleavage by exonuclease III. By virtue of EBCB's outstanding capacity to discriminate DNA conformation, the protein-ligand interaction could be effectively monitored through a fluorescence change in EBCB. A high fluorescence signal was detected when the hairpin DNA was protected in the presence of the target protein, whereas a much lower signal was observed in the presence of nontarget proteins.Our results demonstrated that the proposed strategy had high potential, such as high selectivity and relatively high sensitivity, for monitoring protein-ligand interaction and detecting protein activity. We believe these results will pave the way for applying dsDNA-lighted fluorophore EBCB as an effective signal transducer for DNA conformation transformation-mediated biochemical sensing.展开更多
This is a brief review of the computational modeling of protein-ligand interactions using a recently developed fully polarizable continuum model(FPCM)and rational drug design.Computational modeling has become a powerf...This is a brief review of the computational modeling of protein-ligand interactions using a recently developed fully polarizable continuum model(FPCM)and rational drug design.Computational modeling has become a powerful tool in understanding detailed protein-ligand interactions at molecular level and in rational drug design.To study the binding of a protein with multiple molecular species of a ligand,one must accurately determine both the relative free energies of all of the molecular species in solution and the corresponding microscopic binding free energies for all of the molecular species binding with the protein.In this paper,we aim to provide a brief overview of the recent development in computational modeling of the solvent effects on the detailed protein-ligand interactions involving multiple molecular species of a ligand related to rational drug design.In particular,we first briefly discuss the main challenges in computational modeling of the detailed protein-ligand interactions involving the multiple molecular species and then focus on the FPCM model and its applications.The FPCM method allows accurate determination of the solvent effects in the first-principles quantum mechanism(QM)calculations on molecules in solution.The combined use of the FPCM-based QM calculations and other computational modeling and simulations enables us to accurately account for a protein binding with multiple molecular species of a ligand in solution.Based on the computational modeling of the detailed protein-ligand interactions,possible new drugs may be designed rationally as either small-molecule ligands of the protein or engineered proteins that bind/metabolize the ligand.The computational drug design has successfully led to discovery and development of promising drugs.展开更多
目的评价免疫检查点抑制剂(ICIs)一线治疗晚期胃癌的有效性及安全性。方法检索PubMed、Web of Science、Embase、The Cochrane Library、万方数据、中国知网、维普网,收集ICIs一线治疗晚期胃癌的Ⅲ期临床随机对照试验(RCT)及相关肿瘤学...目的评价免疫检查点抑制剂(ICIs)一线治疗晚期胃癌的有效性及安全性。方法检索PubMed、Web of Science、Embase、The Cochrane Library、万方数据、中国知网、维普网,收集ICIs一线治疗晚期胃癌的Ⅲ期临床随机对照试验(RCT)及相关肿瘤学术年会的会议摘要,检索时限为建库起至2025年6月1日。筛选文献、提取数据、评价文献质量后,采用R语言软件4.3.2版进行网状Meta分析。结果共纳入8项研究,共计7801例患者。网状Meta分析结果显示,在有效性方面,与化疗(Chemo)比较,SHR-1701_Chemo、卡度尼利单抗+化疗(Cadoni_Chemo)、信迪利单抗+化疗、帕博利珠单抗+化疗和替雷利珠单抗+化疗均能显著延长患者的中位总生存期(OS)和中位无进展生存期(PFS)(P<0.05);而纳武利尤单抗+化疗仅显著延长了患者的中位PFS(P<0.05)。累积排名曲线下面积(SUCRA)结果显示,中位OS排名前2位的干预措施为SHR-1701_Chemo和Cadoni_Chemo;中位PFS排名前2位的干预措施为Cadoni_Chemo和SHR-1701_Chemo。对于程序性死亡受体配体1(PD-L1)综合阳性评分(CPS)≥5分患者,Cadoni_Chemo和SHR-1701_Chemo同样展现出最优的OS和PFS获益(P<0.05)。在安全性方面,各干预措施的任意不良事件(AEs)发生率及≥3级AEs发生率比较,差异均无统计学意义(P>0.05)。任意AEs发生率SUCRA排名前2位的为SHR-1701_Chemo和Chemo;≥3级AEs发生率SUCRA排名前2位的为Chemo和舒格利单抗+化疗。结论对于晚期胃癌患者,Cadoni_Chemo和SHR-1701_Chemo展现出最佳的OS和PFS获益,且在PD-L1 CPS≥5分的患者中优势依然明确;在安全性方面,Chemo引起的任意AEs及≥3级AEs的发生风险相对较低。展开更多
基金financial supports of“the Fundamental Research Funds for the Central Universities”(DUT22YG218),NSFC(22278053,22078041)China Postdoctoral Science Foundation(2022M710578)“the Dalian High-level Talents Innovation Support Program”(2021RQ105).
文摘Binding kinetic properties of protein–ligand complexes are crucial factors affecting the drug potency.Nevertheless,the current in silico techniques are insufficient in providing accurate and robust predictions for binding kinetic properties.To this end,this work develops a variety of binding kinetic models for predicting a critical binding kinetic property,dissociation rate constant,using eight machine learning(ML)methods(Bayesian Neural Network(BNN),partial least squares regression,Bayesian ridge,Gaussian process regression,principal component regression,random forest,support vector machine,extreme gradient boosting)and the descriptors of the van der Waals/electrostatic interaction energies.These eight models are applied to two case studies involving the HSP90 and RIP1 kinase inhibitors.Both regression results of two case studies indicate that the BNN model has the state-of-the-art prediction accuracy(HSP90:R^(2)_(test)=0:947,MAE_(test)=0.184,rtest=0.976,RMSE_(test)=0.220;RIP1 kinase:R^(2)_(test)=0:745,MAE_(test)=0.188,rtest=0.961,RMSE_(test)=0.290)in comparison with other seven ML models.
基金supported in part by the National Natural Science Foundation of China(Grant Nos.T2225007 and T2222012)the Foundation for Innovative Research Groups of State Key Laboratory of Microbial Technology,China(Grant No.WZCX2021-03).
文摘Since its establishment in 2013,BioLiP has become one of the widely used resources for protein-ligand interactions.Nevertheless,several known issues occurred with it over the past decade.For example,the protein-ligand interactions are represented in the form of single chain-based tertiary structures,which may be inappropriate as many interactions involve multiple protein chains(known as quaternary structures).We sought to address these issues,resulting in Q-BioLiP,a comprehensive resource for quaternary structure-based protein-ligand interactions.The major features of Q-BioLiP include:(1)representing protein structures in the form of quaternary structures rather than single chain-based tertiary structures;(2)pairing DNA/RNA chains properly rather than separation;(3)providing both experimental and predicted binding affinities;(4)retaining both biologically relevant and irrelevant interactions to alleviate the wrong justification of ligands’biological relevance;and(5)developing a new quaternary structure-based algorithm for the modelling of protein-ligand complex structure.With these new features,Q-BioLiP is expected to be a valuable resource for studying biomolecule interactions,including protein-small molecule interaction,protein-metal ion interaction,protein-peptide interaction,protein-protein interaction,protein-DNA/RNA interaction,and RNA-small molecule interaction.Q-BioLiP is freely available at https://yanglab.qd.sdu.edu.cn/Q-BioLiP/.
文摘目的探究血清分泌型卷曲相关蛋白5(secreted frizzled related protein 5,SFRP-5)、C-X-C基序趋化因子配体16(C-X-C motif chemokine ligand 16,CXCL16)对心肌梗死患者经皮冠状动脉介入(percutaneous coronary intervention,PCI)治疗后心力衰竭(heart failure,HF)发生的预测价值。方法选取2022年6月至2024年1月于保定市第二中心医院实施PCI治疗的心肌梗死患者152例为研究对象。术后随访1年,根据患者是否发生HF分为HF组和(n=47)非HF组(n=105)。采用酶联免疫吸附试验(enzyme-linked immunosorbent assay,ELISA)法检测PCI治疗前患者血清SFRP-5、CXCL16的浓度;采用多因素Logistic回归法分析影响心肌梗死患者PCI治疗后HF发生的因素;绘制受试者工作特征(receiver operating characteristic,ROC)曲线分析血清SFRP-5、CXCL16浓度对心肌梗死患者PCI治疗后HF发生的预测价值。结果与非HF组患者比较,HF组患者性别、体质量指数(body mass index,BMI)、吸烟史、原发性高血压(高血压)史、糖尿病史、收缩压、舒张压及血肌酐(serum creatinine,Scr)、空腹血糖、总胆固醇浓度比较,差异无统计学意义(P>0.05);血清SFRP-5浓度显著降低,年龄及纤维蛋白原、CXCL16浓度浓度显著升高,差异有统计学意义(P<0.05)。年龄(OR=1.712)、纤维蛋白原(OR=2.240)、CXCL16浓度升高(OR=3.948),SFRP-5浓度降低(OR=0.284)均是影响心肌梗死患者PCI治疗后HF发生的危险因素(P<0.05)。血清SFRP-5、CXCL16浓度单独预测心肌梗死患者PCI治疗后HF发生的曲线下面积(area under the curve,AUC)分别为0.698(95%CI:0.619~0.770)、0.801(95%CI:0.729~0.861),二者联合预测的AUC为0.952(95%CI:0.905~0.980),灵敏度为91.49%,特异度为91.43%。联合预测价值显著高于单一指标预测(Z_(三者联合-SFRP-5)=5.839、Z_(三者联合-CXCL16)=3.564,P<0.05)。结论血清SFRP-5、CXCL16浓度对心肌梗死患者PCI治疗后HF发生具有一定的预测价值,且二者联合的预测价值更高。
文摘In recent time, data analysis using machine learning accelerates optimized solutions on clinical healthcare systems. The machine learning methods greatly offer an efficient prediction ability in diagnosis system alternative with the clinicians. Most of the systems operate on the extracted features from the patients and most of the predicted cases are accurate. However, in recent time, the prevalence of COVID-19 has emerged the global healthcare industry to find a new drug that suppresses the pandemic outbreak. In this paper, we design a Deep Neural Network(DNN)model that accurately finds the protein-ligand interactions with the drug used. The DNN senses the response of protein-ligand interactions for a specific drug and identifies which drug makes the interaction that combats effectively the virus. With limited genome sequence of Indian patients submitted to the GISAID database, we find that the DNN system is effective in identifying the protein-ligand interactions for a specific drug.
基金supported by the National Natural Science Foundation of China (21605008, 21735001, 21575018, 21505006)the Hunan Provincial Natural Science Foundation (2016JJ3001)
文摘Because of their important roles in cellular functions, life activities, drug screening, and disease treatment, the development of efficient methods for monitoring protein-ligand interaction is essential. In this study, inspired by our previous studies on DNA conformation-selective fluorescent indicators, we developed a new sensing platform for monitoring protein-ligand interaction and detecting protein activity based on binding-mediated DNA protection and the dsDNA-lighted fluorophore, ethyl-4-[3,6-bis(1-methyl-4-vinylpyridium iodine)-9 H-carbazol-9-yl)] butanoate(EBCB). The ligand was purposefully linked to the 3?-terminal of a hairpin DNA probe to selectively bind with the target protein and protect the DNA from cleavage by exonuclease III. By virtue of EBCB's outstanding capacity to discriminate DNA conformation, the protein-ligand interaction could be effectively monitored through a fluorescence change in EBCB. A high fluorescence signal was detected when the hairpin DNA was protected in the presence of the target protein, whereas a much lower signal was observed in the presence of nontarget proteins.Our results demonstrated that the proposed strategy had high potential, such as high selectivity and relatively high sensitivity, for monitoring protein-ligand interaction and detecting protein activity. We believe these results will pave the way for applying dsDNA-lighted fluorophore EBCB as an effective signal transducer for DNA conformation transformation-mediated biochemical sensing.
基金supported by the National Science Foundation(grant CHE-1111761)the National Institutes of Health(grants R01 DA032910,R01 DA013930,R01 DA025100,R01 DA021416,and RC1 MH088480)+1 种基金Alzheimer’s Drug Discovery Foundation(ADDA)Institute for the Study of Aging(ISOA).
文摘This is a brief review of the computational modeling of protein-ligand interactions using a recently developed fully polarizable continuum model(FPCM)and rational drug design.Computational modeling has become a powerful tool in understanding detailed protein-ligand interactions at molecular level and in rational drug design.To study the binding of a protein with multiple molecular species of a ligand,one must accurately determine both the relative free energies of all of the molecular species in solution and the corresponding microscopic binding free energies for all of the molecular species binding with the protein.In this paper,we aim to provide a brief overview of the recent development in computational modeling of the solvent effects on the detailed protein-ligand interactions involving multiple molecular species of a ligand related to rational drug design.In particular,we first briefly discuss the main challenges in computational modeling of the detailed protein-ligand interactions involving the multiple molecular species and then focus on the FPCM model and its applications.The FPCM method allows accurate determination of the solvent effects in the first-principles quantum mechanism(QM)calculations on molecules in solution.The combined use of the FPCM-based QM calculations and other computational modeling and simulations enables us to accurately account for a protein binding with multiple molecular species of a ligand in solution.Based on the computational modeling of the detailed protein-ligand interactions,possible new drugs may be designed rationally as either small-molecule ligands of the protein or engineered proteins that bind/metabolize the ligand.The computational drug design has successfully led to discovery and development of promising drugs.
