Identification of the drug-binding residues on the surface of proteins is a vital step in drug discovery and it is important for understanding protein function. Most previous researches are based on the structural inf...Identification of the drug-binding residues on the surface of proteins is a vital step in drug discovery and it is important for understanding protein function. Most previous researches are based on the structural information of proteins, but the structures of most proteins are not available. So in this article, a sequence-based method was proposed by combining the support vector machine (SVM)-based ensemble learning and the improved position specific scoring matrix (PSSM). In order to take the local environment information of a drug-binding site into account, an improved PSSM profile scaled by the sliding window and smoothing window was used to improve the prediction result. In addition, a new SVM-based ensemble learning method was developed to deal with the imbalanced data classification problem that commonly exists in the binding site predictions. When performed on the dataset of 985 drug-binding residues, the method achieved a very promising prediction result with the area under the curve (AUC) of 0.9264. Furthermore, an independent dataset of 349 drug- binding residues was used to evaluate the pre- diction model and the prediction accuracy is 84.68%. These results suggest that our method is effective for predicting the drug-binding sites in proteins. The code and all datasets used in this article are freely available at http://cic.scu.edu.cn/bioinformatics/Ensem_DBS.zip.展开更多
Pancreatic ductal adenocarcinoma(PDAC) is one of the most aggressive diseases and is characterized by high chemoresistance, leading to the lack of effective therapeutic approaches and grim prognosis. Despite increasin...Pancreatic ductal adenocarcinoma(PDAC) is one of the most aggressive diseases and is characterized by high chemoresistance, leading to the lack of effective therapeutic approaches and grim prognosis. Despite increasing understanding of the mechanisms of chemoresistance in cancer and the role of ATPbinding cassette(ABC) transporters in this resistance, the therapeutic potential of their pharmacological inhibition has not been successfully exploited yet. In spite of the discovery of potent pharmacological modulators of ABC transporters, the results obtained in clinical trials have been so far disappointing, with high toxicity levels impairing their successful administration to the patients. Critically, although ABC transporters have been mostly studied for their involvement in development of multidrug resistance(MDR), in recent years the contribution of ABC transporters to cancer initiation and progression has emerged as an important area of research, the understanding of which could significantly influence the development of more specific and efficient therapies. In this review, we explore the role of ABC transporters in the development and progression of malignancies, with focus on PDAC. Their established involvement in development of MDR will be also presented. Moreover, an emerging role for ABC transporters as prognostic tools for patients' survival will be discussed, demonstrating the therapeutic potential of ABC transporters in cancer therapy.展开更多
In a recent study published in Nature Medicine,Wang et al.developed an excellent framework called UniBind based on artificial intelligence(AI),which enables accurately predicting infectivity of SARS-CoV-2 variants and...In a recent study published in Nature Medicine,Wang et al.developed an excellent framework called UniBind based on artificial intelligence(AI),which enables accurately predicting infectivity of SARS-CoV-2 variants and evolutionary trends of future viral variants.1 This computational method holds the possibility to not only serve as a valuable early-warning tool for monitoring potential pathogenic SARS-CoV-2 variants but also facilitate fundamental research on protein-protein interactions(PPIs).展开更多
目的探讨AKI risk评分(基质金属蛋白酶-2×胰岛素样生长因子-7,TIMP-2×IGFBP-7)对急诊脓毒症患者死亡风险的预测价值。方法前瞻性观察2021年9月至2022年12月中国科学技术大学附属第一医院及北京协和医院急诊科收住的脓毒症患者...目的探讨AKI risk评分(基质金属蛋白酶-2×胰岛素样生长因子-7,TIMP-2×IGFBP-7)对急诊脓毒症患者死亡风险的预测价值。方法前瞻性观察2021年9月至2022年12月中国科学技术大学附属第一医院及北京协和医院急诊科收住的脓毒症患者,分别测量患者入院时和入院后6 h的AKI risk评分并计算其变化值(AKI risk-gap),利用多因素Logistic回归、Cox回归、受试者工作特征(ROC)曲线及曲线下面积(AUC)分析AKI risk评分对患者院内死亡风险的预测效能;亚组分析中根据患者是否罹患AKI进一步分析AKI risk评分与不同亚组(AKI组和非AKI组)患者预后的关系。结果本研究共纳入患者202例,住院期间死亡87例(43%)。ROC曲线显示,6 h AKI risk评分预测脓毒症患者院内死亡最为准确,其AUC为0.71(95%CI 0.63~0.78)。亚组分析中AKI组患者6 h AKI risk评分预测院内死亡的AUC为0.76(95%CI 0.65~0.85),非AKI组AUC为0.63(95%CI 0.52~0.73)。多因素Logistic回归和Cox回归分析表明,6 h AKI risk评分和AKI risk-gap是患者院内死亡的独立危险因素。结论AKI risk评分对脓毒症患者院内死亡风险有较好的预测价值,尤其6 h AKI risk评分在罹患AKI的亚组患者中预测价值最高,可为临床区分高危患者并给予相应治疗提供参考。展开更多
Effective identification of major histocompatibility complex (MHC) molecules restricted peptides is a critical step in discovering immune epitopes. Although many online servers have been built to predict class Ⅱ MH...Effective identification of major histocompatibility complex (MHC) molecules restricted peptides is a critical step in discovering immune epitopes. Although many online servers have been built to predict class Ⅱ MHC-peptide binding affinity, they have been trained on different datasets, and thus fail in providing a unified comparison of various methods. In this paper, we present our implementation of seven popular predictive methods, namely SMM-align, ARB, SVR-pairwise, Gibbs sampler. ProPred, LP-top2, and MHCPred, on a single web server named BiodMHC (http://biod.whu.edu.cn/BiodMHC/index.html, the software is available upon request). Using a standard measure of AUC (Area Under the receiver operating characteristic Curves), we compare these methods by means of not only cross validation but also prediction on independent test datasets. We find that SMM-align, ProPred, SVR-pairwise, ARB, and Gibbs sampler are the five best-performing methods. For the binding affinity prediction of class Ⅱ MHC-peptide, BiodMHC provides a convenient online platform for researchers to obtain binding information simultaneously using various methods.展开更多
文摘Identification of the drug-binding residues on the surface of proteins is a vital step in drug discovery and it is important for understanding protein function. Most previous researches are based on the structural information of proteins, but the structures of most proteins are not available. So in this article, a sequence-based method was proposed by combining the support vector machine (SVM)-based ensemble learning and the improved position specific scoring matrix (PSSM). In order to take the local environment information of a drug-binding site into account, an improved PSSM profile scaled by the sliding window and smoothing window was used to improve the prediction result. In addition, a new SVM-based ensemble learning method was developed to deal with the imbalanced data classification problem that commonly exists in the binding site predictions. When performed on the dataset of 985 drug-binding residues, the method achieved a very promising prediction result with the area under the curve (AUC) of 0.9264. Furthermore, an independent dataset of 349 drug- binding residues was used to evaluate the pre- diction model and the prediction accuracy is 84.68%. These results suggest that our method is effective for predicting the drug-binding sites in proteins. The code and all datasets used in this article are freely available at http://cic.scu.edu.cn/bioinformatics/Ensem_DBS.zip.
文摘Pancreatic ductal adenocarcinoma(PDAC) is one of the most aggressive diseases and is characterized by high chemoresistance, leading to the lack of effective therapeutic approaches and grim prognosis. Despite increasing understanding of the mechanisms of chemoresistance in cancer and the role of ATPbinding cassette(ABC) transporters in this resistance, the therapeutic potential of their pharmacological inhibition has not been successfully exploited yet. In spite of the discovery of potent pharmacological modulators of ABC transporters, the results obtained in clinical trials have been so far disappointing, with high toxicity levels impairing their successful administration to the patients. Critically, although ABC transporters have been mostly studied for their involvement in development of multidrug resistance(MDR), in recent years the contribution of ABC transporters to cancer initiation and progression has emerged as an important area of research, the understanding of which could significantly influence the development of more specific and efficient therapies. In this review, we explore the role of ABC transporters in the development and progression of malignancies, with focus on PDAC. Their established involvement in development of MDR will be also presented. Moreover, an emerging role for ABC transporters as prognostic tools for patients' survival will be discussed, demonstrating the therapeutic potential of ABC transporters in cancer therapy.
基金the National Natural Science Foundation of China:82201932,82025001ZhongNanShan Medical Foundation of Guangdong Province:ZNSA-2020012Guangdong Basic and Applied Basic Research Foundation:2022B1515020059,2021B1515130005.
文摘In a recent study published in Nature Medicine,Wang et al.developed an excellent framework called UniBind based on artificial intelligence(AI),which enables accurately predicting infectivity of SARS-CoV-2 variants and evolutionary trends of future viral variants.1 This computational method holds the possibility to not only serve as a valuable early-warning tool for monitoring potential pathogenic SARS-CoV-2 variants but also facilitate fundamental research on protein-protein interactions(PPIs).
文摘目的探讨AKI risk评分(基质金属蛋白酶-2×胰岛素样生长因子-7,TIMP-2×IGFBP-7)对急诊脓毒症患者死亡风险的预测价值。方法前瞻性观察2021年9月至2022年12月中国科学技术大学附属第一医院及北京协和医院急诊科收住的脓毒症患者,分别测量患者入院时和入院后6 h的AKI risk评分并计算其变化值(AKI risk-gap),利用多因素Logistic回归、Cox回归、受试者工作特征(ROC)曲线及曲线下面积(AUC)分析AKI risk评分对患者院内死亡风险的预测效能;亚组分析中根据患者是否罹患AKI进一步分析AKI risk评分与不同亚组(AKI组和非AKI组)患者预后的关系。结果本研究共纳入患者202例,住院期间死亡87例(43%)。ROC曲线显示,6 h AKI risk评分预测脓毒症患者院内死亡最为准确,其AUC为0.71(95%CI 0.63~0.78)。亚组分析中AKI组患者6 h AKI risk评分预测院内死亡的AUC为0.76(95%CI 0.65~0.85),非AKI组AUC为0.63(95%CI 0.52~0.73)。多因素Logistic回归和Cox回归分析表明,6 h AKI risk评分和AKI risk-gap是患者院内死亡的独立危险因素。结论AKI risk评分对脓毒症患者院内死亡风险有较好的预测价值,尤其6 h AKI risk评分在罹患AKI的亚组患者中预测价值最高,可为临床区分高危患者并给予相应治疗提供参考。
基金supported by the National Nature Science Foundation of China (No.60773010)the Shanghai Committee of Science and Technology, China (No.08DZ2271800 and 09DZ2272800)
文摘Effective identification of major histocompatibility complex (MHC) molecules restricted peptides is a critical step in discovering immune epitopes. Although many online servers have been built to predict class Ⅱ MHC-peptide binding affinity, they have been trained on different datasets, and thus fail in providing a unified comparison of various methods. In this paper, we present our implementation of seven popular predictive methods, namely SMM-align, ARB, SVR-pairwise, Gibbs sampler. ProPred, LP-top2, and MHCPred, on a single web server named BiodMHC (http://biod.whu.edu.cn/BiodMHC/index.html, the software is available upon request). Using a standard measure of AUC (Area Under the receiver operating characteristic Curves), we compare these methods by means of not only cross validation but also prediction on independent test datasets. We find that SMM-align, ProPred, SVR-pairwise, ARB, and Gibbs sampler are the five best-performing methods. For the binding affinity prediction of class Ⅱ MHC-peptide, BiodMHC provides a convenient online platform for researchers to obtain binding information simultaneously using various methods.