流感病毒神经氨酸酶抑制剂的理性筛选

介绍了理性筛选流感病毒神经氨酸酶抑制剂的全过程，共分4个阶段：1)化合物数据库类药性处理；2)建立神经氨酸酶抑制剂三维药效团并对目标数据库进行构象搜索；3)分子对接及对接后分析；4)神经氨酸酶抑制模型的建立及待测化合物的活性检测。活性检测后发现4个活性化合物，其中Ic。为10。M的化合物1个．Ic，。为10^-6M的化合物2个，IC50为10^-7M的化合物1个。应用理性筛选方法，从化合物数据库中挑选出部分化合物进行神经氨酸酶抑制活性的筛选，减少了药物筛选的盲目性，提高了药物发现的机率。     

乙酰胆碱M3受体拮抗剂的从头设计

M3受体是人体内分布广泛的一种重要的毒蕈碱乙酰胆碱受体亚型,与膀胱过度活动症、心律失常、呼吸道及支气管疾病密切相关.设计与合成M3受体拮抗剂对于开发治疗相关疾病的药物具有重要理论意义和应用价值。本文采用同源模建方法,构建了人M3受体蛋白的三维结构,基于M3受体拮抗剂的结构构建了其药效团模型,其中较理想的模型含有6个药效团特征元素。利用药效团模型进行了虚拟筛选,虚拟筛选的数据库是本实验室构建的虚拟化合物库,发现了10个新型的对M3受体有拮抗作用的化合物。最后对这10个化合物进行了分子对接,根据对接结果,发现3个化合物对接能量及结合方式比较合理,为M3受体拮抗剂的合成研究及活性测定奠定了基础。     

基于深度神经网络的药物蛋白虚拟筛选

药物的研发是一种投入成本高、耗费时间长且成功率较低的一种研究,为了在药物开发阶段可以快速获得潜在的化合物,针对性地提出一种基于深度神经网络的药物蛋白虚拟筛选的方法。首先从给定数据集中学习如何提取相关特征,获取配体原子和残基类型进行特征分析,快速识别活性分子和非活性分子,然后使用降维方式和K折验证等方法对药物筛选的模型进行处理,最后通过分析富集因子和AUC值验证诱饵化合物与分子蛋白的互相作用验证模型的可靠程度,实验结果表明所提出的筛选方法具有很好的可行性和有效性,有效地加快了虚拟筛选过程。     

基于图卷积神经网络的小分子虚拟筛选

新药研发存在研发周期长、成本高和成功率低等问题。为了解决这一系列问题,提高早期药物研发效率,提出一种基于图卷积神经网络的虚拟筛选方法,并利用模型对EGFR(Epidermal Growth Factor Receptor,表皮生长因子受体)靶点进行虚拟筛选。首先获取EGFR靶点的相关数据,对其进行数据处理后用于模型训练;随后应用模型筛选大量化合物,筛选出小分子后,将其与药物分子进行化合物相似性搜索,验证其是否与已知的EGFR药物存在相似性;同时,将图卷积神经网络(Graph Convolutional Networks,GCN)模型与其他传统机器学习模型进行比较,证明本研究模型在各项指标中均优于其他模型。实验结果表明,本研究提出的方法具有较好的预测性和准确性,为发现潜在药物提供了助力。     

计算机药物筛选方法探讨

本文论述了计算机药物筛选方法及其应用程序的开发,并通过建立乙酰胆碱酯酶（AchE)抑制剂的筛选模型,检测化合物样品的生物活性,比较生物活性结果与计算机筛选结果,检验了计算机药物筛选方法的可靠性。结果表明,计算机药物筛选方法在创新药物研究中具有重要意义,但需要进一步改进,并结合其他方法来提高它的可靠性。     

计算机药物筛选方法探讨

本文论述了计算机药物筛选方法及其应用程序的开发,并通过建立乙酰胆碱酯酶(AchE)抑制剂的筛选模型,检测化合物样品的生物活性,比较生物活性结果与计算机筛选结果,检验了计算机药物筛选方法的可靠性.结果表明,计算机药物筛选方法在创新药物研究中具有重要意义,但需要进一步改进,并结合其他方法来提高它的可靠性.     

HMG-CoA还原酶抑制剂的虚拟筛选模型的建立

HMG-CoA还原酶(简称HMGR)是降血脂药物设计的重要靶标,抑制该酶的活性可以有效地降低血浆总胆固醇水平,从而降低罹患心脑血管疾病的几率。虽然已经有数种他汀类药物作为HMGR抑制剂应用于临床,但是他汀类药物的安全性,特别是长期服用的安全性一直备受关注,所以设计新型安全的HMGR抑制剂仍然十分迫切。论文根据hHMGR的晶体结构,利用Dock、FlexX、Autodock 3个程序建立了hHMGR抑制剂的虚拟筛选模型,模型的可靠性通过重复晶体结构、对比对接打分和化合物的活性之间的相关性等方法得以验证,最后,分析各种对接软件的特点,指出了hHMGR抑制剂虚拟筛选,特别是目筛中应当注意的问题,以期为新型HMGR抑制剂的设计提供指导。     

DDGrid:一种大规模药物虚拟筛选网格

化合物活性筛选是创新药物研究的起点和具有决定意义的步骤,利用网格计算技术进行药物虚拟筛选能够极大提高药物筛选的有效性,同时可以大量减少新药研制的成本和时间。新药研发网格DDGrid是中国国家网格CNGrid的重要支持项目,通过实施主从模式架构并在网格资源监控中使用适配器模式,DDGrid可以对超过10万规模的化合物分子数据库进行虚拟筛选。     

超大规模药物虚拟筛选的实现与应用

基于分子对接的药物虚拟筛选技术通过评估多个配体化合物与受体的结合强度来筛选最强结合的分子。在新冠病毒疫情全球蔓延形势下,超大规模快速药物虚拟筛选对于从海量配体结构中筛选出潜药分子至关重要。超级计算机的强大算力为药物虚拟筛选提供了硬件保障,但超大规模的药物虚拟筛选还面临着很多挑战,影响了计算的有效进行。在对挑战进行分析的基础上,提出了以中央数据库进行集中任务分发的方案,设计了多层级任务分发框架,并通过多层级智能调度、海量小分子文件多层级压缩处理、动态负载均衡、高容错管理等技术有效应对了面临的各种挑战,开发了简单易用的“树”形多层级任务分发系统,实现了快速高效稳定的药物虚拟筛选任务分发、计算和结果处理功能,计算效率近线性。在此基础上,采用异构计算技术在国产先进计算系统上针对新冠病毒两种不同活性位点快速完成了超过20亿化合物的药物虚拟筛选,为应对暴发性恶性传染病的超大规模快速虚拟筛选提供了强大计算保障。     

抗药物依赖药效团模型的构建与虚拟筛选

运用计算机辅助药物设计方法,基于多巴胺D2和D3受体部分激动剂构建具有抗药物依赖功效的药效团模型。再以该药效团模型作为提问结构,在天然产物数据库中进行虚拟筛选,利用分子对接技术,对筛选结果进行分析和评价,初步得到具有抗药物依赖功效的目标化合物。最后对目标化合物进行虚拟水溶性、肠道吸收性和血脑屏障通透性研究,为抗药物依赖新药的研发提供理论基础。     

Identification of potential bivalent inhibitors from natural compounds for acetylcholinesterase through in silico screening using multiple pharmacophores

The symptomatic cure observed in the treatment of Alzheimer's disease (AD) by FDA approved drugs could possibly be due to their specificity against the active site of acetylcholinesterase (AChE) and not by targeting its pathogenicity. The AD pathogenicity involved in AChE protein is mainly due to amyloid beta peptide aggregation, which is triggered specifically by peripheral anionic site (PAS) of AChE. In the present study, a workflow has been developed for the identification and prioritization of potential compounds that could interact not only with the catalytic site but also with the PAS of AChE. To elucidate the essential structural elements of such inhibitors, pharmacophore models were constructed using PHASE, based on a set of fifteen best known AChE inhibitors. All these models on validation were further restricted to the best seven. These were transferred to PHASE database screening platform for screening 89,425 molecules deposited at the “ZINC natural product database”. Novel lead molecules retrieved were subsequently subjected to molecular docking and ADME profiling. A set of 12 compounds were identified with high pharmacophore fit values and good predicted biological activity scores. These compounds not only showed higher affinity for catalytic residues, but also for Trp86 and Trp286, which are important, at PAS of AChE. The knowledge gained from this study, could lead to the discovery of potential AChE inhibitors that are highly specific for AD treatment as they are bivalent lead molecules endowed with dual binding ability for both catalytic site and PAS of AChE.     

Strategies for generating less toxic P-selectin inhibitors: pharmacophore modeling, virtual screening and counter pharmacophore screening to remove toxic hits

This paper describes the generation of ligand-based as well as structure-based models and virtual screening of less toxic P-selectin receptor inhibitors. Ligand-based model, 3D-pharmacophore was generated using 27 quinoline salicylic acid compounds and is used to retrieve the actives of P-selectin. This model contains three hydrogen bond acceptors (HBA), two ring aromatics (RA) and one hydrophobic feature (HY). To remove the toxic hits from the screened molecules, a counter pharmacophore model was generated using inhibitors of dihydrooratate dehydrogenase (DHOD), an important enzyme involved in nucleic acid synthesis, whose inhibition leads to toxic effects. Structure-based models were generated by docking and scoring of inhibitors against P-selectin receptor, to remove the false positives committed by pharmacophore screening. The combination of these ligand-based and structure-based virtual screening models were used to screen a commercial database containing 538,000 compounds.     

Identification of potent inhibitors of DNA methyltransferase 1 (DNMT1) through a pharmacophore-based virtual screening approach

DNA methylation is an epigenetic change that results in the addition of a methyl group at the carbon-5 position of cytosine residues. DNA methyltransferase (DNMT) inhibitors can suppress tumour growth and have significant therapeutic value. However, the established inhibitors are limited in their application due to their substantial cytotoxicity. Additionally, the standard drugs for DNMT inhibition are non-selective cytosine analogues with considerable cytotoxic side-effects. In the present study, we have designed a workflow by integrating various ligand-based and structure-based approaches to discover new agents active against DNMT1. We have derived a pharmacophore model with the help of available DNMT1 inhibitors. Utilising this model, we performed the virtual screening of Maybridge chemical library and the identified hits were then subsequently filtered based on the Naïve Bayesian classification model. The molecules that have returned from this classification model were subjected to ensemble based docking. We have selected 10 molecules for the biological assay by inspecting the interactions portrayed by these molecules. Three out of the ten tested compounds have shown DNMT1 inhibitory activity. These compounds were also found to demonstrate potential inhibition of cellular proliferation in human breast cancer MDA-MB-231 cells. In the present study, we have utilized a multi-step virtual screening protocol to identify inhibitors of DNMT1, which offers a starting point to develop more potent DNMT1 inhibitors as anti-cancer agents.     

Multi-step virtual screening to develop selective DYRK1A inhibitors

Developing selective inhibitors for a particular kinase remains a major challenge in kinase-targeted drug discovery. Here we performed a multi-step virtual screening for dual-specificity tyrosine-phosphorylation-regulated kinase 1A (DYRK1A) inhibitors by focusing on the selectivity for DYRK1A over cyclin-dependent kinase 5 (CDK5). To examine the key factors contributing to the selectivity, we constructed logistic regression models to discriminate between actives and inactives for DYRK1A and CDK5, respectively, using residue-based binding free energies. The residue-based parameters were calculated by molecular mechanics-generalized Born surface area (MM-GBSA) decomposition methods for kinase–ligand complexes modeled by computer ligand docking. Based on the findings from the logistic regression models, we built a three-dimensional (3D) pharmacophore model and chose filter criteria for the multi-step virtual screening. The virtual hit compounds obtained from the screening were assessed for their inhibitory activities against DYRK1A and CDK5 by in vitro assay. Our screening identified two novel selective DYRK1A inhibitors with IC₅₀ values of several μM for DYRK1A and >100 μM for CDK5, which can be further optimized to develop more potent selective DYRK1A inhibitors.     

基于结构的组蛋白去乙酰化酶抑制剂虚拟筛选

组蛋白去乙酰化酶是抗肿瘤作用的新靶点,基于该酶复合物的三维结构,首先对具有分子多样性的数据库进行了虚拟筛选;然后根据已知HDAC抑制剂的结构特征和筛选的结果,以及与生物大分子互补性,选择合理的构建单元,组建靶向的虚拟组合库;最后进行数据库虚拟筛选,对分子对接的结果进行评分,选择出理论上与HDAC有较好结合能力的化合物,设计了酰胺类、脲类和酰肼类全新结构类型的HDAC抑制剂,初步生物活性评价结果表明,预期有生物活性的化合物显示出一定的HDAC酶抑制活性。     

Structure based virtual screening-driven identification of monastrol as a potent urease inhibitor

Virtual screening uses computer based methods to discover new ligands on the basis of biological structures. Among all virtual screening methods structure based docking has received considerable attention. In an attempt to identify new ligands as urease inhibitors, structure-based virtual screening (SBVS) of an in-house database of 10,000 organic compounds was carried out. The X-ray crystallographic structure of Bacillus pasteurii (BP) in complex with acetohydroxamic acid (PDB Code 4UBP) was used as a protein structure. As a starting point, ~10,000 compounds of our in-house database were analyzed to check redundancy and the compounds found repeated were removed from the database. Finally 6993 compounds were docked into the active site of BP urease using GOLD and MOE-Dock software. A remarkable feature of this study was the identification of monastrol, a well-known KSP inhibitor already in clinical trials, as a novel urease inhibitor. The hits identified were further evaluated by molecular docking and on examination of the affinity predictions, twenty-seven analogs of monastrol were synthesized by a multicomponent Biginelli reaction followed by their in vitro screening as urease inhibitors. Finally twelve compounds were identified as new urease inhibitors. The excellent in vitro activity suggested that these compounds may serve as viable lead compounds for the treatment of urease related problems.     

A support vector machines approach for virtual screening of active compounds of single and multiple mechanisms from large libraries at an improved hit-rate and enrichment factor

Support vector machines (SVM) and other machine-learning (ML) methods have been explored as ligand-based virtual screening (VS) tools for facilitating lead discovery. While exhibiting good hit selection performance, in screening large compound libraries, these methods tend to produce lower hit-rate than those of the best performing VS tools, partly because their training-sets contain limited spectrum of inactive compounds. We tested whether the performance of SVM can be improved by using training-sets of diverse inactive compounds. In retrospective database screening of active compounds of single mechanism (HIV protease inhibitors, DHFR inhibitors, dopamine antagonists) and multiple mechanisms (CNS active agents) from large libraries of 2.986 million compounds, the yields, hit-rates, and enrichment factors of our SVM models are 52.4–78.0%, 4.7–73.8%, and 214–10,543, respectively, compared to those of 62–95%, 0.65–35%, and 20–1200 by structure-based VS and 55–81%, 0.2–0.7%, and 110–795 by other ligand-based VS tools in screening libraries of ≥1 million compounds. The hit-rates are comparable and the enrichment factors are substantially better than the best results of other VS tools. 24.3–87.6% of the predicted hits are outside the known hit families. SVM appears to be potentially useful for facilitating lead discovery in VS of large compound libraries.     

A support vector machines approach for virtual screening of active compounds of single and multiple mechanisms from large libraries at an improved hit-rate and enrichment factor

Support vector machines (SVM) and other machine-learning (ML) methods have been explored as ligand-based virtual screening (VS) tools for facilitating lead discovery. While exhibiting good hit selection performance, in screening large compound libraries, these methods tend to produce lower hit-rate than those of the best performing VS tools, partly because their training-sets contain limited spectrum of inactive compounds. We tested whether the performance of SVM can be improved by using training-sets of diverse inactive compounds. In retrospective database screening of active compounds of single mechanism (HIV protease inhibitors, DHFR inhibitors, dopamine antagonists) and multiple mechanisms (CNS active agents) from large libraries of 2.986 million compounds, the yields, hit-rates, and enrichment factors of our SVM models are 52.4–78.0%, 4.7–73.8%, and 214–10,543, respectively, compared to those of 62–95%, 0.65–35%, and 20–1200 by structure-based VS and 55–81%, 0.2–0.7%, and 110–795 by other ligand-based VS tools in screening libraries of ≥1 million compounds. The hit-rates are comparable and the enrichment factors are substantially better than the best results of other VS tools. 24.3–87.6% of the predicted hits are outside the known hit families. SVM appears to be potentially useful for facilitating lead discovery in VS of large compound libraries.     

机器学习预测ACEI的比较与分析

血管紧张素转换酶抑制剂（ACEI）对高血压的治疗具有重要意义。基于从结构复杂的化合物数据库中构建的候选小分子数据集,采用分子对接技术从数据集中筛选出样本构建分类模型。分别采用支持向量机、[K]近邻、决策树、随机森林和贝叶斯方法建立血管紧张素转换酶潜在抑制剂和非抑制剂的分类模型。经结果对比,支持向量机相比于其他方法有更高的预测率,其中模型总体预测率和相关系数分别为82.4%和0.653。研究表明,支持向量机方法对于虚拟筛选血管紧张素转换酶抑制剂具有良好的效果。