基于定量构效关系的数据集可建模性。
Data set modelability by QSAR.
机构信息
Laboratory for Molecular Modeling, Division of Chemical Biology and Medicinal Chemistry, UNC Eshelman School of Pharmacy, University of North Carolina , Chapel Hill, North Carolina 27599, United States.
出版信息
J Chem Inf Model. 2014 Jan 27;54(1):1-4. doi: 10.1021/ci400572x. Epub 2014 Jan 8.
Abstract
We introduce a simple MODelability Index (MODI) that estimates the feasibility of obtaining predictive QSAR models (correct classification rate above 0.7) for a binary data set of bioactive compounds. MODI is defined as an activity class-weighted ratio of the number of nearest-neighbor pairs of compounds with the same activity class versus the total number of pairs. The MODI values were calculated for more than 100 data sets, and the threshold of 0.65 was found to separate the nonmodelable and modelable data sets.
摘要
我们提出了一个简单的可模性指数（MODI），用于估计获得生物活性化合物二元数据集的预测性定量构效关系（QSAR）模型（正确分类率高于 0.7）的可行性。MODI 定义为活性类别加权的化合物的最近邻对的数量与具有相同活性类别的化合物的总数的比值。MODI 值已针对 100 多个数据集进行了计算，发现阈值为 0.65 可用于区分不可建模和可建模数据集。
相似文献
1
Data set modelability by QSAR.基于定量构效关系的数据集可建模性。
J Chem Inf Model. 2014 Jan 27;54(1):1-4. doi: 10.1021/ci400572x. Epub 2014 Jan 8.
2
Study of Data Set Modelability: Modelability, Rivality, and Weighted Modelability Indexes.数据集可建模性研究：可建模性、竞争和加权可建模性指标。
J Chem Inf Model. 2018 Sep 24;58(9):1798-1814. doi: 10.1021/acs.jcim.8b00188. Epub 2018 Sep 5.
3
Regression Modelability Index: A New Index for Prediction of the Modelability of Data Sets in the Development of QSAR Regression Models.回归可模型化指数：一种新的指数，用于预测 QSAR 回归模型开发中数据集的可模型化性。
J Chem Inf Model. 2018 Oct 22;58(10):2069-2084. doi: 10.1021/acs.jcim.8b00313. Epub 2018 Sep 25.
4
Study of the Applicability Domain of the QSAR Classification Models by Means of the Rivality and Modelability Indexes.应用域的定量构效关系分类模型的研究通过竞争和可模型化指数。
Molecules. 2018 Oct 24;23(11):2756. doi: 10.3390/molecules23112756.
5
An automated framework for QSAR model building.一种用于定量构效关系（QSAR）模型构建的自动化框架。
J Cheminform. 2018 Jan 16;10(1):1. doi: 10.1186/s13321-017-0256-5.
6
Kernel Target Alignment Parameter: A New Modelability Measure for Regression Tasks.核目标对准参数：回归任务的一种新的可建模性度量。
J Chem Inf Model. 2016 Jan 25;56(1):6-11. doi: 10.1021/acs.jcim.5b00539. Epub 2015 Dec 23.
7
Differentiation of AmpC beta-lactamase binders vs. decoys using classification kNN QSAR modeling and application of the QSAR classifier to virtual screening.使用分类kNN QSAR模型区分AmpCβ-内酰胺酶结合剂与诱饵，并将QSAR分类器应用于虚拟筛选。
J Comput Aided Mol Des. 2008 Sep;22(9):593-609. doi: 10.1007/s10822-008-9199-2. Epub 2008 Mar 13.
8
Application of predictive QSAR models to database mining: identification and experimental validation of novel anticonvulsant compounds.预测性定量构效关系模型在数据库挖掘中的应用：新型抗惊厥化合物的鉴定与实验验证
J Med Chem. 2004 Apr 22;47(9):2356-64. doi: 10.1021/jm030584q.
9
Combinatorial QSAR of ambergris fragrance compounds.龙涎香香料化合物的组合定量构效关系
J Chem Inf Comput Sci. 2004 Mar-Apr;44(2):582-95. doi: 10.1021/ci034203t.
10
A combined Fisher and Laplacian score for feature selection in QSAR based drug design using compounds with known and unknown activities.基于已知和未知活性化合物的 QSAR 药物设计中特征选择的 Fisher 和拉普拉斯得分的组合。
J Comput Aided Mol Des. 2018 Feb;32(2):375-384. doi: 10.1007/s10822-017-0094-6. Epub 2017 Dec 26.
引用本文的文献
1
Development of synthetic chloride transporters using high-throughput screening and machine learning.利用高通量筛选和机器学习开发合成氯离子转运体。
Digit Discov. 2025 Aug 13. doi: 10.1039/d5dd00140d.
2
Establishing a Pharmacoinformatics Repository of Approved Medicines: A Database to Support Drug Product Development.建立已批准药物的药物信息学知识库：一个支持药品开发的数据库。
Mol Pharm. 2025 Jan 6;22(1):408-423. doi: 10.1021/acs.molpharmaceut.4c00991. Epub 2024 Dec 20.
3
MolPredictX: A Pioneer Mobile App Version for Online Biological Activity Predictions by Machine Learning Models.MolPredictX：一款用于通过机器学习模型进行在线生物活性预测的先驱移动应用程序版本。
Methods Mol Biol. 2025;2834:351-371. doi: 10.1007/978-1-0716-4003-6_17.
4
Predicting Chemical Immunotoxicity through Data-Driven QSAR Modeling of Aryl Hydrocarbon Receptor Agonism and Related Toxicity Mechanisms.通过基于数据驱动的芳烃受体激动作用及相关毒性机制的定量构效关系模型预测化学物质的免疫毒性
Environ Health (Wash). 2024 May 28;2(7):474-485. doi: 10.1021/envhealth.4c00026. eCollection 2024 Jul 19.
5
Predictions of Colloidal Molecular Aggregation Using AI/ML Models.使用人工智能/机器学习模型预测胶体分子聚集
ACS Omega. 2024 Jun 18;9(26):28691-28706. doi: 10.1021/acsomega.4c02886. eCollection 2024 Jul 2.
6
POxload: Machine Learning Estimates Drug Loadings of Polymeric Micelles.POxload：用于估算聚合物胶束药物载量的机器学习方法。
Mol Pharm. 2024 Jul 1;21(7):3356-3374. doi: 10.1021/acs.molpharmaceut.4c00086. Epub 2024 May 28.
7
Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR.将 QSAR 建模与深度学习整合到药物发现中：深 QSAR 的出现。
Nat Rev Drug Discov. 2024 Feb;23(2):141-155. doi: 10.1038/s41573-023-00832-0. Epub 2023 Dec 8.
8
Mpropred: A machine learning (ML) driven Web-App for bioactivity prediction of SARS-CoV-2 main protease (Mpro) antagonists.Mpropred：一个基于机器学习 (ML) 的 SARS-CoV-2 主蛋白酶 (Mpro) 拮抗剂生物活性预测的网络应用程序。
PLoS One. 2023 Jun 23;18(6):e0287179. doi: 10.1371/journal.pone.0287179. eCollection 2023.
9
Exploring QSAR models for activity-cliff prediction.探索用于活性悬崖预测的定量构效关系模型。
J Cheminform. 2023 Apr 17;15(1):47. doi: 10.1186/s13321-023-00708-w.
10
Data-Driven Quantitative Structure-Activity Relationship Modeling for Human Carcinogenicity by Chronic Oral Exposure.基于数据的定量构效关系模型在人类经口慢性暴露致癌性研究中的应用。
Environ Sci Technol. 2023 Apr 25;57(16):6573-6588. doi: 10.1021/acs.est.3c00648. Epub 2023 Apr 11.
本文引用的文献
1
Using Graph Indices for the Analysis and Comparison of Chemical Datasets.使用图索引进行化学数据集的分析与比较。
Mol Inform. 2013 Oct;32(9-10):827-42. doi: 10.1002/minf.201300076. Epub 2013 Sep 9.
2
Best Practices for QSAR Model Development, Validation, and Exploitation.定量构效关系（QSAR）模型开发、验证及应用的最佳实践
Mol Inform. 2010 Jul 12;29(6-7):476-88. doi: 10.1002/minf.201000061. Epub 2010 Jul 6.
3
Recent progress in understanding activity cliffs and their utility in medicinal chemistry.理解活性悬崖及其在药物化学中的应用的最新进展。
J Med Chem. 2014 Jan 9;57(1):18-28. doi: 10.1021/jm401120g. Epub 2013 Sep 13.
4
Human intestinal transporter database: QSAR modeling and virtual profiling of drug uptake, efflux and interactions.人类肠道转运体数据库：药物摄取、外排和相互作用的定量构效关系建模和虚拟特征分析。
Pharm Res. 2013 Apr;30(4):996-1007. doi: 10.1007/s11095-012-0935-x. Epub 2012 Dec 27.
5
A comprehensive statistical analysis of predicting in vivo hazard using high-throughput in vitro screening.使用高通量体外筛选对体内危害进行预测的综合统计分析。
Toxicol Sci. 2012 Aug;128(2):398-417. doi: 10.1093/toxsci/kfs159. Epub 2012 Apr 26.
6
From activity cliffs to target-specific scoring models and pharmacophore hypotheses.从活动悬崖到目标特异性评分模型和药效团假说。
ChemMedChem. 2011 Sep 5;6(9):1630-9, 1533. doi: 10.1002/cmdc.201100179. Epub 2011 Jul 12.
7
Trust, but verify: on the importance of chemical structure curation in cheminformatics and QSAR modeling research.信任，但要验证：关于化学结构 curated 在 cheminformatics 和 QSAR 建模研究中的重要性。
J Chem Inf Model. 2010 Jul 26;50(7):1189-204. doi: 10.1021/ci100176x.
8
A high-throughput method for assessing chemical toxicity using a Caenorhabditis elegans reproduction assay.利用秀丽隐杆线虫生殖测定评估化学毒性的高通量方法。
Toxicol Appl Pharmacol. 2010 Jun 1;245(2):153-9. doi: 10.1016/j.taap.2010.02.014. Epub 2010 Mar 4.
9
Combinatorial QSAR modeling of chemical toxicants tested against Tetrahymena pyriformis.针对梨形四膜虫测试的化学毒物的组合定量构效关系建模。
J Chem Inf Model. 2008 Apr;48(4):766-84. doi: 10.1021/ci700443v. Epub 2008 Mar 1.
10
Structure--activity landscape index: identifying and quantifying activity cliffs.结构-活性景观指数：识别和量化活性悬崖
J Chem Inf Model. 2008 Mar;48(3):646-58. doi: 10.1021/ci7004093. Epub 2008 Feb 28.
Zotero 插件