Enhanced QSAR Model Performance by Integrating Structural and Gene Expression Information

被引:5
作者
Chen, Qian [1 ]
Wu, Leihong [1 ]
Liu, Wei [1 ]
Xing, Li [1 ]
Fan, Xiaohui [1 ]
机构
[1] Zhejiang Univ, Coll Pharmaceut Sci, Pharmaceut Informat Inst, Hangzhou 310058, Zhejiang, Peoples R China
来源
MOLECULES | 2013年 / 18卷 / 09期
基金
美国国家科学基金会;
关键词
quantitative structure-activity relationships (QSAR); SAR paradox; molecular modeling; gene expression; integrative analysis; RISK-ASSESSMENT; METALLOTHIONEIN; SELECTION; CANCER; PREDICTION; TOXICITY; CARCINOGENESIS; CLASSIFICATION; MECHANISMS; PARADIGM;
D O I
10.3390/molecules180910789
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Despite decades of intensive research and a number of demonstrable successes, quantitative structure-activity relationship (QSAR) models still fail to yield predictions with reasonable accuracy in some circumstances, especially when the QSAR paradox occurs. In this study, to avoid the QSAR paradox, we proposed a novel integrated approach to improve the model performance through using both structural and biological information from compounds. As a proof-of-concept, the integrated models were built on a toxicological dataset to predict non-genotoxic carcinogenicity of compounds, using not only the conventional molecular descriptors but also expression profiles of significant genes selected from microarray data. For test set data, our results demonstrated that the prediction accuracy of QSAR model was dramatically increased from 0.57 to 0.67 with incorporation of expression data of just one selected signature gene. Our successful integration of biological information into classic QSAR model provided a new insight and methodology for building predictive models especially when QSAR paradox occurred.
引用
收藏
页码:10789 / 10801
页数:13
相关论文
共 50 条
[31]   A new LSTM-based gene expression prediction model: L-GEPM [J].
Wang, Huiqing ;
Li, Chun ;
Zhang, Jianhui ;
Wang, Jingjing ;
Ma, Yue ;
Lian, Yuanyuan .
JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY, 2019, 17 (04)
[32]   The ability to classify patients based on gene-expression data varies by algorithm and performance metric [J].
Piccolo, Stephen ;
Mecham, Avery ;
Golightly, Nathan ;
Johnson, Jeremie L. ;
Miller, Dustin .
PLOS COMPUTATIONAL BIOLOGY, 2022, 18 (03)
[33]   QSAR of Natural Sesquiterpene Lactones as Inhibitors of Myb-dependent Gene Expression [J].
Castellano, Gloria ;
Redondo, Lucia ;
Torrens, Francisco .
CURRENT TOPICS IN MEDICINAL CHEMISTRY, 2017, 17 (30) :3256-3268
[34]   Integrating gene regulatory pathways into differential network analysis of gene expression data [J].
Grimes, Tyler ;
Potter, S. Steven ;
Datta, Somnath .
SCIENTIFIC REPORTS, 2019, 9 (1)
[35]   Integrating Biological Heuristics and Gene Expression Data for Gene Regulatory Network Inference [J].
Zarnegar, Armita ;
Jelinek, Herbert F. ;
Vamplew, Peter ;
Stranieri, Andrew .
PROCEEDINGS OF THE AUSTRALASIAN COMPUTER SCIENCE WEEK MULTICONFERENCE (ACSW 2019), 2019,
[36]   Integrating Data Mining, Deep Learning, and Gene Ontology Analysis for Gene Expression-Based Disease Diagnosis Systems [J].
Babichev, Sergii ;
Liakh, Igor ;
Skvor, Jiri .
IEEE ACCESS, 2025, 13 :21265-21278
[37]   Enhanced gene expression by a novel designed leucine zipper endosomolytic peptide [J].
Ahmad, Aqeel ;
Rilla, Kirsi ;
Zou, Jing ;
Zhang, Weikai ;
Pyykko, Ilmari ;
Kinnunen, Paavo ;
Ranjan, Sanjeev .
INTERNATIONAL JOURNAL OF PHARMACEUTICS, 2021, 601
[38]   Integrative Construction of Gene Signatures Based on Fusion of Expression and Ontology Information [J].
Labaj, Wojciech ;
Polanski, Andrzej .
MAN-MACHINE INTERACTIONS 4, ICMMI 2015, 2016, 391 :237-249
[39]   Information governance structural model for banks [J].
Faria, Fernando de Abreu ;
Gastaud Macada, Antonio Carlos ;
Kumar, Kuldeep .
RAE-REVISTA DE ADMINISTRACAO DE EMPRESAS, 2017, 57 (01) :79-95
[40]   Nuclear Envelope: Connecting Structural Genome Organization to Regulation of Gene Expression [J].
Stancheva, Irina ;
Schirmer, Eric C. .
CANCER BIOLOGY AND THE NUCLEAR ENVELOPE: RECENT ADVANCES MAY ELUCIDATE PAST PARADOXES, 2014, 773 :209-244