Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data

被引:334
作者
Aliper, Alexander [1 ]
Plis, Sergey [2 ,3 ]
Artemov, Artem [1 ]
Ulloa, Alvaro [3 ]
Mamoshina, Polina [1 ]
Zhavoronkov, Alex [1 ,4 ]
机构
[1] Johns Hopkins Univ, Insilico Med, ETC, B301, Baltimore, MD 21218 USA
[2] Datalyt Solut, 1101 Yale Blvd NE, Albuquerque, NM 87106 USA
[3] Mind Res Network, Albuquerque, NM 87106 USA
[4] Biogerontol Res Fdn, Oxford, England
关键词
deep learning DNN; predictor; drug repurposing drug discovery; confusion matrix; deep neural networks; GENE-EXPRESSION; ACTIVATION; CLASSIFICATION;
D O I
10.1021/acs.molpharmaceut.6b00248
中图分类号
R-3 [医学研究方法]; R3 [基础医学];
学科分类号
1001 ;
摘要
Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice and video recognition, robotics, and autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We used the perturbation samples of 678 drugs across A549, MCF-7, and PC-3 cell lines from the LINCS Project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we utilized both gene level transcriptomic data and transcriptomic data processed using a pathway activation scoring algorithm, for a pooled data set of samples perturbed with different concentrations of the drug for 6 and 24 hours. In both pathway and gene level classification, DNN achieved high classification accuracy and convincingly outperformed the support vector machine (SVM) model on every multiclass classification problem, however, models based on pathway level data performed significantly better. For the first time we demonstrate a deep learning neural net trained on transcriptomic data to recognize pharmacological properties of multiple drugs across different biological systems and conditions. We also propose using deep neural net confusion matrices for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery and development.
引用
收藏
页码:2524 / 2530
页数:7
相关论文
共 40 条
[1]  
[Anonymous], 2012, ARXIV PREPRINT ARXIV
[2]   A method for predicting target drug efficiency in cancer based on the analysis of signaling pathway activation [J].
Artemov, Artem ;
Aliper, Alexander ;
Korzinkin, Michael ;
Lezhnina, Ksenia ;
Jellen, Leslie ;
Zhukov, Nikolay ;
Roumiantsev, Sergey ;
Gaifullin, Nurshat ;
Zhavoronkov, Alex ;
Borisov, Nicolas ;
Buzdin, Anton .
ONCOTARGET, 2015, 6 (30) :29347-29356
[3]   Searching for exotic particles in high-energy physics with deep learning [J].
Baldi, P. ;
Sadowski, P. ;
Whiteson, D. .
NATURE COMMUNICATIONS, 2014, 5
[4]  
Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
[5]   BDDCS Class Prediction for New Molecular Entities [J].
Broccatelli, Fabio ;
Cruciani, Gabriele ;
Benet, Leslie Z. ;
Oprea, Tudor I. .
MOLECULAR PHARMACEUTICS, 2012, 9 (03) :570-580
[6]   Oncofinder, a new method for the analysis of intracellular signaling pathway activation using transcriptomic data [J].
Buzdin, Anton A. ;
Zhavoronkov, Alex A. ;
Korzinkin, Mikhail B. ;
Venkova, Larisa S. ;
Zenin, Alexander A. ;
Smirnov, Philip Yu. ;
Borisov, Nikolay M. .
FRONTIERS IN GENETICS, 2014, 5
[7]   Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy [J].
Combrisson, Etienne ;
Jerbi, Karim .
JOURNAL OF NEUROSCIENCE METHODS, 2015, 250 :126-136
[8]  
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[9]  
Glorot X., 2010, P 13 INT C ART INT S, P249, DOI DOI 10.1109/LGRS.2016.2565705
[10]   Genenames.org: the HGNC resources in 2015 [J].
Gray, Kristian A. ;
Yates, Bethan ;
Seal, Ruth L. ;
Wright, Mathew W. ;
Bruford, Elspeth A. .
NUCLEIC ACIDS RESEARCH, 2015, 43 (D1) :D1079-D1085