딥러닝을 이용한 약물 화학 구조 예측

다국어 초록 (Multilingual Abstract)

Numerous computer-based methods have been investigated in attempts to reduce the time and cost of drug development. In particular, with the recent development of deep learning techniques, various generation models for generating the chemical formulas of candidate compounds and reinforcement learning models to generate chemical formulas that satisfy specific conditions have been presented. In this paper, we propose a reinforcement learning model that exploits predicted binding affinity information between specific proteins and generated compounds. More specifically, the generative model used in this paper is Stack-RNN, and reinforcement learning is implemented by using Stack-RNN as a policy to ensure that the generated formula has specific chemical properties and high binding affinity with specific proteins. The proposed model generates paper, we generated the chemical formulas of compounds that are similar to three anti-cancer drugs (Sorafenib, Sunitinib, and Dasatinib) by using the target protein information of these three anti-cancer drugs.

참고문헌 (Reference)

1 서상민, "딥러닝을 이용한 화합물-단백질 상호작용 예측" 한국정보과학회 46 (46): 1054-1060, 2019

2 B. K. Shoichet, "Virtual screening of chemical libraries" 432 : 862-865, 2004

3 N. Jaques, "Tuning recurrent neural networks with reinforcement learning"

4 M. Manica, "Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders" 2019

5 H. Chen, "The rise of deep learning in drug discovery" 23 : 1241-1250, 2018

6 A. P. Bento, "The ChEMBL bioactivity database: an update" 42 : D1083-D1090, 2014

7 T. Cheng, "Structure-based virtual screening for drug discovery: a problem-centric review" 14 : 133-141, 2012

8 G. Jinesh G, "Smac mimetic enables the anticancer action of BCG‐stimulated neutrophils through TNF‐α but not through TRAIL and FasL" 92 : 233-244, 2012

9 R. J. Williams, "Simple statistical gradient-following algorithms for connectionist reinforcement learning" 8 : 229-256, 1992

10 L. Yu, "Seqgan:Sequence generative adversarial nets with policy gradient" 2017

11 D. P. Kingma, "Semi-supervised learning with deep generative models" 3581-3589, 2014

12 D. Weininger, "SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules" 28 : 31-36, 1988

13 T. Scior, "Recognizing pitfalls in virtual screening: a critical review" 52 : 867-881, 2012

14 Y.-Y. Li, "Pim-3, a proto-oncogene with serine/threonine kinase activity, is aberrantly expressed in human pancreatic cancer and phosphorylates bad to block bad-mediated apoptosis in human pancreatic cancer cell lines" 66 : 6741-6747, 2006

15 J. Born, "PaccMannRL:Designing anticancer drugs from transcriptomic data via reinforcement learning"

16 J. Lim, "Molecular generative model based on conditional variational autoencoder for de novo molecular design" 10 : 1-9, 2018

17 M. Olivecrona, "Molecular de-novo design through deep reinforcement learning" 9 : 48-, 2017

18 S. Hochreiter, "Long short-term memory" 9 : 1735-1780, 1997

19 A. Joulin, "Inferring algorithmic patterns with stack-augmented recurrent nets" 190-198, 2015

20 W. K. Chan, "GLASS: a comprehensive database for experimentally validated GPCR-ligand associations" 31 : 3035-3042, 2015

21 C. A. Lipinski, "Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings" 23 : 3-25, 1997

22 R. Erber, "EphB4 controls blood vascular morphogenesis during postnatal angiogenesis" 25 : 628-641, 2006

23 C. Knox, "DrugBank 3.0: a comprehensive resource for ‘omics’ research on drugs" 39 : D1035-D1041, 2010

24 M. Popova, "Deep reinforcement learning for de novo drug design" 4 : eaap7885-, 2018

25 J. Reymond, "Chemical space as a source for new drugs" 1 (1): 30-38, 2010

26 M. K. Gilson, "BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology" 44 : D1045-D1053, 2016

27 R. Gómez-Bombarelli, "Automatic chemical design using a data-driven continuous representation of molecules" 4 : 268-276, 2018

28 P. Baldi, "Autoencoders, unsupervised learning, and deep architectures" 37-49, 2012

29 D. P. Kingma, "Auto-encoding variational bayes"

30 C. Fujii, "Aberrant expression of serine/threonine kinase Pim‐3 in hepatocellular carcinoma development and its role in the proliferation of human hepatoma cell lines" 114 : 209-218, 2005

31 X. Lin, "A review on applications of computational methods in drug screening and design" 25 : 1375-, 2020