ABSTRACT
Chemical-chemical interaction (CCI) plays a key role in predicting candidate drugs, toxicity, therapeutic effects, and biological functions. In various types of chemical analyses, computational approaches are often required due to the amount of data that needs to be handled. The recent remarkable growth and outstanding performance of deep learning have attracted considerable research attention. However, even in state-of-the-art drug analysis methods, deep learning continues to be used only as a classifier, although deep learning is capable of not only simple classification but also automated feature extraction. In this paper, we propose the first end- to-end learning method for CCI, named DeepCCI. Hidden features are derived from a simplified molecular input line entry system (SMILES), which is a string notation representing the chemical structure, instead of learning from crafted features. To discover hidden representations for the SMILES strings, we use convolutional neural networks (CNNs). To guarantee the commutative property for homogeneous interaction, we apply model sharing and hidden representation merging techniques. The performance of DeepCCI was compared with a plain deep classifier and conventional machine learning methods. The proposed DeepCCI showed the best performance in all seven evaluation metrics used. In addition, the commutative property was experimentally validated. The automatically extracted features through end-to-end SMILES learning alleviates the significant efforts required for manual feature engineering. It is expected to improve prediction performance in drug analyses.
- Babak Alipanahi, Andrew Delong, Matthew T Weirauch, and Brendan J Frey 2015. Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning. Nature biotechnology, Vol. 33, 8 (2015), 831--838.Google Scholar
- Christof Angermueller, Tanel Parnamaa, Leopold Parts, and Oliver Stegle 2016. Deep learning for computational biology. Molecular systems biology Vol. 12, 7 (2016), 878.Google Scholar
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).Google Scholar
- Petko Bogdanov and Ambuj K Singh 2010. Molecular function prediction using neighborhood features. IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), Vol. 7, 2 (2010), 208--217. Google ScholarDigital Library
- Leo Breiman. 2001. Random forests. Machine learning, Vol. 45, 1 (2001), 5--32. Google ScholarDigital Library
- Lei Chen, Tao Huang, Jian Zhang, Ming-Yue Zheng, Kai-Yan Feng, Yu-Dong Cai, and Kuo-Chen Chou 2013. Predicting drugs side effects based on chemical-chemical interactions and protein-chemical interactions. BioMed research international Vol. 2013 (2013).Google Scholar
- Lei Chen, Jing Lu, Jian Zhang, Kai-Rui Feng, Ming-Yue Zheng, and Yu-Dong Cai. 2013. Predicting chemical toxicity effects based on chemical-chemical interactions. PLoS One, Vol. 8, 2 (2013), e56517.Google ScholarCross Ref
- Lei Chen, Jing Yang, Mingyue Zheng, Xiangyin Kong, Tao Huang, and Yu-Dong Cai. 2015. The use of chemical-chemical interaction and chemical structure to identify new candidate chemicals related to lung cancer. PloS one, Vol. 10, 6 (2015), e0128696.Google Scholar
- François Chollet. 2015. Keras: Deep Learning library for Theano and TensorFlow. https://github.com/fchollet/keras. (2015).Google Scholar
- Ryszard Czermi'nski, Abdelaziz Yasri, and David Hartsough. 2001. Use of support vector machine in pattern classification: Application to QSAR studies. Molecular Informatics Vol. 20, 3 (2001), 227--240.Google Scholar
- George E Dahl, Navdeep Jaitly, and Ruslan Salakhutdinov. 2014. Multi-task neural networks for QSAR predictions. arXiv preprint arXiv:1406.1231 (2014).Google Scholar
- Li Deng and Roberto Togneri 2015. Deep dynamic models for learning hidden representations of speech features. Speech and Audio Processing for Coding, Enhancement and Recognition. Springer, 153--195.Google Scholar
- Jean-Pierre Doucet, Florent Barbault, Hairong Xia, Annick Panaye, and Botao Fan. 2007. Nonlinear SVM approaches to QSPR/QSAR studies and drug design. Current Computer-Aided Drug Design Vol. 3, 4 (2007), 263--289.Google ScholarCross Ref
- Jesse Eickholt and Jianlin Cheng 2013. DNdisorder: predicting protein disorder using boosting and deep networks. BMC bioinformatics, Vol. 14, 1 (2013), 88.Google Scholar
- Andrea Franceschini, Damian Szklarczyk, Sune Frankild, Michael Kuhn, Milan Simonovic, Alexander Roth, Jianyi Lin, Pablo Minguez, Peer Bork, Christian Von Mering, and others. 2013. STRING v9. 1: protein-protein interaction networks, with increased coverage and integration. Nucleic acids research Vol. 41, D1 (2013), D808--D815.Google Scholar
- Yoav Freund and Robert E Schapire 1995. A desicion-theoretic generalization of on-line learning and an application to boosting European conference on computational learning theory. Springer, 23--37. Google ScholarDigital Library
- Rafael Gómez-Bombarelli, David Duvenaud, José Miguel Hernández-Lobato, Jorge Aguilera-Iparraguirre, Timothy D Hirzel, Ryan P Adams, and Alán Aspuru-Guzik 2016. Automatic chemical design using a data-driven continuous representation of molecules. arXiv preprint arXiv:1610.02415 (2016).Google Scholar
- Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton. 2013. Speech recognition with deep recurrent neural networks Acoustics, speech and signal processing (icassp), 2013 ieee international conference on. IEEE, 6645--6649.Google Scholar
- Stephen Heller, Alan McNaught, Stephen Stein, Dmitrii Tchekhovskoi, and Igor Pletnev. 2013. InChI-the worldwide chemical structure identifier standard. Journal of cheminformatics Vol. 5, 1 (2013), 7.Google ScholarCross Ref
- Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, and others 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine Vol. 29, 6 (2012), 82--97.Google ScholarCross Ref
- Sepp Hochreiter and Jürgen Schmidhuber 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Le-Le Hu, Chen Chen, Tao Huang, Yu-Dong Cai, and Kuo-Chen Chou 2011. Predicting biological functions of compounds based on chemical-chemical interactions. PLoS One, Vol. 6, 12 (2011), e29491.Google ScholarCross Ref
- Sergey Ioffe and Christian Szegedy 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015).Google Scholar
- Hawoong Jeong, Sean P Mason, A-L Barabási, and Zoltan N Oltvai 2001. Lethality and centrality in protein networks. Nature, Vol. 411, 6833 (2001), 41--42.Google Scholar
- Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom. 2014. A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014).Google Scholar
- Yoon Kim 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014).Google Scholar
- T Kindt, S Morse, E Gotschlich, and K Lyons. 1991. Structure-based strategies for drug design and discovery. Nature Vol. 352 (1991), 581.Google Scholar
- Diederik Kingma and Jimmy Ba 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Diederik P Kingma and Max Welling 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).Google Scholar
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks Advances in neural information processing systems. 1097--1105. Google ScholarDigital Library
- Michael Kuhn, Christian von Mering, Monica Campillos, Lars Juhl Jensen, and Peer Bork 2008. STITCH: interaction networks of chemicals and proteins. Nucleic acids research Vol. 36, suppl 1 (2008), D684--D688.Google Scholar
- Steve Lawrence, C Lee Giles, Ah Chung Tsoi, and Andrew D Back 1997. Face recognition: A convolutional neural-network approach. IEEE transactions on neural networks Vol. 8, 1 (1997), 98--113. Google ScholarDigital Library
- Byunghan Lee, Junghwan Baek, Seunghyun Park, and Sungroh Yoon 2016. deepTarget: end-to-end learning framework for microRNA target prediction using deep recurrent neural networks. arXiv preprint arXiv:1603.09123 (2016).Google Scholar
- Byunghan Lee, Taehoon Lee, Byunggook Na, and Sungroh Yoon. 2015. DNA-level splice junction prediction using deep recurrent neural networks. arXiv preprint arXiv:1512.05135 (2015).Google Scholar
- Taehoon Lee and Sungroh Yoon 2015. Boosted Categorical Restricted Boltzmann Machine for Computational Prediction of Splice Junctions.. In ICML. 2483--2492. Google ScholarDigital Library
- Michael KK Leung, Hui Yuan Xiong, Leo J Lee, and Brendan J Frey. 2014. Deep learning of the tissue-regulated splicing code. Bioinformatics, Vol. 30, 12 (2014), i121--i129.Google ScholarCross Ref
- Zachary C Lipton, John Berkowitz, and Charles Elkan. 2015. A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015).Google Scholar
- Alessandro Lusci, Gianluca Pollastri, and Pierre Baldi. 2013. Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. Journal of chemical information and modeling, Vol. 53, 7 (2013), 1563.Google ScholarCross Ref
- Seonwoo Min, Byunghan Lee, and Sungroh Yoon 2016. Deep learning in bioinformatics. Briefings in Bioinformatics (2016), bbw068.Google Scholar
- Vinod Nair and Geoffrey E Hinton 2010. Rectified linear units improve restricted boltzmann machines Proceedings of the 27th international conference on machine learning (ICML-10). 807--814. Google ScholarDigital Library
- Ka-Lok Ng, Jin-Shuei Ciou, and Chien-Hung Huang. 2010. Prediction of protein functions based on function--function correlation relations. Computers in Biology and Medicine Vol. 40, 3 (2010), 300--305. Google ScholarDigital Library
- Maxime Oquab, Leon Bottou, Ivan Laptev, and Josef Sivic. 2014. Learning and transferring mid-level image representations using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1717--1724. Google ScholarDigital Library
- Hakime Öztürk, Elif Ozkirimli, and Arzucan Özgür 2016. A comparative study of SMILES-based compound similarity functions for drug-target interaction prediction. BMC bioinformatics, Vol. 17, 1 (2016), 128.Google Scholar
- Seunghyun Park, Seonwoo Min, Hyunsoo Choi, and Sungroh Yoon. 2016. deepMiRGene: deep neural network based precursor microRNA prediction. arXiv preprint arXiv:1605.00017 (2016).Google Scholar
- Bharath Ramsundar, Steven Kearnes, Patrick Riley, Dale Webster, David Konerding, and Vijay Pande. 2015. Massively multitask networks for drug discovery. arXiv preprint arXiv:1502.02072 (2015).Google Scholar
- Ambrish Roy, Alper Kucukural, and Yang Zhang. 2010. I-TASSER: a unified platform for automated protein structure and function prediction. Nature protocols, Vol. 5, 4 (2010), 725--738.Google Scholar
- Jean-Franccois Rual, Kavitha Venkatesan, Tong Hao, Tomoko Hirozane-Kishikawa, Amélie Dricot, Ning Li, Gabriel F Berriz, Francis D Gibbons, Matija Dreze, Nono Ayivi-Guedehoussou, and others. 2005. Towards a proteome-scale map of the human protein--protein interaction network. Nature, Vol. 437, 7062 (2005), 1173--1178.Google ScholarCross Ref
- Leander Schietgat, Bertrand Cuissart, Alban Lepailleur, Kurt De Grave, Bruno Crémilleux, Ronan Bureau, and Jan Ramon. 2013. Comparing chemical fingerprints for ecotoxicology. 6èmes journées de la Société Franccaise de Chémoinformatique.Google Scholar
- Marwin HS Segler, Thierry Kogej, Christian Tyrchan, and Mark P Waller 2017. Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks. arXiv preprint arXiv:1701.01329 (2017).Google Scholar
- Roded Sharan, Igor Ulitsky, and Ron Shamir. 2007. Network-based prediction of protein function. Molecular systems biology Vol. 3, 1 (2007), 88.Google Scholar
- Xingjian Shi, Hao Wang, and Dit Yan Yeung 2016. Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks. (2016).Google Scholar
- Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research Vol. 15, 1 (2014), 1929--1958. Google ScholarDigital Library
- Andrew J Stuper, William E Brügger, and Peter C Jurs. 1979. Computer assisted studies of chemical structure and biological function. John Wiley & Sons.Google Scholar
- Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks Advances in neural information processing systems. 3104--3112. Google ScholarDigital Library
- Vladimir Svetnik, Andy Liaw, Christopher Tong, J Christopher Culberson, Robert P Sheridan, and Bradley P Feuston 2003. Random forest: a classification and regression tool for compound classification and QSAR modeling. Journal of chemical information and computer sciences, Vol. 43, 6 (2003), 1947--1958.Google ScholarCross Ref
- Matt Swain. 2014. PubChemPy: a way to interact with PubChem in Python. http://pubchempy.readthedocs.io. (2014).Google Scholar
- Mahmud Tareq Hassan Khan. 2010. Predictions of the ADMET properties of candidate drug molecules utilizing different QSAR/QSPR modelling approaches. Current Drug Metabolism Vol. 11, 4 (2010), 285--295.Google ScholarCross Ref
- Kai Tian, Mingyu Shao, Yang Wang, Jihong Guan, and Shuigeng Zhou 2016. Boosting compound-protein interaction prediction by deep learning. Methods Vol. 110 (2016), 64--72.Google ScholarCross Ref
- Roberto Todeschini and Viviana Consonni 2009. Molecular descriptors for chemoinformatics, volume 41 (2 volume set). Vol. Vol. 41. John Wiley & Sons.Google Scholar
- Han Van De Waterbeemd and Eric Gifford 2003. ADMET in silico modelling: towards prediction paradise? Nature reviews Drug discovery Vol. 2, 3 (2003), 192--204.Google Scholar
- Vladimir Vapnik. 2013. The nature of statistical learning theory. Springer science & business media.Google Scholar
- Vladimir Naumovich Vapnik and Vlamimir Vapnik 1998. Statistical learning theory. Vol. Vol. 1. Wiley New York.Google Scholar
- Qin Wang, Xiao Li, Hongbin Yang, Yingchun Cai, Yinyin Wang, Zhuang Wang, Weihua Li, Yun Tang, and Guixia Liu 2017. In silico prediction of serious eye irritation or corrosion potential of chemicals. RSC Advances, Vol. 7, 11 (2017), 6697--6703.Google ScholarCross Ref
- Yanli Wang, Jewen Xiao, Tugba O Suzek, Jian Zhang, Jiyao Wang, and Stephen H Bryant. 2009. PubChem: a public information system for analyzing bioactivities of small molecules. Nucleic acids research Vol. 37, suppl 2 (2009), W623--W633.Google Scholar
- David Weininger. 1970. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. In Proc. Edinburgh Math. SOC, Vol. Vol. 17. 1--14.Google Scholar
- Jan Wildenhain, Michaela Spitzer, Sonam Dolma, Nick Jarvik, Rachel White, Marcia Roy, Emma Griffiths, David S Bellows, Gerard D Wright, and Mike Tyers. 2016. Systematic chemical-genetic and chemical-chemical interaction datasets for prediction of compound synergism. Scientific Data Vol. 3 (2016).Google Scholar
- Matthew D Zeiler and Rob Fergus 2014. Visualizing and understanding convolutional networks European conference on computer vision. Springer, 818--833.Google Scholar
- Haoyang Zeng, Matthew D Edwards, Ge Liu, and David K Gifford. 2016. Convolutional neural network architectures for predicting DNA--protein binding. Bioinformatics, Vol. 32, 12 (2016), i121--i127.Google ScholarCross Ref
Index Terms
- DeepCCI: End-to-end Deep Learning for Chemical-Chemical Interaction Prediction
Recommendations
Deep Learning Based-Virtual Screening Using 2D Pharmacophore Fingerprint in Drug Discovery
AbstractPredicting biological activity and molecular properties is one of the most important goals in the pharmaceutical and bioinformatics field in order to discover potential new drugs. Although machine learning methods have been used in drug discovery ...
An Analysis Of Convolutional Neural Networks For Image Classification
AbstractThis paper presents an empirical analysis of theperformance of popular convolutional neural networks (CNNs) for identifying objects in real time video feeds. The most popular convolution neural networks for object detection and object category ...
LightNet: pruned sparsed convolution neural network for image classification
Deep learning has become the most sought-after approach in the area of artificial intelligence (AI). However, deep learning models pose some challenges in the learning process. It is computationally intensive to train deep learning networks and also ...
Comments